Automated multi-target tracking with kinematic and non-kinematic information
Access Status
Authors
Date
2012Collection
Type
Metadata
Show full item recordAbstract
The authors address an automated multi-target tracking (MTT) problem. In particular, our study is focused on robust data association considering an additional feature and the reliable track management by avoiding track duplications. As the additional feature, the amplitude information is combined with position measurements to improve the performance of the data association so as to effectively distinguish target-originated measurements from clutters. Because of its form of signal-to-noise ratio (SNR), which is often fluctuated according to targets' aspect and effective radar cross section, the usage of the amplitude information is not straightforward. To reduce the certain level of uncertainty of the SNR, the authors propose the SNR estimation algorithm. Moreover, the authors avoid the track duplication problem to achieve the reliability of track maintenance. Specifically, the authors solve the problem by exploiting well-known mean shift algorithm to merge duplications into appropriate clusters. Simulation results demonstrate the effectiveness and high estimation accuracy of the proposed MTT filter compared to existing methods. © 2012 The Institution of Engineering and Technology.
Citation
Source Title
Department
Related items
Showing items related by title, author, creator and subject.
-
Mallick, M.; Rubin, S.; Vo, Ba-Ngu (2013)Space object (satellite or space-debris) tracking (SOT) has not received much attention in the Information Fusion community, although the first Fusion conference was held in 1998. A special session on SOT was organized ...
-
Albrecht, Thomas (2012)Mobile surveillance systems play an important role to minimise security and safety threats in high-risk or hazardous environments. Providing a mobile marine surveillance platform with situational awareness of its environment ...
-
Mahler, Ronald; El-Fallah, A. (2012)Most multitarget tracking algorithms, such as JPDA, MHT, and the PHD and CPHD filters, presume the following measurement model: (a) targets are point targets, (b) every target generates at most a single measurement, and ...