Name
Abstract | ||
|---|---|---|
Recent years, there has tremendous progress in human detection, whereas only upright poses are usually considered, but the body poses in our daily lives are varied. In this paper, we mainly focus on localizing highly deformable persons which commonly appears in personal photo albums. Decomposition-based human localization is extremely challenging, due to the large pose variances, disabling the traditional part-based template detectors. To deal with the infeasibility of the template-based person models, we propose a decomposition-based human localization model based on the observation that highly deformable persons usually have a distinct body part (upper body) that possesses rigid and highly detectable structural nature, while the rest parts of the human are discriminative yet dependent to the upper body. The model tackles persons with highly deformable in three steps: firstly detect a stable upper body, then extend a set of bigger bounding boxes, from which the most appropriate instance is distinguished by a discriminative Whole Person Model (WPModel). From the experiment results, we can see that our decomposition-based model worked very well in localizing deformable persons, which improved the average precision by 10 % compared to state-of-the-art person detectors. And furthermore, Similar Pose Feature (SPF) shows the feasibility of projecting persons having similar poses into same clusters which facilitate a novel pose-based photo album browsing functionality. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1007/s00530-014-0422-9 | Multimedia Systems |
Keywords | Field | DocType |
Human detection, Decomposition-based human localization, Similar pose retrieval, Image browsing, Big data | Computer vision,Computer science,Artificial intelligence,Discriminative model,Big data,Bounding overwatch | Journal |
Volume | Issue | ISSN |
22 | 1 | 1432-1882 |
Citations | PageRank | References |
1 | 0.35 | 22 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Shaozi Li | 1 | 403 | 54.27 |
| Miaohui Zhang | 2 | 1 | 0.35 |
| Song-zhi Su | 3 | 61 | 8.53 |
| Bing Shuai | 4 | 237 | 12.51 |
| Rongrong Ji | 5 | 3616 | 189.98 |