• 방송공학회논문지
• /
• 제11권1호
• /
• pp.91-99
• /
• 2006

전처리는 영상의 질을 개선하거나 영상을 특정한 응용 목적에 알맞도록 변환시키는 등의 영상 처리를 의미한다. Depth 카메라로부터 획득한 화소단위의 8비트 깊이 정보 (depth map) 에는 depth 카메라의 특성상 잡음으로 생각할 수 있는 많은 성분들이 포함되어 있고, RGB 정보에서의 윤곽선에 비해 물체의 특성이나 조명 조건에 의해서 왜곡되어 나타난다. 일반적으로 잡음 제 거 필터가 사용되지만, 이는 깊이 정보 내의 잡음만을 줄이는 역할을 하기 때문에 깊이 정보의 왜곡된 윤곽선 처리는 하지 못 하고 있다. 본 논문에서는 깊이 정보의 잡음을 줄이는 동시에 RGB 정보의 윤곽선을 이용하여 깊이 정보의 왜곡된 윤곽선을 개선하는 알고리즘을 제안함으로써 다시점 입체 영상 생성 시 오차를 줄이고자 한다.

• 한국공간정보시스템학회:학술대회논문집
• /
• 한국공간정보시스템학회 2005년도 GIS/RS 공동 춘계학술대회
• /
• pp.345-349
• /
• 2005

Massive amount of satellite image processing such asglobal/continental-level analysis and monitoring requires automated and speedy georegistration. There could be two major automated approaches: (1) rigid mathematical modeling using sensor model and ephemeris data; (2) heuristic co-registration approach with respect to existing reference image. In case of ETM+, the accuracy of the first approach is known as RMSE 250m, which is far below requested accuracy level for most of satellite image processing. On the other hands, the second approach is to find identical points between new image and reference image and use heuristic regression model for registration. The latter shows better accuracy but has problems with expensive computation. To improve efficiency of the coregistration approach, the author proposed a pre-qualified matching algorithm which is composed of feature extraction with canny operator and area matching algorithm with correlation coefficient. Throughout the pre-qualification approach, the computation time was significantly improved and make the registration accuracy is improved. A prototype was implemented and tested with the proposed algorithm. The performance test of 14 TM/ETM+ images in the U.S. showed: (1) average RMSE error of the approach was 0.47 dependent upon terrain and features; (2) the number average matching points were over 15,000; (3) the time complexity was 12 min per image with 3.2GHz Intel Pentium 4 and 1G Ram.

• 시스템엔지니어링학술지
• /
• 제1권2호
• /
• pp.26-33
• /
• 2005

In this paper, an algorithm is presented to recognize road based on unpaved test courses image. The road images obtained by a video camera undergoes a pre-processing that includes filtering, gray level slicing, masking and identification of unpaved test courses. After this pre-processing, a part of image is grouped into 27 sub-windows and fed into a three-layer feed-forward neural network. The neural network is trained to indicate the road direction. The proposed algorithm has been tested with the images different from the training images, and demonstrated its efficacy for recognizing unpaved road. Based on the test results, it can be said that the algorithm successfully combines the traditional image processing and the neural network principles towards a simpler and more efficient driver warning or assistance system.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.96.6-96
• /
• 2002

In this study an image processing system is designed and developed, which can detect and assort some defects on the surface of an object moving with high speed. For real time surface detection of high speed moving object, the fast processing should be managed and the image information including some surface features should be captured. It is difficult to acquire the noise free image due to various light sources and high speed moving materials under the environment of the general industrial site. In general, because pre-processing methods are employed for getting a noise free feature, the image processing speed has some limitation and the expensive image processing devices are required. This...

• 한국멀티미디어학회:학술대회논문집
• /
• 한국멀티미디어학회 2002년도 추계학술발표논문집
• /
• pp.118-121
• /
• 2002

The study on shilla monumental inscription has been accomplished by many historians. However, the research on segmentation of monumental inscription image using digital image processing is not sufficient for restoration of the image. Although, many image processing methods have been proposed for region extraction in still image, there is no suitable method for accurate interpretation of monumental inscription image. To distinguish foreground and background region in the image, this paper presents new segmentation algorithm composed of contrast adjustment and median filtering, thresholding and sobel operation, as pre-processing and post-processing. The result show that background and foreground regions are segmented in monumental inscription image.

• 방송공학회논문지
• /
• 제23권1호
• /
• pp.162-165
• /
• 2018

본 논문에서는 초고해상도 영상의 효율적인 부호화를 위해 공간적 다운스케일된 입력영상을 이용하여 장면 전환 정보를 획득하기 위한 전처리(pre-processing)과정과 이 정보를 기반으로 화면 간 예측 과정에서 참조 픽처 리스트를 재구성하는 방법을 제안한다. 본 논문에서 제안하는 전처리 과정을 통해 얻어진 정보를 기반으로 참조 픽처 리스트를 재구성하였을 때 기존의 HM 16.12 대비 0.44%의 BD-Rate 개선과 동시에 12.46%의 부호화 속도 향상을 얻을 수 있다.

• 제어로봇시스템학회논문지
• /
• 제9권7호
• /
• pp.498-506
• /
• 2003

A computer vision system applied to an intelligent safety vehicle has been required to be worked on a small sized real time special purposed hardware not on a general purposed computer. In addition, the system should have a high reliability even under the adverse road traffic environment. This paper presents a design and an implementation of an onboard hardware system taking into account for high speed image processing to analyze a road traffic scene. The system is mainly composed of two parts: an early processing module of FPGA and a postprocessing module of DSP. The early processing module is designed to extract several image primitives such as the intensity of a gray level image and edge attributes in a real-time Especially, the module is optimized for the Sobel edge operation. The postprocessing module of DSP utilizes the image features from the early processing module for making image understanding or image analysis of a road traffic scene. The performance of the proposed system is evaluated by an experiment of a lane-related information extraction. The experiment shows the successful results of image processing speed of twenty-five frames of 320$\times$240 pixels per second.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.605-608
• /
• 1999

A conventional image coder, such as JPEG, requires not only DCT and quantization but also additional pre-filtering under noisy environment. Since the pre-filtering removes camera noise and improves coding efficiency dramatically, its efficient implementation has been an important issue. Based on well-known noise removal techniques in image processing fields, this paper introduces an efficient scheme by adapting a noise removal procedure to block-based image coders. By using two-dimensional DCT factorization, the proposed image coder has only a modified DCT and a VLC, and performs pre-filtering and quantization simultaneously in the modified DCT operation.

• 산업경영시스템학회지
• /
• 제22권50호
• /
• pp.11-21
• /
• 1999

In this paper, an algorithm to generate the mounting position and orientation of SMD is proposed. For the proposed algorithm, we used the image captured from PCB and utilized image processing technique. Pre-processing technique, threshold level determination method, divided recognition of the SMD pattern on a PCB, calculating mounting position and orientation are related topics of this research. All of the related topics were reviewed and the results of this research were obtained from applying the algorithm to the real Surface Mounting Machine(model:MCUl/CPM) made by Samsung Electronics Co.

• 대한공간정보학회지
• /
• 제13권4호
• /
• pp.3-9
• /
• 2005

최근 영상 처리를 이용한 교통 정보 추출은 기존의 물리적인 장비들에 비하여 상대적으로 간단한 설치와 적은 비용으로 다양한 정보를 추출하는 장점으로 인하여 널리 연구되고 있다. 이러한 영상을 기반으로 하는 교통정보 추출 알고리즘들은 영상에서 관심 정보인 차량을 정확히 추출하는데서 시작된다. 교통 정보를 추출하는 전단계로서 영상 내에서 움직이는 차량을 검출하기 위해 많이 사용되는 배경빼기(background subtraction) 연산 후 영상 이진화 과정에서 상당한 양의 노이즈가 발생하며, 이는 교통정보의 정확도에 영향을 미친다. 이러한 노이즈는 모든 교통정보가 도로를 주행하고 있는 차량들로부터 추출됨에도 불구하고 실제 영상에서는 비도로영역의 가로수나 행인이 차량과 함께 움직임으로 검출되기 때문에 발생한다. 이를 위해 본 연구에서는 차선정보를 이용하여 도로영역을 추출함으로써 노이즈의 상당부분을 제거할 수 있었으며, 연산의 속도도 높일 수 있었다. 또한, 연속된 영상간의 비(ratio)를 이용하여 차량으로 인한 그림자의 효과를 최소화하였다.