抄録
We propose a strategy of background subtraction for an image sequence captured by a moving camera. To adapt for camera motion, it is necessary to estimate the relation between consecutive frames in background subtraction. However, simple background subtraction using the relation between consecutive frames results in many false detections. We use re-projection error to handle this problem. The re-projection error has a low value in a background region. According to re-projection error, our method searches neighboring background models and tunes a threshold value for detection in order to reduce false detections. We evaluated the accuracy of detection of our method in experiments. Our method provided better detection than a method that does not search neighboring background models. Our method thus reduced the number of false detections.
| 元の言語 | 英語 |
|---|---|
| ホスト出版物のタイトル | 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings |
| 出版者 | IEEE Computer Society |
| ページ | 2626-2630 |
| ページ数 | 5 |
| ISBN（電子版） | 9781479983391 |
| DOI | |
| 出版物ステータス | 出版済み - 12 9 2015 |
| イベント | IEEE International Conference on Image Processing, ICIP 2015 - Quebec City, カナダ 継続期間: 9 27 2015 → 9 30 2015 |
出版物シリーズ
| 名前 | Proceedings - International Conference on Image Processing, ICIP |
|---|---|
| 巻 | 2015-December |
| ISSN（印刷物） | 1522-4880 |
その他
| その他 | IEEE International Conference on Image Processing, ICIP 2015 |
|---|---|
| 国 | カナダ |
| 市 | Quebec City |
| 期間 | 9/27/15 → 9/30/15 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
- Computer Vision and Pattern Recognition
- Signal Processing
これを引用
Adaptive search of background models for object detection in images taken by moving cameras. / Minematsu, Tsubasa; Uchiyama, Hideaki; Shimada, Atsushi; Nagahara, Hajime; Taniguchi, Rin Ichiro.
2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. IEEE Computer Society, 2015. p. 2626-2630 7351278 (Proceedings - International Conference on Image Processing, ICIP; 巻 2015-December).研究成果: 著書/レポートタイプへの貢献 › 会議での発言
}
TY - GEN
T1 - Adaptive search of background models for object detection in images taken by moving cameras
AU - Minematsu, Tsubasa
AU - Uchiyama, Hideaki
AU - Shimada, Atsushi
AU - Nagahara, Hajime
AU - Taniguchi, Rin Ichiro
PY - 2015/12/9
Y1 - 2015/12/9
N2 - We propose a strategy of background subtraction for an image sequence captured by a moving camera. To adapt for camera motion, it is necessary to estimate the relation between consecutive frames in background subtraction. However, simple background subtraction using the relation between consecutive frames results in many false detections. We use re-projection error to handle this problem. The re-projection error has a low value in a background region. According to re-projection error, our method searches neighboring background models and tunes a threshold value for detection in order to reduce false detections. We evaluated the accuracy of detection of our method in experiments. Our method provided better detection than a method that does not search neighboring background models. Our method thus reduced the number of false detections.
AB - We propose a strategy of background subtraction for an image sequence captured by a moving camera. To adapt for camera motion, it is necessary to estimate the relation between consecutive frames in background subtraction. However, simple background subtraction using the relation between consecutive frames results in many false detections. We use re-projection error to handle this problem. The re-projection error has a low value in a background region. According to re-projection error, our method searches neighboring background models and tunes a threshold value for detection in order to reduce false detections. We evaluated the accuracy of detection of our method in experiments. Our method provided better detection than a method that does not search neighboring background models. Our method thus reduced the number of false detections.
UR - http://www.scopus.com/inward/record.url?scp=84956627642&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84956627642&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2015.7351278
DO - 10.1109/ICIP.2015.7351278
M3 - Conference contribution
AN - SCOPUS:84956627642
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 2626
EP - 2630
BT - 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
PB - IEEE Computer Society
ER -