• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.658-660
• /
• 2016

최근 디지털 기술의 발달로 인하여 실외 환경에서 획득된 영상은 민수분야 및 군사분야 등과 같이 다양한 목적에 따라 활용되는 분야의 폭이 넓어지고 있다. 교통정보 수집장치, 차량 블랙박스, 산불 및 지진관측, 선락/해안경비 감시, 국경 및 군사표적이동 감시 등의 목적에 의해 촬영된 영상들은 대부분 획득된 영상을 통해서 분석 및 판독의 과정을 거쳐서 각 원하는 정보 획득에 목적을 두고 있다. 하지만 실외에서 촬영된 영상은 실내에서 촬영된 영상에 비해서 기상에 따른 환경적인 요인에 노출이 쉽게 됨으로써 영상에 대한 화질 저하가 발생하는 문제점이 존재한다. 본 논문에서는 화질저하의 원인이 되는 다양한 요인 중에서도 대기중에 존재하는 먼지, 물방울 연무, 안개, 연기 등으로 인해 빛이 산란됨으로써 밝기 값을 왜곡시키는 문제점에 대한 해결 방법을 제안한다.

• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.543-544
• /
• 2012

객체 추적 및 모니터링 시스템에서 안개와 같은 환경적 불완전 요소는 비전 처리 성능에 많은 영향을 준다. 특히 안개는 빛의 산란과 흡수에 의한 감쇠로 탐지 영역내의 물체의 색상이 비슷해지고 채도가 매우 떨어지게 되어 객체의 형태를 구별하기 어려워진다. 따라서 실외에서 신뢰할 수 있는 비전 처리를 위해서는 안개와 같은 환경적 불완전 요소의 제거가 필수라 할 수 있다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.576-578
• /
• 2015

This paper propose the help of the secure a clear view and safe navigation of the coastal ship through the sea-fog removal algorithm. Interest in marine accidents and vessel safety has increased in recent Sewol ferry event. According to statistics coastal ship cause of the marine accident when sea fog on the sea did not secure clear view the ship's occur several incidents of collisions between ships and can see that accounts for a high percentage. Algorithm for image exist sea fog is number of studies. but, such studies take up a lot of calculation quantity in the course of performing the algorithm. In this paper, we improve the computational speed of sea fog over the GPU-based technique was removed to suit real-time video. Furthermore, by using GPU, we succeeded in accelerating the simulation 250 times.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.8
• /
• pp.51-57
• /
• 2014

In this paper, we propose a novel method to effectively eliminate flickering artifacts caused by dehazing in video sequences. When applying a dehazing technique directly to each image in a video sequence, flicker artifacts may occur because atmospheric values are calculated without considering the relation of adjacent frames. Although some existing methods reduce flickering artifacts by calculating highly correlated transmission values between adjacent frames, flickering artifacts may still occur. Therefore, in order to effectively reduce flickering artifacts, we propose a novel approach considering temporal averages of atmospheric light values calculated from adjacent frames. Experimental results have shown that the proposed method achieves better performance of video dehazing with less flickering artifact than existing methods.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.8
• /
• pp.45-52
• /
• 2017

This paper presents a high-performance software-hardware dehazing system based on a dedicated hardware accelerator for the haze removal. In the proposed system, the dedicated hardware accelerator performs the dark-channel-prior-based dehazing process, and the software performs the other control processes. For this purpose, the dehazing process is realized as an OpenCL kernel by finding the inherent parallelism in the algorithm and is synthesized into a hardware by employing a high-level-synthesis technique. The proposed system executes the dehazing process much faster than the previous software-only dehazing system: the performance improvement is up to 96.3% in terms of the execution time.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.3
• /
• pp.119-128
• /
• 2014

This paper presents a new method for improving the quality of images corrupted by an external source that generates an attenuation and scattering of light like dust, water droplets and fog. Conventional defog methods typically encounter a distortion such that the restored image has low contrast and oversaturation of color in some regions because of the mis-estimated airlight and wrong media transmission. Therefore, in order to mitigate these problems, we propose a robust airlight selection method and local saturation evaluation method for estimating media transmission. The proposed method addresses the wrong media transmission and over-saturation problems caused by the mis-estimated airlight and thereby improves the restored image quality. The results of relevant experiments of the proposed method against conventional ones confirm the improved accuracy of atmospheric light estimation and the quality of restored images with regard to objective and subjective performance measures.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4420-4438
• /
• 2021

Image dehazing is an ill-posed problem which is far from being solved. Traditional image dehazing methods often yield mediocre effects and possess substandard processing speed, while modern deep learning methods perform best only in certain datasets. The haze removal effect when processed by said methods is unsatisfactory, meaning the generalization performance fails to meet the requirements. Concurrently, due to the limited processing speed, most dehazing algorithms cannot be employed in the industry. To alleviate said problems, a lightweight fast dehazing network based on a multiple scale-patch framework (MSP) is proposed in the present paper. Firstly, the multi-scale structure is employed as the backbone network and the multi-patch structure as the supplementary network. Dehazing through a single network causes problems, such as loss of object details and color in some image areas, the multi-patch structure was employed for MSP as an information supplement. In the algorithm image processing module, the image is segmented up and down for processed separately. Secondly, MSP generates a clear dehazing effect and significant robustness when targeting real-world homogeneous and nonhomogeneous hazy maps and different datasets. Compared with existing dehazing methods, MSP demonstrated a fast inference speed and the feasibility of real-time processing. The overall size and model parameters of the entire dehazing model are 20.75M and 6.8M, and the processing time for the single image is 0.026s. Experiments on NTIRE 2018 and NTIRE 2020 demonstrate that MSP can achieve superior performance among the state-of-the-art methods, such as PSNR, SSIM, LPIPS, and individual subjective evaluation.