Development of Multi Target Trackers for Surveillance Radar Using MATLAB
Srihari B R, BEL
A multi-target tracker developed for surface target tracking in a coastal surveillance scenario needs a robust track initiation and maintenance algorithm for tracking small targets and reducing the false alarm rate in the presence of sea clutter. The multi-object tracks in Sensor Fusion and Tracking Toolbox™ are evaluated with time-stamped detections recorded from the field. The GNN and ToMHT tracker module parameters are tuned by varying track initiation methods, estimation filters, thresholds, and hypothesis maintenance parameters. The resulting track data from each approach is benchmarked with recorded track data from the OEM system in the field. The performance of the MATLAB® tracker is compared with reference to Track ID maintenance, accuracy in estimated position, speed, course of targets, and time taken for processing each scan data. The results from multi-track line GNN and ToMHT approach with customized EKF and IMM-EKF are found satisfactory with respect to Tack maintenance and kinematics. To improve processing time, sub-optimal assignment methods and custom cost-matrix computation is tried out. The covariance fusion function in SFTT is used for correlating similar confirmed tracks from different tracking lines and removing duplicate tracks from confirmed track list. Code generation from MATLAB Coder™ is used for generating a C++ library with tuned tracker parameters. A wrapper function is written in C++ for interfacing radar detection input and track output to display. Further, custom enhancements are incorporated in C++ deployable code for improving track maintenance and processing time with respect to one scan data. The deployable tracker module is interfaced with a radar in the field and performance evaluation is in progress. An attempt is made to tune tracker parameters generated in C++ library to adapt to present environment conditions based on input data attributes. A display interface is provided for the operator to tune thresholds for reducing false alarm rate.
Published: 1 Jul 2019
Related Products
Learn More
Featured Product
MATLAB
Up Next:
Related Videos:
웹사이트 선택
번역된 콘텐츠를 보고 지역별 이벤트와 혜택을 살펴보려면 웹사이트를 선택하십시오. 현재 계신 지역에 따라 다음 웹사이트를 권장합니다:
또한 다음 목록에서 웹사이트를 선택하실 수도 있습니다.
사이트 성능 최적화 방법
최고의 사이트 성능을 위해 중국 사이트(중국어 또는 영어)를 선택하십시오. 현재 계신 지역에서는 다른 국가의 MathWorks 사이트 방문이 최적화되지 않았습니다.
미주
- América Latina (Español)
- Canada (English)
- United States (English)
유럽
- Belgium (English)
- Denmark (English)
- Deutschland (Deutsch)
- España (Español)
- Finland (English)
- France (Français)
- Ireland (English)
- Italia (Italiano)
- Luxembourg (English)
- Netherlands (English)
- Norway (English)
- Österreich (Deutsch)
- Portugal (English)
- Sweden (English)
- Switzerland
- United Kingdom (English)
아시아 태평양
- Australia (English)
- India (English)
- New Zealand (English)
- 中国
- 日本Japanese (日本語)
- 한국Korean (한국어)