Paper
9 September 2022 Point cloud segmentation of overlapping citrus fruits based on supervoxel clustering and European clustering
XiangWei Mou, Qian Wu, LinTao Chen, GuoQi Sun
Author Affiliations +
Proceedings Volume 12328, Second International Conference on Optics and Image Processing (ICOIP 2022); 123280R (2022) https://doi.org/10.1117/12.2644446
Event: Second International Conference on Optics and Image Processing (ICOIP 2022), 2022, Taian, China
Abstract
In view of the low segmentation accuracy of multiple overlapping images in traditional 3D point cloud segmentation, this paper proposes an overlapping citrus fruit point cloud segmentation method combining supervoxels clustering and European clustering. The color image and depth image of overlapping citrus fruits are obtained by Kinect V2 camera, and the three-dimensional color point cloud of citrus is obtained. Set the color difference threshold to obtain the fruit image, then carry out statistical outlier filtering, and then carry out European clustering segmentation. Set a certain number of point cloud thresholds to extract the point cloud clusters in adhesion state. The segmentation of citrus hypervoxel is realized by clustering the state of citrus hypervoxel. The results of field experiments show that the proposed method has a certain improvement in accuracy and time efficiency compared with the traditional segmentation method.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
XiangWei Mou, Qian Wu, LinTao Chen, and GuoQi Sun "Point cloud segmentation of overlapping citrus fruits based on supervoxel clustering and European clustering", Proc. SPIE 12328, Second International Conference on Optics and Image Processing (ICOIP 2022), 123280R (9 September 2022); https://doi.org/10.1117/12.2644446
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Clouds

Image segmentation

Color difference

Detection and tracking algorithms

Optical filters

Cameras

Distance measurement

Back to Top