Fast and Accurate Online Video Object Segmentation via Tracking Parts

Jingchun Cheng, Yi Hsuan Tsai, Wei Chih Hung, Shengjin Wang, Ming Hsuan Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

22 Citations (Scopus)

Abstract

Online video object segmentation is a challenging task as it entails to process the image sequence timely and accurately. To segment a target object through the video, numerous CNN-based methods have been developed by heavily finetuning on the object mask in the first frame, which is time-consuming for online applications. In this paper, we propose a fast and accurate video object segmentation algorithm that can immediately start the segmentation process once receiving the images. We first utilize a part-based tracking method to deal with challenging factors such as large deformation, occlusion, and cluttered background. Based on the tracked bounding boxes of parts, we construct a region-of-interest segmentation network to generate part masks. Finally, a similarity-based scoring function is adopted to refine these object parts by comparing them to the visual information in the first frame. Our method performs favorably against state-of-the-art algorithms in accuracy on the DAVIS benchmark dataset, while achieving much faster runtime performance.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
PublisherIEEE Computer Society
Pages7415-7424
Number of pages10
ISBN (Electronic)9781538664209
DOIs
Publication statusPublished - 2018 Dec 14
Event31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 - Salt Lake City, United States
Duration: 2018 Jun 182018 Jun 22

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Conference

Conference31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
CountryUnited States
CitySalt Lake City
Period18/6/1818/6/22

Fingerprint

Masks

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Cheng, J., Tsai, Y. H., Hung, W. C., Wang, S., & Yang, M. H. (2018). Fast and Accurate Online Video Object Segmentation via Tracking Parts. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 (pp. 7415-7424). [8578872] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). IEEE Computer Society. https://doi.org/10.1109/CVPR.2018.00774
Cheng, Jingchun ; Tsai, Yi Hsuan ; Hung, Wei Chih ; Wang, Shengjin ; Yang, Ming Hsuan. / Fast and Accurate Online Video Object Segmentation via Tracking Parts. Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE Computer Society, 2018. pp. 7415-7424 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{63b955b22b384307bd36b364e95688a2,
title = "Fast and Accurate Online Video Object Segmentation via Tracking Parts",
abstract = "Online video object segmentation is a challenging task as it entails to process the image sequence timely and accurately. To segment a target object through the video, numerous CNN-based methods have been developed by heavily finetuning on the object mask in the first frame, which is time-consuming for online applications. In this paper, we propose a fast and accurate video object segmentation algorithm that can immediately start the segmentation process once receiving the images. We first utilize a part-based tracking method to deal with challenging factors such as large deformation, occlusion, and cluttered background. Based on the tracked bounding boxes of parts, we construct a region-of-interest segmentation network to generate part masks. Finally, a similarity-based scoring function is adopted to refine these object parts by comparing them to the visual information in the first frame. Our method performs favorably against state-of-the-art algorithms in accuracy on the DAVIS benchmark dataset, while achieving much faster runtime performance.",
author = "Jingchun Cheng and Tsai, {Yi Hsuan} and Hung, {Wei Chih} and Shengjin Wang and Yang, {Ming Hsuan}",
year = "2018",
month = "12",
day = "14",
doi = "10.1109/CVPR.2018.00774",
language = "English",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "7415--7424",
booktitle = "Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018",
address = "United States",

}

Cheng, J, Tsai, YH, Hung, WC, Wang, S & Yang, MH 2018, Fast and Accurate Online Video Object Segmentation via Tracking Parts. in Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018., 8578872, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, pp. 7415-7424, 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, United States, 18/6/18. https://doi.org/10.1109/CVPR.2018.00774

Fast and Accurate Online Video Object Segmentation via Tracking Parts. / Cheng, Jingchun; Tsai, Yi Hsuan; Hung, Wei Chih; Wang, Shengjin; Yang, Ming Hsuan.

Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE Computer Society, 2018. p. 7415-7424 8578872 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Fast and Accurate Online Video Object Segmentation via Tracking Parts

AU - Cheng, Jingchun

AU - Tsai, Yi Hsuan

AU - Hung, Wei Chih

AU - Wang, Shengjin

AU - Yang, Ming Hsuan

PY - 2018/12/14

Y1 - 2018/12/14

N2 - Online video object segmentation is a challenging task as it entails to process the image sequence timely and accurately. To segment a target object through the video, numerous CNN-based methods have been developed by heavily finetuning on the object mask in the first frame, which is time-consuming for online applications. In this paper, we propose a fast and accurate video object segmentation algorithm that can immediately start the segmentation process once receiving the images. We first utilize a part-based tracking method to deal with challenging factors such as large deformation, occlusion, and cluttered background. Based on the tracked bounding boxes of parts, we construct a region-of-interest segmentation network to generate part masks. Finally, a similarity-based scoring function is adopted to refine these object parts by comparing them to the visual information in the first frame. Our method performs favorably against state-of-the-art algorithms in accuracy on the DAVIS benchmark dataset, while achieving much faster runtime performance.

AB - Online video object segmentation is a challenging task as it entails to process the image sequence timely and accurately. To segment a target object through the video, numerous CNN-based methods have been developed by heavily finetuning on the object mask in the first frame, which is time-consuming for online applications. In this paper, we propose a fast and accurate video object segmentation algorithm that can immediately start the segmentation process once receiving the images. We first utilize a part-based tracking method to deal with challenging factors such as large deformation, occlusion, and cluttered background. Based on the tracked bounding boxes of parts, we construct a region-of-interest segmentation network to generate part masks. Finally, a similarity-based scoring function is adopted to refine these object parts by comparing them to the visual information in the first frame. Our method performs favorably against state-of-the-art algorithms in accuracy on the DAVIS benchmark dataset, while achieving much faster runtime performance.

UR - http://www.scopus.com/inward/record.url?scp=85055454746&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055454746&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2018.00774

DO - 10.1109/CVPR.2018.00774

M3 - Conference contribution

AN - SCOPUS:85055454746

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 7415

EP - 7424

BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018

PB - IEEE Computer Society

ER -

Cheng J, Tsai YH, Hung WC, Wang S, Yang MH. Fast and Accurate Online Video Object Segmentation via Tracking Parts. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE Computer Society. 2018. p. 7415-7424. 8578872. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2018.00774