Abstract
Online multi-person tracking in image sequences is commonly guided by recursive filters, whose predictive models define the expected positions of future states. When a predictive model deviates too much from the true motion of a pedestrian, which is often the case in crowded scenes due to unpredicted accelerations, the data association is prone to fail. In this paper we propose a novel predictive model on the basis of Gaussian Process Regression. The model takes into account the motion of every tracked pedestrian in the scene and the prediction is executed with respect to the velocities of all interrelated persons. As shown by the experiments, the model is capable of yielding more plausible predictions even in the presence of mutual occlusions or missing measurements. The approach is evaluated on a publicly available benchmark and outperforms other state-of-the-art trackers.
Highlights
Visual pedestrian tracking is one of the most active research topics in the fields of image sequence analysis and computer vision
Available context-aware approaches to pedestrian tracking often require binary decisions about group membership of individuals, or they constrain the interactions by a Markovian assumption
The remainder of this paper is structured as follows: First we review the related work on the topic of visual multi-pedestrian tracking with a focus on approaches that investigate motion context, and on the topic of Gaussian Process Regression applied in the context of tracking (Sec. 2)
Summary
Visual pedestrian tracking is one of the most active research topics in the fields of image sequence analysis and computer vision. Our approach considers the context between every possible pair of pedestrians without being explicit about their interactions To this end we propose a new model for the predictive function of a recursive filter that is based on Gaussian Process Regression. In this context, we formulate a new covariance function taking. As we avoid explicit grouping of pedestrians, we refer to the information captured by the covariance matrix as implicit motion context The remainder of this paper is structured as follows: First we review the related work on the topic of visual multi-pedestrian tracking with a focus on approaches that investigate motion context, and on the topic of Gaussian Process Regression applied in the context of tracking (Sec. 2).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
