• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.766-771
• /
• 2002

Automatic change detection based on the vector-to-raster comparison is hard especially in high-resolution image. This paper proposes a method to designate roads in high-resolution image in sequential manner using the information from vector map in which Hough transform is used for reliability. By its linearity, the road of urban areas in a vector map can be easily parameterized. Following some pre-processing to remove undesirable objects, we obtain the edge map of raster image. Then the edge map is transformed to a parameter space to find the selected road from vector map. The comparison is done in the parameter space to find the best matching. The set of parameters of a road from vector map is treated as the constraints to do matching. After designating the road, we may overlay it on the raster image for precise monitoring. The results can be used for detection of changes in road object in a semi-automatic fashion.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.241-244
• /
• 2005

Many building detection methods mainly rely on line segments extracted from aerial or satellite imagery. Building detection methods based on line segments, however, are difficult to succeed in high resolution satellite imagery such as IKONOS imagery, for most buildings in IKONOS imagery have small size of roofs with low contrast between roof and background. In this paper, we propose an efficient method to extract line segments and group them at the same time. First, edge preserving filtering is applied to the imagery to remove the noise. Second, we segment the imagery by watershed method, which collects the pixels with similar intensities to obtain homogeneous region. The boundaries of homogeneous region are not completely coincident with roof boundaries due to low contrast in the vicinity of the roof boundaries. Finally, to resolve this problem, we set up snake model with segmented region boundaries as initial snake's positions. We used a greedy algorithm to fit a snake to roof boundary. Experimental results show our method can obtain more .correct roof boundary with small size and low contrast from IKONOS imagery. Snake algorithm, building roof detection, watershed segmentation, edge-preserving filtering

• 전기학회논문지P
• /
• 제62권2호
• /
• pp.90-94
• /
• 2013

In this paper, we propose a new algorithm to improve the contrast ratio, to preserve information of bright regions and to maintain the color of backlight image that appears with a great relative contrast. Backlight images of the natural environment have characteristics for difference of local brightness; the overall image contrast improvement is not easy. To improve the contrast of the backlight images, MSR (Multi-Scale Retinex) algorithm using the existing multi-scale Gaussian filter is applied. However, existing multi-scale Gaussian filter involves color distortion and information loss of bright regions due to excessive contrast enhancement and noise because of the brightness improvement of dark regions. Moreover, it also increases computational complexity due to the use of multi-scale Gaussian filter. In order to solve these problems, a linear MSR is performed that reduces the amount of computation from the HSV color space preventing the color distortion and information loss due to excessive contrast enhancement. It can also remove the noise of the dark regions which is occurred due to the improved contrast through edge preserving filter. Through experimental evaluation of the average color difference comparison of CIELAB color space and the visual assessment, we have confirmed excellent performance of the proposed algorithm compared to conventional MSR algorithm.

• 한국조명전기설비학회:학술대회논문집
• /
• 한국조명전기설비학회 2009년도 추계학술대회 논문집
• /
• pp.73-76
• /
• 2009

The optical structure of edge-lit LED backlight has been optimized via simulation study in order to remove bright spots appearing on the entrance region of the light guide plate (LGP) and thus to improve the luminance uniformity. The density of scattering dots located on the back surface of LGP was adjusted according to the location of LED's. In addition, lenticular lenses or a diffuse transmissive surface were formed on the side surface of LGP facing the LED's, and the density of lenticular lenses was optimized for redistributing rays emitted from LED's into wider angles. The bright spots which could be seen from conventional LED backlight were removed by the combination of these two optical structures. The application of diffuse surface to the entrance face gave better uniformity than the application of lenticular lenses. However, dark regions still appear on the entrance region of LGP, which should be removed by more appropriate optical design for achieving better luminance uniformity on the LED backlight.

• 한국멀티미디어학회논문지
• /
• 제17권12호
• /
• pp.1393-1401
• /
• 2014

This paper presents an adaptive image interpolation method using a pixel-based neighbor embedding which is modified from the patch-based neighbor embedding of contemporary super resolution algorithms. Conventional interpolation methods for high resolution detect at least 16-directional edges in order to remove zig-zaging effects and selectively choose the interpolation strategy according to the direction and value of edge. Thus, they require much computation and high complexity. In order to develop a simple interpolation method preserving edge's directional shape, the proposed algorithm adopts the simplest Haar wavelet and suggests a new pixel-based embedding scheme. First, the low-quality image but high resolution, magnified into 1 octave above, is acquired using an adaptive 8-directional interpolation based on the high frequency coefficients of the wavelet transform. Thereafter, the pixel embedding process updates a high resolution pixel of the magnified image with the weighted sum of the best matched pixel value, which is searched at its low resolution image. As the results, the proposed scheme is simple and removes zig-zaging effects without any additional process.

• Tribology and Lubricants
• /
• 제33권6호
• /
• pp.282-287
• /
• 2017

SU-8 is an epoxy-type photoresist widely used for the fabrication of high-aspect-ratio (HAR) micro-structures in micro-electro-mechanical systems (MEMS). To fabricate highly integrated structures, chemical mechanical polishing (CMP) has emerged as the preferred manufacturing process for planarizing the MEMS structure. In SU-8 CMP, an oxidizer decomposes organic impurities and particles in the CMP slurry remove the chemically reacted surface of SU-8. To fabricate HAR microstructures using the CMP process, the adhesion between SU-8 and substrate material is important to avoid the delamination of the SU-8 film caused by the mechanical-dominant material removal characteristic. In this study, the friction force during the CMP process is measured with a CMP monitoring system to detect the delamination phenomenon and investigate the delamination of the SU-8 film from the silicon substrate under various pressure conditions. The increase in applied pressure causes an increase in the frictional force and wafer-edge stress concentration. The frictional force measurement shows that the friction force changes according to the delamination phenomenon of the SU-8 film, and that it is possible to monitor the delamination phenomenon during the SU-8 CMP process. The delamination at a high applied pressure is explained by the effect of stress distribution and pad deformation. Consequently, it is necessary to control the pressure of polishing, which can avoid the delamination in SU-8 CMP.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.250-253
• /
• 2002

The operation of surface and edge finishing is the last and essential process of parts machining, because a product is completed as an assembly. Therefore, the quality of the finished parts has a direct effect upon the performance of the product. Especially, the edge quality depending on the burr control process is very important. A number of deburring processes have been developed for macro burrs such as barreling, brushing, chemical methods, etc. However, micro burr removal when piercing a very thin plate is very difficult, because this badly deteriorates the surface quality of the processed part. When ultrasonic wave is propagated in liquids, it forms an infinitude of micro bubbles. These bubbles generate extremely strong force, which removes micro burrs. In ultrasonic micro deburring, the problem is that burrs are not removed completely, because only components of the explosive force directly act on the burrs, which is not enough. An attempt was made to remove the burrs using ultrasonic vibration in water with SiC as an abrasive agent. Because of the abrasive, smoother edges have been achieved. There are many control parameters in ultrasonic deburring such as abrasive size, ultrasonic frequency and amplitude, distance between tool and workpiece, tilt angle of workpiece etc. This study focuses on how distance and tilt angle influence deburring effect. A number of experiments for these parameters have been carried out, and then the effect of each parameter analyzed.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2017년도 추계학술대회
• /
• pp.694-696
• /
• 2017

영상처리는 사회가 고도의 디지털 정보화 시대로 발전함에 따라 응용분야가 점차 다양해지고, 중요한 분야로 각광 받고 있다. 특히, 영상에 첨가되는 잡음을 제거하기 위한 연구가 활발하게 진행되고 있다. 따라서 본 논문에서는 salt and pepper 잡음 환경에서 훼손된 영상을 복원하기 위해, 영상에 발생한 잡음을 이웃 화소로 대체하는 동시에 에지 보존을 위해 국부 마스크의 방향에 따른 가중치 필터로 처리하는 영상 복원 필터를 제안하였다. 그리고 개선 효과의 객관적 판단 기준으로 PSNR(peak signal to noise ratio)을 사용하여 기존의 방법들과 비교하였다.

• 융합신호처리학회논문지
• /
• 제15권3호
• /
• pp.76-79
• /
• 2014

얼굴 인식은 표정과 포즈 또는 주변 조명변화 등 예기치 못한 영향으로 어려움이 크다. 또한 모바일 장치에서 실시간 처리를 위하여 모바일 환경의 한정된 제한이 필히 고려되어야 한다. 본 논문에서 모바일 환경에서 주파수 영역의 정합 필터를 이용한 얼굴 검출 방법을 제안한다. 얼굴 검출은 선형(Linear) 또는 위상(Phase-only) 정합 필터(Matched filter), 순차적인 검증 단계를 이용하여 수행된다. 먼저 얼굴 후보 윈도우 영역은 정합필터의 출력에 의하여 추출되고 그 다음에 피부색 테스트와 에지 마스크 필터링 테스트로 검출된 후보 영역 중 오경보(False alarm) 영역이 제거된다. 제안된 방법은 Android 플랫폼에서 JAVA를 이용하여 개발되었다. 실험 결과는 모바일 환경에서 얼굴 인식이 실시간으로 성공적으로 수행될 수 있음을 보인다.

• 대한임베디드공학회논문지
• /
• 제17권1호
• /
• pp.41-49
• /
• 2022

This paper proposes a novel lane detection algorithm based on inverse perspective transformation and machine learning in lightweight embedded system. The inverse perspective transformation method is presented for obtaining a bird's-eye view of the scene from a perspective image to remove perspective effects. This method requires only the internal and external parameters of the camera without a homography matrix with 8 degrees of freedom (DoF) that maps the points in one image to the corresponding points in the other image. To improve the accuracy and speed of lane detection in complex road environments, machine learning algorithm that has passed the first classifier is used. Before using machine learning, we apply a meaningful first classifier to the lane detection to improve the detection speed. The first classifier is applied in the bird's-eye view image to determine lane regions. A lane region passed the first classifier is detected more accurately through machine learning. The system has been tested through the driving video of the vehicle in embedded system. The experimental results show that the proposed method works well in various road environments and meet the real-time requirements. As a result, its lane detection speed is about 3.85 times faster than edge-based lane detection, and its detection accuracy is better than edge-based lane detection.