講演抄録/キーワード |
講演名 |
2008-12-19 14:15
Context-based Robust Face Detection Algorithm for Surveillance Cameras ○Shotaro Miwa・Hiroshi Kage・Kazuhiko Sumi(Mitsubishi Electric Corp.) PRMU2008-181 |
抄録 |
(和) |
This paper describes a context-based robust face detection framework for surveillance cameras. Different from familiar faces in our daily lives, faces captured by surveillance cameras are smaller and darker with motion-blurs and distortions. Furthermore from cameras upward, e.g. on ceilings, faces are downward and partially unseen from cameras. To detect such various directed and degraded faces, we utilize contextual information about faces of walking people in surveillance cameras. We built a probabilistic detection framework combining a face detector with contextual information. Firstly we use a boosted face detector to calculate a primary probability distribution of possible face regions. After this fast filtering to select small amount of possible face regions, we use a HoG feature-based outline detector to calculate a conditional probability from neighboring regions. Combining those two detector-based probabilities with probability of face sizes estimated from a camera configuration, we achieved a high face detection rate of 93.7 % with about 1,000 times lower false positive rate than one in the case of only face detector as well as keeping computational efficiency of the boosted face detector. |
(英) |
This paper describes a context-based robust face detection framework for surveillance cameras. Different from familiar faces in our daily lives, faces captured by surveillance cameras are smaller and darker with motion-blurs and distortions. Furthermore from cameras upward, e.g. on ceilings, faces are downward and partially unseen from cameras. To detect such various directed and degraded faces, we utilize contextual information about faces of walking people in surveillance cameras. We built a probabilistic detection framework combining a face detector with contextual information. Firstly we use a boosted face detector to calculate a primary probability distribution of possible face regions. After this fast filtering to select small amount of possible face regions, we use a HoG feature-based outline detector to calculate a conditional probability from neighboring regions. Combining those two detector-based probabilities with probability of face sizes estimated from a camera configuration, we achieved a high face detection rate of 93.7 % with about 1,000 times lower false positive rate than one in the case of only face detector as well as keeping computational efficiency of the boosted face detector. |
キーワード |
(和) |
contextual information / surveillance camera / face detection / HoG feature / Haar-like feature / AdaBoost / / |
(英) |
contextual information / surveillance camera / face detection / HoG feature / Haar-like feature / AdaBoost / / |
文献情報 |
信学技報, vol. 108, no. 363, PRMU2008-181, pp. 201-206, 2008年12月. |
資料番号 |
PRMU2008-181 |
発行日 |
2008-12-11 (PRMU) |
ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
PRMU2008-181 |