Efficient Region Tracking With Parametric Models of Geometry and Illumination
IEEE Transactions on Pattern Analysis and Machine Intelligence
CONDENSATION—Conditional Density Propagation forVisual Tracking
International Journal of Computer Vision
Mean Shift, Mode Seeking, and Clustering
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hyperplane Approximation for Template Matching
IEEE Transactions on Pattern Analysis and Machine Intelligence
Color-Based Probabilistic Tracking
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Proceedings of the 24th DAGM Symposium on Pattern Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Real-Time Tracking Using Trust-Region Methods
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust Object Tracking Via Online Dynamic Spatial Bias Appearance Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
EURASIP Journal on Advances in Signal Processing
Multiple people labeling and tracking using stereo for human computer interaction
HCI'07 Proceedings of the 12th international conference on Human-computer interaction: intelligent multimodal interaction environments
Realtime depth estimation and obstacle detection from monocular video
DAGM'06 Proceedings of the 28th conference on Pattern Recognition
Efficient object identification and localization for image retrieval using query-by-region
Computers & Mathematics with Applications
High-performance template tracking
Journal of Visual Communication and Image Representation
Are you looking at me, are you talking with me: multimodal classification of the focus of attention
TSD'06 Proceedings of the 9th international conference on Text, Speech and Dialogue
Hi-index | 0.00 |
In this paper, we compare and evaluate five contemporary, data-driven, real-time 2D object tracking methods: the region tracker by Hager et al., the Hyperplane tracker, the CONDENSATION tracker, and the Mean Shift and Trust Region trackers. The first two are classical template based methods, while the latter three are from the more recently proposed class of histogram based trackers. All trackers are evaluated for the task of pure translation tracking, as well as tracking translation plus scaling. For the evaluation, we use a publically available, labeled data set consisiting of surveillance videos of humans in public spaces. This data set demonstrates occlusions, changes in object appearance, and scaling.