Article

Repairing People Trajectories Based on Point Clustering

07/2010;
Source: arXiv

ABSTRACT This paper presents a method for improving any object tracking algorithm based on machine learning. During the training phase, important trajectory features are extracted which are then used to calculate a confidence value of trajectory. The positions at which objects are usually lost and found are clustered in order to construct the set of 'lost zones' and 'found zones' in the scene. Using these zones, we construct a triplet set of zones i.e. three zones: In/Out zone (zone where an object can enter or exit the scene), 'lost zone' and 'found zone'. Thanks to these triplets, during the testing phase, we can repair the erroneous trajectories according to which triplet they are most likely to belong to. The advantage of our approach over the existing state of the art approaches is that (i) this method does not depend on a predefined contextual scene, (ii) we exploit the semantic of the scene and (iii) we have proposed a method to filter out noisy trajectories based on their confidence value.

0 Bookmarks
 · 
76 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Vision algorithms face many challenging issues when it comes to analyze human activities in video surveillance applications. For instance, occlusions makes the detection and tracking of people a hard task to perform. Hence advanced and adapted solutions are required to analyze the content of video sequences. We here present a people detection algorithm based on a hierarchical tree of Histogram of Oriented Gradients referred to as HOG. The detection is coupled with independently trained body part detectors to enhance the detection performance and to reach state of the art performances. We adopt a person tracking scheme which calculates HOG dissimilarities between detected persons throughout a sequence. The algorithms are tested in videos with challenging situations such as occlusions. False alarms are further reduced by using 2D and 3D information of moving objects segmented from a background reference frame.
    AVSS - 7th IEEE International Conference on Advanced Video and Signal-Based Surveillance. 01/2010;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a method to evaluate online the performance of tracking algorithms in surveillance videos. We use a set of features to compute the confidence of trajectories and also the precision of tracking results. A global score is computed online based on these features and is used to estimate the performance of tracking algorithms. The method has been tested with two real video sequences and two tracking algorithms. The similar variations between the results obtained by the proposed method and the output of a supervised evaluation tool using ground truth data have showed the performance of our global score. The advantages of our approach over the existing state of the art approaches are: (i) few a priori knowledge information is required, (ii) the method can be applied in complex scenes containing several mobile objects and (iii) we can simultaneously compare the performance of different tracking algorithms.
    Crime Detection and Prevention (ICDP 2009), 3rd International Conference on; 01/2010
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a new algorithm to track mobile objects in different scene conditions. The main idea of the proposed tracker includes estimation, multi-features similarity measures and trajectory filtering. A feature set (distance, area, shape ratio, color histogram) is defined for each tracked object to search for the best matching object. Its best matching object and its state estimated by the Kalman filter are combined to update position and size of the tracked object. However, the mobile object trajectories are usually fragmented because of occlusions and misdetections. Therefore, we also propose a trajectory filtering, named global tracker, aims at removing the noisy trajectories and fusing the fragmented trajectories belonging to a same mobile object. The method has been tested with five videos of different scene conditions. Three of them are provided by the ETISEO benchmarking project (http://www-sop.inria.fr/orion/ETISEO) in which the proposed tracker performance has been compared with other seven tracking algorithms. The advantages of our approach over the existing state of the art ones are: (i) no prior knowledge information is required (e.g. no calibration and no contextual models are needed), (ii) the tracker is more reliable by combining multiple feature similarities, (iii) the tracker can perform in different scene conditions: single/several mobile objects, weak/strong illumination, indoor/outdoor scenes, (iv) a trajectory filtering is defined and applied to improve the tracker performance, (v) the tracker performance outperforms many algorithms of the state of the art.
    06/2011;

Full-text (3 Sources)

View
27 Downloads
Available from
May 17, 2014