• 한국정보과학회논문지:소프트웨어및응용
• /
• 제30권7_8호
• /
• pp.713-718
• /
• 2003

조건부 밀도 전파(Condensation)는 강건한 추적 성능과 실시간 구현이 가능하다는 장점을 지닌다. 그러나 정확한 추적을 수행하기 위해서는 복잡한 형태 모델과 많은 수의 샘플을 요구하므로 현실적으로 실시간 다중 추적에 적합하지 않은 경우가 많다. 본 논문에서는 실시간 응용에 적합하도록 작은 탐색 공간을 갖는 이산 형태의 형태 모델과 다중 추적 시각 추적기간의 상호 경쟁 관계를 고려하여 적은 수의 샘플로도 좋은 추적 성능을 보이는 경쟁적 Condensation 알고리즘을 제안한다. 실험 결과, 제안한 경쟁적 추적 알고리즘은 복잡하게 이동하는 여러 군중을 실시간으로 강건하게 추적함을 보인다.

• Journal of information and communication convergence engineering
• /
• 제6권3호
• /
• pp.331-336
• /
• 2008

In this paper, we propose a real-time people tracking system with multiple CCD cameras for security inside the building. To achieve this goal, we present a method for 3D walking human tracking based on the IMPRESARIO framework incorporating cascaded classifiers into hypothesis evaluation. The efficiency of adaptive selection of cascaded classifiers has been also presented. The camera is mounted from the ceiling of the laboratory so that the image data of the passing people are fully overlapped. The implemented system recognizes people movement along various directions. To track people even when their images are partially overlapped, the proposed system estimates and tracks a bounding box enclosing each person in the tracking region. The approximated convex hull of each individual in the tracking area is obtained to provide more accurate tracking information. We have shown the improvement of reliability for likelihood calculation by using cascaded classifiers. Experimental results show that the proposed method can smoothly and effectively detect and track walking humans through environments such as dense forests.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권3호
• /
• pp.163-169
• /
• 2008

In this paper, we propose a real-time people tracking system with multiple CCD cameras for security inside the building. The camera is mounted from the ceiling of the laboratory so that the image data of the passing people are fully overlapped. The implemented system recognizes people movement along various directions. To track people even when their images are partially overlapped, the proposed system estimates and tracks a bounding box enclosing each person in the tracking region. The approximated convex hull of each individual in the tracking area is obtained to provide more accurate tracking information. To achieve this goal, we propose a method for 3D walking human tracking based on the IMPRESARIO framework incorporating cascaded classifiers into hypothesis evaluation. The efficiency of adaptive selection of cascaded classifiers have been also presented. We have shown the improvement of reliability for likelihood calculation by using cascaded classifiers. Experimental results show that the proposed method can smoothly and effectively detect and track walking humans through environments such as dense forests.

• 한국산업융합학회 논문집
• /
• 제22권3호
• /
• pp.265-272
• /
• 2019

For tracking a varying number of people using laser range finder, it is important to deal with appearance/disappearance of people due to various causes including occlusions. We propose a method for tracking people with automatic initialization by integrating observations from laser range finder. In our method, the problem of estimating 2D positions and orientations of multiple people's walking direction is formulated based on a mixture kalman filter. Proposal distributions of a kalman filter are constructed by using a mixture model that incorporates information from a laser range scanner. Our experimental results demonstrate the effectiveness and robustness of our method.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2008년도 춘계종합학술대회 A
• /
• pp.877-881
• /
• 2008

In this paper, we propose a real-time people tracking system with multiple CCD cameras for security inside the building. The camera is mounted from the ceiling of the laboratory so that the image data of the passing people are fully overlapped. The implemented system recognizes people movement along various directions. To track people even when their images are partially overlapped, the proposed system estimates and tracks a bounding box enclosing each person in the tracking region. The approximated convex hull of each individual in the tracking area is obtained to provide more accurate tracking information. To achieve this goal, we propose a method for 3D walking human tracking based on the IMPRESARIO framework incorporating cascaded classifiers into hypothesis evaluation. The efficiency of adaptive selection of cascaded classifiers have been also presented. We have shown the improvement of reliability for likelihood calculation by using cascaded classifiers. Experimental results show that the proposed method can smoothly and effectively detect and track walking humans through environments such as dense forests.

• 한국멀티미디어학회논문지
• /
• 제15권4호
• /
• pp.449-471
• /
• 2012

In intelligent surveillance systems, it is required to robustly track multiple people. Most of the previous studies adopted a Gaussian mixture model (GMM) for discriminating the object from the background. However, it has a weakness that its performance is affected by illumination variations and shadow regions can be merged with the object. And when two foreground objects overlap, the GMM method cannot correctly discriminate the occluded regions. To overcome these problems, we propose a new method of tracking and identifying multiple people. The proposed research is novel in the following three ways compared to previous research: First, the illuminative variations and shadow regions are reduced by an illumination normalization based on the median and inverse filtering of the L*a*b* image. Second, the multiple occluded and overlapped people are tracked by combining the GMM in the still image and the Lucas-Kanade-Tomasi (LKT) method in successive images. Third, with the proposed human tracking and the existing face detection & recognition methods, the tracked multiple people are successfully identified. The experimental results show that the proposed method could track and recognize multiple people with accuracy.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2007년도 학술대회 1부
• /
• pp.630-635
• /
• 2007

In this paper, we propose a system for multiple people tracking using fragment based histogram matching. Appearance model is based on IHLS color histogram which can be calculated efficiently using integral histogram representation. Since histograms will loss all spatial information, we define a fragment based region representation which retain spatial information, robust against occlusion and scale issue by using disparity information. Multiple people labeling is maintained by creating online appearance representation for each people detected in scene and calculating fragment vote map. Initialization is performed automatically from background segmentation step.

• 대한인간공학회지
• /
• 제35권5호
• /
• pp.391-401
• /
• 2016

Objective: This study aims to examine domestic literature on eye-tracking in the design area, and to present new eye-tracking application directions. Background: Eye-tracking was introduced in the experimental psychology field for the first time in the 1950s. Eye-tracking has high utilization values in the design application area because eye-tracking can accumulate data on what people see, providing the quantitative values on eye movement. Method: This study examined the papers published in domestic journals, as well as the papers presented in conferences from 2000 to 2016 through DBPIA. Results: Although the use of eye-tracking technology was slightly meager in the product design area, it has been actively used for the evaluation analyses of preference and attention in architecture/public design. Eye-tracking also presented a method to design advertisement that is helpful to advertisement effect measurement, and product salesin the advertisement design area. Since detail psychological analysis is possible, the application of eye-tracking in the studies related with user interface has been active. Conclusion: The eye-tracking technology is projected to be actively used as a new interface means, such as in helping in disabled people's communication and in device control, in addition to conventional application areas. Application: This study would be of help to find future research areas of eye-tracking.

• 로봇학회논문지
• /
• 제4권2호
• /
• pp.130-138
• /
• 2009

Recently, people tracking technology is being required to various area including security application. This paper suggests a method to track people with multiple laser scanners to detect the waist part of human. Multi-target model and Kalman filter based estimation are employed to track the human movement. The proposed method is applied to a novel system to monitor the entrance area and to filter out the trespasser to pass through the door without identification. Experiments for various cases are performed to verify the usefulness of the developed system.

• 대한인간공학회지
• /
• 제36권1호
• /
• pp.53-67
• /
• 2017

Objective: The purpose of this study is to build basic data to systematically develop a hand function evaluation tool by determining the effects of age, gender and target force level on the difference in hand function according to the target force level. Background: Precise and objective evaluation of hand functionality is a very important factor in quantifying treatment progress in patients or elderly people, and in verifying treatment effects. However, most hand function evaluations lack objectivity and accuracy, and therefore it is difficult to properly treat patients according to the given situation. Method: Sixteen healthy subjects (eight elderly and eight young people) participated in this study to evaluate the effects of age, gender, and target force level on tracking performance through rRMSE in terms of the tracking force and actual exerted force, by carrying out a task of maintaining six different target force levels for 20 seconds. Results: The result of this experiment indicated that elderly people and women had a lower ability to maintain a certain level of force than young people and men by 16% and 10%, respectively. The target force level results showed that the tracking error of the lowest force level (5% MVC) was significantly higher than that of 15% MVC, which in turn showed a higher tracking error than that of the higher target force levels. Conclusion: The results of this study can thus be utilized to develop a rehabilitation program for elderly people or other patients. Application: The authors expect that the results of the present study will be valuable to develop a rehabilitation program and hand function evaluation tool.