基于嵌入式的机器人视觉伺服寻迹系统研究-A Biprocessor-Oriented Vision-Based Target Tracking System.pdf

500 IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, VOL. 49, NO. 2, APRIL 2002 A Biprocessor-Oriented Vision-Based Target Tracking System Raphaël Canals, Anthony Roussel, Jean-Luc Famechon, and Sylvie Treuillet Abstract— The design and realization of a vision-based target The second approach uses primitive or block matching, im- tracking system is proposed. The objective is to derive the orienta- plementing the technique of correlation [1], [4], [21], [30], [38]. tion of a pan-tilt camera fitting a drone in order to track a target Each position of a block is tested inside a predefined search and to maintain its position in the middle of the image. Image data and drone attitude are the only information available for the zone by using a difference measurement. In the literature, the camera control to be achieved correctly. This embedded system block matching technique is principally used in motion estima- requires low-cost hardware for surveillance or attack drone appli- tion schemes for video transmission, especially for low bit-rate cations: a digital signal processor for the image processing, and a coding (H261 [7], MPEG [28]). Thus, displacements of objects microcontroller for the camera control. To ensure real-time video moving in an image sequence can be measured and used to pre- operation, an algorithmic solution integrating a successive-step and multi-block search method is implemented, thus allowing dict the content of frames later in the sequence. The basic tech- complex target displacements. The microcontroller uses this nique consists of dividing each image in