Abstract | ||
---|---|---|
Human body segmentation is essential for many practical applications, e.g., video surveillance analysis in intelligent urban. However, existing methods mainly suffer from various human poses. In this paper, we try to address this issue by introducing human shape constraint. First, human pose estimation is performed, and locations of human body parts are determined. Contrast to the previous work, we just use the human body parts with high precision. Then we combines the star convexity and the human body parts’ locations as shape constraint. The final segmentation results are acquired through the optimization step. Comprehensive and comparative experimental results demonstrate that the proposed method achieves promising performance and outperforms many state-of-the-art methods over publicly available challenging datasets. |
Year | DOI | Venue |
---|---|---|
2017 | https://doi.org/10.1007/s00138-017-0829-3 | Mach. Vis. Appl. |
Keywords | Field | DocType |
Human body segmentation,Shape constraint,Image retrieval,Intelligent video surveillance | Computer vision,Convexity,Scale-space segmentation,Pattern recognition,Segmentation,Computer science,Image retrieval,Pose,Artificial intelligence,Human body | Journal |
Volume | Issue | ISSN |
28 | 7 | 0932-8092 |
Citations | PageRank | References |
2 | 0.40 | 22 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lei Huang | 1 | 24 | 6.42 |
Nie Jie | 2 | 51 | 12.88 |
Zhiqiang Wei | 3 | 307 | 35.82 |