%0 Conference Paper
%B 2011 18th IEEE International Conference on Image Processing (ICIP)
%D 2011
%T Face tracking in low resolution videos under illumination variations
%A Zou, W.W.W.
%A Chellapa, Rama
%A Yuen, P.C.
%K Adaptation models
%K Computational modeling
%K Face
%K face recognition
%K face tracking
%K GLF-based tracker
%K gradient methods
%K gradient-logarithmic field feature
%K illumination variations
%K lighting
%K low resolution videos
%K low-resolution
%K particle filter
%K particle filter framework
%K particle filtering (numerical methods)
%K Robustness
%K tracking
%K video signal processing
%K Videos
%K Visual face tracking
%X In practical face tracking applications, the face region is often small and affected by illumination variations. We address this problem by using a new feature, namely the Gradient-Logarithmic Field (GLF) feature, in the particle filter framework. The GLF feature is robust under illumination variations and the GLF-based tracker does not assume any model for the face being tracked and is effective in low-resolution video. Experimental results show that the proposed GFL-based tracker works well under significant illumination changes and outperforms some of the state-of-the-art algorithms.
%B 2011 18th IEEE International Conference on Image Processing (ICIP)
%I IEEE
%P 781 - 784
%8 2011/09/11/14
%@ 978-1-4577-1304-0
%G eng
%R 10.1109/ICIP.2011.6116672
%0 Conference Paper
%B 2011 18th IEEE International Conference on Image Processing (ICIP)
%D 2011
%T Illumination robust dictionary-based face recognition
%A Patel, Vishal M.
%A Tao Wu
%A Biswas,S.
%A Phillips,P.J.
%A Chellapa, Rama
%K albedo
%K approximation theory
%K classification
%K competitive face recognition algorithms
%K Databases
%K Dictionaries
%K Face
%K face recognition
%K face recognition method
%K filtering theory
%K human face recognition
%K illumination robust dictionary-based face recognition
%K illumination variation
%K image representation
%K learned dictionary
%K learning (artificial intelligence)
%K lighting
%K lighting conditions
%K multiple images
%K nonstationary stochastic filter
%K publicly available databases
%K relighting
%K relighting approach
%K representation error
%K residual vectors
%K Robustness
%K simultaneous sparse approximations
%K simultaneous sparse signal representation
%K sparseness constraint
%K Training
%K varying illumination
%K vectors
%X In this paper, we present a face recognition method based on simultaneous sparse approximations under varying illumination. Our method consists of two main stages. In the first stage, a dictionary is learned for each face class based on given training examples which minimizes the representation error with a sparseness constraint. In the second stage, a test image is projected onto the span of the atoms in each learned dictionary. The resulting residual vectors are then used for classification. Furthermore, to handle changes in lighting conditions, we use a relighting approach based on a non-stationary stochastic filter to generate multiple images of the same person with different lighting. As a result, our algorithm has the ability to recognize human faces with good accuracy even when only a single or a very few images are provided for training. The effectiveness of the proposed method is demonstrated on publicly available databases and it is shown that this method is efficient and can perform significantly better than many competitive face recognition algorithms.
%B 2011 18th IEEE International Conference on Image Processing (ICIP)
%I IEEE
%P 777 - 780
%8 2011/09/11/14
%@ 978-1-4577-1304-0
%G eng
%R 10.1109/ICIP.2011.6116670
%0 Conference Paper
%B 2011 IEEE International Conference on Automatic Face & Gesture Recognition and Workshops (FG 2011)
%D 2011
%T Recent advances in age and height estimation from still images and video
%A Chellapa, Rama
%A Turaga,P.
%K age estimation
%K biometrics (access control)
%K Calibration
%K Estimation
%K Geometry
%K height estimation
%K HUMANS
%K image fusion
%K image-formation model fusion
%K Legged locomotion
%K multiview-geometry
%K Robustness
%K SHAPE
%K shape-space geometry
%K soft-biometrics
%K statistical analysis
%K statistical methods
%K video signal processing
%X Soft-biometrics such as gender, age, race, etc have been found to be useful characterizations that enable fast pre-filtering and organization of data for biometric applications. In this paper, we focus on two useful soft-biometrics - age and height. We discuss their utility and the factors involved in their estimation from images and videos. In this context, we highlight the role that geometric constraints such as multiview-geometry, and shape-space geometry play. Then, we present methods based on these geometric constraints for age and height-estimation. These methods provide a principled means by fusing image-formation models, multi-view geometric constraints, and robust statistical methods for inference.
%B 2011 IEEE International Conference on Automatic Face & Gesture Recognition and Workshops (FG 2011)
%I IEEE
%P 91 - 96
%8 2011/03/21/25
%@ 978-1-4244-9140-7
%G eng
%R 10.1109/FG.2011.5771367
%0 Conference Paper
%B 2011 18th IEEE International Conference on Image Processing (ICIP)
%D 2011
%T Variable remapping of images from very different sources
%A Wei Zhang
%A Yanlin Guo
%A Meth, R.
%A Sokoloff, H.
%A Pope, A.
%A Strat, T.
%A Chellapa, Rama
%K automatic object identification
%K Buildings
%K CAMERAS
%K Conferences
%K constrained motion estimation
%K coordinates system
%K Estimation
%K G-RANSAC framework
%K image context enlargement
%K Image Enhancement
%K image registration
%K image sequence registration
%K Image sequences
%K Motion estimation
%K Robustness
%K temporal integration
%K variable image remapping
%X We present a system which registers image sequences acquired by very different sources, so that multiple views could be transformed to the same coordinates system. This enables the functionality of automatic object identification and confirmation across views and platforms. The capability of the system comes from three ingredients: 1) image context enlargement through temporal integration; 2) robust motion estimation using the G-RANSAC framework with a relaxed correspondence criteria; 3) constrained motion estimation within the G-RANSAC framework. The proposed system has worked successfully on thousands of frames from multiple collections with significant variations in scale and resolution.
%B 2011 18th IEEE International Conference on Image Processing (ICIP)
%I IEEE
%P 1501 - 1504
%8 2011/09/11/14
%@ 978-1-4577-1304-0
%G eng
%R 10.1109/ICIP.2011.6115729
%0 Journal Article
%J IEEE Transactions on Pattern Analysis and Machine Intelligence
%D 2010
%T Online Empirical Evaluation of Tracking Algorithms
%A Wu,Hao
%A Sankaranarayanan,A. C
%A Chellapa, Rama
%K Back
%K Biomedical imaging
%K Computer vision
%K Filtering
%K formal model validation techniques
%K formal verification
%K ground truth
%K Kanade Lucas Tomasi feature tracker
%K Karhunen-Loeve transforms
%K lighting
%K Markov processes
%K mean shift tracker
%K model validation.
%K online empirical evaluation
%K particle filtering (numerical methods)
%K Particle filters
%K Particle tracking
%K performance evaluation
%K receiver operating characteristic curves
%K Robustness
%K SNR
%K Statistics
%K Surveillance
%K time reversed Markov chain
%K tracking
%K tracking algorithms
%K visual tracking
%X Evaluation of tracking algorithms in the absence of ground truth is a challenging problem. There exist a variety of approaches for this problem, ranging from formal model validation techniques to heuristics that look for mismatches between track properties and the observed data. However, few of these methods scale up to the task of visual tracking, where the models are usually nonlinear and complex and typically lie in a high-dimensional space. Further, scenarios that cause track failures and/or poor tracking performance are also quite diverse for the visual tracking problem. In this paper, we propose an online performance evaluation strategy for tracking systems based on particle filters using a time-reversed Markov chain. The key intuition of our proposed methodology relies on the time-reversible nature of physical motion exhibited by most objects, which in turn should be possessed by a good tracker. In the presence of tracking failures due to occlusion, low SNR, or modeling errors, this reversible nature of the tracker is violated. We use this property for detection of track failures. To evaluate the performance of the tracker at time instant t, we use the posterior of the tracking algorithm to initialize a time-reversed Markov chain. We compute the posterior density of track parameters at the starting time t = 0 by filtering back in time to the initial time instant. The distance between the posterior density of the time-reversed chain (at t = 0) and the prior density used to initialize the tracking algorithm forms the decision statistic for evaluation. It is observed that when the data are generated by the underlying models, the decision statistic takes a low value. We provide a thorough experimental analysis of the evaluation methodology. Specifically, we demonstrate the effectiveness of our approach for tackling common challenges such as occlusion, pose, and illumination changes and provide the Receiver Operating Characteristic (ROC) curves. Finally, we also s how the applicability of the core ideas of the paper to other tracking algorithms such as the Kanade-Lucas-Tomasi (KLT) feature tracker and the mean-shift tracker.
%B IEEE Transactions on Pattern Analysis and Machine Intelligence
%V 32
%P 1443 - 1458
%8 2010/08//
%@ 0162-8828
%G eng
%N 8
%R 10.1109/TPAMI.2009.135
%0 Conference Paper
%B 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)
%D 2010
%T Sectored Random Projections for Cancelable Iris Biometrics
%A Pillai,J.K.
%A Patel, Vishal M.
%A Chellapa, Rama
%A Ratha,N. K
%K biometric pattern
%K Biometrics
%K Cancelable Biometrics
%K cancelable iris biometrics
%K data mining
%K data privacy
%K Degradation
%K Eyelashes
%K Eyelids
%K Iris
%K iris recognition
%K pattern recognition
%K privacy
%K random processes
%K Random Projections
%K Robustness
%K sectored random projection
%K Secure Biometrics
%K Security
%K security of data
%X Privacy and security are essential requirements in practical biometric systems. In order to prevent the theft of biometric patterns, it is desired to modify them through revocable and non invertible transformations called Cancelable Biometrics. In this paper, we propose an efficient algorithm for generating a Cancelable Iris Biometric based on Sectored Random Projections. Our algorithm can generate a new pattern if the existing one is stolen, retain the original recognition performance and prevent extraction of useful information from the transformed patterns. Our method also addresses some of the drawbacks of existing techniques and is robust to degradations due to eyelids and eyelashes.
%B 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)
%I IEEE
%P 1838 - 1841
%8 2010/03//
%@ 978-1-4244-4295-9
%G eng
%R 10.1109/ICASSP.2010.5495383
%0 Conference Paper
%B 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
%D 2010
%T Tracking via object reflectance using a hyperspectral video camera
%A Nguyen,Hien Van
%A Banerjee, A.
%A Chellapa, Rama
%K Computer vision
%K electronic design
%K hyperspectral datacubes
%K hyperspectral image analysis
%K Hyperspectral imaging
%K Hyperspectral sensors
%K hyperspectral video camera
%K Image motion analysis
%K Image sensors
%K lighting
%K Motion estimation
%K motion prediction
%K Object detection
%K object reflectance tracking
%K random projection
%K Reflectivity
%K robust methods
%K Robustness
%K sensor design
%K spectral detection
%K Surveillance
%K tracking
%K Video surveillance
%X Recent advances in electronics and sensor design have enabled the development of a hyperspectral video camera that can capture hyperspectral datacubes at near video rates. The sensor offers the potential for novel and robust methods for surveillance by combining methods from computer vision and hyperspectral image analysis. Here, we focus on the problem of tracking objects through challenging conditions, such as rapid illumination and pose changes, occlusions, and in the presence of confusers. A new framework that incorporates radiative transfer theory to estimate object reflectance and the mean shift algorithm to simultaneously track the object based on its reflectance spectra is proposed. The combination of spectral detection and motion prediction enables the tracker to be robust against abrupt motions, and facilitate fast convergence of the mean shift tracker. In addition, the system achieves good computational efficiency by using random projection to reduce spectral dimension. The tracker has been evaluated on real hyperspectral video data.
%B 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
%I IEEE
%P 44 - 51
%8 2010/06/13/18
%@ 978-1-4244-7029-7
%G eng
%R 10.1109/CVPRW.2010.5543780
%0 Journal Article
%J IEEE Signal Processing Magazine
%D 2010
%T Utilizing Hierarchical Multiprocessing for Medical Image Registration
%A Plishker,W.
%A Dandekar,O.
%A Bhattacharyya, Shuvra S.
%A Shekhar,R.
%K Acceleration
%K application parallelism
%K Biomedical imaging
%K domain-specific taxonomy
%K GPU acceleration
%K gradient descent approach
%K Graphics processing unit
%K hierarchical multiprocessing
%K image registration
%K Magnetic resonance imaging
%K Medical diagnostic imaging
%K medical image processing
%K medical image registration
%K multicore platform set
%K Multicore processing
%K PARALLEL PROCESSING
%K parallel programming
%K Robustness
%K Signal processing algorithms
%K Ultrasonic imaging
%X This work discusses an approach to utilize hierarchical multiprocessing in the context of medical image registration. By first organizing application parallelism into a domain-specific taxonomy, an algorithm is structured to target a set of multicore platforms.The approach on a cluster of graphics processing units (GPUs) requiring the use of two parallel programming environments to achieve fast execution times is demonstrated.There is negligible loss in accuracy for rigid registration when employing GPU acceleration, but it does adversely effect our nonrigid registration implementation due to our usage of a gradient descent approach.
%B IEEE Signal Processing Magazine
%V 27
%P 61 - 68
%8 2010
%@ 1053-5888
%G eng
%N 2
%0 Conference Paper
%B IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009
%D 2009
%T Combining powerful local and global statistics for texture description
%A Yong Xu
%A Si-Bin Huang
%A Hui Ji
%A Fermüller, Cornelia
%K Computer science
%K discretized measurements
%K fractal geometry
%K Fractals
%K geometric transformations
%K global statistics
%K Histograms
%K illumination transformations
%K image classification
%K image resolution
%K Image texture
%K lighting
%K local measurements SIFT features
%K local statistics
%K MATHEMATICS
%K multifractal spectrum
%K multiscale representation
%K Power engineering and energy
%K Power engineering computing
%K Robustness
%K Solids
%K Statistics
%K texture description
%K UMD high-resolution dataset
%K wavelet frame system
%K Wavelet transforms
%X A texture descriptor is proposed, which combines local highly discriminative features with the global statistics of fractal geometry to achieve high descriptive power, but also invariance to geometric and illumination transformations. As local measurements SIFT features are estimated densely at multiple window sizes and discretized. On each of the discretized measurements the fractal dimension is computed to obtain the so-called multifractal spectrum, which is invariant to geometric transformations and illumination changes. Finally to achieve robustness to scale changes, a multi-scale representation of the multifractal spectrum is developed using a framelet system, that is, a redundant tight wavelet frame system. Experiments on classification demonstrate that the descriptor outperforms existing methods on the UIUC as well as the UMD high-resolution dataset.
%B IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009
%I IEEE
%P 573 - 580
%8 2009/06/20/25
%@ 978-1-4244-3992-8
%G eng
%R 10.1109/CVPR.2009.5206741
%0 Conference Paper
%B IEEE Swarm Intelligence Symposium, 2009. SIS '09
%D 2009
%T A cooperative combinatorial Particle Swarm Optimization algorithm for side-chain packing
%A Lapizco-Encinas,G.
%A Kingsford, Carl
%A Reggia, James A.
%K Algorithm design and analysis
%K Amino acids
%K combinatorial mathematics
%K cooperative combinatorial particle swarm optimization algorithm
%K Design optimization
%K Encoding
%K Feedback
%K numerical optimization
%K Optimization methods
%K particle swarm optimisation
%K Particle swarm optimization
%K Partitioning algorithms
%K Proteins
%K proteomics
%K proteomics optimization
%K Robustness
%K side-chain packing
%X Particle Swarm Optimization (PSO) is a well-known, competitive technique for numerical optimization with real-parameter representation. This paper introduces CCPSO, a new Cooperative Particle Swarm Optimization algorithm for combinatorial problems. The cooperative strategy is achieved by splitting the candidate solution vector into components, where each component is optimized by a particle. Particles move throughout a continuous space, their movements based on the influences exerted by static particles that then get feedback based on the fitness of the candidate solution. Here, the application of this technique to side-chain packing (a proteomics optimization problem) is investigated. To verify the efficiency of the proposed CCPSO algorithm, we test our algorithm on three side-chain packing problems and compare our results with the provably optimal result. Computational results show that the proposed algorithm is very competitive, obtaining a conformation with an energy value within 1% of the provably optimal solution in many proteins.
%B IEEE Swarm Intelligence Symposium, 2009. SIS '09
%I IEEE
%P 22 - 29
%8 2009/04/30/March
%@ 978-1-4244-2762-8
%G eng
%R 10.1109/SIS.2009.4937840
%0 Conference Paper
%B IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007. IROS 2007
%D 2007
%T Combining motion from texture and lines for visual navigation
%A Bitsakos,K.
%A Li Yi
%A Fermüller, Cornelia
%K 3D structure information
%K CAMERAS
%K Computer vision
%K extended Kalman filter
%K Frequency
%K image frequencies
%K Image motion analysis
%K Image texture
%K Kalman filters
%K Layout
%K motion control
%K Motion estimation
%K Navigation
%K Optical computing
%K phase correlation
%K piecewise planar scene
%K Robustness
%K Simultaneous localization and mapping
%K Speech processing
%K textured plane
%K video signal processing
%K visual navigation
%X Two novel methods for computing 3D structure information from video for a piecewise planar scene are presented. The first method is based on a new line constraint, which clearly separates the estimation of distance from the estimation of slant. The second method exploits the concepts of phase correlation to compute from the change of image frequencies of a textured plane, distance and slant information. The two different estimates together with structure estimates from classical image motion are combined and integrated over time using an extended Kalman filter. The estimation of the scene structure is demonstrated experimentally in a motion control algorithm that allows the robot to move along a corridor. We demonstrate the efficacy of each individual method and their combination and show that the method allows for visual navigation in textured as well as un-textured environments.
%B IEEE/RSJ International Conference on Intelligent Robots and Systems, 2007. IROS 2007
%I IEEE
%P 232 - 239
%8 2007/11/29/Oct.
%@ 978-1-4244-0912-9
%G eng
%R 10.1109/IROS.2007.4399568
%0 Journal Article
%J IEEE Journal on Selected Areas in Communications
%D 2007
%T Efficient lookup on unstructured topologies
%A Morselli,R.
%A Bhattacharjee, Bobby
%A Marsh,M.A.
%A Srinivasan, Aravind
%K Computer science
%K DHT
%K distributed algorithms
%K Distributed computing
%K distributed hash table
%K Least squares approximation
%K LMS
%K local minima search
%K lookup protocol
%K Network topology
%K node failures
%K Peer to peer computing
%K Performance analysis
%K Protocols
%K replication strategy
%K Resilience
%K Robustness
%K table lookup
%K telecommunication network topology
%K unstructured network topology
%X We present LMS, a protocol for efficient lookup on unstructured networks. Our protocol uses a virtual namespace without imposing specific topologies. It is more efficient than existing lookup protocols for unstructured networks, and thus is an attractive alternative for applications in which the topology cannot be structured as a Distributed Hash Table (DHT). We present analytic bounds for the worst-case performance of LMS. Through detailed simulations (with up to 100,000 nodes), we show that the actual performance on realistic topologies is significantly better. We also show in both simulations and a complete implementation (which includes over five hundred nodes) that our protocol is inherently robust against multiple node failures and can adapt its replication strategy to optimize searches according to a specific heuristic. Moreover, the simulation demonstrates the resilience of LMS to high node turnover rates, and that it can easily adapt to orders of magnitude changes in network size. The overhead incurred by LMS is small, and its performance approaches that of DHTs on networks of similar size
%B IEEE Journal on Selected Areas in Communications
%V 25
%P 62 - 72
%8 2007/01//
%@ 0733-8716
%G eng
%N 1
%R 10.1109/JSAC.2007.07007
%0 Conference Paper
%B Proceedings of the 22nd International Conference on Data Engineering, 2006. ICDE '06
%D 2006
%T Approximate Data Collection in Sensor Networks using Probabilistic Models
%A Chu,D.
%A Deshpande, Amol
%A Hellerstein,J. M
%A Wei Hong
%K Batteries
%K Biological system modeling
%K Biosensors
%K data mining
%K Databases
%K Energy consumption
%K Intelligent networks
%K Intelligent sensors
%K Robustness
%K Wireless sensor networks
%X Wireless sensor networks are proving to be useful in a variety of settings. A core challenge in these networks is to minimize energy consumption. Prior database research has proposed to achieve this by pushing data-reducing operators like aggregation and selection down into the network. This approach has proven unpopular with early adopters of sensor network technology, who typically want to extract complete "dumps" of the sensor readings, i.e., to run "SELECT *" queries. Unfortunately, because these queries do no data reduction, they consume significant energy in current sensornet query processors. In this paper we attack the "SELECT " problem for sensor networks. We propose a robust approximate technique called Ken that uses replicated dynamic probabilistic models to minimize communication from sensor nodes to the network’s PC base station. In addition to data collection, we show that Ken is well suited to anomaly- and event-detection applications. A key challenge in this work is to intelligently exploit spatial correlations across sensor nodes without imposing undue sensor-to-sensor communication burdens to maintain the models. Using traces from two real-world sensor network deployments, we demonstrate that relatively simple models can provide significant communication (and hence energy) savings without undue sacrifice in result quality or frequency. Choosing optimally among even our simple models is NPhard, but our experiments show that a greedy heuristic performs nearly as well as an exhaustive algorithm.
%B Proceedings of the 22nd International Conference on Data Engineering, 2006. ICDE '06
%I IEEE
%P 48 - 48
%8 2006/04/03/07
%@ 0-7695-2570-9
%G eng
%R 10.1109/ICDE.2006.21
%0 Conference Paper
%B 2006 IEEE International Conference on Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings
%D 2006
%T Frequency Independent Flexible Spherical Beamforming Via Rbf Fitting
%A Yerukhimovich,A.
%A Duraiswami, Ramani
%A Gumerov, Nail A.
%A Zotkin,Dmitry N
%K acoustic signal processing
%K array signal processing
%K band-limited radial basis functions
%K Computer science
%K Educational institutions
%K Eigenvalues and eigenfunctions
%K Equations
%K Frequency
%K frequency independent beamformer weights
%K frequency independent flexible spherical beamforming
%K microphone arrays
%K Nails
%K Position measurement
%K RBF fitting
%K Robustness
%K sound analysis
%K spherical array data
%K spherical microphone array
%X We describe a new method for sound analysis using a spherical microphone array without the use of quadrature over the sphere. Quadrature based solutions are very sensitive to the placement of microphones on the sphere, needing measurements to be made at exactly the quadrature positions. We propose to use fitting with band-limited radial basis functions (RBFs) rather than quadrature. Our approach results in frequency independent beamformer weights for flexibly placed microphone locations. Results are demonstrated using both synthetic and real spherical array data
%B 2006 IEEE International Conference on Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings
%I IEEE
%V 5
%P V-V - V-V
%8 2006/05//
%@ 1-4244-0469-X
%G eng
%R 10.1109/ICASSP.2006.1661208
%0 Conference Paper
%B 19th IEEE Computer Security Foundations Workshop, 2006
%D 2006
%T Managing policy updates in security-typed languages
%A Swamy,N.
%A Hicks, Michael W.
%A Tse,S.
%A Zdancewic,S.
%K Access control
%K Computer languages
%K Data security
%K Database systems
%K dynamic queries
%K dynamic semantics
%K Educational institutions
%K high level languages
%K Information security
%K information-flow policy management
%K Lattices
%K Network servers
%K Operating systems
%K policy update management
%K Robustness
%K role-based security policies
%K RT role-based trust-management framework
%K Rx security-typed programming language
%K security of data
%K statically verified transactions
%K transitive flows
%X This paper presents Rx, a new security-typed programming language with features intended to make the management of information-flow policies more practical. Security labels in Rx, in contrast to prior approaches, are defined in terms of owned roles, as found in the RT role-based trust-management framework. Role-based security policies allow flexible delegation, and our language Rx provides constructs through which programs can robustly update policies and react to policy updates dynamically. Our dynamic semantics use statically verified transactions to eliminate illegal information flows across updates, which we call transitive flows. Because policy updates can be observed through dynamic queries, policy updates can potentially reveal sensitive information. As such, Rx considers policy statements themselves to be potentially confidential information and subject to information-flow metapolicies
%B 19th IEEE Computer Security Foundations Workshop, 2006
%I IEEE
%P 13 pp.-216 - 13 pp.-216
%8 2006///
%@ 0-7695-2615-2
%G eng
%R 10.1109/CSFW.2006.17
%0 Conference Paper
%B 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
%D 2006
%T A Projective Invariant for Textures
%A Yong Xu
%A Hui Ji
%A Fermüller, Cornelia
%K Computer science
%K Computer vision
%K Educational institutions
%K Fractals
%K Geometry
%K Image texture
%K Level set
%K lighting
%K Robustness
%K Surface texture
%X Image texture analysis has received a lot of attention in the past years. Researchers have developed many texture signatures based on texture measurements, for the purpose of uniquely characterizing the texture. Existing texture signatures, in general, are not invariant to 3D transforms such as view-point changes and non-rigid deformations of the texture surface, which is a serious limitation for many applications. In this paper, we introduce a new texture signature, called the multifractal spectrum (MFS). It provides an efficient framework combining global spatial invariance and local robust measurements. The MFS is invariant under the bi-Lipschitz map, which includes view-point changes and non-rigid deformations of the texture surface, as well as local affine illumination changes. Experiments demonstrate that the MFS captures the essential structure of textures with quite low dimension.
%B 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
%I IEEE
%V 2
%P 1932 - 1939
%8 2006///
%@ 0-7695-2597-0
%G eng
%R 10.1109/CVPR.2006.38
%0 Conference Paper
%B Proceedings of the 2005 IEEE International Conference on Robotics and Automation, 2005. ICRA 2005
%D 2005
%T Robust Contrast Invariant Stereo Correspondence
%A Ogale, A. S
%A Aloimonos, J.
%K Apertures
%K Calibration
%K CAMERAS
%K Computer science
%K contrast invariance
%K diffusion
%K Educational institutions
%K Frequency
%K gabor
%K Hardware
%K occlusions
%K Robot vision systems
%K Robotics and automation
%K Robustness
%K stereo
%X A stereo pair of cameras attached to a robot will inevitably yield images with different contrast. Even if we assume that the camera hardware is identical, due to slightly different points of view, the amount of light entering the two cameras is also different, causing dynamically adjusted internal parameters such as aperture, exposure and gain to be different. Due to the difficulty of obtaining and maintaining precise intensity or color calibration between the two cameras, contrast invariance becomes an extremely desirable property of stereo correspondence algorithms. The problem of achieving point correspondence between a stereo pair of images is often addressed by using the intensity or color differences as a local matching metric, which is sensitive to contrast changes. We present an algorithm for contrast invariant stereo matching which relies on multiple spatial frequency channels for local matching. A fast global framework uses the local matching to compute the correspondences and find the occlusions. We demonstrate that the use of multiple frequency channels allows the algorithm to yield good results even in the presence of significant amounts of noise.
%B Proceedings of the 2005 IEEE International Conference on Robotics and Automation, 2005. ICRA 2005
%I IEEE
%P 819 - 824
%8 2005/04/18/22
%@ 0-7803-8914-X
%G eng
%R 10.1109/ROBOT.2005.1570218
%0 Journal Article
%J IEEE Transactions on Speech and Audio Processing
%D 2004
%T Accelerated speech source localization via a hierarchical search of steered response power
%A Zotkin,Dmitry N
%A Duraiswami, Ramani
%K accelerated speech source localization
%K Acceleration
%K array signal processing
%K conferencing system
%K Delay
%K delay-and-sum beamforming
%K direction-of-arrival estimation
%K Frequency
%K hierarchical search algorithm
%K Inverse problems
%K multimedia applications
%K Multimedia communication
%K multiple speech sound source
%K Position measurement
%K Robustness
%K search problems
%K Sensor arrays
%K Signal processing algorithms
%K speech
%K speech enhancement
%K Speech processing
%K steered response power
%K steered response power phase-transform weighted source localization algorithm
%K transducer arrays
%K User interfaces
%X Accurate and fast localization of multiple speech sound sources is a problem that is of significant interest in applications such as conferencing systems. Recently, approaches that are based on search for local peaks of the steered response power are becoming popular, despite their known computational expense. Based on the observation that the wavelengths of the sound from a speech source are comparable to the dimensions of the space being searched and that the source is broadband, we have developed an efficient search algorithm. Significant speedups are achieved by using coarse-to-fine strategies in both space and frequency. We present applications of the search algorithm to speed up simple delay-and-sum beamforming and steered response power phase-transform weighted (SRP-PHAT) source localization algorithms. A systematic series of comparisons with previous algorithms are made that show that the technique is much faster, robust, and accurate. The performance of the algorithm can be further improved by using constraints from computer vision.
%B IEEE Transactions on Speech and Audio Processing
%V 12
%P 499 - 508
%8 2004/09//
%@ 1063-6676
%G eng
%N 5
%R 10.1109/TSA.2004.832990
%0 Conference Paper
%B 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2004. (IROS 2004). Proceedings
%D 2004
%T Compound eye sensor for 3D ego motion estimation
%A Neumann, J.
%A Fermüller, Cornelia
%A Aloimonos, J.
%A Brajovic,V.
%K 3D camera motion estimation
%K CAMERAS
%K compound eye vision sensor
%K Computer vision
%K Equations
%K Eyes
%K Geometry
%K Image sensors
%K Insects
%K linear equations
%K Motion estimation
%K robot vision
%K Robustness
%K sampling geometry
%K Sampling methods
%K Sensor phenomena and characterization
%X We describe a compound eye vision sensor for 3D ego motion computation. Inspired by eyes of insects, we show that the compound eye sampling geometry is optimal for 3D camera motion estimation. This optimality allows us to estimate the 3D camera motion in a scene-independent and robust manner by utilizing linear equations. The mathematical model of the new sensor can be implemented in analog networks resulting in a compact computational sensor for instantaneous 3D ego motion measurements in full six degrees of freedom.
%B 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2004. (IROS 2004). Proceedings
%I IEEE
%V 4
%P 3712- 3717 vol.4 - 3712- 3717 vol.4
%8 2004/10/28/Sept.
%@ 0-7803-8463-6
%G eng
%R 10.1109/IROS.2004.1389992
%0 Conference Paper
%B Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004
%D 2004
%T A Rao-Blackwellized particle filter for EigenTracking
%A Zia Khan
%A Balch, T.
%A Dellaert, F.
%K analytically tractable integrals
%K Computer vision
%K EigenTracking
%K Filters
%K Gaussian processes
%K modal analysis
%K multi-modal distributions
%K NOISE
%K noisy targets
%K optimisation
%K optimization-based algorithms
%K Particle filters
%K Particle measurements
%K Particle tracking
%K Principal component analysis
%K probabilistic principal component analysis
%K Rao-Blackwellized particle filter
%K Robustness
%K SHAPE
%K State estimation
%K state vector
%K subspace coefficients
%K Subspace representations
%K target tracking
%K vectors
%X Subspace representations have been a popular way to model appearance in computer vision. In Jepson and Black's influential paper on EigenTracking, they were successfully applied in tracking. For noisy targets, optimization-based algorithms (including EigenTracking) often fail catastrophically after losing track. Particle filters have recently emerged as a robust method for tracking in the presence of multi-modal distributions. To use subspace representations in a particle filter, the number of samples increases exponentially as the state vector includes the subspace coefficients. We introduce an efficient method for using subspace representations in a particle filter by applying Rao-Blackwellization to integrate out the subspace coefficients in the state vector. Fewer samples are needed since part of the posterior over the state vector is analytically calculated. We use probabilistic principal component analysis to obtain analytically tractable integrals. We show experimental results in a scenario in which we track a target in clutter.
%B Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004
%V 2
%P II - 980-II-986 Vol.2
%8 2004/06//
%G eng
%0 Journal Article
%J Circuits and Systems for Video Technology, IEEE Transactions on
%D 2003
%T Joint security and robustness enhancement for quantization based data embedding
%A Wu,M.
%K (signal);
%K authentication;
%K binary
%K compensation;
%K data
%K data;
%K DETECTION
%K digital
%K distortion
%K distortion;
%K embedding;
%K encapsulation;
%K enhancement;
%K error
%K features;
%K hiding;
%K lookup
%K lookup;
%K LUT;
%K message
%K multimedia
%K nontrivial
%K probability;
%K quantisation
%K quantization
%K quantized
%K Robustness
%K run
%K Security
%K statistics;
%K systems;
%K table
%K table;
%K watermarking;
%X The paper studies joint security and robustness enhancement of quantization-based data embedding for multimedia authentication applications. We present an analysis showing that through a nontrivial run lookup table (LUT) that maps quantized multimedia features randomly to binary data, the probability of detection error can be considerably smaller than the traditional quantization embedding. We quantify the security strength of LUT embedding and enhance its robustness through distortion compensation. Introducing a joint security and capacity measure, we show that the proposed distortion-compensated LUT embedding provides joint enhancement of security and robustness over the traditional quantization embedding.
%B Circuits and Systems for Video Technology, IEEE Transactions on
%V 13
%P 831 - 841
%8 2003/08//
%@ 1051-8215
%G eng
%N 8
%R 10.1109/TCSVT.2003.815951
%0 Conference Paper
%B Design, Automation and Test in Europe Conference and Exhibition, 2003
%D 2003
%T On-chip stochastic communication [SoC applications]
%A Tudor Dumitras
%A Marculescu, R.
%K buffer overflow
%K CMOS technology
%K CMOS technology scaling
%K Costs
%K data upsets
%K Design automation
%K Digital audio players
%K Fault tolerance
%K Fault tolerant systems
%K generic tile-based architecture
%K integrated circuit design
%K integrated circuit interconnections
%K interconnect correctness requirements
%K Logic Design
%K logic simulation
%K MP3 encoder
%K Multiprocessor interconnection networks
%K on-chip fault-tolerance
%K on-chip stochastic communication
%K packet drops
%K Pervasive computing
%K Robustness
%K SoC design
%K SoC verification
%K Stochastic processes
%K Synchronisation
%K synchronization failures
%K system latency
%K system-level fault-tolerance
%K system-on-chip
%K systems-on-chip
%K video coding
%X As CMOS technology scales down into the deep-submicron (DSM) domain, the costs of design and verification for systems-on-chip (SoCs) are rapidly increasing due to the inefficiency of traditional CAD tools. Relaxing the requirement of 100% correctness for devices and interconnects drastically reduces the costs of design but, at the same time, requires that SoCs be designed with some system-level fault-tolerance. In this paper, we introduce a new communication paradigm for SoCs, namely stochastic communication. The newly proposed scheme not only separates communication from computation, but also provides the required built-in fault-tolerance to DSM failures, is scalable and cheap to implement. For a generic tile-based architecture, we show how a ubiquitous multimedia application (an MP3 encoder) can be implemented using stochastic communication in an efficient and robust manner. More precisely, up to 70% data upsets, 80% packet drops because of buffer overflow, and severe levels of synchronization failures can be tolerated while maintaining a low latency.
%B Design, Automation and Test in Europe Conference and Exhibition, 2003
%P 790 - 795
%8 2003///
%G eng
%0 Conference Paper
%B 16th International Conference on Pattern Recognition, 2002. Proceedings
%D 2002
%T Mixture models for dynamic statistical pressure snakes
%A Abd-Almageed, Wael
%A Smith,C.E.
%K active contour models
%K Active contours
%K Artificial intelligence
%K Bayes methods
%K Bayesian methods
%K Bayesian theory
%K complex colored object
%K Computer vision
%K decision making
%K decision making mechanism
%K dynamic statistical pressure snakes
%K Equations
%K expectation maximization algorithm
%K Gaussian distribution
%K image colour analysis
%K Image edge detection
%K Image segmentation
%K Intelligent robots
%K mixture models
%K mixture of Gaussians
%K mixture pressure model
%K Robot vision systems
%K robust pressure model
%K Robustness
%K segmentation results
%K statistical analysis
%K statistical modeling
%X This paper introduces a new approach to statistical pressure snakes. It uses statistical modeling for both object and background to obtain a more robust pressure model. The Expectation Maximization (EM) algorithm is used to model the data into a Mixture of Gaussians (MoG). Bayesian theory is then employed as a decision making mechanism. Experimental results using the traditional pressure model and the new mixture pressure model demonstrate the effectiveness of the new models.
%B 16th International Conference on Pattern Recognition, 2002. Proceedings
%I IEEE
%V 2
%P 721- 724 vol.2 - 721- 724 vol.2
%8 2002///
%@ 0-7695-1695-X
%G eng
%R 10.1109/ICPR.2002.1048404
%0 Conference Paper
%B IEEE Workshop on Detection and Recognition of Events in Video, 2001. Proceedings
%D 2001
%T Multimodal 3-D tracking and event detection via the particle filter
%A Zotkin,Dmitry N
%A Duraiswami, Ramani
%A Davis, Larry S.
%K algorithms
%K APPROACH
%K audio data collection
%K audio signal processing
%K Bayesian inference
%K Bayesian methods
%K belief networks
%K CAMERAS
%K capture
%K conversation
%K echo
%K Educational institutions
%K Event detection
%K event occurrence
%K filtering theory
%K flying echo locating bat behaviour
%K Image motion analysis
%K inference mechanisms
%K Laboratories
%K microphone arrays
%K moving object tracking
%K moving participants
%K moving prey
%K multimodal 3D tracking
%K multiple cameras
%K Object detection
%K particle filter
%K Particle filters
%K Particle tracking
%K Robustness
%K search
%K smart video conferencing setup
%K target tracking
%K Teleconferencing
%K tracking filters
%K turn-taking detection
%K video data collection
%K video signal processing
%X Determining the occurrence of an event is fundamental to developing systems that can observe and react to them. Often, this determination is based on collecting video and/or audio data and determining the state or location of a tracked object. We use Bayesian inference and the particle filter for tracking moving objects, using both video data obtained from multiple cameras and audio data obtained using arrays of microphones. The algorithms developed are applied to determining events arising in two fields of application. In the first, the behavior of a flying echo locating bat as it approaches a moving prey is studied, and the events of search, approach and capture are detected. In a second application we describe detection of turn-taking in a conversation between possibly moving participants recorded using a smart video conferencing setup
%B IEEE Workshop on Detection and Recognition of Events in Video, 2001. Proceedings
%I IEEE
%P 20 - 27
%8 2001///
%@ 0-7695-1293-3
%G eng
%R 10.1109/EVENT.2001.938862
%0 Conference Paper
%B IEEE Workshop on Omnidirectional Vision, 2000. Proceedings
%D 2000
%T Multi-camera networks: eyes from eyes
%A Fermüller, Cornelia
%A Aloimonos, J.
%A Baker, P.
%A Pless, R.
%A Neumann, J.
%A Stuart, B.
%K Biosensors
%K CAMERAS
%K Computer vision
%K Eyes
%K Image sequences
%K intelligent systems
%K Layout
%K Machine vision
%K Robot vision systems
%K Robustness
%K Spatiotemporal phenomena
%K video cameras
%K Virtual reality
%X Autonomous or semi-autonomous intelligent systems, in order to function appropriately, need to create models of their environment, i.e., models of space time. These are descriptions of objects and scenes and descriptions of changes of space over time, that is, events and actions. Despite the large amount of research on this problem, as a community we are still far from developing robust descriptions of a system's spatiotemporal environment using video input (image sequences). Undoubtedly, some progress has been made regarding the understanding of estimating the structure of visual space, but it has not led to solutions to specific applications. There is, however, an alternative approach which is in line with today's “zeitgeist.” The vision of artificial systems can be enhanced by providing them with new eyes. If conventional video cameras are put together in various configurations, new sensors can be constructed that have much more power and the way they “see” the world makes it much easier to solve problems of vision. This research is motivated by examining the wide variety of eye design in the biological world and obtaining inspiration for an ensemble of computational studies that relate how a system sees to what that system does (i.e. relating perception to action). This, coupled with the geometry of multiple views that has flourished in terms of theoretical results in the past few years, points to new ways of constructing powerful imaging devices which suit particular tasks in robotics, visualization, video processing, virtual reality and various computer vision applications, better than conventional cameras. This paper presents a number of new sensors that we built using common video cameras and shows their superiority with regard to developing models of space and motion
%B IEEE Workshop on Omnidirectional Vision, 2000. Proceedings
%I IEEE
%P 11 - 18
%8 2000///
%@ 0-7695-0704-2
%G eng
%R 10.1109/OMNVIS.2000.853797
%0 Conference Paper
%B , 1997 IEEE Symposium on Security and Privacy, 1997. Proceedings
%D 1997
%T A secure and reliable bootstrap architecture
%A Arbaugh, William A.
%A Farber,D. J
%A Smith,J. M
%K active networks
%K AEGIS architecture
%K bootstrap architecture
%K Computer architecture
%K computer bootstrapping
%K data integrity
%K Distributed computing
%K Hardware
%K hardware validity
%K initialization
%K integrity chain
%K integrity check failures
%K Internet
%K Internet commerce
%K IP networks
%K Laboratories
%K lower-layer integrity
%K Microprogramming
%K Operating systems
%K recovery process
%K reliability
%K robust systems
%K Robustness
%K Security
%K security of data
%K software reliability
%K system integrity guarantees
%K system recovery
%K transitions
%K Virtual machining
%X In a computer system, the integrity of lower layers is typically treated as axiomatic by higher layers. Under the presumption that the hardware comprising the machine (the lowest layer) is valid, the integrity of a layer can be guaranteed if and only if: (1) the integrity of the lower layers is checked and (2) transitions to higher layers occur only after integrity checks on them are complete. The resulting integrity “chain” inductively guarantees system integrity. When these conditions are not met, as they typically are not in the bootstrapping (initialization) of a computer system, no integrity guarantees can be made, yet these guarantees are increasingly important to diverse applications such as Internet commerce, security systems and “active networks”. In this paper, we describe the AEGIS architecture for initializing a computer system. It validates integrity at each layer transition in the bootstrap process. AEGIS also includes a recovery process for integrity check failures, and we show how this results in robust systems
%B , 1997 IEEE Symposium on Security and Privacy, 1997. Proceedings
%I IEEE
%P 65 - 71
%8 1997/05/04/7
%@ 0-8186-7828-3
%G eng
%R 10.1109/SECPRI.1997.601317
%0 Conference Paper
%B Proceedings of International Symposium on Computer Vision, 1995
%D 1995
%T Iso-distortion contours and egomotion estimation
%A LoongFah Cheong
%A Aloimonos, J.
%K Automation
%K Computer vision
%K Degradation
%K depth distortion
%K Educational institutions
%K egomotion estimation
%K Equations
%K erroneous motion estimates
%K Error analysis
%K HUMANS
%K Image sequences
%K iso-distortion contours
%K Laboratories
%K Layout
%K Motion estimation
%K Robustness
%K visibility constraint
%X This paper introduces the framework of iso-distortion contour to deal with the problem of depth distortion due to erroneous motion estimates, and various related aspects such as the effectiveness of the visibility constraint. The framework can also be used to inquire the uniqueness aspect of normal flow. Future work will examine the implications of the iso-distortion contours for the problem of multiple frame integration
%B Proceedings of International Symposium on Computer Vision, 1995
%I IEEE
%P 55 - 60
%8 1995/11/21/23
%@ 0-8186-7190-4
%G eng
%R 10.1109/ISCV.1995.476977
%0 Conference Paper
%B , 1993 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1993. Proceedings CVPR '93
%D 1993
%T Global 3D motion estimation
%A Fermüller, Cornelia
%K 3D motion parameters
%K Automation
%K axis of rotation
%K Computer vision
%K direction of translation
%K Educational institutions
%K Equations
%K Fluid flow measurement
%K global 3D motion estimation
%K Laboratories
%K Layout
%K monocular observer
%K Motion estimation
%K Motion measurement
%K normal flow measurements
%K Robustness
%K Rotation measurement
%K search problems
%K search technique
%K State estimation
%X It is shown how a monocular observer can estimate its 3D motion relative to the scene by using normal flow measurements in a global and qualitative way. It is proved that local normal flow measurements form global patterns in the image plane. The position of these patterns is related to the 3D motion parameters. By locating some of these patterns, which depend only on subsets of the motion parameters, through a simple search technique, the 3D motion parameters can be found. The proposed algorithmic procedure is very robust, since it is not affected by small perturbations in the normal flow measurements. The direction of translation and the axis of rotation can be estimated with up to 100% error in the image measurements
%B , 1993 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1993. Proceedings CVPR '93
%I IEEE
%P 415 - 421
%8 1993/06/15/17
%@ 0-8186-3880-X
%G eng
%R 10.1109/CVPR.1993.341097
%0 Conference Paper
%B , 11th IAPR International Conference on Pattern Recognition, 1992. Vol.III. Conference C: Image, Speech and Signal Analysis, Proceedings
%D 1992
%T Hierarchical curve representation
%A Fermüller, Cornelia
%A Kropatsch,W.
%K Automation
%K continuous curves
%K curvature
%K data mining
%K digital images
%K Educational institutions
%K Feature extraction
%K hierarchical curve representation
%K IMAGE PROCESSING
%K image recognition
%K image resolution
%K Image segmentation
%K multiresolution structure
%K Object recognition
%K planar curves
%K pyramid
%K Robustness
%K Sampling methods
%K Smoothing methods
%X Presents a robust method for describing planar curves in multiple resolution using curvature information. The method is developed by taking into account the discrete nature of digital images as well as the discrete aspect of a multiresolution structure (pyramid). The authors deal with the robustness of the technique, which is due to the additional information that is extracted from observing the behavior of corners in the pyramid. Furthermore the resulting algorithm is conceptually simple and easily parallelizable. They develop theoretical results, analyzing the curvature of continuous curves in scale-space, which show the behavior of curvature extrema under varying scale. These results are used to eliminate any ambiguities that might arise from sampling problems due to the discreteness of the representation. Finally, experimental results demonstrate the potential of the method
%B , 11th IAPR International Conference on Pattern Recognition, 1992. Vol.III. Conference C: Image, Speech and Signal Analysis, Proceedings
%I IEEE
%P 143 - 146
%8 1992/09/30/Aug-3
%@ 0-8186-2920-7
%G eng
%R 10.1109/ICPR.1992.201947
%0 Conference Paper
%B , 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92
%D 1992
%T Multi-resolution shape description by corners
%A Fermüller, Cornelia
%A Kropatsch,W.
%K ambiguities
%K Automation
%K computational geometry
%K Computer vision
%K continuous curves
%K corners
%K curvature extrema
%K curvature information
%K curve fitting
%K digital images
%K Feature extraction
%K IMAGE PROCESSING
%K image resolution
%K Image segmentation
%K Laboratories
%K multiple resolution
%K multiresolution structure
%K parallelizable
%K planar curves
%K Robustness
%K Sampling methods
%K scale-space
%K SHAPE
%K Smoothing methods
%K varying scale
%X A robust method for describing planar curves in multiple resolution using curvature information is presented. The method is developed by taking into account the discrete nature of digital images as well as the discrete aspect of a multiresolution structure (pyramid). The main contribution lies in the robustness of the technique, which is due to the additional information that is extracted from observing the behavior of corners in the whole pyramid. Furthermore, the resulting algorithm is conceptually simple and easily parallelizable. Theoretical results are developed analyzing the curvature of continuous curves in scale-space and showing the behavior of curvature extrema under varying scale. The results are used to eliminate any ambiguities that might arise from sampling problems due to the discreteness of the representation. Experimental results demonstrate the potential of the method
%B , 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92
%I IEEE
%P 271 - 276
%8 1992/06/15/18
%@ 0-8186-2855-3
%G eng
%R 10.1109/CVPR.1992.223264
%0 Conference Paper
%B Proceedings of 10th International Conference on Pattern Recognition, 1990
%D 1990
%T Purposive and qualitative active vision
%A Aloimonos, J.
%K active vision
%K Automation
%K brain models
%K complex visual tasks
%K Computer vision
%K environmental knowledge
%K highly sophisticated navigational tasks
%K HUMANS
%K Image reconstruction
%K intentions
%K Kinetic theory
%K Laboratories
%K Medusa
%K Motion analysis
%K Navigation
%K planning
%K planning (artificial intelligence)
%K purposive-qualitative vision
%K recovery problem
%K Robust stability
%K Robustness
%K SHAPE
%K stability
%X The traditional view of the problem of computer vision as a recovery problem is questioned, and the paradigm of purposive-qualitative vision is offered as an alternative. This paradigm considers vision as a general recognition problem (recognition of objects, patterns or situations). To demonstrate the usefulness of the framework, the design of the Medusa of CVL is described. It is noted that this machine can perform complex visual tasks without reconstructing the world. If it is provided with intentions, knowledge of the environment, and planning capabilities, it can perform highly sophisticated navigational tasks. It is explained why the traditional structure from motion problem cannot be solved in some cases and why there is reason to be pessimistic about the optimal performance of a structure from motion module. New directions for future research on this problem in the recovery paradigm, e.g., research on stability or robustness, are suggested
%B Proceedings of 10th International Conference on Pattern Recognition, 1990
%I IEEE
%V i
%P 346-360 vol.1 - 346-360 vol.1
%8 1990/06/16/21
%@ 0-8186-2062-5
%G eng
%R 10.1109/ICPR.1990.118128