- 林裕司, 遠山聖司, 藤吉弘亘
- 人工知能学会SIG-Challenge研究会, pp. 38–43, 2005
Download: PDF (Japanese)
In the RoboCup F180 Small Size League, a global vision system using multiple cameras has been used to capture the whole field view. In the overlapping area of two camera’s views, a process to merge information from both cameras should be needed. To avoid this complex process and rule-based approach, we propose a mosaic-based global vision system which produces high resolution images from multiple cameras. Three mosaic images, which take into account the height of each object such as our robots, opponent robots, and the ball on the field are generated by pseudo corresponding points. Our system archives a position accuracy of better than 14.2 mm(mean: 4 mm) over a 5,500 × 4,000 mm field.