Orthogonal object proposal and its application
- Authors
- Park, Sung Woo; Kwon, Junseok
- Issue Date
- Jun-2019
- Publisher
- INST ENGINEERING TECHNOLOGY-IET
- Keywords
- learning (artificial intelligence); object tracking; video signal processing; object detection; orthogonal object proposal; orthogonal planes; temporal-horizontal planes; vertical-horizontal plane; video; temporal-vertical planes; visual tracking; deep-learning
- Citation
- IET COMPUTER VISION, v.13, no.4, pp 420 - 427
- Pages
- 8
- Journal Title
- IET COMPUTER VISION
- Volume
- 13
- Number
- 4
- Start Page
- 420
- End Page
- 427
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/32861
- DOI
- 10.1049/iet-cvi.2018.5346
- ISSN
- 1751-9632
1751-9640
- Abstract
- In this study, the authors propose an object proposal algorithm that can accurately propose object candidate regions at each frame, despite noise in a video. Accordingly, they define three orthogonal planes, namely vertical-horizontal, temporal-vertical, and temporal-horizontal planes. As these planes are orthogonal, they are the most compact planes that can span the spatiotemporal space of a video. Their algorithm selects good object proposals for the vertical-horizontal plane with the help of the object proposal results of the other planes. Experimental results demonstrate that the proposed algorithm produces better object proposals than the baseline algorithm and other state-of-the-art methods. In particular, their method provides more accurate object proposals in challenging environments with severe noise and background clutter. In addition, the object proposal results are utilised for visual tracking problems, and the experimental results show that their visual tracker outperforms recent deep-learning-based trackers.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > School of Computer Science and Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/32861)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.