Edge-Based Template Matching and Tracking for Perspectively Distorted Planar Objects
ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing
Anytime learning for the NoSLLiP tracker
Image and Vision Computing
Multi-object detection and tracking by stereo vision
Pattern Recognition
Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking
International Journal of Computer Vision
Linear Regression and Adaptive Appearance Models for Fast Simultaneous Modelling and Tracking
International Journal of Computer Vision
Ultra-fast tracking based on zero-shift points
Image and Vision Computing
Online learning of linear predictors for real-time tracking
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Robust and accurate shape model fitting using random forest regression voting
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Exploiting features: locally interleaved sequential alignment for object detection
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Efficient learning of linear predictors using dimensionality reduction
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Eye pupil localization with an ensemble of randomized trees
Pattern Recognition
Evaluation of two-view geometry methods with automatic ground-truth generation
Image and Vision Computing
| Hi-index | 0.14 |
We propose a learning approach to tracking explicitly minimizing the computational complexity of the tracking process subject to user-defined probability of failure (loss-of-lock) and precision. The tracker is formed by a Number of Sequences of Learned Linear Predictors (NoSLLiP). Robustness of NoSLLiP is achieved by modeling the object as a collection of local motion predictors - object motion is estimated by the outlier-tolerant Ransac algorithm from local predictions. Efficiency of the NoSLLiP tracker stems from (i) the simplicity of the local predictors and (ii) from the fact that all design decisions - the number of local predictors used by the tracker, their computational complexity (i.e. the number of observations the prediction is based on), locations as well as the number of Ransac iterations are all subject to the optimization (learning) process. All time-consuming operations are performed during the learning stage - tracking is reduced to only a few hundreds integer multiplications in each step. On PC with 1xK8 3200+, a predictor evaluation requires about 30 microseconds. The proposed approach is verified on publicly-available sequences with approximately 12000 frames with ground-truth. Experiments demonstrates, superiority in frame rates and robustness with respect to the SIFT detector, Lucas-Kanade tracker and other trackers.