首页|Study Findings from Sun Yat-sen University Provide New Insights into Androids (A ip-net: an Anchor-free Instance-level Human Part Detection Network)
Study Findings from Sun Yat-sen University Provide New Insights into Androids (A ip-net: an Anchor-free Instance-level Human Part Detection Network)
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 Daily News Daily News-Investigators publish new report on Ro botics-Androids. According to news reporting out of Shenzhen, People's Republi c of China, by NewsRx editors, research stated, "Human part detection has signif icant research and application in computer vision fields such as human- robot in teraction, motion capture, facial recognition, and human key point detection. Ho wever, the current human body part detection method encounters challenges when d etecting multi -scale objects and capturing the correlation relationship between human instances and human parts." Funders for this research include Shenzhen Science and Technology Program, Guang dong Basic and Applied Basic Research Foundation, National Natural Science Found ation of China (NSFC), Science, Technology, and the Innovation Commission of She nzhen Municipality. Our news journalists obtained a quote from the research from Sun Yat-sen Univers ity, "To address these problems, a new anchor -free instance -level human part d etection network (AIP-Net) is proposed. AIP-Net is a ‘two-level'structure that c onsists of two lightweight anchor -free detectors: a body detector and a parts d etector. AIP-Net gradually focuses the human body on the human part from top to down, effectively avoiding the interference of extraneous background and enhanci ng the correlation relationship between human instances and body parts. Addition ally, we design a body -part multidimensional context (BPMC) model in the parts detector branch to enhance the capability of the network. We trained the AIP-Ne end -to -end and achieved a state-of-the-art (SOTA) performance of 36.2 mean ave rage precision (mAP) on COCO Human Parts Dataset."
ShenzhenPeople's Republic of ChinaAs iaAndroidsEmerging TechnologiesHuman-Robot InteractionMachine LearningRobotRoboticsSun Yat-sen University
NETL
NSTL
