A Scalable Multi-Target Tracking Algorithm for Wireless Sensor Networks

Abstract

Multi-target tracking is a representative real-time application of sensor networks as it exhibits different aspects of sensor networks such as event detection, sensor information fusion, multihop communication, sensor management, and real-time decision making. The task of tracking multiple objects in a wireless sensor network is challenging due to constraints on a sensor node such as short communication and sensing ranges, a limited amount of memory, and limited computational power. In addition, since a sensor network surveillance system needs to operate autonomously without human operators, it requires an autonomous realtime tracking algorithm which can track an unknown number of targets. In this paper, we develop a scalable real-time multi-target tracking algorithm that is autonomous and robust against transmission failures, communication delays, and sensor localization error. The algorithm is based on a rigorous probabilistic model and an approximation scheme for the optimal Bayesian filter. In particular, an extensive simulation study shows that there is no performance loss up to an average localization error of 0.7 times the separation between sensors and the algorithm tolerates up to 50% lost-to-total packet ratio and 90% delayed-to-total packet ratio. The proposed algorithm has been successfully applied to real-time multi-target tracking problems using wireless sensor networks.

Object tracking sensor networks in smart cities: Taxonomy, architecture, applications, research challenges and future directions

“…When there are many objects, it would be difficult to know which observation belongs to which object. In [63], [64], [65], [66], [67], [57], [68], [69], [70], [71], [72], [73], [74] authors have proposed different solutions for solving the problem with multiple object tracking approaches. In [63], the authors proposed a rule-based algorithm for multiple objects target tracking by using acoustic sensor nodes.…”

Decentralized sparsity-based multi-source association and state tracking

“…whereŝ k t−K+m,j (ℓ) correspond to the ℓth entry of the state estimatesŝ k t−K+m,j obtained via ADMM as described next at the end of coordinate cycle k. Using similar arguments as in Apdx. B, it turns out that the optimal solution in (28) is: iii) Minimize the augmented Lagrangian function in (27) w.r.t the variables z j ′ τ,j while fixing s τ,j , v j ′ τ,j and ω j ′ τ,j to their most up-to-date values s k+1 τ,j (κ) obtained at step ii),…”

“…Availability of a model is crucial in associating the sources with the sensor measurements. Existing data association schemes [27,14,39,16,26] match observations with sources across time and rely on probabilistic models. Differently, the sensors-sources association scheme 30 2 proposed here is relying only on the acquired sensor data and no probabilistic models are adopted.…”

Cooperative Data Management in Wireless Sensor Networks

“…The event-driven model of sensor networks supports many applications, such as flood detection, 21 telemonitoring of human health status, 22 vehicle anti-theft 23 and target tracking. 24 Among these applications, those that involve mobile events are more challenging than that for static events, since mobile events need to be tracked in a continuous manner. Target tracking is usually used for monitoring a geographic region where mobile persons or vehicles may intrude.…”