Trajectory Analysis and Semantic Region Modeling Using Nonparametric Hierarchical Bayesian Models
International Journal of Computer Vision
Mid-level features and spatio-temporal context for activity recognition
Pattern Recognition
Hybrid Linear Modeling via Local Best-Fit Flats
International Journal of Computer Vision
Background subtraction using low rank and group sparsity constraints
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Multi-scale clustering of frame-to-frame correspondences for motion segmentation
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part I
Advances in Computational Mathematics
Multi-layer spectral clustering for video segmentation
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part II
Motion segmentation by velocity clustering with estimation of subspace dimension
ACCV'12 Proceedings of the 11th international conference on Computer Vision - Volume 2
Background subtraction via coherent trajectory decomposition
Proceedings of the 21st ACM international conference on Multimedia
Editor's Choice Article: Motion-based segmentation of objects using overlapping temporal windows
Image and Vision Computing
Hi-index | 0.14 |
In this paper, we study the problem of segmenting tracked feature point trajectories of multiple moving objects in an image sequence. Using the affine camera model, this problem can be cast as the problem of segmenting samples drawn from multiple linear subspaces. In practice, due to limitations of the tracker, occlusions, and the presence of nonrigid objects in the scene, the obtained motion trajectories may contain grossly mistracked features, missing entries, or corrupted entries. In this paper, we develop a robust subspace separation scheme that deals with these practical issues in a unified mathematical framework. Our methods draw strong connections between lossy compression, rank minimization, and sparse representation. We test our methods extensively on the Hopkins155 motion segmentation database and other motion sequences with outliers and missing data. We compare the performance of our methods to state-of-the-art motion segmentation methods based on expectation-maximization and spectral clustering. For data without outliers or missing information, the results of our methods are on par with the state-of-the-art results and, in many cases, exceed them. In addition, our methods give surprisingly good performance in the presence of the three types of pathological trajectories mentioned above. All code and results are publicly available at http://perception.csl.uiuc.edu/coding/motion/.