Image processing for robotic person tracking

Mahmoud Tarokh, Paulo Merloti, Wen Shan Lin

研究成果: Conference contribution

摘要

The paper addresses the problem of person tracking in indoor and outdoor environments with significant light variations. This is achieved in part by real-time control of camera parameters affecting the light exposure, i.e. camera gain, shutter speed and iris. Several other new strategies are also formulated to recognize and segment the person from the environment, and to reacquire the person when he is lost during difficult walking maneuvers. The centroid of person's image, which is a critical quantity for person tracking, is determined using a new method based on detected regions and color of the regions. In addition to the camera exposure control, the camera pan and tilt and the moving platform's speed and steering are controlled using the characteristics of the detected person's image such as mass (area) and centroid. The system has been implemented on a Segway robotic platform that has been equipped with a camera, an onboard computer, loud speakers, game-pad, etc. Extensive trials have been carried out both indoors and outdoors, and a video has been prepared that shows the person following under a variety of conditions.

原文English
主出版物標題Proceedings of the 2010 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2010
頁面830-836
頁數7
出版狀態Published - 2010
事件2010 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2010 - Las Vegas, NV, United States
持續時間: 2010 7月 122010 7月 15

出版系列

名字Proceedings of the 2010 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2010
2

Conference

Conference2010 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2010
國家/地區United States
城市Las Vegas, NV
期間10-07-1210-07-15

All Science Journal Classification (ASJC) codes

  • 電腦繪圖與電腦輔助設計
  • 電腦視覺和模式識別

指紋

深入研究「Image processing for robotic person tracking」主題。共同形成了獨特的指紋。

引用此