Real-Time Multi-human Tracking Using a Probability Hypothesis Density Filter and Multiple Detectors

Eiselein, Volker; Arp, Daniel J.; Pätzold, Michael; Sikora, Thomas

doi:10.1109/avss.2012.59

Cited by 56 publications

(40 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[3][4][5][6] have focused on the common crisis of tracking, without particularly addressing the challenges of a multiple objects. Traditional tracking methods classically assume a static background or easily discernible moving objects, and, as a result, are limited to scenes with relatively few constituents 9,10 .…”

Section: Introductionmentioning

confidence: 99%

Hybrid tracking model for multiple object videos using second derivative based visibility model and tangential weighted spatial tracking model

Philip

Mukesh

2016

IJCIS

View full text Add to dashboard Cite

In the area of video surveillance, tracking model for multiple object video is still a challenging task since the objects are usually affected with inter-object occlusion, object confusion, different posing, environment with heavy clutter, small size of objects, similar appearance among objects, and interaction among the multiple objects In order to alleviate these challenges, literature presents different tracking models using spatial and visual information. Accordingly, in this paper, we have developed a hybrid tracking model for tracking the multiple objects from the videos using twofold architecture. At first, visibility model for tracking is proposed based on the second derivative model, which considers the second derivative function to predict the objects. Secondly, a spatial tracking model is proposed using tangential weighted function. Finally, these two contributions are effectively included in the hybrid tracking model for multiple object tracking and the performance analysis is carried out using two videos from UCSD dataset. From the results, we proved that the proposed hybrid tracking model achieves the Multiple Object Tracking Precision (MOTP) of 99% than the other exiting tracking models.

show abstract

Section: Introductionmentioning

confidence: 99%

Hybrid tracking model for multiple object videos using second derivative based visibility model and tangential weighted spatial tracking model

Philip

Mukesh

2016

IJCIS

View full text Add to dashboard Cite

show abstract

“…Online multi-object tracking can be achieved by using joint state-space model for multi-targets [7,8,9,10]. For instance, a mixture particle filter has been proposed in [8] to obtain the posterior probability by using the collaboration between an object detector and the proposal distribution of the particle filter.…”

Section: Introductionmentioning

confidence: 99%

Online multi-person tracking via robust collaborative model

Naiel

Ahmad

Swamy

et al. 2014

2014 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

The past decade has witnessed significant progress in object detection and tracking in videos. In this paper, we present a model for collaboration between a pre-trained object detector and multiple single object trackers in the particle filter tracking framework. For each frame, we construct an association between the trackers and the detections, and when a tracker is successfully associated to a detection, we treat this detection as the key-sample for this tracker. We present a dual motion model that incorporates the associated detections with the object dynamics. Then, a likelihood function provides different weights for the propagated and the newly created particles, reducing the effect of false positives and missed detections in the tracking process. In addition, we use generative and discriminative appearance models to maximize the appearance variation among the targets. The performance of the proposed algorithm compares favorably with that of the state-of-the-art approaches on three public sequences.

show abstract

“…In this latter case, the fusion of the classifiers may be performed by recovering their output in a probabilistic form, and then applying some combination rules which are more or less ad-hoc, such as a product, or a pseudo-likelihood as the averaged sum of the individual likelihoods over the detectors [7] in order to cope better with individual missed detections. Alternatively, multiple kernel learning (MKL) is a well established methodology which aims to combine different kernels relying on different data representations as a linear combination, by casting this information fusion task as a convex optimization problem [9].…”

Section: Related Workmentioning

confidence: 99%

An evidential framework for pedestrian detection in high-density crowds

Vandoni

Aldea

Hégarat‐Mascle

2017

2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

View full text Add to dashboard Cite

This paper addresses the problem of pedestrian detection in high-density crowd images, characterized by strong homogeneity and clutter. We propose an evidential fusion algorithm which is able to exploit multiple detectors based on different gradient, texture and orientation descriptors. The evidential framework allows us to model the spatial imprecision arising from each of the detectors. A first result of our study is that the fusion results underline clearly the good complementarity among the four descriptors we considered for this specific context. Moreover, the proposed algorithm outperforms a fusion solution based on Multiple Kernel Learning on difficult high-density crowd images acquired at Makkah at the height of the Muslim pilgrimage.

show abstract

Real-Time Multi-human Tracking Using a Probability Hypothesis Density Filter and Multiple Detectors

Cited by 56 publications

References 12 publications

Hybrid tracking model for multiple object videos using second derivative based visibility model and tangential weighted spatial tracking model

Hybrid tracking model for multiple object videos using second derivative based visibility model and tangential weighted spatial tracking model

Online multi-person tracking via robust collaborative model

An evidential framework for pedestrian detection in high-density crowds

Contact Info

Product

Resources

About