심도정보의 Entropy를 이용한 개선된 DCP 안개제거 방법
Improved DCP haze removal method using entropy of depth information
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
본 논문은 안개제거를 위한 대표적인 알고리즘인 DCP(Dark Channel Prior)에서 발생하는 블록현상을 개선하기 위해개선된 전달량 맵(transmission map)을 이용한 안개제거 방법을 제안한다. 기존의 안개제거 방법은 전달량 추정과정에서DCP를 수행할 때 국부영역에 대한 안개 추정을 하기 때문에 블록현상이 발생한다. 제안하는 방법은 확률적 특성인 엔트로피(Entropy)를 이용해 dark channel에서 심도(depth)정보와 경계선(edge)정보를 추정하여 블록현상이 발생하는 부분을 예측하고 그 부분에서 안개 특성을 반영한 상대적으로 작은 크기의 가변의 윈도우를 사용하여 새로운 전달량 맵을 구하고블록현상을 줄인다.
Abstract
This paper proposes a fog removal method that utilizes a new dark channel to improve the block artifact occurring in Dark Channel Prior (DCP). The conventional fog removal method generates a block artifact, because the fog estimation is performed on the local region in the dark channel operation in the process of estimating the amount of delivery. The proposed method estimates the depth and the edge information in the dark channel using the stochastic property, entropy; predicts the region where the block artifact occurs; and obtains the new dark channel using the relatively small-sized window, only in the region that reduces the block artifact.
참고문헌 (15)
- E. R. Davies, "Machine Vision, Third Edition : Theory, Algorithms, Practicallities (Signal Processing and its Applications)" (2005), Morgan Kaufmann
- Z. Rahman, "Multi-scale retinex for color image enhancement", IEEE Proceeding International conference on Image Processing, 3, pp.1003~1006 (1996)
- G. Yadav, "Contrast limited adaptive histogram equalization based enhancement for real time video system", 2014 International Conference on Communications and Informatics Advances in Computing (ICACCI), pp.2392~2397 (2014)
- J. H. Kim, "Single image dehazing based on contrast enhancement", Proceedings of the IEEE Acoustics, Speech and Signal Processing, pp.1273~1276 (2011)
- R. T. Tan, "Visibility in bad weather from a single image", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1~8 (2008)
- K. He, "Single image haze removal using dark channel prior", IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(12), pp.2341~2353 (2011)
- K. He, "Guided image filtering", IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(6), pp.1397~1409 (2012)
- 문선아, "이중 다크 채널에 기반한 고속 고품질의 안개 제거 방법", 방송공학회 논문지, 20(5), pp.697~705 (2015), 한국방송∙미디어공학회[DOI]
- H. Koschmieder, "Theorie der horizontalen sichtweite: kontrast and Sichtweite" (1925), Keim & Nemnich
- C. E. Shannon, "Prediction and entropy of printed English", The Bell System Techinical Journal, 30(1), pp.50~64 (1951)
- B. Singh, "Edge detection in gray level images based on the shannon entropy", Journal of Computer Science, 4(3), pp.186~191 (2008)
- R. C. Gonzalez, "Digital Image Processing using MATLAB" (2004)
- R. C. Gonzalez, "Digital Image Processing" (2007), Prentice Hall
- C. Tomasi, "Bilateral Filtering for Gray and Color Images", Sixth International Conference on Computer Vision, pp.839~846 (1998)
- N. Hautiere, "Blind contrast enhancement assessment by gradient ratioing at visible edges", Image Analysis & Stereology Journal, 27(2), pp.1~7 (2008)