Abstract
Video-based multiple human tracking often involves several challenges, including target number variation, object occlusions, and noise corruption in sensor measurements. In this paper, we propose a novel method to address these challenges based on probability hypothesis density (PHD) filtering with a Markov chain Monte Carlo (MCMC) implementation. More specifically, a novel social force model (SFM) for describing the interaction between the targets is used to calculate the likelihood within the MCMC resampling step in the prediction step of the PHD filter, and a one class support vector machine (OCSVM) is then used in the update step to mitigate the noise in the measurements, where the SVM is trained with features from both color and oriented gradient histograms. The proposed method is evaluated and compared with state-of-the-art techniques using sequences from the CAVIAR, TUD, and PETS2009 datasets based on the mean Euclidean tracking error on each frame, the optimal subpattern assignment metric, and the multiple object tracking precision metric. The results show improved performance of the proposed method over the baseline algorithms, including the traditional particle PHD filtering method, the traditional SFM-based particle filtering method, multi-Bernoulli filtering, and an online-learning-based tracking method.
Highlights
V IDEO based multiple human tracking plays an important role in many applications such as surveillance, guidance, and homeland security, especially in enclosed environments such as an airport, campus or shopping mall
When an input frame is obtained from the video sequence, two main steps are performed based upon the fundamental Bayesian filtering framework: firstly, a social force model is established and an Markov chain Monte Carlo (MCMC) resampling step is performed which serves as the prediction part; secondly, background subtraction is employed in the probability hypothesis density (PHD) update step with an one class support vector machine (OCSVM) classifier to obtain the states of the human targets as the resulting output
In order to evaluate the performance of the proposed system for multiple human tracking, to handle the situation of varying number of targets, close interactions and occlusions, we firstly chose sequences from three different publicly available video datasets: one from the PETS2009 dataset [36] where 3–6 human targets are walking in an outdoor campus environment, one sequence from the CAVIAR dataset [37] where 1–5 human targets are walking in a shopping mall environment and Algorithm 3: Social force model-aided MCMC-OCSVM particle PHD filter (SFM-MCMC-OCSVM-PHD)
Summary
V IDEO based multiple human tracking plays an important role in many applications such as surveillance, guidance, and homeland security, especially in enclosed environments such as an airport, campus or shopping mall. Tracking multiple human targets in the above situations presents several challenges including varying number of targets, object occlusion, and the adverse effect of environmental noise within measurements [1], Manuscript received June 23, 2016; revised October 24, 2016; accepted December 4, 2016. Date of publication December 9, 2016; date of current version March 15, 2017. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. It is not always possible to associate measurements with particular targets which results in false alarms and missed detections [3]. In this work we attempt to address aspects of these challenges and focus on the problem of estimating the position of an unknown number of human targets, based on noisy observations, with the possible presence of missed detections and false alarms due to clutter
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have