• Proceedings of the Optical Society of Korea Conference
• /
• 1999.08a
• /
• pp.52-53
• /
• 1999

• Journal of the Institute of Convergence Signal Processing
• /
• v.19 no.1
• /
• pp.1-6
• /
• 2018

In this paper, we propose the method to eliminate repetitive processes for key-point detection on multi-scale image space. The proposed method detects key-points from the original image, and select a good key-points using the cluster filters, and create the key-point clusters. And it select reference objects by using direction angles of the key-point clusters, predict the scale of the original image by using the distributed distance ratio. It transform the scale of the reference image, and apply the detection of key-points to the transformed reference image. In the results of the experiment, the proposed method can be found to improve the key-points detection time by 75 % and 71 % compared to SIFT method and scaled ORB method using the multi-scale images.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.3
• /
• pp.1-9
• /
• 2012

In this paper, we propose a vision-based robust vehicle detection and inter-vehicle distance estimation algorithm for driving assistance system. We use the haar-like features of car rear-shadows, as well as the edge features for detecting of vehicles. The use of additional vehicle edge features greatly reduces the false-positive errors in the vehicle detection. And, after analyzing the conventional two inter-vehicle distance estimation methods: the location-based and the vehicle width-based, an improved inter-vehicle distance estimation algorithm which has the advantage of both method is proposed. Several experimental results show the effectiveness of the proposed method.

• Journal of KIISE:Computer Systems and Theory
• /
• v.27 no.7
• /
• pp.629-638
• /
• 2000

The main difference between mono-volume rendering and multi-volume rendering is data intermixing. In this paper, we first propose a selective rendering method for fast visualizing specific volume according to the surface level and then present data intermixing method for multiple volumes. The selective rendering method is to generate distance transformed volume using a distance transform to determine the minimum distance to the nearest interesting part and then render it. The data intermixing method for multiple volumes is to combine several volumes using intensity weighted intermixing method, opacity weighted intermixing method, opacity weighted intermixing method with depth information and then render it. We show the results of selective rendering of left ventricle and right ventricle generated from EBCT cardiac images and of data intermixing for combining original volume and left ventricular volume or right ventricular volume. Our method offers a visualization technique of specific volume according to the surface level and an acceleration technique using a distance transformed volume and the effective visual output and relation of multiple images using three different intermixing methods in three-dimensional space.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.1
• /
• pp.1-10
• /
• 2001

In order to generate the gray scale image by the binary state imaging devices such as a digital printer, the gray scale image needs to be converted into the binary image by the halftoning techniques. This paper presents a new error diffusion technique to achieve the homogeneous dot distributions on the binary images. In this paper,'the minimum pixel distance'from the current pixel under binarization to the nearest minor pixel is defined first. Also, the gray levels of the input image are converted into a new variable based on the principal distance for the error diffusion. In the proposed method, the difference in the principal distances is utilized for the error propagation, whereas the gray level difference due to the binarization is diffused to the neighboring pixels in the existing error diffusion techniques. The quantization is accomplished by comparing the updated principal distance with the minimum pixel distance. In order to calculate the minimum pixel distance, MPOA(Minor Pixel Offset Array) is employed to reduce the computational loads and memory resources.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.11
• /
• pp.89-94
• /
• 1999

In vector quantization (VQ), mean squared error (MSE) is widely used as a distance measure between vectors. But the distance between averages appears as a dominant quantity in MSE. In the case of image vectors, the coincidence of edge pattern is also important considering human visual system (HVS). Therefore, this paper presents a new distance measure using the variance of difference (VD) as a criterion for the coincidence of edge pattern. By using this in the VQ encoding, we can reduce the degradation of edge region in the reconstructed image. And applying this to the codebook design, we can obtain the final codebook that has a lot of various edge codevectors instead of redundant shade ones.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37C no.12
• /
• pp.1271-1280
• /
• 2012

In the recent parking assistant systems, finding out the distance to the object behind a car is often performed by the range sensors such as ultrasonic sensors, radars. However, the installation of additional sensors on the used vehicle could be difficult and require extra cost. On the other hand, the motion stereo technique that extracts distance information using only an image sensor was also proposed. However, In the stereo rectification step, the motion stereo requires good features and exacts matching result. In this paper, we propose a fast algorithm that extracts the accurate distance information for the parallel parking situation using the consecutive images that is acquired by a rear-view camera. The proposed algorithm uses the quadrangle transform of the image, the horizontal line integral projection, and the blocking-based correlation measurement. In the experiment with the magna parallel test sequence, the result shows that the line-accurate distance measurement with the image sequence from the rear-view camera is possible.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.16 no.1
• /
• pp.3-7
• /
• 2012

Purpose : In myocardial perfusion SPECT, the type of orbit (circular vs. body contouring) that affect the image quality is still on the debate. Presently in the nuclear medicine field, the body contouring orbit acquisition is widely used to improve the image quality on the myocardial perfusion SPECT. But in case of body contouring acquisition using the vertical method with dual detect machine, there is a tendency of increasing the radius. In this research, we compared body contouring orbit acquisition with circular orbit acquisition, so we suggest ideal method that reduces the radius for improving image quality. Materials and Methods : Phantom and clinical studies were performed. The anthropomorphic torso phantom was made on equally with counts from patient's body. The study was performed under six different conditions. To compare image quality according to the radius, we increased radius sequentially per step during circular orbit acquisition. On the other hand, sensors that protect a collision and reduce the radius automatically were used to acquire image during body contouring orbit acquisition. So we compared FWHM value of apex. In clinical studies, we analyzed the 40 patients who were examined by Tl-201 gated myocardial perfusion SPECT in department of nuclear medicine at Asan Medical Center in August 2011. To acknowledge the differences according to the radius, we acquired the results two times using circular orbit acquisition and body contouring orbit acquisition. Results : In phantom study, we analyzed that increase of radius resulted in changes of FWHM value. It was 5.41, 6.24, 6.33, 6.42, 6.93 mm. On the other hand, using the body contouring orbit acquisition, FWHM value was 6.23 mm. In clinical study, difference of average radius between two methods was 2.5 cm (circular orbit acquisition was more close to patients). Conclusion : Through the experiments using Anthropomorphic torso phantom and patients data, we found that FWHM value of circular orbit acquisition was lower than body contouring orbit acquisition. As a result, if the difference of average radius exists approximately 3 cm, circular orbit type acquisition is better than body contouring type acquisition. But clinical investigation is only aimed to average radius, so it needs more investigation in comparison of patient's image.

• ICROS
• /
• v.19 no.4
• /
• pp.32-38
• /
• 2013

전방향 영상 시스템은 한 장의 영상에 360도 모든 방향의 영상정보를 담을 수 있는 영상획득 시스템을 의미한다. 기하광학소자를 이용하여 사람의 눈이나 기존의 카메라로는 한 번에 볼 수 없는 매우 넓은 범위의 영상데이터를 효율적으로 얻을 수 있다. 또한 전방향 영상획득의 원리와 시점이 다른 두 영상, 즉 스테레오 영상획득의 원리를 적용한 전방향 스테레오 영상 시스템은 두 영상간의 정합을 통해 3차원 거리를 측정할 수 있다는 특징이 있다. 본 고에서는 전방향 스테레오 영상획득에 관해 기존에 제안된 연구결과들의 광학적 원리와 장단점을 조사, 비교하였다.

• Proceedings of the KAIS Fall Conference
• /
• 2011.05a
• /
• pp.389-392
• /
• 2011

본 논문에서는 영상의 색 항등성을 달성하기 위해 본질 영상의 핵심인 불변 방향을 K-means 클러스터링을 이용해 검출하는 개선된 알고리즘을 제안한다. 우선, RGB 영상을 K-means 클러스터링 기법에 의해 다수의 클러스터로 분할한다. 이 때, 클러스터 간의 거리 측정은 유클리드 거리이다. 그리고 분할된 클러스터 중 가장 많은 색을 가진 클러스터만을 x-색도 공간으로 도시하여 해당되는 후보 불변 방향을 계산한다. 검출된 후보 불변 방향은 방향별로 프로젝션된 히스토그램에서 3개 이상의 프로젝션된 데이터를 가진 bin들의 개수가 가장 적은 방향이다. 그 후, 분할된 다른 여러 클러스터에 해당되는 후 보 불변 방향을 계산하여 가장 많은 빈도로 나타나는 방향을 영상의 최종 불변 방향으로 결정한다. 실험에서 Ebner에 의해 제안된 데이터집합을 실험 영상으로 사용하였고, 색항등성 측도를 평가 척도로 사용하였다. 실험 결과, 제안한 기법은 형광성 표면을 가진 형광 데이터집합에 보다 적합하였으며, 엔트로피 기법보다 색항등성이 1.5배 이상 높았다.