• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.3
• /
• pp.10-20
• /
• 2019

Irregular rainfall caused by climate change, in combination with non-point pollution, can cause water systems worldwide to suffer from frequent eutrophication and algal blooms. This type of water pollution is more common in agricultural prone to water system inflow of non-point pollution. Therefore, in this study, the correlation between Unmanned Aerial Vehicle(UAV) multi-spectral images and total phosphorus, total nitrogen, and chlorophyll-a with indirect association of algal blooms, was analyzed to identify the usability of UAV image to identify water quality characteristics in agricultural streams. The analysis the vegetation index Normalized Differences Index (NDVI), the Normalized Differences Red Edge(NDRE), and the Chlorophyll Index Red Edge(CIRE) for the detection of multi-spectral images and algal blooms collected from the target regions Yang cheon and Hamyang Wicheon. The analysis of the correlation between image values and water quality analysis values for the water sampling points, total phosphorus at a significance level of 0.05 was correlated with the CIRE(0.66), and chlorophyll-a showed correlation with Blue(-0.67), Green(-0.66), NDVI(0.75), NDRE (0.67), CIRE(0.74). Total nitrogen was correlated with the Red(-0.64), Red edge (-0.64) and Near-Infrared Ray(NIR)(-0.72) wavelength at the significance level of 0.05. The results of this study confirmed a significant correlations between multi-spectral images collected through UAV and the factors responsible for water pollution, In the case of the vegetation index used for the detection of algal bloom, the possibility of identification of not only chlorophyll-a but also total phosphorus was confirmed. This data will be used as a meaningful data for counterplan such as selecting non-point pollution apprehensive area in agricultural area.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.3
• /
• pp.11-22
• /
• 2010

This paper is a study on implementation of intelligent image surveillance system using context information and supplements temporal-spatial constraint, the weak point in which it is hard to process it in real time. In this paper, we propose scene analysis algorithm which can be processed in real time in various environments at low resolution video(320*240) comprised of 30 frames per second. The proposed algorithm gets rid of background and meaningless frame among continuous frames. And, this paper uses wavelet transform and edge histogram to detect shot boundary. Next, representative key-frame in shot boundary is selected by key-frame selection parameter and edge histogram, mathematical morphology are used to detect only motion region. We define each four basic contexts in accordance with angles of feature points by applying vertical and horizontal ratio for the motion region of detected object. These are standing, laying, seating and walking. Finally, we carry out scene analysis by defining simple context model composed with general context and emergency context through estimating each context's connection status and configure a system in order to check real time processing possibility. The proposed system shows the performance of 92.5% in terms of recognition rate for a video of low resolution and processing speed is 0.74 second in average per frame, so that we can check real time processing is possible.

• Journal of KIISE:Databases
• /
• v.36 no.4
• /
• pp.263-279
• /
• 2009

Shape features in a content-based image retrieval (CBIR) system are divided into two classes: contour-based and region-based. Contour-based shape features are simple but they are not as efficient as region-based shape features. Most systems using the region-based shape feature have to extract the region firs t. The prior works on region-based systems still have shortcomings. They are complex to implement, particularly with respect to region extraction, and do not sufficiently use the spatial relationship between regions in the distance model In this paper, a region extraction method that is the combination of an edge-based method and a region growing method is proposed to accurately extract regions inside an object. Edges inside an object are accurately detected based on the Canny edge detector and the Hough transform. And the modified Integrated Region Matching (IRM) scheme which includes the adjacency relationship of regions is also proposed. It is used to compute the distance between images for the similarity search using shape features. The experimental results show the effectiveness of our region extraction method as well as the modified IRM. In comparison with other works, it is shown that the new region extraction method outperforms others.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.6
• /
• pp.12-18
• /
• 2010

Automatic Target Detection (ATD) systems that use forward-looking infrared (FLIR) consists of three stages. preprocessing, detection, and clutter rejection. All potential targets are extracted in preprocessing and detection stages. But, this results in a high false alarm rates. To reduce false alarm rates of ATD system, true targets are extracted in the clutter rejection stage. This paper focuses on clutter rejection stage. This paper presents a new clutter rejection technique using PCA features and stochastic features of clutters and targets. PCA features are obtained from Euclidian distances using which potential targets are projected to reduced eigenspace selected from target eigenvectors. CV is used for calculating stochastic features of edges in targets and clutters images. To distinguish between target and clutter, LDA (Linear Discriminant Analysis) is applied. The experimental results show that the proposed algorithm accurately classify clutters with a low false rate compared to PCA method or CV method

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.3
• /
• pp.102-112
• /
• 2013

In this paper, two step processing method of contour extraction and complement which contain hexagonal shape for low contrast and noisy images is proposed. This method is based on the combination of Laplacian-Gaussian filter and an idea of filters which are dependent on the shape. At the first step, an algorithm which has six masks as its extractors to extract the hexagonal edges especially in the corners is used. Here, two tricorn filters are used to detect the tricorn joints of hexagons and other four masks are used to enhance the line segments of hexagonal edges. As a natural image, a corneal endothelial cell image which usually has regular hexagonal form is selected. The edge extraction of hexagonal shapes in corneal endothelial cell is important for clinical diagnosis. The proposed algorithm and other conventional methods are applied to noisy hexagonal images to evaluate each efficiency. As a result, this proposed algorithm shows a robustness against noises and better detection ability in the aspects of the output signal to noise ratio, the edge coincidence ratio and the extraction accuracy factor as compared with other conventional methods. At the second step, the lacking part of the thinned image by an energy minimum algorithm is complemented, and then the area and distribution of cells which give necessary information for medical diagnosis are computed.

• Journal of the Korean Society of Radiology
• /
• v.17 no.4
• /
• pp.523-529
• /
• 2023

In order to achieve excellent spatial resolution, very small scintillation pixels are used in detectors of positron emission tomography for small animals. However, by using these very small scintillation pixels, scintillation pixels at the edge of the array may overlap in a flood image. To solve this problem, a light guide capable of changing the distribution of light was used. Depending on the material of the light guide, the light spreading tendency is different, and accordingly, the presence or absence of overlapping is different depending on the material of the light guide used. In this study, instead of the conventional glass light guide, a detector using the same material as the scintillation pixel was designed. A scintillator light guide has a higher refractive index than a glass light guide, so the light spread is different. Flood images were acquired to evaluate the degree of separation of the scintillation pixels at the edge of the detector using the two light guides. The degree of separation was evaluated by calculating the distance between the center and the spatial resolution of the image of two scintillation pixels at the edge of the obtained flood image. As a result, when the scintillator light guide was used, better spatial resolution was shown, and the distance between centers of scintillation pixels was wider. When a detector is constructed using a scintillator light guide instead of a conventional glass light guide, it is possible to use a smaller scintillation pixel, thereby securing better spatial resolution.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.678-681
• /
• 2004

In this paper, efficient tracking of a moving object using optimal representative blocks is implemented by a mobile robot with a pan-tilt camera. The key idea comes from the fact that when the image size of moving object is shrunk in an image frame according to the distance between the camera of mobile robot and the moving object, the tracking performance of a moving object can be improved by changing the size of representative blocks according to the object image size. Motion estimation using Edge Detection(ED) and Block-Matching Algorithm(BMA) is often used in the case of moving object tracking by vision sensors. However these methods often miss the real-time vision data since these schemes suffer from the heavy computational load. In this paper, the optimal representative block that can reduce a lot of data to be computed, is defined and optimized by changing the size of representative block according to the size of object in the image frame to improve the tracking performance. The proposed algorithm is verified experimentally by using a two degree-of-freedom active camera mounted on a mobile robot.

• Journal of Digital Contents Society
• /
• v.8 no.3
• /
• pp.329-339
• /
• 2007

In this paper we present a facial region detection algorithm for real-time image with complex background and various illumination using spatial and temporal methods. For Detecting Human region It used summation of Edge-Difference Image between continuous image sequences. Then, Detected facial candidate region is vertically divided two objected. Non facial region is reduced using Analysis of Major Color Component. Non facial region has not available Major Color Component. And then, Background is reduced using boundary information. Finally, The Facial region is detected through horizontal, vertical projection of Images. The experiments show that the proposed algorithm can detect robustly facial region with complex background various illumination images.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2003.09a
• /
• pp.77-77
• /
• 2003

CT와 MRI의 단면 영상을 대상으로 영상분할 (Image segmentation)과 Image registration방법을 이용하여 인체 모델을 개발 하고자 한다. 우선 인체의 Head와 Neck부분의 CT와 MR 영상을 얻어 뼈, 근육, 인대, 그리고 그 밖의 장기의 해부학적 영상 특징을 분석하였다. 인체의 Head와 Neck 부분에 대한 CT와 MR 영상에 대해 각 부위별로 ROI(region-of-interrest)를 설정하였고, 각 volxel 마다 3차원 좌표를 계산할 수 있는 소프트웨어를 개발하였다. 특히 각 해부학적 영상에서 부위별로 CT 번호를 분석하고, pulse sequence에 따른 MRI 영상의 부위별 특정을 분석하였다. 이 분석한 자료를 바탕으로 영상 분할을 하였다. 영상 분할전에 각종 잡음(noise) 제거 및 영상 분할을 효과적으로 처리하기 위해 기본적인 영상처리 (filtering)를 구현하였고, 대조도(contrast) 및 밝기(brightness)를 조절할 수 있게 프로그램을 구현하였다. 영상 분할 방법 중 선(line) 및 에지(edge) 의 검출 방법, 문턱치화(threshold) 방법, 영역확대(region growing) 방법으로 영상 분할을 해봄으로써 우리의 인체 모델링 개발에 가장 적합한 영상 분할 알고리듬 방법을 찾도록 시도하였다. 결과적으로 말하면, 한가지 방법의 알고리듬을 쓰는 것보다는 인체의 부위에 따라 두 가지 이상의 알고리듬 방법을 쓰는 것이 원하고자 하는 부위를 영상 분할하는데 더 효과적이다는 것을 알게 되었다. 우리의 연구 과제에서는 영역확대(region growing) 방법과 문턱치화 방법, 모드법(피크니스, 밸리)의 알고리듬을 이용하여 영상 분할을 한 결과 우리가 얻고자 하는 인체 부위별 중 근육과 뼈를 구별하는데는 별 무리가 없었으나, 인대 및 기타 장기를 구별하는데는 어려움을 겪게 되었다. 이후에 좀더 알고리듬을 연구하여 이번 연구에서 구별하기 어려운 장기 부분도 구별 할 수 있도록 노력하겠다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2000.11a
• /
• pp.207-217
• /
• 2000

In this paper, we describe an image processing algorithm which is able to recognize the road lane. This algorithm performs to recognize the interrelation between AGV and the other vehicle. We experimented on AGV driving test with color CCD camera which is setup on the top of vehicle and acquires the digital signal. This paper is composed of two parts. One is image preprocessing part to measure the condition of the lane and vehicle. This finds the information of lines using RGB ratio cutting algorithm, the edge detection and Hough transform. The other obtains the situation of other vehicles using the image processing and viewport. At first, 2 dimension image information derived from vision sensor is interpreted to the 3 dimension information by the angle and position of the CCD camera. Through these processes, if vehicle knows the driving conditions which are angle, distance error and real position of other vehicles, we should calculate the reference steering angle.