首页|Investigators from Jiangsu University Zero in on Robotics (An Image Segmentation and Point Cloud Registration Combined Scheme for Sensing of Obscured Tree Branc hes)
Investigators from Jiangsu University Zero in on Robotics (An Image Segmentation and Point Cloud Registration Combined Scheme for Sensing of Obscured Tree Branc hes)
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-Fresh data on Robotics are presented i n a new report. According to news reporting originating in Jiangsu, People's Rep ublic of China, by NewsRx journalists, research stated, "Automated robots are em erging as a solution for labor-intensive fruit orchard management. Three-dimensi onal (3D) reconstruction of tree branches is a fundamental requirement for robot s to perform tasks like pruning and fruit harvesting." The news reporters obtained a quote from the research from Jiangsu University, " Current branch sensing methods often rely on planar segmentation with limited 3D information or computationally expensive point cloud segmentation, which may no t be suitable for natural orchards with obscured tree branches. This study propo ses a novel scheme that reconstructs occluded branches from RGB-D (Red-Green-Blu e- Depth) images by integrating the point clouds converted from planar segmentati on masks and depth images. The proposed approach extends the existing 2D branch sensing techniques to 3D, leveraging multi-view information. The deep learning m odels DeeplabV3 + and Pix2pix are employed to generate the segmentation masks, s eparately. And the Fast Global Registration (FGR) is used to register the multi- view point clouds. The results demonstrate that the output point clouds have at least a 24 % increase in the number of corresponding points after FGR. Furthermore, the time cost per hundred corresponding points is reduced by 8 5 % and 69 % when using the DeepLabV3 + and Pix2pix- based schemes, respectively, compared to the PointNet ++ approach."
JiangsuPeople's Republic of ChinaAsi aEmerging TechnologiesMachine LearningNano-robotRoboticsJiangsu Univer sity
NETL
NSTL
