• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.72-74
• /
• 2011

최근 IT 기술이 융합된 지능형 자동차 기술에 대한 관심이 높아짐에 따라 이에 대한 연구가 활발히 진행되고 있다. 차선 검출은 지능형 자동차의 주요 과제인 첨단 안전자동차 기술의 핵심적인 부분으로 국내외에서 다양한 방법들에 대한 연구가 진행되었다. 차량의 안전을 향상시키기 위해서는 충분한 제동거리 확보가 가능한 거리까지 정확하고 빠른 차선 검출이 이루어져야 한다. 기존의 경계선 검출기법들은 조명 변화에 따라 그 성능의 변화가 크게 발생하였다. 이는 차선과 도로의 사이의 값의 차이가 조명 조건에 따라 변하기 때문이다. 따라서 본 논문에서는 영상 분석을 통하여 경계선을 판단하는 값을 조절함으로써 환경에 적응적인 경계선 추출 방법을 제안한다. 차량 주행 영상에서 제안한 방법과 기존의 경계선 검출 기법을 적용하여 성능을 비교한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2006-2009
• /
• 2005

This paper presents a method for registering images using phase correlation technique in fourier domain, hough transform and multi-resolution wavelet. To register images, source and input images are transformed to wavelet domain. An angular transition can be obtained by applying hough transform technique followed by phase correlation. Then we apply phase correlation technique to find x-axis and y-axis transition. We apply wavelet transform to reduce processing time and also use its coefficients as edge information instead of canny detector. With multi-resolution property of wavelet transform, registration time can be greatly reduced. After we get all transition parameters, we transform the input images according to these parameters. Then, we compose and blend all images into a new large image with details of all source images. From our experiment, we can find the accurate transition both x-y translation and angular transition with less error.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1887-1890
• /
• 2003

This paper presents a three-dimensional (3D) head pose estimation algorithm using the stereo image. Given a pair of stereo image, we automatically extract several important facial feature points using the disparity map, the gabor filter and the canny edge detector. To detect the facial feature region , we propose a region dividing method using the disparity map. On the indoor head & shoulder stereo image, a face region has a larger disparity than a background. So we separate a face region from a background by a divergence of disparity. To estimate 3D head pose, we propose a 2D-3D Error Compensated-SVD (EC-SVD) algorithm. We estimate the 3D coordinates of the facial features using the correspondence of a stereo image. We can estimate the head pose of an input image using Error Compensated-SVD (EC-SVD) method. Experimental results show that the proposed method is capable of estimating pose accurately.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.1729-1730
• /
• 2008

In the industry, the automation of brazing system is very important using the vision senor and the edge detection of the bronze pipe. And also, the accurate coordination is needed for the finding of the precise location. In this paper, we propose an algorithm for the measurement of 3D information of the brazing material and the detection algorithm of soldering area using the camera and IR sensor. We use Canny edge detector in noisy environments. The experimental study shows that camera and IR sensor is useful for the measurement of distance in the brazing work.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.90-93
• /
• 2003

본 논문에서는 watershed segmentation을 이용해서 특정한 영역의 윤곽선정보를 바탕으로 영상을 추출하는 방법을 제안한다. 일반적인 영역추출방법에는 폐곡선을 이용한 영역추출방법, snake라 불리는 에너지 최소화를 이용한 active contour 방법 등 여러 가지가 있다. 특히 이러한 방법에는 연산시간이 많이 걸린다는 단점이 있는데, 이러한 문제점을 해결하기 위해서 canny edge detector를 사용하여 윤곽선 정보를 추출하고, watershed segmentation으로 영상을 분할한 후 윤곽선 정보를 이용해서 특정 영상의 영역에 대한 부분을 병합하여 추출하는 방법을 사용하였다. 제안하는 방법으로 기존의 추출 방법중의 하나인 levelset과 비교 실험한 결과 거의 동일한 영상의 결과를 얻을 수 있었으며 연산시간을 줄일 수 있었다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.431-434
• /
• 2003

In this paper, we propose an efficient method not only f3r producing accurate region segmentation, solving the over-segmentation problem of watershed algorithm but also f3r reducing post-processing time by reducing computation loads. Through this proposed method, region segmentation of neighboring objects and discrimination of similar intensities were effectively obtained. Input image of watershed algorithm has used the derivative-based detectors such as Sobel and Canny. But proposed method uses the pixels-similarity-based detector, that is, SUSAN. By adopting this proposed method, we can reduce the noise problem and solve the problem of over-segmentation and not lose the edge information of objects. We also propose Zero-Crossing SUSAN. With Zero-Crossing SUSAN, the edge localization, times and computation loads can be improved over those obtained from existing SUSAN

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.2
• /
• pp.83-90
• /
• 2011

In cell biology area, microscopy enables detecting objects inside cells that are stained or fluorescently tagged. It is disadvantageous for observing these objects because of the noisy characteristics of their environmental surrounding. In this paper, a framework is proposed to increase the throughput and reliability for analysis of these images. First, we apply adaptive beamlet transform to extract edges meaningfully followed by orientation, location, and length in different scales. Then, a post-process is implemented to extend and map them onto original image. Our proposed scheme is compared with Canny edge detector and conventional beamlet transform from four evaluation aspects. It produces better results when experiments are conducted on real images. Much better results for observing internal parts make this framework competitive for analysis of cell images.

• The Korean Journal of Applied Statistics
• /
• v.32 no.5
• /
• pp.721-740
• /
• 2019

Noise reduction is an important field in image processing and requires a statistical approach. However, it is difficult to assume a specific distribution of noise, and a spatial filter that reflects regional characteristics is a small sample and cannot be accessed in a parametric manner. The first order image differential and the second order image differential show a clear difference according to the noise level included in the image and can be more clearly understood using the canyon edge detector. The Fligner-Killeen test was performed and the bootstrap method was used to statistically check the noise level. The estimated noise level was set between 0 and 1 using the cumulative distribution function of the beta distribution. In this paper, we propose a nonparametric noise reduction algorithm that accounts for the noise level included in the image.

• Proceedings of KOSOMES biannual meeting
• /
• 2006.05a
• /
• pp.47-52
• /
• 2006

The cultural grounds of laver has been surveyed using SPOT-5 satellite images to calculate the facilities of laver cultivation area in the coastal waters of Korea 10m resolution multispectral images of SPOT-5 are adopted for the south area of Daebu Island, Hwaseong city to develop an automatic detection approach of laver nets that consists of the following: band difference technique, canny edge detector and morphological analysis. The satellite-based facilities number was relatively high as compared with the licensed number in 2005, 676,749 chaek and 572,745 chaek(柵, unit of measure for laver farm), respectively. The data could be applied to achieve a good harvest for laver seaweed growers and to control its national production keeping a stable market price for the government body.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.21 no.1
• /
• pp.1-11
• /
• 2018

Mapping accurate spatial information is important for constructing three-dimensional (3D) spatial models and managing artificial facilities, and, especially, mapping road centerlines is necessary for constructing accurate road maps. This research developed a semi-automatic methodology for mapping road centerlines using the MMS(Mobile Mapping System) LiDAR(Light Detection And Ranging) point cloud as follows. First, the intensity image was generated from the given MMS LiDAR data through the interpolation method. Next, the line segments were extracted from the intensity image through the edge detection technique. Finally, the road centerline segments were manually selected among the extracted line segments. The statistical results showed that the generated road centerlines had 0.065 m overall accuracy but had some errors in the areas near road signs.