Optical flow-based branch segmentation for complex orchard environments

被引:5
|
作者
You, Alexander [1 ]
Grimm, Cindy [1 ]
Davidson, Joseph R. [1 ]
机构
[1] Oregon State Univ, Collaborat Robot & Intelligent Syst CoRIS Inst, Corvallis, OR 97331 USA
关键词
D O I
10.1109/IROS47612.2022.9982017
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Machine vision is a critical subsystem for enabling robots to be able to perform a variety of tasks in orchard environments. However, orchards are highly visually complex environments, and computer vision algorithms operating in them must be able to contend with variable lighting conditions and background noise. Past work on enabling deep learning algorithms to operate in these environments has typically required large amounts of hand-labeled data to train a deep neural network or physically controlling the conditions under which the environment is perceived. In this paper, we train a neural network system in simulation only using simulated RGB data and optical flow. This resulting neural network is able to perform foreground segmentation of branches in a busy orchard environment without additional real-world training or using any special setup or equipment beyond a standard camera. Our results show that our system is highly accurate and, when compared to a network using manually labeled RGBD data, achieves significantly more consistent and robust performance across environments that differ from the training set.
引用
收藏
页码:9180 / 9186
页数:7
相关论文
共 50 条
  • [11] Miniaturized optical chemosensor for flow-based assays
    Marta Pokrzywnicka
    David J. Cocovi-Solberg
    Manuel Miró
    Víctor Cerdà
    Robert Koncki
    Łukasz Tymecki
    Analytical and Bioanalytical Chemistry, 2011, 399 : 1381 - 1387
  • [12] Towards Optical Flow-based Robotic Homing
    Diamantas, Sotirios Ch.
    Oikonomidis, Anastasios
    Crowder, Richard M.
    2010 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS IJCNN 2010, 2010,
  • [13] Optical flow-based transport on image manifolds
    Nagaraj, S.
    Hegde, C.
    Sankaranarayanan, A. C.
    Baraniuk, R. G.
    APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS, 2014, 36 (02) : 280 - 301
  • [14] Flow-Based Line Detection and Segmentation for Neuromorphic Vision Sensors
    Khairallah, Mahmoud Z.
    Bonardi, Fabien
    Roussel, David
    Bouchafa, Samia
    2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 3603 - 3610
  • [15] A Gradient Vector Flow-Based Method for Video Character Segmentation
    Trung Quy Phan
    Shivakumara, Palaiahnakote
    Su, Bolan
    Tan, Chew Lim
    11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011), 2011, : 1024 - 1028
  • [16] A geometric flow-based approach for diffusion tensor image segmentation
    Guo, Weihong
    Chen, Yunmei
    Zeng, Qingguo
    PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 2008, 366 (1874): : 2279 - 2292
  • [17] Knowledge Distillation for Optical Flow-Based Video Superresolution
    Lee J.
    Park S.-H.
    Journal of Computing Science and Engineering, 2023, 17 (01) : 13 - 19
  • [18] Optical Flow-Based Vascular Respiratory Motion Compensation
    Yang, Keke
    Zhang, Zheng
    Li, Meng
    Cao, Tuoyu
    Ghaffari, Maani
    Song, Jingwei
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 8 (11) : 6987 - 6994
  • [19] Recent electrochemical and optical sensors in flow-based analysis
    Chailapakul, Orawon
    Ngamukot, Passapol
    Yoosamran, Alongkorn
    Siangproh, Weena
    Wangfuengkanagul, Nattakarn
    SENSORS, 2006, 6 (10): : 1383 - 1410
  • [20] Optical flow-based control for automatic steering systems
    Okafuji, Yuki
    Fukao, Takanori
    Yokokohji, Yasuyoshi
    Inou, Hiroshi
    2015 IEEE/SICE INTERNATIONAL SYMPOSIUM ON SYSTEM INTEGRATION (SII), 2015, : 483 - 488