• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.1
• /
• pp.1-10
• /
• 2012

In this paper, we propose a new class of color histogram model suitable for object tracking. In addition to the pixel count, each bin of the proposed model also contains the spatial mean and the average value of the pixels located at a certain distance from the mean location of the bin. Using the proposed color histogram model, we derive a mean shift procedure using the modified Bhattacharyya distance. Unlike most mean shift based methods, our algorithm performs well even when the object being tracked shares similar colors with the background. Experimental results demonstrate improved tracking performance over existing methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.21-29
• /
• 2011

At existing skin detection methods using skin color information defined based on the prior knowldege, threshold value to be used at the stage of dividing the backround and the skin region was decided on a subjective point of view through experiments. Also, threshold value was selected in a passive manner according to their background and illumination environments in these existing methods. These existing methods displayed a drawback in that their performance was fully influenced by the threshold value estimated through repetitive experiments. To overcome the drawback of existing methods, this paper propose a skin region detection method using a histogram approximation based on the mean shift algorithm. The proposed method is to divide the background region and the skin region by using the mean shift method at the histogram of the skin-map of the input image generated by the comparison of the similarity with the standard skin color at the CbCr color space and actively finding the maximum value converged by brightness level. Since the histogram has a form of discontinuous function accumulated according to the brightness value of the pixel, it gets approximated as a Gaussian Mixture Model (GMM) using the Bezier Curve method. Thus, the proposed method detects the skin region by using the mean shift method and actively finding the maximum value which eventually becomes the dividing point, not by using the manually selected threshold value unlike other existing methods. This method detects the skin region high performance effectively through experiments.

• Annual Conference of KIPS
• /
• 2001.04a
• /
• pp.123-126
• /
• 2001

영상내의 문자 정보는 색인에 필요한 유용한 정보를 제공하므로, 이를 이용한 멀티미디어 데이터의 인덱싱기법이 최근 많이 연구되고 있다. 본 논문은 mean shift 알고리즘을 이용한 텍스춰 기반의 문자 영역 추출 방법을 제안한다. 다양한 크기와 모양의 문자에 적응성을 가지는 필터를 만들기 위해 신경망을 이용한다. 문자 영역의 위치와 크기는 문자 확률 영상상에서 mean shift 알고리즘을 이용하여, 국소 탐색만으로 별도의 후처리 과정 없이 기존의 문자 추출 방법보다 우수한 성능을 보인다.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1307-1317
• /
• 2018

To deal with the problems of occlusion, pose variations and illumination changes in the object tracking system, a regression model weighted multi-templates mean-shift (MS) algorithm is proposed in this paper. Target templates and occlusion templates are extracted to compose a multi-templates set. Then, the MS algorithm is applied to the multi-templates set for obtaining the candidate areas. Moreover, a regression model is trained to estimate the Bhattacharyya coefficients between the templates and candidate areas. Finally, the geometric center of the tracked areas is considered as the object's position. The proposed algorithm is evaluated on several classical videos. The experimental results show that the regression model weighted multi-templates MS algorithm can track an object accurately in terms of occlusion, illumination changes and pose variations.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.1
• /
• pp.56-63
• /
• 2007

In this paper, an eye tracking method is presented using a neural network (NN) and mean-shift algorithm that can accurately detect and track user's eyes under the cluttered background. In the proposed method, to deal with the rigid head motion, the facial region is first obtained using skin-color model and con-nected-component analysis. Thereafter the eye regions are localized using neural network (NN)-based tex-ture classifier that discriminates the facial region into eye class and non-eye class, which enables our method to accurately detect users' eyes even if they put on glasses. Once the eye region is localized, they are continuously and correctly tracking by mean-shift algorithm. To assess the validity of the proposed method, it is applied to the interface system using eye movement and is tested with a group of 25 users through playing a 'aligns games.' The results show that the system process more than 30 frames/sec on PC for the $320{\times}240$ size input image and supply a user-friendly and convenient access to a computer in real-time operation.

• Journal of Broadcast Engineering
• /
• v.19 no.3
• /
• pp.329-341
• /
• 2014

Kernel-based mean-shift object tracking has gained more interests nowadays, with the aid of its feasibility of reliable real-time implementation of object tracking. This algorithm calculates the best mean-shift vector based on the color histogram similarity between target model and target candidate models, where the color histograms are usually produced after uniform color-space quantization for the implementation of real-time tracker. However, when the image of target model has a reduced contrast, such uniform quantization produces the histogram model having large values only for a few histogram bins, resulting in a reduced accuracy of similarity comparison. To solve this problem, a non-uniform quantization algorithm has been proposed, but it is hard to apply to real-time tracking applications due to its high complexity. Therefore, this paper proposes a fast non-uniform color-space quantization method using the histogram equalization, providing an adjusted histogram distribution such that the bins of target model histogram have as many meaningful values as possible. Using the proposed method, the number of bins involved in similarity comparison has been increased, resulting in an enhanced accuracy of the proposed mean-shift tracker. Simulations with various test videos demonstrate the proposed algorithm provides similar or better tracking results to the previous non-uniform quantization scheme with significantly reduced computation complexity.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.9 no.3
• /
• pp.166-171
• /
• 2009

In recent years, video detection systems have been implemented in various infrastructures such as airport, public transportation, power generation system, water dam and so on. Recognizing moving objects in video sequence is an important problem in computer vision, with applications in several fields, such as video surveillance and target tracking. Segmentation and tracking of multiple vehicles in crowded situations is made difficult by inter-object occlusion. In the system described in this paper, the mean shift algorithm is firstly used to filter and segment a color vehicle image in order to get candidate regions. These candidate regions are then analyzed and classified in order to decide whether a candidate region contains a license plate or not. And then some characters in the license plate is recognized by using the fuzzy ARTMAP neural network, which is a relatively new architecture of the neural network family and has the capability to learn incrementally unlike the conventional BP network. We finally design a license plate recognition system using the mean shift algorithm and fuzzy ARTMAP neural network and show its performance via some computer simulations.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.6
• /
• pp.731-736
• /
• 2008

In this paper, we propose the movement detection algorithm by using virtual skeleton model. To do this, first, we eliminate error values by using conventioanl method based on RGB color model and eliminate unnecessary values by using the HSI color model. Second, we construct the virtual skeleton model with skeleton information of 10 peoples. After matching this virtual model to original image, we extract the real head silhouette by using the proposed circle searching method. Third, we extract the object by using the mean-shift algorithm and this head information. Finally, we validate the applicability of the proposed method through the various experiments in a complex environments.

• The KIPS Transactions:PartB
• /
• v.17B no.1
• /
• pp.15-22
• /
• 2010

Background generation is very important for accurate object tracking in video surveillance systems. Traditional background generation techniques have some problems with non-moving objects for longer periods. To overcome this problem, we propose a newbackground generation method using mean-shift and Fast Marching Method (FMM) to use pixel information along temporal and spatial dimensions. The mode of pixel value density along time axis is estimated by mean-shift algorithm and spatial information is evaluated by FMM, and then they are used together to generate a desirable background in the existence of non-moving objects during longer period. Experimental results show that our proposed method is more efficient than the traditional method.

• Annual Conference of KIPS
• /
• 2015.10a
• /
• pp.1597-1599
• /
• 2015

본 논문에서는 곡물이나 광석 등의 원료들 중에서 양품 및 불량품을 검출하기 위해, Color CCD 카메라로 촬영한 원료영상에서 Mean-Shift 클러스터링 알고리즘과 단계별 병합 방법을 제안하고 있다. 먼저 원료 학습 영상에서 배경을 제거하고 영상 색 분포정도를 기준으로 모폴로지를 이용하여 영상의 전경맵을 얻는다. 전경맵 영상에 대해서 Mean-Shift 군집화 알고리즘을 적용하여 영상을 N개의 군집으로 나누고, 단계별로 위치 근접성, 색상대푯값 유사성을 비교하여 비슷한 군집끼리 통합한다. 이렇게 통합된 원료 객체는 영상채널마다의 연관관계를 반영할 수 있도록 RG/GB/BR의 2차원 컬러분포도로 표현한다. 원료 객체별로 변환된 2차원 컬러 분포도에서 분포의 주성분의 기울기와 타원들을 생성한다. 객체별 분포 타원은 테스트 원료 영상데이터에서 양품과 불량품을 검출하는 임계값이 된다. 본 논문에서 제안한 방법으로 다양한 원료영상에 실험한 결과, 기존 선별방식에 비해 사용자의 인위적 조작이 적고 정확한 원료 선별 결과를 얻을 수 있었다.