• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.293-297
• /
• 2007

This thesis suggests a new algorithm to detects multiple moving objects using a CMODE(Correct Multiple Object DEtection) method in the color images acquired in real-time and to track the interested pedestrian using motion and hue information. The multiple objects are detected, and then shaking trees or moving cars are removed using structural characteristics and shape information of the man , the interested pedestrian can be detected, The first similarity judgment for tracking an interested pedestrian is to use the distance between the previous interested pedestrian's centroid and the present pedestrian's centroid. For the area where the first similarity is detected, three feature points are calculated using k-mean algorithm, and the second similarity is judged and tracked using the average hue value for the $3{\times}3$ area of each feature point. The zooming of camera is adjusted to track an interested pedestrian at a long distance easily and the FOV(Field of View) of camera is adjusted in case the pedestrian is not situated in the fixed range of the screen. As a experiment results, comparing the suggested CMODE method with the labeling method, an average approach rate is one fourth of labeling method, and an average detecting time is faster three times than labeling method. Even in a complex background, such as the areas where trees are shaking or cars are moving, or the area of shadows, interested pedestrian detection is showed a high detection rate of average 96.5%. The tracking of an interested pedestrian is showed high tracking rate of average 95% using the information of situation and hue, and interested pedestrian can be tracked successively through a camera FOV and zooming adjustment.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.12
• /
• pp.3710-3717
• /
• 1999

For the development of unmanned autonomous vehicle, it is essential to detect obstacles, especially vehicles, in the forward direction of navigation. In order to reliably exclude regions that do not contain obstacles and save a considerable amount of computational effort, it is often necessary to confine computation only to ROI(region of interest)s. A ROI is usually chosen as the interior region of the lane. We propose a computationally simple and efficient method for the detection of lanes based on Hough transform and quadratic curve fitting. The proposed method first employs Hough transform to get approximate locations of lanes, and then applies quadratic curve fitting to the locations computed by Hough transform. We have experimented the proposed method on real outdoor road scene. Experimental results show that our method gives accurate detection of straight and curve lanes, and is computationally very efficient.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.3
• /
• pp.65-75
• /
• 2017

As a 360-degree image carries information of all directions, it often has too much information. Moreover, in order to investigate a 360-degree image on a 2D display, a user has to either click and drag the image with a mouse, or project it to a 2D panorama image, which inevitably introduces severe distortions. In consequence, investigating a 360-degree image and finding an object of interest in such a 360-degree image could be a tedious task. To resolve this issue, this paper proposes a method to find a region of interest and produces a 2D naturally looking image from a given 360-degree image that best matches a description given by a user in a natural language sentence. Our method also considers photo composition so that the resulting image is aesthetically pleasing. Our method first converts a 360-degree image to a 2D cubemap. As objects in a 360-degree image may appear distorted or split into multiple pieces in a typical cubemap, leading to failure of detection of such objects, we introduce a modified cubemap. Then our method applies a Long Short Term Memory (LSTM) network based object detection method to find a region of interest with a given natural language sentence. Finally, our method produces an image that contains the detected region, and also has aesthetically pleasing composition.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.1C
• /
• pp.44-53
• /
• 2005

In this paper, a improved moving object detection algorithm for stable performance of surveillance system in case of iterative moving in limited area and rapidly illuminance change in background scene is proposed. The proposed algorithm is that background scenes are sampled for initializing background image then the sampled fames are divided by block and sum of graylevel value for each block pixel was calculated, respectively. The initialization of background image is that background frame is respectively reconstructed with selecting only the maximum graylevel value and the minimum graylevel value of blocks located at same position between adjacent frames, then reference images of background are set by the reconstructed background images. Moving object detecting is that the current image frame is divided by block then sum of graylevel value for each block pixel is calculated. If the calculated value is out of graylevel range of the initialized two reference images, it is decided with moving objects block, otherwise it is decided background. The evaluated results is that the error rate of the proposed method is less than the error rate of the existing methods from $0.01{\%}$ to $20.33{\%}$ and the detection rate of the proposed method is better than the existing methods from $0.17{\%}\;to\;22.83{\%}$.

• Journal of the Korea Society of Computer and Information
• /
• v.6 no.2
• /
• pp.41-47
• /
• 2001

In this paper, I propose a detection algorithm that can reliably separate moving objects from noisy background in the image sequence received from a camera at the fixed position. The proposed algorithm consists of four processes: generation of the difference image between the input image and the reference image. multilevel quantization of the difference image, and multistage merging in the quantized image, detection of the moving object using a back propagation in a neural network. The test results show that the proposed algorithm can detect moving objects very effectively in noisy environment.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.242-246
• /
• 2001

본 논문은 유전자알고리즘과 영상처리기법을 이용해 특정 대상물의 절단위치를 추출하는 방법을 제시한 것으로서, 최근에는 기존의 아날로그 센서를 사용하여 단지 대상의 명암으로 물체를 구분한 대신에 CCD(Charge-Couple Device)카메라로부터 얻어진 화상 데이터를 이용해 물체의 정보를 추출해 이용하는 방법이 많이 응용되고 있고, 영상의 형태학, 지식기반의 영상 해석 시스템에 대한 관심이 많이 높아 졌다. 그리고 지금에는 거의 모든 분야에서 화상처리기법들이 사용되어지고 있다. 따라서 본 논문에서는 실시간 그레이 레벨의 입력 화상에 대하여 특정 물체의 특정위치를 유전 알고리즘과 영상처리기법을 이용해 검출 방법을 제안하고, 실제의 시스템에 적용한 예를 제시하려고 한다.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.842_843
• /
• 2009

본 논문에서는 Magnetic Inductance Tomography System(이하 MIDT System)을 이용하여 대상물체의 위치와 밀도 변화 시의 신호해석에 관한 연구를 하였다. MIDT System은 외부에서 자기장을 인가하고, 인가된 자기장에 의해 변화하는 자기장을 홀센서로 검출한다. MIDT System은 시스템이 간단하고 대상물체에 물리적인 손상을 가하지 않고 측정이 가능하다. 본연구에서는 MIDT System을 직접 구성하여 이론적인 해석신호와 실제 실험을 통한 해석신호의 일치여부를 비교 분석하고 MIDT System을 이용하여 대상물체 위치 변화시의 신호 해석할 수 있는 적합성 여부를 판단하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.819-822
• /
• 2007

In this paper, we propose an object-tracking of mobile robots using CHT(Circular Hough transform) algorithm. The proposed method extracts the region of moving objects using 1-D projection algorithm, and detects circular objects using CHT. In order to verify the effectiveness of the proposed tracking method, we perform experiments of ball shape object-tracking using mobile robot based on ARM processor with CMOS camera.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.11a
• /
• pp.224-227
• /
• 2000

본 논문에서는 기준 영상으로부터 면의 반사특성을 검출하고, 구해진 반사특성을 임의의 물체에 적용하여 3매의 명암영상을 얻는다. 이 영상을 측광입체시법(photometric stereo method)에 적용하여 3차원 형상인식하는 방법을 제시한다. 본 연구에서 목적으로 하는 물체의 반사특성은 난반사(diffuse reflection)성분과 전반사(specular reflection)성분이 혼합된 혼합 반사면(hybrid reflectance surface)을 그 대상으로 하며, 이러한 면의 반사특성은 Torrance-sparrow모델로 가정하여 문제를 해결해 나간다. 본 연구에서 목적으로 하는 대상 물체는 동일한 재질로 이루어졌다는 가정 하에서 몇개의 표본점들을 취해 반복수치 계산하기 때문에 계산속도가 빠르며, 각 표본점들로부터 계산된 면특성 파라메터들의 평균값을 취해서 다시 Torrance-sparrow모델에 적용함으로써 측광입체시법의 해석을 가능토록 한다. 즉, 3차원 형상인식 과정시 계산된 면특성 파라메터를 사용해 생성한 참조표와 명암영상과의 비교에 의해 빠른 면방향 복구를 행할 수 있다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.289-292
• /
• 2007

An object color identification and classification embedded system realization for uninhabited stock management is presented in this paper. The embedded system is realized by using ultrasonic sensor to extract the object and distance, and detecting binary image from USB CCD camera. The algorithm is identified by comparing the reference pattern with the color pattern of input image, and move to the settled rack at the store. The experimental result leads to use the uninhibited stock management with practice as a robot.