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
  • [31] Motion estimation with optical flow-based adaptive search region
    Kim, KK
    Ban, SW
    Lee, KI
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2001, E84A (06): : 1529 - 1531
  • [32] Optical Flow-Based Bird Tracking and Counting for Congregating Flocks
    Tou, Jing Yi
    Toh, Chen Chuan
    INTELLIGENT INFORMATION AND DATABASE SYSTEMS (ACIIDS 2012), PT III, 2012, 7198 : 514 - 523
  • [33] Optical Flow-based Video Completion in Spherical Image Sequences
    Xu, Binbin
    Pathak, Sarthak
    Fujii, Hiromitsu
    Yamashita, Atsushi
    Asama, Hajime
    2016 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS (ROBIO), 2016, : 388 - 395
  • [34] Evaluation of three optical flow-based observation models for tracking
    Lucena, M
    Fuertes, JM
    de la Blanca, NP
    PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 4, 2004, : 236 - 239
  • [35] Optical flow-based observation models for particle filter tracking
    Lucena, Manuel
    Manuel Fuertes, Jose
    Perez de la Blanca, Nicolas
    PATTERN ANALYSIS AND APPLICATIONS, 2015, 18 (01) : 135 - 143
  • [36] An Optical Flow-Based Method to Predict Infantile Cerebral Palsy
    Stahl, Annette
    Schellewald, Christian
    Stavdahl, Oyvind
    Aamo, Ole Morten
    Adde, Lars
    Kirkerod, Harald
    IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2012, 20 (04) : 605 - 614
  • [37] Motion estimation with optical flow-based adaptive search region
    Kim, K.-K.
    Ban, S.-W.
    Lee, K.-I.
    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2001, E84-A (06) : 1529 - 1531
  • [38] Optical flow-based observation models for particle filter tracking
    Manuel Lucena
    Jose Manuel Fuertes
    Nicolas Perez de la Blanca
    Pattern Analysis and Applications, 2015, 18 : 135 - 143
  • [39] Comparing YOLOv8 and Mask R-CNN for instance segmentation in complex orchard environments
    Sapkota, Ranjan
    Ahmed, Dawood
    Karkee, Manoj
    ARTIFICIAL INTELLIGENCE IN AGRICULTURE, 2024, 13 : 84 - 99
  • [40] Flow-based microimmunoassay
    Hayes, MA
    Polson, NA
    Phayre, AN
    Garcia, AA
    ANALYTICAL CHEMISTRY, 2001, 73 (24) : 5896 - 5902