Reflection Removal Under Fast Forward Camera Motion
- Authors
- Cheong, Jun Young; Simon, Christian; Kim, Chang-Su; Park, In Kyu
- Issue Date
- 12월-2017
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Black box camera; fast forward motion; reflection removal; dirt removal; layer separation; average image prior
- Citation
- IEEE TRANSACTIONS ON IMAGE PROCESSING, v.26, no.12, pp.6061 - 6073
- Indexed
- SCIE
SCOPUS
- Journal Title
- IEEE TRANSACTIONS ON IMAGE PROCESSING
- Volume
- 26
- Number
- 12
- Start Page
- 6061
- End Page
- 6073
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/81337
- DOI
- 10.1109/TIP.2017.2748389
- ISSN
- 1057-7149
- Abstract
- The image quality of an in-vehicle black box camera is often degraded by the reflections of internal objects, dirt, and dust on the windshield. In this paper, we propose a novel algorithm that simultaneously removes the reflections and small dirt artifacts from in-vehicle black box videos under fast forward camera motion. The algorithm exploits the spatiotemporal coherence of the reflection and dirt, which remain stationary relative to the fast-moving background. Unlike previous algorithms, the algorithm first separates stationary reflection and then restores the background scene. To this end, we propose an average image prior, thereby imposing spatiotemporal coherence. The separation model is a two-layer model composed of stationary and background layers, where different gradient sparsity distributions are utilized in a region-based manner. Motion compensation in postprocessing is proposed to alleviate layer jitter due to vehicle vibrations. In evaluation experiments, the proposed algorithm successfully extracts the stationary layer from several real and synthetic black box videos.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > School of Electrical Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholar.korea.ac.kr/handle/2021.sw.korea/81337)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.