• The KIPS Transactions:PartB
• /
• v.12B no.3 s.99
• /
• pp.273-282
• /
• 2005

Real-time Object tracking is an important field in developing vision applications such as surveillance systems and vision based navigation. mean-shift algerian and Condensation algorithm are widely used in robust object tracking systems. Since the mean-shift algorithm is easy to implement and is effective in object tracking computation, it is widely used, especially in real-time tracking systems. One of the drawbacks is that it always converges to a local maximum which may not be a global maximum. Therefore, in a cluttered environment, the Mean-shift algorithm does not perform well. On the other hand, since it uses multiple hypotheses, the Condensation algorithm is useful in tracking in a cluttered background. Since it requires a complex object model and many hypotheses, it contains a high computational complexity. Therefore, it is not easy to apply a Condensation algorithm in real-time systems. In this paper, by combining the merits of the Condensation algorithm and the mean-shift algorithm we propose a new model which is suitable for real-time tracking. Although it uses only a few hypotheses, the proposed method use a high-likelihood hypotheses using mean-shift algorithm. As a result, we can obtain a better result than either the result produced by the Condensation algorithm or the result produced by the mean-shift algorithm.

• Journal of Korea Multimedia Society
• /
• v.10 no.7
• /
• pp.827-837
• /
• 2007

Conventional color-based object tracking using Mean Shift algorithm does not provide appropriate result when initial color distribution disappears. In this paper we propose a tracking algorithm that updates the object color sample when the color is changing. Mean Shift analysis is first used to derive the object candidate with maximum increase in density direction from current position. The color information of object is updated iteratively. The proposed algorithm achieves accurate tracking of objects when initial color samples are changed and finally disappeared. The validity of the effective approach is illustrated by the experimental results.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.11a
• /
• pp.137-140
• /
• 2006

본 논문은 급격한 컬러 변화를 보이는 물체를 추적하기 위해 새로운 알고리즘에 대해서 기술하였다. 이를 수행하기 위해 컬러기반의 추적 알고리즘인 Mean Shift를 개선하여 적용한다. 지존의 Mean Shift 알고리즘은 물체 추적을 위해 컬러 분포 정보를 설정한다. 하지만 초기의 컬러 분포 정보가 사라질 경우 물체 추적을 정확히 수행하기 힘들다는 문제점을 안고 있다. 본 논문에서는 이를 해결하기 위해 Mean Shift를 개선하여, 추적 대상의 컬러 정보를 반복적으로 업데이트하여 초기의 컬러 정보가 사라지더라도 추적이 가능하도록 개선하였다. 개선된 추적 알고리즘은 시간에 따라 초기의 컬러 분포 정보가 완전히 사라지더라도 실시간 추적이 가능하도록 구현하였다. 이를 입증하기 위해 본 논문의 실험에서는 실험적인 환경에서 급격한 컬러 변화를 보이는 간단한 문제의 추적과 실생활에서의 예를 함께 보여준다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.579-582
• /
• 2015

The Mean-Shift is a robustness algorithm that can be used for tracking the object using the similarity of histogram distributions of target model and target candidate. However, Mean-shift using hue information has disadvantage of tracking a wrong target when the target and background has similar hue distributions. We then propose a robust Mean-Shift tracking algorithm using new image that combined upper 4bit-planes in hue and saturation, respectively.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.195-198
• /
• 2013

Recognition and Tracking of interesting object is the significant field in Computer Vision. Mean-Shift algorithm have chronic problems that some errors are occurred when histogram of tracking area is similar to another area. in this paper, we propose to solve the problem. Each algorithm blocks skin color filtering, face detect and Mean-Shift started consecutive order assists better operation of the next algorithm. Avoid to operations of the overhead of tracking area similar to a histogram distribution areas overlap only consider the number of white pixels by running the Viola-Jones algorithm, simple arithmetic increases the convergence of the Mean-Shift. The experimental results, it comes to 78% or more of white pixels in the Mean-Shift search area, only if the recognition of the face area when it is configured to perform a Viola-Jones algorithm is tracking the object, was 100 percent successful.

• Journal of Advanced Navigation Technology
• /
• v.23 no.1
• /
• pp.77-83
• /
• 2019

In this paper, we propose an object tracking algorithm based on color histogram and convolutional neural network model. In order to increase the tracking accuracy, we synthesize generic object tracking using regression network algorithm which is one of the convolutional neural network model-based tracking algorithms and a mean-shift tracking algorithm which is a color histogram-based algorithm. Both algorithms are classified through support vector machine and designed to select an algorithm with higher tracking accuracy. The mean-shift tracking algorithm tends to move the bounding box to a large range when the object tracking fails, thus we improve the accuracy by limiting the movement distance of the bounding box. Also, we improve the performance by initializing the tracking start positions of the two algorithms based on the average brightness and the histogram similarity. As a result, the overall accuracy of the proposed algorithm is 1.6% better than the existing generic object tracking using regression network algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.10
• /
• pp.2417-2422
• /
• 2015

Mean-Shift tracking using hue has a problem that it fail in the object tracking when background has similar hue to the object. This paper proposes an improved Mean-Shift tracking algorithm using new data instead of a hue. The new data is generated by adaptive mixture of hue and saturation which have low interrelationship . That is, the proposed algorithm selects a main attribute of color that is able to distinguish the object and background well and a secondary one which don't, and places their upper 4 bits on upper 4 bits and lower 4 bits on the mixture data, respectively. The proposed algorithm properly tracks the object, keeping tracking error maximum 2.0~4.2 pixel and average 0.49~1.82 pixel, by selecting the saturation as the main attribute of color under tracking environment that background has similar hue to the object.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.11
• /
• pp.2733-2737
• /
• 2014

Motion detection according to the movement and the change area detection method according to the background difference and the motion history image for use in a motion estimation technique using a real-time image, the motion detection method according to the optical flow, the back-projection of the histogram of the object to track for motion tracking At the heart of MeanShift center point of the object and the object to track, while used, the size, and the like due to the motion tracking algorithm CamShift, Kalman filter to track with direction. In this paper, we implemented the motion detection algorithm based on color and shape information of the object and verify.

• Journal of KIISE:Software and Applications
• /
• v.34 no.10
• /
• pp.937-944
• /
• 2007

In this paper, we propose multiple human tracking with an moving stereo camera. The tracking process is based on mean shift algorithm which is using color information of the target. Color based tracking approach is invariant to translation and rotation of the target but, it has several problems. Because of mean shift uses color distribution, it is sensitive to color distribution of background and targets. In order to solve this problem, we combine color and depth information of target. Also, we build human body part model to handle occlusions and we have created adaptive box scale. As a result, the proposed method is simple and efficient to track multiple humans in real time.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.901-903
• /
• 2005

본 논문은 스테레오 카메라를 이용한 이동 카메라 환경에서 다수의 사람을 검출하여 검출된 사람을 추적하는 방법을 제안한다. 카메라가 이동하게 되면 카메라의 움직임과 검출 대상이 되는 사람의 움직임이 동시에 발생하기 때문에 카메라 움직임을 변환 모델을 사용하여 보정하고, 독립적인 움직임을 추출하여 사람을 검출 하였다. 추적은 검출된 사람 영역의 컬러 분포에 기반하여 평균 이동(Mean Shift) 알고리즘을 적용하였다. 평균 이동 알고리즘은 빠르고 안정적인 성능으로 실시간 추적에 적합하다. 그러나 객체의 컬러 정보만으로는 배경과 컬러 분포가 유사한 객체의 경우 추적에 실패할 수 있는 단점이 있다. 이점을 보완하기 위하여 본 논문에서는 변위 지도(Disparity map)를 결합하여 객체와 배경을 분리하는 깊이 마스크를 생성하였다. 변위 지도를 사용하여 다수의 사람이 등장 할 경우 발생하는 가려짐, 겹침 등 다양한 실내 환경에서 발생하는 문제도 해결 하였다. 본 논문에서 제안하는 알고리즘은 다양한 데이터에 대해서 실험한 결과 정확한 검출과 추적에 우수한 성능을 확인 할 수 있었다.