Appearance-based tracking and recognition using the 3D trilinear tensor
| Title | Appearance-based tracking and recognition using the 3D trilinear tensor |
| Publication Type | Conference Papers |
| Year of Publication | 2004 |
| Authors | Shao J, Zhou SK, Chellappa R |
| Conference Name | Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on |
| Date Published | 2004/05// |
| Keywords | 3D, 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 |
| Abstract | 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. |
| DOI | 10.1109/ICASSP.2004.1326619 |