Nonlinear component analysis as a kernel eigenvalue problem
Neural Computation
Motion Segmentation and Tracking Using Normalized Cuts
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Vehicle Identification between Non-Overlapping Cameras without Direct Feature Matching
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Robust tracking with motion estimation and local Kernel-based color modeling
Image and Vision Computing
Object matching in disjoint cameras using a color transfer approach
Machine Vision and Applications
Support vector machines for histogram-based image classification
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
Multi-view tracking of objects in video surveillance consists in segmenting and automatically following them through different camera views. This may be achieved using geometric methods, e.g. by calibrating camera sensors and using their transformation matrices. However, in practice the precision of calibration is a major issue when trying to achieve this task robustly. In this paper, we present an alternative framework for multiview object matching and tracking based on canonical correlation analysis. Our method is purely statistical and encodes intrinsic object appearances while being view-point invariant. We will show that our technique is (i) easy-to-set (ii) theoretically well grounded and (iii) provides robust matching and tracking results for traffic surveillance.