Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
Robust Fragments-based Tracking using the Integral Histogram
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
ACM Computing Surveys (CSUR)
Toeplitz And Circulant Matrices: A Review (Foundations and Trends(R) in Communications and Information Theory)
Incremental Learning for Robust Visual Tracking
International Journal of Computer Vision
Semi-supervised On-Line Boosting for Robust Tracking
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Distortion-invariant kernel correlation filters for general object recognition
Distortion-invariant kernel correlation filters for general object recognition
Robust Object Tracking with Online Multiple Instance Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence
Recent advances and trends in visual tracking: A review
Neurocomputing
IEEE Transactions on Pattern Analysis and Machine Intelligence
Globally optimal solution to multi-object tracking with merged measurements
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Struck: Structured output tracking with kernels
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
GMCP-Tracker: global multi-object tracking using generalized minimum clique graphs
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Who are you?: A wearable face recognition system to support human memory
Proceedings of the 4th Augmented Human International Conference
Hi-index | 0.00 |
Recent years have seen greater interest in the use of discriminative classifiers in tracking systems, owing to their success in object detection. They are trained online with samples collected during tracking. Unfortunately, the potentially large number of samples becomes a computational burden, which directly conflicts with real-time requirements. On the other hand, limiting the samples may sacrifice performance. Interestingly, we observed that, as we add more and more samples, the problem acquires circulant structure. Using the well-established theory of Circulant matrices, we provide a link to Fourier analysis that opens up the possibility of extremely fast learning and detection with the Fast Fourier Transform. This can be done in the dual space of kernel machines as fast as with linear classifiers. We derive closed-form solutions for training and detection with several types of kernels, including the popular Gaussian and polynomial kernels. The resulting tracker achieves performance competitive with the state-of-the-art, can be implemented with only a few lines of code and runs at hundreds of frames-per-second. MATLAB code is provided in the paper (see Algorithm 1).