• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.337-339
• /
• 2006

이동 카메라 환경에서의 객체 추적은 배경과 객체의 동시 이동으로 인친 배경 모델링과 같은 고정 카메라 환경에서의 접근방법으로는 해결이 어려운 문제이다. 또한 다중 객체의 추적에서는 객체간 가려짐이 발생하는 상황에 대한 안정적 기법이 필수적으로 요구된다. 본 연구에서는 커널에 기반한 객체의 표현과 Mean shift 알고리즘을 통해 여러 명의 사람을 실시간으로 추적하고, 객체간의 공간 정보와 확률적 유사도에 기반한 객체간의 가려짐의 발생과 가려짐 후의 복원에 대한 방법을 제안하였다.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.25 no.3
• /
• pp.296-303
• /
• 2014

In this paper, we propose an algorithm to visualize radio wave environment based on the measured Received Signal Strength Indication( RSSI) and 3D geographic information. We estimate the source position using the circumcenter of the triangle and visualize the radio wave environment using the empirical propagation models. A mode seeking algorithm(mean-shift clustering) is used to seek the peak points and the center of gravity is utilized to reduce the estimation errors. Our approach finds its applications in the radio wave monitoring systems for the efficient utilization of radio resources.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.12
• /
• pp.560-567
• /
• 2008

In this paper, we discuss a simple and straightforward binarization procedure which can generate black/white comics from the video frame image. Generally, the region of human's skin is colored white or light gray, while the dark region is filled with the irregular but regular patterns like hatching in most of the black/white comics. Note that it is not enough for simple threshold method to perform this work. Our procedure is decoupled into four processes. First, we use bilateral filter to suppress noise color variation and reserve boundaries. Then, we perform mean-shift segmentation for each similar colored pixels to be clustered. Third, the clustered regions are merged and extended by our region extension algorithm considering each color of their regions. Finally, we decide which pixels are on or off using by our dynamic binarization method based on the HSV color model. Our novel black/white cartooning procedure was so successful to render comic cuts from a well-known cinema in a resonable time and manual intervention.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.675-678
• /
• 2018

Since the face has a unique property to identify human, the face recognition is actively used in a security area and an authentication area such as access control, criminal search, and CCTV. The frontal face image has the most face information. Therefore, it is necessary to acquire the front face image as much as possible for face recognition. In this study, the face region is detected using the Adaboost algorithm using Haar-like feature and tracks it using the mean-shifting algorithm. Then, the feature points of the facial elements such as the eyes and the mouth are extracted from the face region, and the ratio of the two eyes and degree of rotation of the face is calculated using their geographical information, and the approximate front face image is presented in real time.

• Journal of Digital Convergence
• /
• v.11 no.12
• /
• pp.459-465
• /
• 2013

This paper is a study on an object extraction method which using color features of an object and background in the image. A human recognizes an object through the color difference of object and background in the image. So we must to emphasize the color's difference that apply to extraction result in this image. Therefore, we have converted to HSV color images which similar to human visual system from original RGB images, and have created two each other images that applied Median Filter and we merged two Median filtered images. And we have applied the Mean Shift algorithm which a data clustering method for clustering color features. Finally, we have normalized 3 image channels to 1 image channel for binarization process. And we have created object map through the binarization which using average value of whole pixels as a threshold. Then, have extracted major object from original image use that object map.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.6 no.1
• /
• pp.1-5
• /
• 2013

The number of pedestrians is considered essential information which can be used to control a person who makes a entrance or a exit into a building. The number of pedestrians, also, can be used to help to manage pedestrian traffic and the volume of pedestrian flow within the building. Due to the fact there is incorrect detection by occluded, shadows, and illumination, however, difficulty can arise in existing system which is for detection and counts of a person who makes a entrance or a exit into a building. In this paper, it is minimized that the change of illumination and the effect of shadow through the transmitted image from camera which is created and processed with great adaptability. The accuracy of the calculations can be increase as well by using Kalman Filter and Mean-Shift Algorithm in order to avoid overlapped counts. As a result of the test, it is proved that the count method that shows the accuracy of 95.4% should be effective for detection and counts.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.3
• /
• pp.434-442
• /
• 2018

In this paper, we propose a road lane color recognition method from the image obtained from a driving vehicle. In autonomous vehicle techniques, lane information becomes more important as the level of autonomous driving such as lane departure warning and dynamic lane keeping assistance is increased. In particular the lane color recognition, especially the white and the yellow lanes, is necessary technique because it is directly related to traffic accidents. In this paper, color information of lane and road area is mapped to a 2-dimensional S-color space based on lane detection. And the center of the feature distribution is obtained by using an improved mean-shift algorithm in the S-color space. The lane color is determined by using the distance between the center coordinates of the color features of the left and right lanes and the road area. In various illumination conditions, about 97% color recognition rate is achieved.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.691-693
• /
• 2004

비디오 시퀀스에서의 객체 추적은 보안 및 감시 시스템(Security and surveillance system), 비디오 원격 회의(Video teleconferencing)등과 같이 컴퓨터 비전 응용 분야에 널리 이용되어, 정정 그 중요성이 증가하고 있다 여러 가지 이유로 인친 카메라 덜(View)로부터 객체의 가시 상태가 변하는 경우, 하나의 뷰만을 이용해서는 좋은 결과를 가지기 어렵기 때문에 본 논문에서는 객체가 가장 잘 나타나는 뷰를 선택해서 객체를 추적하는 방법을 제안한다. 각각의 카메라 뷰에서 객체를 추적하기 위해 본 논문에서는 다중 후보가 결합된 Mean-shift 알고리즘을 이용한다. 제안된 시스템의 경우, 복잡한 환경으로 인해 객체의 가시 상태가 변하는 환경에서 단일 뷰를 이용하는 경우와 비교해 더 나은 성능을 가질 수 있었다.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.461-462
• /
• 2007

Mean Shift 알고리즘은 매우 빠르며 실시간 추적이 가능하다는 장점을 지니지만 추적의 정확도와 관련하여 scale의 변화와 관련된 적응문제, model의 변화에 대한 적응 문제 등 여러 문제점을 지닌다. 따라서 시스템의 안전성을 보장하기 위해서는 추적 실패를 검출할 수 있는 별도의 검출 방법이 필요하다. 본 연구는 별도의 추가적인 연산 없이 Bhattacharyya coefficient의 변화를 추정하여 물체 추적 실패를 검출하는 방법을 제안한다. 또한 이를 실제 추적 시스템에 구현하여 실험하여 그 성능을 확인하였다.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.15-18
• /
• 2001

동영상에서 움직이는 객체 검출은 동영상의 내용을 표현하고 유사한 동영상을 검색하는 데 있어 중요한 특징간을 추출하는 방법으로 사용된다. 그러나 복잡하게 카메라가 움직이는 동영상에서 움직이는 객체 검출은 아직까지 어려운 과제이다. 본 논문에서는 복잡한 카메라의 움직임이 있는 환경에서 움직이는 객체를 강인하게 검출하는 방법을 제안한다. 움직이는 객체 검출 방법은 입력 영상을 색상간의 클러스터링을 이용하여 각 영역으로 구분하는 Mean Shift 알고리즘과 인접한 프레임에서 구분된 영역을 대응시켜 영역의 모션 벡터를 구하는 영역 매칭, 유사한 궤적을 가지는 영역들의 클러스터링을 이용하여 객체를 검출하는 궤적 클러스터링 알고리즘을 사용한다. 제안한 영역 기반 알고리즘은 기존의 픽셀이나 블록 기반의 방법보다 움직이는 객체를 정확하게 검출하였다. 실험 결과 복잡하게 움직이는 카메라의 환경 속에서 움직이는 객체를 강인하게 검출하였다.