摘要
视觉系统是机器人系统感知外界环境的主要传感器.为了提高系统在不稳定光照条件下的识别准确率和定位精度,提出新的色标设计和根据当前颜色阈值可信度来确定颜色阈值的方法,同时采用数字图像形态学的理论对识别结果进行优化.最后,在"家庭生活支援多机器人系统"中得到了验证.
A robot collects environment information mainly by its vision system.In order to improve recognition accuracy and positioning precision under variable lighting conditions,this paper describes a new pattern design and proposes a method to adjust the color threshold according to the credibility of current color threshold.Image morphology is used to optimize the recognition results.The vision system is tested in the project Family Life Support Multi-Robot Systems.
出处
《上海大学学报（自然科学版）》
CAS
CSCD
北大核心
2010年第3期306-311,共6页
Journal of Shanghai University:Natural Science Edition
基金
国家高技术研究发展计划(863计划)资助项目(2007AA041604)
