Video Instance Segmentation 2019: A winning approach for combined Detection, Segmentation, Classification and Tracking

被引：11
|
作者：
Luiten, Jonathon [1 ,2 ]
Torr, Philip H. S. [2 ]
Leibe, Bastian [1 ]
机构：
[1] Rhein Westfal TH Aachen, Aachen, Germany
[2] Univ Oxford, Oxford, England
来源：
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW) | 2019年
基金：
英国工程与自然科学研究理事会;
关键词：
D O I：
10.1109/ICCVW.2019.00088
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Video Instance Segmentation (VIS) is the task of localizing all objects in a video, segmenting them, tracking them throughout the video and classifying them into a set of pre-defined classes. In this work, divide VIS into these four parts: detection, segmentation, tracking and. classification. We then develop algorithms for petforming each of these four sub tasks individually, and combine these into a complete solution for VIS. Our solution is an adaptation of Un-OVOST, the current best petforming algorithm for Unsupervised Video Object Segmentation, to this VIS task. We benchmark our algorithm on the 2019 YouTube-VIS Challenge, where we obtain first place with an mAP score of 46.7%.
引用
收藏
页码：709 / 712
页数：4
相关论文
共 50 条
  • [41] Temporal video segmentation by event detection: A novelty detection approach
    Krishna M.V.
    Bodesheim P.
    Körner M.
    Denzler J.
    Pattern Recognition and Image Analysis, 2014, 24 (02) : 243 - 255
  • [42] Video objects segmentation and tracking in video sequences
    Shen, Weiming
    Jiang, Liu
    Chong, Yanwen
    Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University, 2004, 29 (03):
  • [43] Key Points Estimation and Point Instance Segmentation Approach for Lane Detection
    Ko, Yeongmin
    Lee, Younkwan
    Azam, Shoaib
    Munir, Farzeen
    Jeon, Moongu
    Pedrycz, Witold
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (07) : 8949 - 8958
  • [44] A local region proposals approach to instance segmentation for intestinal polyp detection
    Maxwell Hwang
    Yucheng Qian
    Cai Wu
    Wei-Cheng Jiang
    Da Wang
    Jingsun Wei
    Kefeng Ding
    Kao-Shing Hwang
    International Journal of Machine Learning and Cybernetics, 2023, 14 : 1591 - 1603
  • [45] Towards End-to-End Lane Detection: an Instance Segmentation Approach
    Neven, Davy
    De Brabandere, Bert
    Georgoulis, Stamatios
    Proesmans, Marc
    Van Gool, Luc
    2018 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), 2018, : 286 - 291
  • [46] Novel approach to video object detection and precise segmentation
    Zhao, Wenzhe
    Qin, Shiyin
    Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics, 2010, 36 (12): : 1490 - 1494
  • [47] A local region proposals approach to instance segmentation for intestinal polyp detection
    Hwang, Maxwell
    Qian, Yucheng
    Wu, Cai
    Jiang, Wei-Cheng
    Wang, Da
    Wei, Jingsun
    Ding, Kefeng
    Hwang, Kao-Shing
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2023, 14 (05) : 1591 - 1603
  • [48] TIVE: A toolbox for identifying video instance segmentation errors
    Jia, Wenhe
    Yang, Lu
    Jia, Zilong
    Zhao, Wenyi
    Zhou, Yilin
    Song, Qing
    NEUROCOMPUTING, 2023, 545
  • [49] Instance Embedding Transfer to Unsupervised Video Object Segmentation
    Li, Siyang
    Seybold, Bryan
    Vorobyov, Alexey
    Fathi, Alireza
    Huang, Qin
    Kuo, C. -C. Jay
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 6526 - 6535
  • [50] TCOVIS: Temporally Consistent Online Video Instance Segmentation
    Li, Junlong
    Yu, Bingyao
    Rao, Yongming
    Zhou, Jie
    Lu, Jiwen
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, : 1097 - 1107
12345