• 한국ITS학회 논문지
• /
• 제16권6호
• /
• pp.90-100
• /
• 2017

본 연구에서는 기존 지점 및 구간 검지체계의 한계를 극복하기 위한 방편으로 드론 촬영영상을 활용하여 차량을 검지 및 레이블링 하고 이를 기반으로 도심부 간선도로상 차간간격을 산정하는 것을 목적으로 한다. 드론 영상 데이터 획득 시 적정 시간대, 위치, 고도를 선정하기 위하여 여러 조건하에서 촬영을 실시하여 최종 영상 데이터를 획득하였다. 다양한 영상분석기법 중 혼합 Gaussian, 영상 이진화, 모폴로지 기법을 적용시켜 차량을 검지하였고 칼만 필터를 적용하여 차량을 레이블링 하였다. 레이블링율 분석 결과 실제 차량 수 285대 중 185대를 검지함으로써 차량 레이블링율은 65%로 나타나는 것을 확인하였다. 차간간격은 픽셀 단위화를 통해 산정하였으며, 결과는 다음 지도와의 비교 분석을 통해 검증을 수행하였다. 검증 결과 차간간격 오차가 모두 5m 미만으로 나타났으며 평균 오차는 선행차량과의 차간간격은 1.67m, 후행차량과의 차간간격은 1.1m로 분석되었다. 본 연구에서 산출된 차간간격은 도심부 도로의 밀도, 서비스 수준 판단 기준 설정 등으로 활용될 수 있을 것이다.

• 대한전자공학회논문지
• /
• 제27권9호
• /
• pp.1448-1455
• /
• 1990

In this paper, a range image segmentation method is proposed. This method consists of an initial segmentation stage by discontinuous edge detection and surface type labeling based on the sign of the principal curvatures. Initially type labeled image is oversegmented, this image is merged via stepwise optimal region merging stage based on polynomial function approxiamtion. The successful segmentation results are presented for two synthetic range images with noise and a real-world ERIM range image.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1266-1268
• /
• 1996

In this study an automatic roiling-coli labeling system using robot vision system and peripheral mechanism is proposed and implemented, which instead of the manual labor to attach labels Rolling-coils in a steel miil. The binary image process for the image processing is performed with the threshold, and the contour line is converted to the binary gradient which detects the discontinuous variation of brightness of rolling-coils. The moment invariants algorithm proposed by Hu is used to make it easy to recognize even when the position of the center are different from the trained data. The position error compensation algorithm of six degrees of freedom industrial robot manipulator is also developed and the data of the position of the center rolling-coils, which is obtained by floor mount camera, are transfered by asynchronous communication method. Therefore even if the position of center is changed, robot moves to the position of center and performs the labeling work successfully. Therefore, this system can be improved the safety and efficiency.

• 대한의용생체공학회:의공학회지
• /
• 제28권4호
• /
• pp.549-555
• /
• 2007

In order to study cortical properties in human, it is necessary to obtain an accurate and explicit representation of the cortical surface in individual subjects. Among many approaches, surface-based method that reconstructs a 3-D model from contour lines on cross-section images is widely used. In general, however, medical brain imaging has some problems such as the complexity of the images, non-linear gain artifacts and so on. Due these limitations, therefore, extracting anatomical structures from imaging data is very a complicated and time-consuming task. In this paper, we present an improved method for extracting contour lines of cortical surface from magnetic resonance images that simplifies procedures of a conventional method. The conventional method obtains contour lines through thinning and chain code process. On the other hand, the proposed method can extract contour lines from comparison between boundary data and labeling image without supplementary processes. The usefulness of the proposed method has been verified using brain image.

• 한국멀티미디어학회논문지
• /
• 제3권5호
• /
• pp.454-460
• /
• 2000

영상과 같은 다양하고 복잡한 데이터 검색은 기존의 키워드를 이용한 검색이 아닌 내용 기반 검색 방법이 요구된다. 본 논문에서는 물체의 위치 이동이나 회전, 크기 변화 등과 같은 각종 변환에 민감하지 않은 불변모멘트(invariant moments)값의 특성을 이용하여 사용자 질의로서 입력된 객체를 효율적으로 검색할 수 있는 시스템을 구현하였다. 영상내의 단일 객체뿐만 아니라 다중 객체들도 효과적으로 검출하기 위해 레이블링(labeling) 알고리즘을 적용해 각각의 객체를 따로 분리하여 불변모멘트를 적용하는 방법을 이용했다. 또한, 검색 시간 단축 및 영상의 효율적인 인덱싱(indexing)을 위해 해싱을 응용한 기법을 적용하였다. 실험결과, precision 85%, recall 23%의 높은 검색효율을 보였고 기존의 전체 영상의 특징을 가지고는 정확히 표현할 수 없는 객체들의 모양을 정확히 표현해 줌으로써 보다 정화한 검색 결과를 얻을 수 있었다.

• 대한기계학회논문집A
• /
• 제25권5호
• /
• pp.841-849
• /
• 2001

The pixel information of the object was obtained sequentially and pixels were clustered to a label by the line labeling method. Feature points were determined by finding the slope for edge pixels after selecting the fixed number of edge pixels. The slope was estimated by the least square method to reduce the detection error. Once a matching point was determined by comparing the feature information of the object and the pattern, the parameters for translation, scaling and rotation were obtained by selecting the longer line of the two which passed through the matching point from left and right sides. Finally, modified Hausdorff Distance has been used to identify the similarity between the object and the given pattern. The multi-label method was developed for recognizing the patterns with more than one label, which performs the modified Hausdorff Distance twice. Experiments have been performed to verify the performance of the proposed algorithm and method for simple target image, complex target image, simple pattern, and complex pattern as well as the partially hidden object. It was proved via experiments that the proposed image matching algorithm for recognizing the object had a good performance of matching.

• 한국멀티미디어학회논문지
• /
• 제19권10호
• /
• pp.1759-1766
• /
• 2016

We can implement the virtual touch recognition system by mounting the virtual touch algorithm into an embedded device connected to a depth camera. Since the computing performance is limited in embedded system, the real-time processing of recognizing the virtual touch is difficult when the resolution of the depth image is large. In order to resolve the problem, this paper improves the algorithms of binarization and labeling that occupy a lot of time in all processing of virtual touch recognition. It processes the binarization and labeling in only necessary regions rather than all of the picture. By appling the proposed algorithm, the system can recognize the virtual touch in real-time as about 31ms per a frame in the depth image that has 640×480 resolution.

• 대한임베디드공학회논문지
• /
• 제3권3호
• /
• pp.151-157
• /
• 2008

In this paper, we propose a three dimensional distance measurement method for a stereo system by using web cams. Using a parallel stereo system, a robot gets two images from each webcam and equalize brightness of both images. And we suggest an image processing method such as labeling, isolating an object from background and finding center of an object. We also propose a method of calculating the focal distance by using least square algorithm based on triangulation and we can reduce calculation error by this method. From experimental results, we show that the proposed method can be effective for 3D distance measurement.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2005년도 추계학술발표대회 및 정기총회
• /
• pp.147-150
• /
• 2005

본 논문에서는 협동적 제품 개발 환경에서 제품 설계 데이터와 제품 내의 객체 정보를 매칭하고 영상 기반에서 공학 데이터를 검색하기 위한 목적으로 영상 내의 객체의 각 영역을 분할 하고자 한다. 제품 설계시 생성 과정에서 CAD 툴 등으로부터 생성되는 영상은 객체 화소값의 차이가 적고 생산환경에 맞게 실시간으로 정보를 제공 할 수 있어야 한다. 위와 같은 두 가지 사항을 해결하기 위해, 전처리 과정이 없이 객체 내의 각 부분 정보를 알 수 있는 에지 기반 라벨링(Edge_Based Labeling) 기법을 제안한다.

• International Journal of Advanced Culture Technology
• /
• 제9권4호
• /
• pp.302-306
• /
• 2021

Indoor localization is one of the basic elements of Location-Based Service, such as indoor navigation, location-based precision marketing, spatial recognition of robotics, augmented reality, and mixed reality. We propose a Voxel Labeling-based visual positioning system using object simultaneous localization and mapping (SLAM). Our method is a method of determining a location through single image 3D cuboid object detection and object SLAM for indoor navigation, then mapping to create an indoor map, addressing it with voxels, and matching with a defined space. First, high-quality cuboids are created from sampling 2D bounding boxes and vanishing points for single image object detection. And after jointly optimizing the poses of cameras, objects, and points, it is a Visual Positioning System (VPS) through matching with the pose information of the object in the voxel database. Our method provided the spatial information needed to the user with improved location accuracy and direction estimation.