首页|Researchers from Tsinghua University Describe Findings in Robotics and Automation (A Spatial Calibration Method for Robust Cooperative Perception)
Researchers from Tsinghua University Describe Findings in Robotics and Automation (A Spatial Calibration Method for Robust Cooperative Perception)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Investigators publish new report on Ro botics - Robotics and Automation. According tonews reporting originating in Bei jing, People’s Republic of China, by NewsRx journalists, research stated,“Coope rative perception is a promising technique for intelligent and connected vehicle s through vehicleto-everything (V2X) cooperation, provided that accurate pose i nformation and relative pose transformsare available. Nevertheless, obtaining p recise positioning information often entails high costs associatedwith navigati on systems.”Financial support for this research came from National Key Ramp;D Program of Chi na.The news reporters obtained a quote from the research from Tsinghua University, “Hence, it is requiredto calibrate relative pose information for multi-agent co operative perception. This letter proposes a simplebut effective object associa tion approach named context-based matching (CBM), which identifies interagento bject correspondences using intra-agent geometrical context. In detail, this met hod constructscontexts using the relative position of the detected bounding box es, followed by local context matching andglobal consensus maximization. The op timal relative pose transform is estimated based on the matchedcorrespondences, followed by cooperative perception fusion. Extensive experiments are conducted on boththe simulated and real-world datasets.”
BeijingPeople’s Republic of ChinaAsiaRobotics and AutomationRoboticsTsinghua University
NETL
NSTL
