Target tracking for automotive radar

• Main Author: Chen, Ziqiu
• Other Authors: Lu Yilong
• Format: Final Year Project
• Language: English
• Published: 2019
• Online Access: http://hdl.handle.net/10356/77574
• Institution: Nanyang Technological University

With the advancement of science and innovation, automated driving has turned into an investigation of concern. Different sorts of testing tools are introduced on driverless vehicles to sense the encompassing condition. Among them, the high flexibility to various climate conditions and relatively low price of radar sensor make it a standout from all categories of sensors. In particular, the 77 GHz car radar can be utilized as both Long Range Radar (LRR) and Short Range Radar (SRR). The radar sensor is relied upon to accomplish better circumstance view for self-supporting vehicles or drivers by distinguishing the hindrances on the ground. In this final year project, both real measured data from 77 GHz automotive radar sensors and simulated data from MATLAB Automated Driving System Toolbox are used to gather information from genuine situations where vehicles and people on foot can be recognized. One of the important processes of the project is to obtain useful data from the raw radar data. The raw radar information just contains discrete data points corresponding to distinguished targets. Along these lines, the visual presentation of radar information, clustering of data points, tracking of moving targets are actualized well ordered to accomplish awareness to surrounding circumstances. The radar information is shown continually frame by frame. The clustering algorithm is developed based on Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering method, while the tracking algorithm based on Kalman Filter.