Unsupervised detection of vineyards by 3D point-cloud UAV photogrammetry for precision agriculture

被引:124
|
作者
Comba, Lorenzo [1 ]
Biglia, Alessandro [2 ]
Aimonino, Davide Ricauda [2 ]
Gay, Paolo [2 ]
机构
[1] Politecn Torino, DENERG, Corso Duca Abruzzi 24, I-10129 Turin, Italy
[2] Univ Torino, DiSAFA, Largo Paolo Braccini 2, I-10095 Grugliasco, TO, Italy
关键词
Precision viticulture; Remote sensing; UAV; 3D point-cloud modelling; Images processing; UNMANNED AERIAL SYSTEMS; MACHINE VISION; MANAGEMENT; IMAGERY; PREDICTION;
D O I
10.1016/j.compag.2018.10.005
中图分类号
S [农业科学];
学科分类号
09 ;
摘要
An effective management of precision viticulture processes relies on robust crop monitoring procedures and, in the near future, to autonomous machine for automatic site-specific crop managing. In this context, the exact detection of vineyards from 3D point-cloud maps, generated from unmanned aerial vehicles (UAV) multispectral imagery, will play a crucial role, e.g. both for achieve enhanced remotely sensed data and to manage path and operation of unmanned vehicles. In this paper, an innovative unsupervised algorithm for vineyard detection and vine-rows features evaluation, based on 3D point-cloud maps processing, is presented. The main results are the automatic detection of the vineyards and the local evaluation of vine rows orientation and of inter-rows spacing. The overall point-cloud processing algorithm can be divided into three mains steps: (1) precise local terrain surface and height evaluation of each point of the cloud, (2) point-cloud scouting and scoring procedure on the basis of a new vineyard likelihood measure, and, finally, (3) detection of vineyard areas and local features evaluation. The algorithm was found to be efficient and robust: reliable results were obtained even in the presence of dense inter-row grassing, many missing plants and steep terrain slopes. Performances of the algorithm were evaluated on vineyard maps at different phenological phase and growth stages. The effectiveness of the developed algorithm does not rely on the presence of rectilinear vine rows, being also able to detect vineyards with curvilinear vine row layouts.
引用
收藏
页码:84 / 95
页数:12
相关论文
共 50 条
  • [1] Point-Cloud Segmentation for 3D Edge Detection and Vectorization
    Betsas, Thodoris
    Georgopoulos, Andreas
    [J]. HERITAGE, 2022, 5 (04): : 4037 - 4060
  • [2] GraVoS: Voxel Selection for 3D Point-Cloud Detection
    Shrout, Oren
    Ben-Shabat, Yizhak
    Tal, Ayellet
    [J]. 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 21684 - 21693
  • [3] 3D point cloud analysis for surface roughness measurement: application of UAV photogrammetry
    Mastrorocco, Giovanni
    Salvini, Riccardo
    Esposito, Giuseppe G.
    Seddaiu, Marcello
    [J]. RENDICONTI ONLINE SOCIETA GEOLOGICA ITALIANA, 2016, 41 : 312 - 315
  • [4] AN UNSUPERVISED OUTLIER DETECTION METHOD FOR 3D POINT CLOUD DATA
    Dey, Emon Kumar
    Awrangjeb, Mohammad
    Stantic, Bela
    [J]. 2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019), 2019, : 2495 - 2498
  • [5] 3D Point Cloud Enhancement using Unsupervised Anomaly Detection
    Regaya, Yousra
    Fadli, Fodil
    Amira, Abbes
    [J]. 2019 5TH IEEE INTERNATIONAL SYMPOSIUM ON SYSTEMS ENGINEERING (IEEE ISSE 2019), 2019,
  • [6] Open-Vocabulary Point-Cloud Object Detection without 3D Annotation
    Lu, Yuheng
    Xu, Chenfeng
    Wei, Xiaobao
    Xie, Xiaodong
    Tomizuka, Masayoshi
    Keutzer, Kurt
    Zhang, Shanghang
    [J]. 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR, 2023, : 1190 - 1199
  • [7] Point-cloud Registration Using 3D Shape Contexts
    Price, Mathew
    Green, Jeremy
    Dickens, John
    [J]. 2012 5TH ROBOTICS AND MECHATRONICS CONFERENCE OF SOUTH AFRICA (ROBOMECH), 2012,
  • [8] 3D vision-based bolt loosening assessment using photogrammetry, deep neural networks, and 3D point-cloud processing
    Pan, Xiao
    Yang, T. Y.
    [J]. JOURNAL OF BUILDING ENGINEERING, 2023, 70
  • [9] Target Detection from 3D Point-Cloud using Gaussian Function and CNN
    Liu, ShuaiXin
    Zheng, JianYing
    Wang, Xiang
    Zhang, ZhenYao
    Sun, RongChuan
    [J]. 2019 34RD YOUTH ACADEMIC ANNUAL CONFERENCE OF CHINESE ASSOCIATION OF AUTOMATION (YAC), 2019, : 562 - 567
  • [10] Fast 3D point-cloud segmentation for interactive surfaces
    Mthunzi, Everett M.
    Getschmann, Christopher
    Echtler, Florian
    [J]. ISS '21 COMPANION: COMPANION PROCEEDINGS OF THE 2021 CONFERENCE ON INTERACTIVE SURFACES AND SPACES SPONSORED, 2021, : 33 - 37