• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.11a
• /
• pp.169-171
• /
• 2016

본 논문에서는 일반 자연 영상에서 주로 적용되어 왔던 안개 제거 기법을 기반으로 하여 악천후 상황의 도로 주행 영상을 개선하는 방법을 제안한다. 악천후 상황이란 안개가 있거나 비, 눈이 오는 상황을 의미한다. 도로를 주행하는 환경에서는 비나 눈이 오는 경우에도 안개가 있는 상황과 비슷하기 때문에 안개 제거 기법을 기반으로 하여 악천후 환경의 영상을 개선한다. 우선 최신의 안개 제거 기법 중 하나인 non-local prior 기반의 기법을 도로 주행 영상에 적용 하였을 경우 문제점이 발생하게 되는데 그에 대한 원인을 분석한다. 그리고 이러한 문제점을 해결하기 위하여 예상된 전달량을 보정한다. 모의 실험을 통해 제안하는 방법을 적용하여 도로 주행 영상에서 발생한 문제점을 완화하고 악천후 상황이 개선된 결과를 얻었다.

• Journal of Broadcast Engineering
• /
• v.21 no.5
• /
• pp.770-781
• /
• 2016

As a result of reducing color information and edge information, object distinction in haze image occurs with difficulty. One of the famous defogging algorithm is haze removal by using 'Dark Channel Prior(DCP)', which is used to predict for transmission rate using color information of an image and eliminates haze from the image. But, In case that haze rate is estimated under color information, there is a miscalculated issue which is posed by haze rate and transmission in area with high brightness such as a white object or a light source. In this paper, We deal with a miscalculated issue by correcting from around haze rate, after application of color normalization used by main white part of image haze. Moreover, We calculation improved transmission based on the result of improved haze rate estimation. And then haze image quality is developed through refining transmission.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.85-88
• /
• 2024

안개 영상은 먼지, 안개 등의 원인으로 영상 내의 물체가 흐리게 보이며, 빛의 산란으로 인하여 영상의 밝기가 높다. 기존의 다크 채널 방식은 하늘 영역을 따로 처리하지 않고, 안개 영상에서 얻어지는 다크채널을 바탕으로 전달량을 추정한다. 이러한 방식은 안개 영상 내 하늘 영역이 왜곡되는 문제가 발생하게 된다. 이와 같은 문제점을 해결하기 위하여 본 논문에서는 영상의 반전, 유클리드, 그리고 감마보정을 이용한 적응형 전달량을 추정하여 성능을 개선하였다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.6
• /
• pp.311-317
• /
• 2011

In this paper, we proposed realtime image enhancing method on the three noise types of input images, such as haze, low contrast and back light images. Some conventional de-hazing algorithms have good performance but need large memories and high computational burdens. We proposed the efficient algorithm which not only removes the haze but also reduces memory usage and computational complexity. We implemented the realtime system by using DM6446 DSP chip, and it showed the excellent result in these three problems; haze, low contrast and back light. We implemented the system with the processing speed at 15 frames/sec.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.11a
• /
• pp.148-150
• /
• 2012

외부 환경에 안개가 존재하는 경우, 영상처리의 다양한 알고리즘을 사용하기 어렵다. 이때 안개가 짙은 정도인 전달량을 이용하여 안개를 제거한다. 안개 제거를 위한 대표적인 방법 중 하나인 Dark Channel Prior 알고리즘은 영상의 색 정보를 이용하여 안개의 전달량을 예상한다. 하지만 RGB 전 채널 모두 높은 값을 갖고 있는 영역이, 전달량을 찾는 마스크보다 클 때 전달량을 잘못 예상하게 된다. 본 논문에서는 영상의 edge 정보를 이용하여 영상의 안개가 짙은 정도에 따라 영역을 분할 후 잘못 예상된 전달량을 보정하는 방법을 제안한다. 잘못된 전달량 예상을 통해 색이 왜곡되는 부분을 제거함으로서 기존의 알고리즘과 비교하여 영상 내의 색상이 자연스럽게 안개가 제거된 결과를 얻었다.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.8
• /
• pp.31-39
• /
• 2010

The paper proposes the median filter based Retinex algorithm to detect the lanes in a foggy image. Whether an input image is foggy or not is determined by analyzing the histogram in the pre-defined ROI(Region of Interest). If the image is determined as a foggy one, then it is improved by the median filter based Retinex algorithm. By replacing the Gaussian filter by the median filter in the Retinex algorithm, the processing time can be reduced and the lane features can be detected more robustly. Once the enhanced image is acquired, the binarization based on multi-threshold and the labeling operations are applied. Finally, it detects the lane information using the size and direction parameters of the detected lane features. The proposed algorithm has been evaluated by using various foggy images collected on different road conditions to prove that it detects lanes more robustly in most cases than the conventional methods.

• Journal of Broadcast Engineering
• /
• v.20 no.5
• /
• pp.738-747
• /
• 2015

It is difficult to use a recognition algorithm of an image in a foggy environment because the color and edge information is removed. One of the famous defogging algorithm is haze removal by using 'Dark Channel Prior(DCP)' which is used to predict for transmission rate using color information of an image and eliminates fog from the image. However, in case that the image has factors such as sunset or yellow dust, there is overemphasized problem on the color of certain channel after haze removal. Furthermore, in case that the image includes an object containing high RGB channel, the transmission related to this area causes a misestimated issue. In this paper, we purpose an enhanced fog elimination algorithm by using improved color normalization and haze rate revision which correct mis-estimation haze area on the basis of color information and edge information of an image. By eliminating the color distortion, we can obtain more natural clean image from the haze image.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.814-817
• /
• 2013

In this paper, we propose a visibility enhancement method using dehazing method in fog situation. The proposed method calculate low bound of the transmission rate that indicate fog rate and transmission that processed power operation in each pixel by the user's control. And we obtain the dehazed image using calculated transmission rate. Proposed method is possible real-time processing, because the method don't cause halo effect and drop operations from filtering by closed form. We can obtain the dehazed image in various fog conditions by user control that strength of removing fog can be adjusted according to the dgree of fog.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.326-329
• /
• 2011

안개나 스모그 등으로 인한 영상의 왜곡에 대해 Dark Channel Prior 를 이용해 안개제거를 하면 깨끗한 결과 영상을 얻을 수 있다. 하지만 이 기법에서 전달량을 정련할 때 많은 시간이 걸리는데 계산 속도 면을 개선하기 위해 Gaussian Filter 를 사용해 정련한다. 이 때 단순한 Gaussian Filter 를 사용하게 되면 결과영상에서 후광효과가 생기게 된다. 후광효과를 줄이기 위해 본 논문에서 제안한 적응 Gaussian Filter 를 사용해 영상을 복원시킨다.

• Journal of Broadcast Engineering
• /
• v.18 no.2
• /
• pp.159-166
• /
• 2013

In this paper, we propose a transmission rate compensation method to remove a haze of an image by using edge information of a haze image and image segmentation. With a hazed image, it is difficult not only to recognize objects in the image but also to use an image processing method. One of the famous defogging algorithm named 'Dark Channel Prior'(DCP) is used to predict fog transmission rate using dark area of an image, and eliminates fog from the image. But there is a big possibility to calculate a wrong transmission rate if the area of high RGB values is larger than the area of the reference area. Therefore we eliminate color distortion area to calculate transmission rate by using the propose method, and obtain a natural clean image from a hazed image.