Appearance-based tracking and recognition using the 3D trilinear tensor

TitleAppearance-based tracking and recognition using the 3D trilinear tensor
Publication TypeConference Papers
Year of Publication2004
AuthorsShao J, Zhou SK, Chellappa R
Conference NameAcoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
Date Published2004/05//
Keywords3D, adaptive, affine-transformation, airborne, algorithm;, appearance, appearance-based, based, estimation;, geometrical, image, mathematical, novel, object, operator;, operators;, perspective, prediction;, processing;, recognition;, representation;, signal, structure, synthesis;, template, tensor, tensor;, tensors;, tracking;, transformation;, trilinear, updating;, video, video-based, video;, view

The paper presents an appearance-based adaptive algorithm for simultaneous tracking and recognition by generalizing the transformation model to 3D perspective transformation. A trilinear tensor operator is used to represent the 3D geometrical structure. The tensor is estimated by predicting the corresponding points using the existing affine-transformation based algorithm. The estimated tensor is used to synthesize novel views to update the appearance templates. Some experimental results using airborne video are presented.