首页|New Robotics Data Have Been Reported by Investigators at Guangxi University (Eff icient and Lightweight Grape and Picking Point Synchronous Detection Model Based On Key Point Detection)
New Robotics Data Have Been Reported by Investigators at Guangxi University (Eff icient and Lightweight Grape and Picking Point Synchronous Detection Model Based On Key Point Detection)
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. According to news originating from Nanning, People's Republic of China, by NewsRx correspondents, research stated, "Precise positioning of fruit and pic king point is crucial for harvesting table grapes using automated picking robots in an unstructured agricultural environment. Most studies employ multi-step met hods for locating picking points based on fruit detection, leading to slow detec tion speed, cumbersome models, and algorithmic fragmentation." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), National Natural Science Foundation of Guangxi Province. Our news journalists obtained a quote from the research from Guangxi University, "This study proposes an improved YOLOv8-GP (YOLOv8-Grape and picking point) mod el based on YOLOv8n-Pose to solve the problem of simultaneous detection of grape clusters and picking points. YOLOv8-GP is an end-to-end network that integrates object detection and key point detection. Specifically, the Bottleneck in C2f i s replaced with FasterNet Block that incorporates EMA (Efficient Multi-Scale Att ention), resulting in C2f-Faster-EMA. BiFPN is applied to substitute the origina l PAN as Neck network. The FasterNet Block, designed based on partial convolutio n (PConv), reduces redundant computation and memory access, thereby extracting s patial features more efficiently. The EMA attention mechanism achieves performan ce gains with lower computational overhead. Furthermore, BiFPN is employed to en hance the effect of feature fusion. Experimental results demonstrate that YOLOv8 -GP achieves AP of 89.7 % for grape cluster detection and a Euclid ean distance error of less than 30 pixels for picking point detection. Additiona lly, the number of Params is reduced by 47.73 %, and the model comp lexity GFlops is 6.1G."
NanningPeople's Republic of ChinaAsi aEmerging TechnologiesMachine LearningNano-robotRoboticsGuangxi Univer sity
NETL
NSTL
