FF-Net: Feature-Fusion-Based Network for Semantic Segmentation of 3D Plant Point Cloud

被引:8
作者
Guo, Xindong [1 ,2 ]
Sun, Yu [1 ]
Yang, Hua [1 ]
机构
[1] Shanxi Agr Univ, Coll Informat Sci & Engn, Jinzhong 030801, Peoples R China
[2] North Univ China, Coll Comp Sci & Technol, Taiyuan 030051, Peoples R China
来源
PLANTS-BASEL | 2023年 / 12卷 / 09期
关键词
plant phenotype; point cloud; semantic segmentation; feature fusion; PHENOMICS;
D O I
10.3390/plants12091867
中图分类号
Q94 [植物学];
学科分类号
071001 ;
摘要
Semantic segmentation of 3D point clouds has played an important role in the field of plant phenotyping in recent years. However, existing methods need to down-sample the point cloud to a relatively small size when processing large-scale plant point clouds, which contain more than hundreds of thousands of points, which fails to take full advantage of the high-resolution of advanced scanning devices. To address this issue, we propose a feature-fusion-based method called FF-Net, which consists of two branches, namely the voxel-branch and the point-branch. In particular, the voxel-branch partitions a point cloud into voxels and then employs sparse 3D convolution to learn the context features, and the point-branch learns the point features within a voxel to preserve the detailed point information. Finally, an attention-based module was designed to fuse the two branch features to produce the final segmentation. We conducted extensive experiments on two large plant point clouds (maize and tomato), and the results showed that our method outperformed three commonly used models on both datasets and achieved the best mIoU of 80.95% on the maize dataset and 86.65% on the tomato dataset. Extensive cross-validation experiments were performed to evaluate the generalization ability of the models, and our method achieved promising segmentation results. In addition, the drawbacks of the proposed method were analyzed, and the directions for future works are given.
引用
收藏
页数:16
相关论文
共 31 条
  • [1] Alexandratos N., 2009, FEED WORLD 2050, P1
  • [2] Bao Y., 2017, 2017 ASABE ANN INT M, DOI [10.13031/aim.201700369, DOI 10.13031/AIM.201700369]
  • [3] Design and Development of a Low-Cost UGV 3D Phenotyping Platform with Integrated LiDAR and Electric Slide Rail
    Cai, Shuangze
    Gou, Wenbo
    Wen, Weiliang
    Lu, Xianju
    Fan, Jiangchuan
    Guo, Xinyu
    [J]. PLANTS-BASEL, 2023, 12 (03):
  • [4] Cortinhal Tiago, 2020, Advances in Visual Computing. 15th International Symposium, ISVC 2020. Proceedings. Lecture Notes in Computer Science (LNCS 12510), P207, DOI 10.1007/978-3-030-64559-5_16
  • [5] Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis
    Dai, Angela
    Qi, Charles Ruizhongtai
    Niessner, Matthias
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 6545 - 6554
  • [6] Ding X., 2019, arXiv
  • [7] A Multi-Resolution Approach for an Automated Fusion of Different Low-Cost 3D Sensors
    Dupuis, Jan
    Paulus, Stefan
    Behmann, Jan
    Pluemer, Lutz
    Kuhlmann, Heiner
    [J]. SENSORS, 2014, 14 (04) : 7563 - 7579
  • [8] LiDAR Platform for Acquisition of 3D Plant Phenotyping Database
    Forero, Manuel G.
    Murcia, Harold F.
    Mendez, Dehyro
    Betancourt-Lozano, Juan
    [J]. PLANTS-BASEL, 2022, 11 (17):
  • [9] A handheld device for leaf area measurement
    Gong, Aiping
    Wu, Xiang
    Qiu, Zhengjun
    He, Yong
    [J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2013, 98 : 74 - 80
  • [10] MIX-NET: Deep Learning-Based Point Cloud Processing Method for Segmentation and Occlusion Leaf Restoration of Seedlings
    Han, Binbin
    Li, Yaqin
    Bie, Zhilong
    Peng, Chengli
    Huang, Yuan
    Xu, Shengyong
    [J]. PLANTS-BASEL, 2022, 11 (23):