A track-before-detect algorithm using joint probabilistic data association filter and interacting multiple models

Abstract

Detection of dim moving point targets in cluttered background can have a great impact on the tracking performances. This may become a crucial problem, especially in low-SNR environments, where target characteristics are highly susceptible to corruption. In this paper, an extended target model, namely Interacting Multiple Model (IMM), applied to Track-Before-Detect (TBD) based detection algorithm, for far objects, in infrared (IR) sequences is presented. The approach can automatically adapts the kinematic parameter estimations, such as position and velocity, in accordance with the predictions as dimensions of the target change. A sub-par sensor can cause tracking problems. In particular, for a single object, noisy observations (i.e. fragmented measures) could be associated to different tracks. In order to avoid this problem, presented framework introduces a cooperative mechanism between Joint Probabilistic Data Association Filter (JPDAF) and IMM. The experimental results on real and simulated sequences demonstrate effectiveness of the proposed approach

Cognitive Dynamic Systems: A Review of Theory, Applications, and Recent Advances

“…The Q-learning algorithm is adopted in the cognitive controller for ensuring that the optimal policy is adhered to by representing the action-reward space as an HMM, and for further details on the implementation of the proposed approach, we refer the reader to the studies [118]. The results of the proposed method were compared against sever other state-of-the-art trackers, including the mean-shift algorithm [119], the fusion filter [120], which uses a covariance matrix trace-based fusion scheme, a modified particle tracker [121], and the least soft-threshold squares tracker [122]. With a dataset consisting of public real image sequences, the proposed technique was demonstrated to achieve tracking results with mses comparable to the other mentioned techniques, despite being a suboptimal implementation [118].…”