This paper presents a new solution for multi-target tracking over a network of sensors with limited spatial coverage. The proposed solution is based on the centralized data fusion architecture. The main contribution of the paper is the introduction of a new track-to-track fusion approach in which the posterior distributions of multi-target states, reported by various sensor nodes, are fused in a way that the redundant information are combined and the rest complement each other. The proposed solution is formulated within the labeled random finite set framework in which the fused posterior incorporates all the state and label information provided by multiple sensor nodes. The performance of the proposed method is evaluated via simulation experiments that involve challenging tracking scenarios. The proposed method is implemented using sequential Monte Carlo method and the results confirm its effectiveness.

One of the core challenges in visual multi-target tracking is occlusion. This is especially important in applications such as video surveillance and sports analytics. While offline batch processing algorithms can utilise future measurements to handle occlusion effectively, online algorithms have to rely on current and past measurements only. As such, it is markedly more challenging to handle occlusion in online applications. To address this problem, we propagate information over time in a way that it generates a sense of déjà vu when similar visual and motion features are observed. To achieve this, we extend the Generalized Labeled Multi-Bernoulli (GLMB) filter, originally designed for tracking point-sized targets, to be used in visual multi-target tracking. The proposed algorithm includes a novel false alarm detection/removal and label recovery methods capable of reliably recovering tracks that are even lost for a substantial period of time. We compare the performance of the proposed method with the state-of-the-art methods in challenging datasets using standard visual tracking metrics. Our comparisons show that the proposed method performs favourably compared to the state-of-the-art methods, particularly in terms of ID switches and fragmentation metrics which signifies occlusion.

This paper reviews the state-of-the-art multi-sensor fusion approaches applicable in the next-generation intelligent transportation systems where connected vehicles are cooperatively driven for maximum safety and efficiency. The review finds out that complementary sensor fusion in a time-varying distributed network is required, and for such applications, the state-of-the-art is sensor fusion in the random finite set filtering framework. The fundamental bases of random finite set filters are reviewed with more elaboration on a particular filter called the Labeled Multi-Bernoulli filter. An information-theoretic approach for data fusion based on minimizing information divergence between statistical densities is presented, along with how different divergence functions can be used for sensor fusion. Different approaches are evaluated for their tracking performance and computational cost in a realistic simulation scenario. Their advantages, and disadvantages in the context of real-time implementation in a connected driving scenario are discussed.

This paper presents a novel Track-Before-Detect (TBD) Labeled Multi-Bernoulli (LMB) filter tailored for industrial mobile platform safety applications. At the core of the developed solution is two techniques for fusion of color and edge information in visual tracking. We derive an application specific separable likelihood function that captures the geometric shape of the human targets wearing safety vests. We use a novel geometric shape likelihood along with a color likelihood to devise two Bayesian updates steps which fuse shape and color related information. One approach is sequential and the other is based on weighted Kullback–Leibler average (KLA). Experimental results show that the KLA based fusion variant of the proposed algorithm outperforms both the sequential update based variant and a state-of-art method in terms of the performance metrics commonly used in computer vision literature.

This paper presents a novel solution to the occlusion handling problem in pedestrian tracking using labeled random finite set theory. The occlusion handling module uses motion and color cues of tracked targets to recover target labels after occlusion. An effective algorithm is also proposed for false alarm detection and removal which is designed based on tracked targets features such as, overlap ratio, size similarity and the time of track initialization of the tracked targets. We implement our solution using sequential Monte Carlo method, and compare it with state-of-the-art visual tracking methods. The results show that the proposed algorithm perform favorably in terms of various standard performance metrics.