Interactive Video Object Mask Annotation

Author(s)

• Trung-Nghia Le, National Institute of Informatics
• Tam V. Nguyen, University of DaytonFollow
• Quoc-Cuong Tran, Vietnam National University
• Lam Nguyen, Vietnam National University
• Trung-Hieu Hoang, Vietnam National University
• Minh-Quan Le, Vietnam National University
• Minh-Triet Tran, Vietnam National University

Document Type

Conference Paper

Publication Date

5-18-2021

Publication Source

Proceedings of the AAAI Conference on Artificial Intelligence

Abstract

In this paper, we introduce a practical system for interactive video object mask annotation, which can support multiple back-end methods. To demonstrate the generalization of our system, we introduce a novel approach for video object annotation. Our proposed system takes scribbles at a chosen key-frame from the end-users via a user-friendly interface and produces masks of corresponding objects at the key-frame via the Control-Point-based Scribbles-to-Mask (CPSM) module. The object masks at the key-frame are then propagated to other frames and refined through the Multi-Referenced Guided Segmentation (MRGS) module. Last but not least, the user can correct wrong segmentation at some frames, and the corrected mask is continuously propagated to other frames in the video via the MRGS to produce the object masks at all video frames.

Publisher

Association for the Advancement of Artificial Intelligence

Volume

35

Issue

18

Keywords

Video Object Mask Annotation, Video Object Segmentation, Human-computer Interaction

eCommons Citation

Le, Trung-Nghia; Nguyen, Tam V.; Tran, Quoc-Cuong; Nguyen, Lam; Hoang, Trung-Hieu; Le, Minh-Quan; and Tran, Minh-Triet, "Interactive Video Object Mask Annotation" (2021). Computer Science Faculty Publications. 213.
https://ecommons.udayton.edu/cps_fac_pub/213