• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.14-25
• /
• 2021

Change detection, which finds changes in remote sensing images of the same location captured at different times, is very important because it is used in various applications. However, registration errors, building displacement errors, and shadow errors cause false positives. To solve these problems, we propose a novle deep convolutional network called CADNet (Change Attention Dense Siamese Network). CADNet uses FPN (Feature Pyramid Network) to detect multi-scale changes, applies a Change Attention Module that attends to the changes, and uses DenseNet as a feature extractor to use feature maps that contain both low-level and high-level features for change detection. CADNet performance measured from the Precision, Recall, F1 side is 98.44%, 98.47%, 98.46% for WHU datasets and 90.72%, 91.89%, 91.30% for LEVIR-CD datasets. The results of this experiment show that CADNet can offer better performance than any other traditional change detection method.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.13 no.1
• /
• pp.155-163
• /
• 2010

The Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) on-board the NASA's Terra spacecraft provides along-track digital stereo image data at 15m resolution with a base-height ratio 0.6. Automated stereocorrelation procedure was implemented using the ENVI 4.1 software to derive DEMs with $15m{\times}15m$ in 43km long and 50km wide area using the ASTER stereo images. The accuracy of DEMs was analyzed in comparison with those which were obtained from digital topographic maps of 1:25,000 scale. Results indicate that RMSE in elevation between ${\pm}7$ and ${\pm}20m$ could be achieved. Excluding cloud, water and building areas as the factors which make RMSE value exceeding 10m, the accuracy of DEMs showed RMSE of ${\pm}5.789m$. Therefore for the purpose of elevating accuracy of topographic information, we intended to detect the cloud areas and shadow areas by a landcover classification method, remove those areas on the ASTER DEM and then replace with those areas detached from the cartographic DEM by band math.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2006.05a
• /
• pp.106-111
• /
• 2006

텔레메틱스, 위치정보서비스, 유비쿼터스 등의 발전과 더불어 3차원 GIS의 활용은 급격히 증가할 것으로 기대된다. 특히 도시모델은 이러한 3D GIS의 근간을 이루며, 이에 도시모델의 획득과 지속적인 수정에 대한 수요 증가도 필연적이다. 따라서 본 연구에서는 기존의 도시모델 구축방법과 달리 보다 효율적이고 정밀한 도시모델을 구축하는 방법을 제시하고 실험적으로 검증하고자 하였다. 제시된 방법은 항공사진과 라이다데이터를 이용하여 지표면모델을 생성하고, 지상사진을 이용하여 건물의 정교한 3차원 모델을 생성하는 것을 핵심으로 한다. 서울시립대학교를 실험대상지역으로 선택하여 전체 23개의 건물을 포함하는 27만 $600m^2$면적의 영역에 대한 도시모델을 구축하였다. 생성된 모델에 대한 검사를 통해 건물과 지표면의 기하학적 구조가 정확하게 재현된 것을 알 수 있었다. 그러나 건물의 외벽 texture는 영상 촬영 시 나무 등에 의해 가려지는 문제, 주변 지물들에 의한 그림자 영향 등으로 깔끔하게 처리되지 못한 것을 볼 수 있었다. 결론적으로 3차원 모델 구축에 있어 texture 추출에 대한 알고리즘 개선이 요구되었고, 건물 내부도 모델링함으로써 더욱 다양한 활용방안도 생각해야 할 것이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.301-304
• /
• 2007

자동으로 이미지 안에 존재하는 객체들을 인식하는 문제는 내용 기반 이미지 검색이나 로봇 비전과 같은 다양한 분야들에서 매우 중요한 문제이다. 이 문제를 해결하기 위하여 본 논문에서는 객체의 주요 색상 정보들을 이용하여 실시간으로 이미지 안의 객체들을 인식하는 알고리즘을 제안한다. 본 논문에서 제안하는 방법의 전체적인 구조는 다음과 같다. 처음에 MPEG-7 색상 정보 기술자들 중 하나인 주요 색상 정보 기술자를 이용하여 객체의 주요 색상 정보들을 추출한다. 이 때 이 정보는 가우시안 색상 모델링을 통하여 빛이나 그림자와 같은 외부 환경 조건에 좀 더 강인한 색상 정보로 변환된다. 다음으로 변환된 색상 정보들을 기반으로 주요 객체와 입력 이미지와의 픽셀 값차이를 계산하고, 임계값 이상의 값을 가지는 픽셀들을 제거한다. 마지막으로 입력 이미지에서 제거되지 않은 픽셀들을 기반으로 하나의 영역을 생성한다. 결론으로서, 본 논문에서는 제안된 방법에 대한 실험 평가들을 수행 및 분석하고 몇몇 한계점들에 대해서 알아본다. 또한 이 문제들을 해결하기 위한 앞으로의 연구 계획에 대해서 기술한다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.4
• /
• pp.104-114
• /
• 2016

Potholes have caused diverse problems such as wheel damage and car accident. A pothole detection technology is the most important to provide efficient pothole maintenance. The previous pothole detections have been performed by manual reporting methods. Thus, the problems caused by potholes have not been solved previously. Recently, many pothole detection systems based on video cameras have been studied, which can be implemented at low costs. In this paper, we propose a new pothole detection algorithm based on saliency map information in order to improve our previously developed algorithm. Our previous algorithm shows wrong detection with complicated situations such as the potholes overlapping with shades and similar surface textures with normal road surfaces. To address the problems, the proposed algorithm extracts more accurate pothole regions using the saliency map information, which consists of candidate extraction and decision. The experimental results show that the proposed algorithm shows better performance than our previous algorithm.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.10
• /
• pp.77-83
• /
• 2020

The technologies of 3D spatial information, such as Smart City and Digital Twins, are developing rapidly for managing land and solving urban problems scientifically. In this construction of 3D spatial information, an object using aerial photo images is built as a digital DB. Realistically, the task of extracting a texturing image, which is an actual image of the object wall, and attaching an image to the object wall are important. On the other hand, occluded areas occur in the texturing image. In this study, the ResNet algorithm in deep learning technologies was tested to solve these problems. A dataset was constructed, and the street tree was detected using the ResNet algorithm. The ability of the ResNet algorithm to detect the street tree was dependent on the brightness of the image. The ResNet algorithm can detect the street tree in an image with side and inclination angles.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.38 no.6
• /
• pp.458-469
• /
• 1989

A measurement method is proposed which finds 3-D position and attitude of a known polyhedra utilizing shading information. Through the systematic interpretation of relations between polyhedra and its image as well as shadow image and also the determination of candidate position, 3-D information with respect to vertex of polyhedra is extracted. Following preprocessing of this information, the image of polyhedra is represented in terms of the scene with positioned object and the correspondence is searched by means of matching process between a scene description of the object and the correspondence is searched by means of matching process between a scene description of the object and a model description stored in data-base. In the experiments, initially 3-D information is employed to select several model regions, and objects are recognized through matching process with respect to scene regions. The results demonstrate that the recognition system performs with a high efficiency by proper selection of the threshold values.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.6
• /
• pp.621-628
• /
• 2015

This paper describes an algorithm for detecting vehicles detection in real time. The proposed algorithm has the technique based on computer vision and image processing. In real, complex environment such as one with road traffic, many algorithms have great difficulty such as low detection rate and increasing computational time due to complex backgrounds and rapid changes. To overcome this problem in this paper, the proposed algorithm consists of the following methods. First, to effectively separate the candidate regions, we use vertical and horizontal edge information, and shadow values from input image sequences. Second, we extracts features by using HOG from the selected candidate regions. Finally, this paper uses the OS fuzzy-ELM based on SLFN to classify the extracted features. The experimental results show that the proposed method perform well for detecting vehicles and improves the accuracy and the computational time of detecting.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.5 s.311
• /
• pp.22-29
• /
• 2006

In this paper, we propose a block-based real-time people counting system that can be used in various environments including showing mall entrances, elevators and escalators. The main contributions of this paper are robust background subtraction, the block-based decision method and real-time processing. For robust background subtraction obtained from a number of image sequences, we used a mixture of K Gaussian. The block-based decision method was used to determine the size of the given objects (moving people) in each block. We divided the images into $6{\times}12$ blocks and trained the mean and variance values of the specific objects in each block. This was done in order to provide real-time processing for up to 4 channels. Finally, we analyzed various actions that can occur with moving people in real world environments.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.9
• /
• pp.1145-1156
• /
• 2002

A method to measure the speed and distance of moving object is proposed using the stereo vision system. One of the most important factors for measuring the speed and distance of moving object is the accuracy of object tracking. Accordingly, the background image algorithm is adopted to track the rapidly moving object and the local opening operator algorithm is used to remove the shadow and noise of object. The extraction efficiency of moving object is improved by using the adaptive threshold algorithm independent to variation of brightness. Since the left and right central points are compensated, the more exact speed and distance of object can be measured. Using the background image algorithm and local opening operator algorithm, the computational processes are reduced and it is possible to achieve the real-time processing of the speed and distance of moving object. The simulation results show that background image algorithm can track the moving object more rapidly than any other algorithm. The application of adaptive threshold algorithm improved the extraction efficiency of the target by reducing the candidate areas. Since the central point of the target is compensated by using the binocular parallax, the error of measurement for the speed and distance of moving object is reduced. The error rate of measurement for the distance from the stereo camera to moving object and for the speed of moving object are 2.68% and 3.32%, respectively.