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
  • [31] DVIS: Decoupled Video Instance Segmentation Framework
    Zhang, Tao
    Tian, Xingye
    Wu, Yu
    Ji, Shunping
    Wang, Xuebo
    Zhang, Yuan
    Wan, Pengfei
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, : 1282 - 1291
  • [32] Spatiotemporal MRF approach to video segmentation:: Application to motion detection and lip segmentation
    Luthon, F
    Caplier, A
    Liévin, M
    SIGNAL PROCESSING, 1999, 76 (01) : 61 - 80
  • [33] Spatiotemporal MRF approach to video segmentation: Application to motion detection and lip segmentation
    Lab. des Images et des Signaux, Inst. Natl. Polytech. de Grenoble, INPG, 46 avenue Félix-Viallet, 38031 Grenoble Cedex, France
    Signal Process, 1 (61-80):
  • [34] Contextual Guided Segmentation Framework for Semi-supervised Video Instance Segmentation
    Trung-Nghia Le
    Tam V. Nguyen
    Minh-Triet Tran
    Machine Vision and Applications, 2022, 33
  • [35] Contextual Guided Segmentation Framework for Semi-supervised Video Instance Segmentation
    Le, Trung-Nghia
    Nguyen, Tam, V
    Tran, Minh-Triet
    MACHINE VISION AND APPLICATIONS, 2022, 33 (02)
  • [36] Detection, Tracking, and Segmentation of Transient Construction Objects in Video Frames
    Liang, Houhao
    Yeoh, Justin K. W.
    COMPUTING IN CIVIL ENGINEERING 2023-DATA, SENSING, AND ANALYTICS, 2024, : 298 - 307
  • [37] Color instance segmentation and classification of cervix images
    Said, Marwa
    Moustafa, Mohamed
    Wahba, Ayman
    2019 IEEE 10TH GCC CONFERENCE & EXHIBITION (GCC), 2019,
  • [38] Video shot segmentation and classification
    Gong, YH
    Liu, X
    15TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1, PROCEEDINGS: COMPUTER VISION AND IMAGE ANALYSIS, 2000, : 860 - 863
  • [39] Instance Segmentation and Classification of Armoured Fighting Vehicles
    Rissanen, Ville
    Toivonen, Emil
    Lagashkin, Ruslan
    Saastamoinen, Kalle
    Rissanen, Antti
    Vankka, Jouko
    5TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, BIG DATA, COMPUTING AND DATA COMMUNICATION SYSTEMS (ICABCD2022), 2022,
  • [40] InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation
    He, Fei
    Zhang, Haoyang
    Gao, Naiyu
    Jia, Jian
    Shan, Yanhu
    Zhao, Xin
    Huang, Kaiqi
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
12345