ASMT: An augmented state-based multi-target tracking algorithm in wireless sensor networks

Due to the resource limitation and low performance of sensor node, research works of multi-target tracking became a hot spot in the applications of wireless sensor networks. Here, we propose an algorithm named augmented state-based multi-target tracking algorithm. To augment the state of the target tracking, augmented state-based multi-target tracking algorithm can effectively reduce the computational complexity of data association. Then, multi-target tracking in wireless sensor networks can be implemented by augmented state-based multi-target tracking algorithm as a simplified Bayesian estimation method is adopted. The simulation of multi-target tracking in wireless sensor networks demonstrates that augmented state-based multi-target tracking algorithm has less computation and higher accuracy than traditional method, especially in the implementation of maneuvering targets with intersection.

[1]  S. Godsill,et al.  Monte Carlo filtering for multi target tracking and data association , 2005, IEEE Transactions on Aerospace and Electronic Systems.

[2]  Majid Sarrafzadeh,et al.  Optimal Energy Aware Clustering in Sensor Networks , 2002 .

[3]  Leonidas J. Guibas,et al.  Collaborative signal and information processing: an information-directed approach , 2003 .

[4]  Bhaskar Krishnamachari,et al.  Energy-Quality Tradeoffs for Target Tracking in Wireless Sensor Networks , 2003, IPSN.

[5]  Konrad Schindler,et al.  Multi-Target Tracking by Discrete-Continuous Energy Minimization , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Robert W. Sittler,et al.  An Optimal Data Association Problem in Surveillance Theory , 1964, IEEE Transactions on Military Electronics.

[7]  Aboelmagd Noureldin,et al.  Unconstrained underwater multi-target tracking in passive sonar systems using two-stage PF-based technique , 2014, Int. J. Syst. Sci..

[8]  Bingpeng Zhou,et al.  Online Variational Bayesian Filtering-Based Mobile Target Tracking in Wireless Sensor Networks , 2014, Sensors.

[9]  Zixing Cai,et al.  Dynamic cluster member selection method for multi-target tracking in wireless sensor network , 2014 .

[10]  Jian Li,et al.  Divide-and-conquer architecture based collaborative sensing for target monitoring in wireless sensor networks , 2017, Inf. Fusion.

[11]  Yaakov Bar-Shalom,et al.  Tracking methods in a multitarget environment , 1978 .

[12]  Zahid Mahmood,et al.  Collaborative Sensing for Heterogeneous Sensor Networks , 2016, J. Inf. Sci. Eng..

[13]  Jiasong Mu,et al.  Throat polyp detection based on compressed big data of voice with support vector machine algorithm , 2014, EURASIP Journal on Advances in Signal Processing.

[14]  Xiaofeng Wang,et al.  Power-Aware Classifier Selection in Wireless Sensor Networks , 2016, J. Inf. Sci. Eng..

[15]  Luca Mottola,et al.  Programming wireless sensor networks , 2011, ACM Comput. Surv..

[16]  Braham Himed,et al.  Group Sparsity Based Multi-Target Tracking in Passive Multi-Static Radar Systems Using Doppler-Only Measurements , 2016, IEEE Transactions on Signal Processing.

[17]  Yu Hen Hu,et al.  Maximum likelihood multiple-source localization using acoustic energy measurements with wireless sensor networks , 2005, IEEE Transactions on Signal Processing.

[18]  Lui Sha,et al.  Dynamic Clustering for Acoustic Target Tracking in Wireless Sensor Networks , 2004, IEEE Trans. Mob. Comput..

[19]  Bing Chen,et al.  Adaptive dual cluster heads collaborative target tracking in wireless sensor networks , 2014, Int. J. Sens. Networks.