• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.136-141
• /
• 2009

This paper proposed a framework for handover method in continuously tracking a person of interest across cooperative pan-tilt-zoom (PTZ) cameras. The algorithm here is based on a robust non-parametric technique for climbing density gradients to find the peak of probability distributions called the mean shift algorithm. Most tracking algorithms use only one cue (such as color). The color features are not always discriminative enough for target localization because illumination or viewpoints tend to change. Moreover the background may be of a color similar to that of the target. In our proposed system, the continuous person tracking across cooperative PTZ cameras by mean shift tracking that using color and shape histogram to be feature distributions. Color and shape distributions of interested person are used to register the target person across cameras. For the first camera, we select interested person for tracking using skin color, cloth color and boundary of body. To handover tracking process between two cameras, the second camera receives color and shape cues of a target person from the first camera and using linear color calibration to help with handover process. Our experimental results demonstrate color and shape feature in mean shift algorithm is capable for continuously and accurately track the target person across cameras.

• Journal of Information Processing Systems
• /
• 제15권2호
• /
• pp.344-358
• /
• 2019

Surveillance cameras have installed in many places because security and safety is becoming important in modern society. Through surveillance cameras installed, we can deal with troubles and prevent accidents. However, watching surveillance videos and judging the accidental situations is very labor-intensive. So now, the need for research to analyze surveillance videos is growing. This study proposes an algorithm to track multiple persons using SURF and background subtraction. While the SURF algorithm, as a person-tracking algorithm, is robust to scaling, rotating and different viewpoints, SURF makes tracking errors with sudden changes in videos. To resolve such tracking errors, we combined SURF with a background subtraction algorithm and showed that the proposed approach increased the tracking accuracy. In addition, the background subtraction algorithm can detect persons in videos, and SURF can initialize tracking targets with these detected persons, and thus the proposed algorithm can automatically detect the enter/exit of persons.

• 디지털산업정보학회논문지
• /
• 제8권2호
• /
• pp.95-104
• /
• 2012

In this paper, an estimation of person height and 3D location of a moving person by using the pan/tilt-embedded stereo tracking system is suggested and implemented. In the proposed system, face coordinates of a target person is detected from the sequential input stereo image pairs by using the YCbCr color model and phase-type correlation methods and then, using this data as well as the geometric information of the stereo tracking system, distance to the target from the stereo camera and 3-dimensional location information of a target person are extracted. Basing on these extracted data the pan/tilt system embedded in the stereo camera is controlled to adaptively track a moving person and as a result, moving trajectory of a target person can be obtained. From some experiments using 780 frames of the sequential stereo image pairs, it is analyzed that standard deviation of the position displacement of the target in the horizontal and vertical directions after tracking is kept to be very low value of 1.5, 0.42 for 780 frames on average, and error ratio between the measured and computed 3D coordinate values of the target is also kept to be very low value of 0.5% on average. These good experimental results suggest a possibility of implementation of a new stereo target tracking system having a high degree of accuracy and a very fast response time with this proposed algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권4호
• /
• pp.2075-2092
• /
• 2017

Person re-identification is to match pedestrians observed from non-overlapping camera views. It has important applications in video surveillance such as person retrieval, person tracking, and activity analysis. However, it is a very challenging problem due to illumination, pose and viewpoint variations between non-overlapping camera views. In this work, we propose a viewpoint invariant method for matching pedestrian images using orientation of pedestrian. First, the proposed method divides a pedestrian image into patches and assigns angle to a patch using the orientation of the pedestrian under the assumption that a person body has the cylindrical shape. The difference between angles are then used to compute the similarity between patches. We applied the proposed method to real-time global multi-object tracking across multiple disjoint cameras with non-overlapping field of views. Re-identification algorithm makes global trajectories by connecting local trajectories obtained by different local trackers. The effectiveness of the viewpoint invariant method for person re-identification was validated on the VIPeR dataset. In addition, we demonstrated the effectiveness of the proposed approach for the inter-camera multiple object tracking on the MCT dataset with ground truth data for local tracking.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2008년도 춘계학술대회 논문집
• /
• pp.499-500
• /
• 2008

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 제36회 하계학술대회 논문집 D
• /
• pp.2796-2798
• /
• 2005

This Paper presents a method that a mobile robot can track persons in complex environment using particle filters. The topic of person following using mobile robot is researched in many different areas. The main problems of following a person are real time constraint, motion change of person during the tracking and occlusion with other objects. We present appearance adaptive models in a particle filter to realize robust visual tracking algorithm. Adaptive appearance model can handle occlusion with other people while target is moving.

• ETRI Journal
• /
• 제37권3호
• /
• pp.551-561
• /
• 2015

We propose a novel multiple-object tracking algorithm for real-time intelligent video surveillance. We adopt particle filtering as our tracking framework. Background modeling and subtraction are used to generate a region of interest. A two-step pedestrian detection is employed to reduce the computation time of the algorithm, and an iterative particle repropagation method is proposed to enhance its tracking accuracy. A matching score for greedy data association is proposed to assign the detection results of the two-step pedestrian detector to trackers. Various experimental results demonstrate that the proposed algorithm tracks multiple objects accurately and precisely in real time.

• 대한기계학회논문집A
• /
• 제37권10호
• /
• pp.1219-1227
• /
• 2013

눈 움직임만으로 물건을 집고자 하는 사지장애자를 위한 웨어러블 로봇을 소개한다. 이 로봇에서는 시선위치추적 알고리즘을 적용하여 파지하고자 하는 물체를 보는 동공의 움직임을 확인하여 물체의 2차원 정보를 구하고 물체까지의 깊이는 로봇 어깨위에 올려져 있는 Kinect라는 장치를 사용하여 구한다. 물체와 로봇, 그리고 카메라간의 좌표변환과 매칭을 통하여 최종 물체의 3차원 정보를 추출하고 이 정보는 로봇제어기인 DSP로 전송되어 물체를 잡을 수 있도록 제어하게 되어 궁극적으로 사용자가 물체를 정확히 잡을 수 있도록 한다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2088-2091
• /
• 2003

We presents a new algorithm for tracking person in video sequence that integrates the meanshift iteration procedure into the particle filtering. Utilizing the nice property of convergence to the modes in the meanshift iteration we show that only a few sample points are sufficient, while in general the particle filtering requires a large number of sample points. Multi-parts of a person is tracked independently of each other based on the color Then, the similarity against the reference model color and the geometric constraints between multi-parts are reflected as the sample weights. Also presented is the computer simulation results, which show successful tracking even for complex background clutter.

• 정보처리학회논문지B
• /
• 제15B권3호
• /
• pp.197-204
• /
• 2008

특정인을 추적하는 기술은 인간처럼 행동하는 로봇기술에서 가장 많이 등장하는 기술이다. 이 기술은 세 가지 영역에서 접근하고 있는데 첫 째가 특정인의 의상 색상이고 두 번째가 특정인의 얼굴과 그 표정이며 세 번째가 특정인의 제스처나 머리의 움직임이다. 그러나 로봇은 센서를 통해 색상이나 제스처를 감지할 수 있기 때문에 폐쇄회로 카메라를 통해 획득한 영상만으로 특정인을 추적하는 것과는 다르다. 폐쇄회로 카메라에서 가장 큰 문제점은 시스템 속도인데 입력된 영상에서 다시 계산에 의해 특정인을 추적하기위해서는 계산수를 줄여야한다. 시스템 속도를 높이기 위해 색상 추적은 통계치를 사용하는 것이 좋고 얼굴인식은 고유 얼굴을 사용하는 것이 바람직하다. 색상과 얼굴인식만으로는 추적에 어려움이 있기 때문에 모션 분석이 필요하다. 기존의 모션 분석이 주어진 영상의 전체 영역에서 형상을 바탕으로 이루어지기 때문에 속도가 느리고 인식률도 떨어진다. 본 논문에서는 얼굴 인식 시 찾아진 얼굴영역에 대한 모션분석을 계산속도가 빠른 운동에너지를 써서 인식률과 인식 속도를 높였다. 본 논문이 제안한 알고리즘과 Girondel, V. 등이 제시한 방법을 같은 동영상에서 실험한 결과 동일한 인식률을 얻었으며 인식속도는 제안한 알고리즘이 더 빨랐으며 LDA를 사용할 경우 속도는 비슷하나 인식률은 더 나은 결과를 얻었으며 특정인을 찾는 것은 제안한 알고리즘이 더 효과적이었다.