Vision Applications
口頭発表
歩行者支援を目的とした環境変動に頑強な道路状況の自動抽出
- Author
- 藤吉弘亘, 小村剛史
- Publication
- 人工知能学会全国大会, 2003
Download: PDF (Japanese)
This paper describes a method for detecting object from real-time video stream as a part of the “Environment-Embedded Terminal (EET)” system supporting mobility of pedestrian.The EET system robustly detects objects at an outdoor surveillance site.We also proposed an evaluation method based on time duration for the object detection.For 23 cases of video evaluation, a high detection rate was measured under the variations caused by meteorological effects.