Design and Verification of Algorithms for Object Detection and Tracking Using Lidar Data - MATLAB & Simulink

Technical Articles

Design and Verification of Algorithms for Object Detection and Tracking Using Lidar Data

By Marco Roggero, Prashant Arora, Gael Goron, Anand Raja, and Elad Kivelevitch, MathWorks


Lidar sensors are essential for autonomous vehicles and most ground moving robots. In their short scan cycles, these sensors generate a large number of points containing information that can be used to detect obstacles in the surrounding environment. While the process of extracting information, detecting and tracking relevant objects, and filtering noise or road reflections is complex, it needs to be reliable and accurate.

In this work, we explain how to preprocess raw point clouds from lidar sensors in MATLAB® to generate detections for conventional trackers that assume one detection per object per sensor scan. We then define a cuboid model to describe kinematics, dimensions, and measurements of extended objects being tracked with a joint probabilistic data association (JPDA) tracker and use an interacting multiple model (IMM) filter. Finally, we mention how to generate C code from the algorithm and verify execution results.

This paper was presented at Embedded World Conference 2020.

Read full paper.

Published 2020

View Articles for Related Capabilities

View Articles for Related Industries