Point clouds segmentation of rapeseed siliques based on sparse-dense point clouds mapping
Authors:
Open Access
- 14 July 2023
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 14, 1188286
Abstract
In this study, we propose a high-throughput and low-cost automatic detection method based on deep learning to replace the inefficient manual counting of rapeseed siliques. First, a video is captured with a smartphone around the rapeseed plants in the silique stage. Feature point detection and matching based on SIFT operators are applied to the extracted video frames, and sparse point clouds are recovered using epipolar geometry and triangulation principles. The depth map is obtained by calculating the disparity of the matched images, and the dense point cloud is fused. The plant model of the whole rapeseed plant in the silique stage is reconstructed based on the structure-from-motion (SfM) algorithm, and the background is removed by using the passthrough filter. The downsampled 3D point cloud data is processed by the DGCNN network, and the point cloud is divided into two categories: sparse rapeseed canopy siliques and rapeseed stems. The sparse canopy siliques are then segmented from the original whole rapeseed siliques point cloud using the sparse-dense point cloud mapping method, which can effectively save running time and improve efficiency. Finally, Euclidean clustering segmentation is performed on the rapeseed canopy siliques, and the RANSAC algorithm is used to perform line segmentation on the connected siliques after clustering, obtaining the three-dimensional spatial position of each silique and counting the number of siliques. The proposed method was applied to identify 1457 siliques from 12 rapeseed plants, and the experimental results showed a recognition accuracy greater than 97.80%. The proposed method achieved good results in rapeseed silique recognition and provided a useful example for the application of deep learning networks in dense 3D point cloud segmentation.Keywords
Funding Information
- Huazhong Agricultural University
This publication has 27 references indexed in Scilit:
- A Point-Based Fully Convolutional Neural Network for Airborne LiDAR Ground Point Filtering in Forested EnvironmentsIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020
- A recessive high-density pod mutant resource of Brassica napusPlant Science, 2020
- A Distributed Storage and Computation k-Nearest Neighbor Algorithm Based Cloud-Edge Computing for Cyber-Physical-Social SystemsIEEE Access, 2020
- Estimating tree stem diameters and volume from smartphone photogrammetric point cloudsForestry: An International Journal of Forest Research, 2019
- Use of SfM-MVS approach to nadir and oblique images generated throught aerial cameras to build 2.5D map and 3D models in urban areasGeocarto International, 2019
- Plant-part segmentation using deep learning and multi-view visionBiosystems Engineering, 2019
- Dynamic Graph CNN for Learning on Point CloudsACM Transactions on Graphics, 2019
- Automatic apple recognition based on the fusion of color and 3D feature for robotic fruit pickingComputers and Electronics in Agriculture, 2017
- Plant Breeding Reviews2011
- Robust Image Segmentation Using FCM With Spatial Constraints Based on New Kernel-Induced Distance MeasureIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2004