Video segmentation using keywords

Vinh Ton-That; Chi-Tai Vong; Xuan-Truong Nguyen-Dao; Minh-Triet Tran

doi:10.1117/12.2310102

13 April 2018 Video segmentation using keywords

Vinh Ton-That, Chi-Tai Vong, Xuan-Truong Nguyen-Dao, Minh-Triet Tran

Proceedings Volume 10696, Tenth International Conference on Machine Vision (ICMV 2017); 106960U (2018) https://doi.org/10.1117/12.2310102
Event: Tenth International Conference on Machine Vision, 2017, Vienna, Austria

Abstract

At DAVIS-2016 Challenge, many state-of-art video segmentation methods achieve potential results, but they still much depend on annotated frames to distinguish between background and foreground. It takes a lot of time and efforts to create these frames exactly. In this paper, we introduce a method to segment objects from video based on keywords given by user. First, we use a real-time object detection system - YOLOv2 to identify regions containing objects that have labels match with the given keywords in the first frame. Then, for each region identified from the previous step, we use Pyramid Scene Parsing Network to assign each pixel as foreground or background. These frames can be used as input frames for Object Flow algorithm to perform segmentation on entire video. We conduct experiments on a subset of DAVIS-2016 dataset in half the size of its original size, which shows that our method can handle many popular classes in PASCAL VOC 2012 dataset with acceptable accuracy, about 75.03%. We suggest widely testing by combining other methods to improve this result in the future.

Citation Download Citation

Vinh Ton-That, Chi-Tai Vong, Xuan-Truong Nguyen-Dao, and Minh-Triet Tran "Video segmentation using keywords", Proc. SPIE 10696, Tenth International Conference on Machine Vision (ICMV 2017), 106960U (13 April 2018); https://doi.org/10.1117/12.2310102

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available