Multiple Person Tracking by Spatiotemporal Tracklet Association

Nie, Weizhi; Liu, An-An; Su, Yuting

doi:10.1109/avss.2012.89

Cited by 13 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each tracklet consists of a set of detection results. The average image from these detected results are utilized to extract feature [23,12] as the feature vector of tracklet. Here, we extract color and Hog features from RGB image and depth image respectively.…”

Section: Data Associationmentioning

confidence: 99%

Effective 3D object detection based on detector and tracker

et al. 2016

Self Cite

View full text Add to dashboard Cite

Section: Data Associationmentioning

confidence: 99%

Effective 3D object detection based on detector and tracker

et al. 2016

Self Cite

View full text Add to dashboard Cite

“…Over the past two decades, a large number of different tracking algorithms [7,8] have been proposed to handle tracking problems. Traditional trackers such as mean-shift, Kalman, particle filter [9,10,11] can be seen as a process of optimization.…”

Section: Introductionmentioning

confidence: 99%

Multiple Person Tracking based on Spatial-temporal Information by Global Graph Clustering

2015

KSII TIIS

View full text Add to dashboard Cite

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.

show abstract

“…Nie et al only used part-based model to detect person in each video frame [2]. However, in this multiple camera scene, many shapes of people are not a whole shape of person.…”

Section: Evaluation Of Multiple Camera Trackingmentioning

confidence: 99%

“…The state-of-the-art methods of graph matching to solve the IQP generally fall into 3 classes: semidefinite programming (SDP) [2,3], graduated assignment (GA) [4], and spectral matching (SM) [5]. However, they would face difficulty when directly utilizing these methods to solve the IQP with affinity constraint which is caused by one-toone tracklet association with three special cases mentioned in Section 4.3.1.…”

Section: Optimizationmentioning

confidence: 99%

“…For example, the irregular changes of human shapes often lead to variations of the features related to the person to be tracked, the partical occlusions leads to the pseudo-disappearance of tracking objects, and the variations of illumination of scene often leads big changes in features of objects. Over the past two decades, a large number of different tracking algorithms [1] [2] have been proposed to handle these problems. Traditional trackers such as mean-shift, kalman, particle filter [3][4] [5] can be seen as a process of optimization.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Single/Cross-Camera Multiple-Person Traffic Tracking by Graph Matching

Li¹,

Zhang²,

Wang³

2018

dtetr

View full text Add to dashboard Cite

Abstract. Multiple person tracking is a very useful task in intelligent video surveillance, which is hindered by many challenges such as the variations of illumination, the irregular changes of human shapes and the particle occlusions. To tackle these challenges, in this paper, we propose a new online learning tracking system to generate the complete trajectory for each tracking object. In detection stage, we build a classifier for each tracking object by online learning in order to provide more accurate detection results. Online learning could real-time update the classifier for an accurately tracking results in the future. In the tracklet generation stage, we apply the spatiotemporal constrain to generate a set of reliable tracklets. Finally, we propose a new Part-based matching method to get the correlation between different tracklets and apply linear programming and greedy algorithm to handle the data association problem to generate the complete trajectory for each tracking object. In particular, our approach is able to cast the multiple cameras tracking problem as a data association problem. The experiments on our proposed method demonstrate state-of-the-art performance in multiple person tracking.

show abstract

Multiple Person Tracking by Spatiotemporal Tracklet Association

Cited by 13 publications

References 21 publications

Effective 3D object detection based on detector and tracker

Effective 3D object detection based on detector and tracker

Multiple Person Tracking based on Spatial-temporal Information by Global Graph Clustering

Single/Cross-Camera Multiple-Person Traffic Tracking by Graph Matching

Contact Info

Product

Resources

About