• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권6호
• /
• pp.2217-2229
• /
• 2015

Since the variations of illumination, the irregular changes of human shapes, and the partial occlusions, multiple person tracking is a challenging work in computer vision. In this paper, we propose a graph clustering method based on spatio-temporal information of moving objects for multiple person tracking. First, the part-based model is utilized to localize individual foreground regions in each frame. Then, we heuristically leverage the spatio-temporal constraints to generate a set of reliable tracklets. Finally, the graph shift method is applied to handle tracklet association problem and consequently generate the completed trajectory for individual object. The extensive comparison experiments demonstrate the superiority of the proposed method.

• 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.

• 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.

• 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.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제12권4호
• /
• pp.241-253
• /
• 2006

현대사회는 광범위한 지역에 산재된 다수의 카메라로부터 사람을 자동적으로 식별하고 추적할 수 있는 감시시스템을 요구하고 있다. 본 논문에서는 넓은 시야의 확보가 용이한 고정된 다수의 비겹침 감시카메라와 사람 추적기술을 결합하여, 한 카메라에서 추적된 사람의 정보를 서버를 통해 다른 카메라에 전달하는 방법을 제안한다. 제안된 방법은 추적대상을 자동적으로 추적하고 서버에 전달함으로써, 한번 추적된 추적대상의 움직임 경로 및 추적 상태를 끝까지 추적할 수 있다. 본 논문에서는 추적대상을 식별하고 전달하기 위해 사람모델을 이용하였다. 서버를 통해 연결된 각 카메라들의 관계와 카메라 상에서 움직이는 사람의 이동은 FOV 라인에 의해 제약되어 추적대상의 정보전달에 이용되었다. 추적대상은 추적되는 동안 6 단계의 상태정보를 가진다. 제안된 시스템은 다양한 실내 동영상에 대해 실험되었으며, 91.2% 의 평균추적율과 96% 의 평균 상태율을 획득하였다.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제22권2호
• /
• pp.61-68
• /
• 2016

현대사회는 보안과 안전이 중요해지면서 감시카메라들이 여러 곳에 설치되어 있다. 하지만 감시영상을 보고 상황을 파악하는 것은 여전히 사람의 몫으로 인력과 시간이 소모된다. 그래서 자동으로 감시영상을 분석하여 주요 사건 중심으로 요약해 주는 연구의 필요성이 커지고 있다. 본 논문에서는 감시영상에서 존재하는 다수의 사람을 추적하고, 추적을 통해 얻은 정보를 이용하여 감시영상을 요약하는 방법을 제안한다. 제안하는 감시영상 요약 시스템은 조명보정을 적용하여 배경제거한 후 다수의 사람을 추출하고, 추출된 사람의 추적 정보를 상태 데이터베이스에 저장한다. 추적을 통해 얻은 정보로 추적 대상들의 추적 경로, 움직임 상태, 지체시간, 카메라 안으로의 출입시간 등을 사용한다. 또 사람의 움직임에 따라 6 가지(Enter, Stay, Slow, Normal, Fast and Exit)로 움직임 상태를 분류하였고, 움직임 상태를 시간별, 공간별로 요약 그래프로 나타내 추적대상의 움직임 상태를 빠르게 파악할 수 있다.

• 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.

• 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.

• 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.

• 제어로봇시스템학회논문지
• /
• 제14권8호
• /
• pp.848-855
• /
• 2008

In this paper, we describe correspondence among multiple images taken by multiple cameras. The correspondence among multiple views is an interesting problem which often appears in the application like visual surveillance or gesture recognition system. We use the principal axis and the ground plane homography to estimate foot of human. The principal axis belongs to the subtracted silhouette-based region of human using subtraction of the predetermined multiple background models with current image which includes moving person. For the calculation of the ground plane homography, we use landmarks on the ground plane in 3D space. Thus the ground plane homography means the relation of two common points in different views. In the normal human being, the foot of human has an exactly same position in the 3D space and we represent it to the intersection in this paper. The intersection occurs when the principal axis in an image crosses to the transformed ground plane from other image. However the positions of the intersection are different depend on camera views. Therefore we construct the correspondence that means the relationship between the intersection in current image and the transformed intersection from other image by homography. Those correspondences should confirm within a short distance measuring in the top viewed plane. Thus, we track a person by these corresponding points on the ground plane. Experimental result shows the accuracy of the proposed algorithm has almost 90% of detecting person for tracking based on correspondence of intersections.