Xinglin Shen
ABSTRACT
Within the Random Finite Set (RFS) framework, the Probability Hypothesis Density (PHD) filter solves the problem of high computational complexity, and has the advantages of low computational complexity and simple implementation. After completing the theoretical research of the algorithm, it is also necessary to push the algorithm to practicality in order to truly realize the value of algorithm research. However, in the current research based on RFS, it is mainly concentrated in the theoretical research part and has not developed in the direction of algorithm practicality. In the current study, the real-time processing architecture of the multi-target tracking algorithm has not been published, the real-time prototype system has not seen public reports, and the performance verification of the algorithm is still very lacking. This paper focuses on the hardware implementation technology of multi-target tracking algorithm. The PHD filter is divided into modules, and the hardware implementation of different modules is distinguished. Then the implementation of the algorithm is completed on the actual circuit board, and a good tracking effect is achieved. This work will further improve the multi-target tracking capability of hardware systems.
- Bar-Shalom Yaakov and Li Xiao-Rong. 1993. Estimation and tracking: principles, techniques and software. Artech House, Norwood, MA, USA.Google Scholar
- Bar-Shalom Yaakov and Li Xiao-Rong. 1995. Multitarget multisensor tracking: principles and techniques. YBS Publishing, Storrs, CT, USA.Google Scholar
- Peyman Setoodeh, Saeid Habibi, and Simon Haykin. 2022. Smooth Variable Structure Filter. Wiley-IEEE Press, 85–112.Google Scholar
- Stefano P. Coraluppi and Craig A. Carthel. 2018. Multiple-Hypothesis Tracking for Targets Producing Multiple Measurements. IEEE Trans. Aerospace Electron. Systems 54, 3 (2018),1485–1498.Google ScholarCross Ref
- Rabeea Basir, Saad Qaisar, Mudassar Ali, Naveed Ahmad Chughtai, Muhammad Ali Imran, and Anas Hashmi. 2021. Performance Analysis of UAV Enabled Disaster Recovery Networks. Wiley-IEEE Press, 157–194.Google Scholar
- Hongyu Wang, Jiefei Ma, and Haifei Chi. 2021. Unmanned Driving System Based on DeepLabV3+ Semantic Segmentation. In 2021 36th Youth Academic Annual Conference of Chinese Association of Automation (YAC). 800–803.Google ScholarCross Ref
- Han Yun-Xiang and Huang Xiao-Qiong. 2022. Modeling of Air Traffic Flow Using Cellular Automata. IEEE Trans. Aerospace Electron. Systems 58, 4 (2022), 2623–2631.Google ScholarCross Ref
- Ronald Mahler. 2007. Statistical Multisource-Multitarget Information Fusion. Artech House, Norwood, MA, USA.Google ScholarDigital Library
- Ronald Mahler. 2014. Advance in Statistical Multisource-Multitarget Information Fusion. Artech House, Norwood, MA, USA.Google Scholar
- Ronald Mahler. 2004. ”Statistics 101” for multisensor, multitarget data fusion. IEEE Aerospace and Electronic Systems Magazine 19, 1 (2004), 53–64.Google Scholar
- Ronald Mahler. 2013. Statistics 102 for Multisource-Multitarget Detection and Tracking. IEEE Journal of Selected Topics in Signal Processing 7, 3 (2013), 376–389.Google ScholarCross Ref
- Ronald Mahler. 2019. Statistics 103 for Multitarget Tracking. Sensors 19, 1 (2019).Google Scholar
- Ronald Mahler. 2003. Multitarget Bayes filtering via first-order multitarget moments. IEEE Trans. Aerospace Electron. Systems 39, 4 (2003), 1152–1178.Google ScholarCross Ref
- Ba Ngu Vo and Wing Kin Ma. 2006. The Gaussian Mixture Probability Hypothesis Density Filter. IEEE Transactions on Signal Processing 54, 11 (2006), 4091–4104.Google ScholarDigital Library
- Ba Ngu Vo, Sumeetpal Singh, and Arnaud Doucet. 2005. Sequential Monte Carlo methods for Multi-target Filtering with Random Finite Sets. IEEE Trans. Aerospace Electron. Systems 41, 4 (2005), 1224–1245.Google ScholarCross Ref
- K. Punithakumar, T. Kirubarajan, and A. Sinha. 2005. A sequential Monte Carlo probability hypothesis density algorithm for multitarget track-before-detect. In Signal and Data Processing of Small Targets 2005, Oliver E. Drummond (Ed.), Vol. 5913. International Society for Optics and Photonics, SPIE, 59131S.Google Scholar
- Ba-Ngu Vo, Ba-Tuong Vo, Nam-Trung Pham, and David Suter. 2010. Joint Detection and Estimation of Multiple Objects From Image Observations. IEEE Transactions on Signal Processing 58, 10 (2010), 5129–5141.Google ScholarDigital Library
- Lesole Kalake, Wanggen Wan, and Li Hou. 2021. Analysis Based on Recent Deep Learning Approaches Applied in Real-Time Multi-Object Tracking: A Review. IEEE Access 9 (2021), 32650–32671.Google ScholarCross Ref
- Weiwei Xing, Yuxiang Yang, Shunli Zhang, Qi Yu, and Liqiang Wang. 2022. NoisyOTNet: A Robust Real-Time Vehicle Tracking Model for Traffic Surveillance. IEEE Transactions on Circuits and Systems for Video Technology 32, 4 (2022), 2107–2119.Google ScholarCross Ref
- Tian Chen, Pei Yang, Hou Peng, and Zhao Qian. 2020. Multi-target tracking algorithm based on PHD filter against multi-range-false-target jamming. Journal of Systems Engineering and Electronics 31, 5 (2020), 859–870.Google ScholarCross Ref
- Wei Yi, Guchong Li, and Giorgio Battistelli. 2020. Distributed Multi-Sensor Fusion of PHD Filters With Different Sensor Fields of View. IEEE Transactions on Signal Processing 68 (2020), 5204–5218.Google ScholarCross Ref
- Yih-Shyh Chiou, Yi-Hsuan Liu, Yu-Jhih Chen, Shih-Lun Chen,Ting-Lan Lin, Wei-Ting Chen, You-Sheng Zhang, Tsung-Hsuan Chen, Tzu-Yu Chen, and Tzu-Chiao Lin. 2020. Design and Implementation of 3D Real-Time Positioning and Tracking Algorithms in FPGA for Location Estimation. In 2020 IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE). 40–43.Google ScholarCross Ref
- Odrika Iqbal, Saquib Siddiqui, Joshua Martin, Sameeksha Katoch, Andreas Spanias, Daniel Bliss, and Suren Jayasuriya. 2020. Design and FPGA Implementation of an Adaptive video Subsampling Algorithm for Energy-Efficient Single Object Tracking. In 2020 IEEE International Conference on Image Processing (ICIP). 3065–3069.Google ScholarCross Ref
Index Terms
- Hardware Implementation of PHD Filter for Image Target Tracking
Recommendations
Iterative RANSAC based adaptive birth intensity estimation in GM-PHD filter for multi-target tracking
This paper investigates a novel multi-target tracking algorithm for jointly estimating the number of multiple targets and their states from noisy measurements in the presence of data association uncertainty, target birth, clutter and missed detections. ...
A box-particle implementation of standard PHD filter for extended target tracking
The paper presents a box-particle implementation of the standard PHD filter. The proposed ET-Box-PHD filter is derived by the cell likelihood function defined. The proposed filter is suitable to the strong clutter surveillance areas. This paper presents ...
The semantic PHD filter for multi-class target tracking: From theory to practice
AbstractIn order for a mobile robot to be able to effectively operate in complex, dynamic environments it must be capable of understanding both where and what the objects around them are. In this paper we introduce the semantic probability ...
Highlights- Adding semantic information improves the performance of multi-target trackers.
- ...
Comments