| Presentation | 2014-12-12 A detection method of human-object interactions in crowded environment based on hierarchical image analysis Yuto MITSUHASHI, Toru ABE, Takuo SUGANUMA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | To apply for surveillance of luggage lifting/leaving in a lobby and monitoring of buying behavior at a shop, several methods have been developed for extracting human and object regions from an image sequence, determining the relations between them, and recognizing the human activities for the objects. However, it is still difficult to determine the relations between humans and objects in crowded environments, and detect various types of human-object interactions. To deal with this difficulty, we propose a method for detecting human-object interactions (actions in which persons move objects) according to the results of hierarchical image analysis. Our proposed method extracts individual person regions from an input image sequence, and then identifies several body parts of each person. Based on those analysis results, the states around region of interest (lower arm) are acquired, and used as the features for detecting human-object interactions in crowded environments. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Surveillance / crowded environments / region extraction / interaction detection / hierarchical analysis |
| Paper # | PRMU2014-77 |
| Date of Issue |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2014/12/4(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Pattern Recognition and Media Understanding (PRMU) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A detection method of human-object interactions in crowded environment based on hierarchical image analysis |
| Sub Title (in English) | |
| Keyword(1) | Surveillance |
| Keyword(2) | crowded environments |
| Keyword(3) | region extraction |
| Keyword(4) | interaction detection |
| Keyword(5) | hierarchical analysis |
| 1st Author's Name | Yuto MITSUHASHI |
| 1st Author's Affiliation | Graduate School of Information Sciences, Tohoku University() |
| 2nd Author's Name | Toru ABE |
| 2nd Author's Affiliation | Cyberscience Center, Tohoku University |
| 3rd Author's Name | Takuo SUGANUMA |
| 3rd Author's Affiliation | Cyberscience Center, Tohoku University |
| Date | 2014-12-12 |
| Paper # | PRMU2014-77 |
| Volume (vol) | vol.114 |
| Number (no) | 356 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |