scholarly journals Low-Rank Spatio-Temporal Video Segmentation

Author(s):  
Alasdair Newson ◽  
Mariano Tepper ◽  
Guillermo Sapiro
Author(s):  
Caiyun Huang ◽  
Guojun Qin

This paper investigates how to perform robust and efficient unsupervised video segmentation while suppressing the effects of data noises and/or corruptions. The low-rank representation is pursued for video segmentation. The supervoxels affinity matrix of an observed video sequence is given, low-rank matrix optimization seeks a optimal solution by making the matrix rank explicitly determined. We iteratively optimize them with closed-form solutions. Moreover, we incorporate a discriminative replication prior into our framework based on the obervation that small-size video patterns, and it tends to recur frequently within the same object. The video can be segmented into several spatio-temporal regions by applying the Normalized-Cut algorithm with the solved low-rank representation. To process the streaming videos, we apply our algorithm sequentially over a batch of frames over time, in which we also develop several temporal consistent constraints improving the robustness. Extensive experiments are on the public benchmarks, they demonstrate superior performance of our framework over other approaches.


2014 ◽  
Vol 23 (9) ◽  
pp. 3829-3840 ◽  
Author(s):  
Yuliya Tarabalka ◽  
Guillaume Charpiat ◽  
Ludovic Brucker ◽  
Bjoern H. Menze

2015 ◽  
Vol 17 (1) ◽  
pp. 3-15 ◽  
Author(s):  
Hanqing Jiang ◽  
Guofeng Zhang ◽  
Huiyan Wang ◽  
Hujun Bao

Sign in / Sign up

Export Citation Format

Share Document