Abstract-We propose a filtering framework for multi-target tracking that is based on the Probability Hypothesis Density (PHD) filter and data association using graph matching. This framework can be combined with any object detectors that generate positional and dimensional information of objects of interest. The PHD filter compensates for missing detections and removes noise and clutter. Moreover, this filter reduces the growth in complexity with the number of targets from exponential to linear by propagating the first-order moment of the multitarget posterior, instead of the full posterior. In order to account for the nature of the PHD propagation, we propose a novel particle resampling strategy and we adapt the dynamic and observation models to cope with varying object scales. The proposed resampling strategy allows us to use the PHD filter when a priori knowledge of the scene is not available. Moreover, the dynamic and observation models are not limited to the PHD filter and can be applied to any Bayesian tracker that can handle State Dependent Variances (SDV). Extensive experimental results on a large standard video surveillance dataset using a standard evaluation protocol show that the proposed filtering framework improves the accuracy of the tracker, especially in cluttered scenes.

I n recent years, the decreasing cost of cameras and advances in miniaturization have favored the deployment of largescale camera networks. This growing number of cameras enables new signal-processing applications that cooperatively use multiple sensors over wide areas. In particular, object tracking is an important step in many applications related to security, traffic monitoring, and event recognition. Such applications require the optimal tradeoff between accuracy, communication, and computing across the network. The costs associated to communication and computing depend on the type and amount of cooperation performed among cameras for information gathering, sharing, and processing to validate decisions as well as to rectify (or to reduce) estimation errors and uncertainties. In this survey, we discuss data fusion and tracking methods for camera networks and compare their performance. In particular, we cover decentralized and distributed trackers and the challenges to be addressed for the design of accurate and energy-efficient algorithms.

We present a content-aware multi-camera selection technique that uses objectand frame-level features. First objects are detected using a color-based change detector. Next trajectory information for each object is generated using multi-frame graph matching. Finally, multiple features including size and location are used to generate an object score. At frame-level, we consider total activity, event score, number of objects and cumulative object score. These features are used to generate score information using a multivariate Gaussian distribution. The algorithm. The best view is selected using a Dynamic Bayesian Network (DBN), which utilizes camera network information. DBN employs previous view information to select the current view thus increasing resilience to frequent switching. The performance of the proposed approach is demonstrated on three multi-camera setups with semi-overlapping fields of view: a basketball game, an indoor airport surveillance scenario and a synthetic outdoor pedestrian dataset. We compare the proposed view selection approach with a maximum score based camera selection criterion and demonstrate a significant decrease in camera flickering. The performance of the proposed approach is also validated through subjective testing.

No abstract

Abstract-We present a novel multi-camera multi-target fusion and tracking algorithm for noisy data. Information fusion is an important step towards robust multi-camera tracking and allows us to reduce the effect of projection and parallax errors as well as of the sensor noise. Input data from each camera view are projected on a top-view through multi-level homographic transformations. These projected planes are then collapsed onto the top-view to generate a detection volume. To increase track consistency with the generated noisy data we propose to use a track-before-detect particle filter (TBD-PF) on a 5D statespace. TBD-PF is a Bayesian method which extends the target state with the signal intensity and evaluates each image segment against the motion model. This results in filtering components belonging to noise only and enables tracking without the need of hard thresholding the signal. We demonstrate and evaluate the proposed approach on real multi-camera data from a basketball match.