MATLAB & Simulink

Automotive Applications

Automated Driving with MATLAB

Course Highlights

This one-day course provides hands-on experience with developing and verifying automated driving perception algorithms. Examples and exercises demonstrate the use of appropriate MATLAB® and Automated Driving System Toolbox™ functionality.
Topics include:

​

  • Labeling of ground truth data

  • Visualizing sensor data

  • Detecting lanes and vehicles

  • Fusing sensor detections

  • Generating driving scenarios and modeling sensors

Prerequisite

MATLAB Fundamentals or equivalent experience using MATLAB. Image Processing with MATLAB, Computer Vision with MATLAB and basic knowledge of image processing and computer vision concepts. Deep Learning with MATLAB is recommended.

Partners 

Upcoming Program

Techsource Systems is
Mathworks Sole and Authorised Distributor and Training Partner

​Course Outlline

​Day 1 of 1

Labeling of Ground Truth Data

​

Objective: Label ground truth data in a video or sequence of images interactively. Automate the labeling with detection and tracking algorithms.

​

  • Overview of Ground Truth Labeler

  • Label ROIs (Regions of Interest) and scenes

  • Automate labeling

  • View/export ground truth results

 

Visualizing Sensor Data

​

Objective: Visualize camera frames, radar and lidar detections. Use appropriate coordinate systems to transform image coordinates to vehicle coordinates and vice versa.

​

  • Create bird’s eye plot

  • Plot sensor coverage areas

  • Visualize detections and lanes

  • Convert from vehicle to image coordinates

  • Annotate video with detections and lane boundaries

 

Detecting Lanes and Vehicles

 

Objective: Segment and model parabolic lane boundaries. Use pretrained object detectors to detect vehicles.

​

  • Perform bird’s eye view transform

  • Detect lane features

  • Compute lane model

  • Validate lane detection with ground truth

  • Detect vehicles with pretrained object detectors

​

Fusing Sensor Detections

 

Objective: Create a multi-object tracker to fuse information from multiple sensors such as camera, radar etc.

​

  • Track multiple objects

  • Preprocess detections

  • Kalman filters

  • Manage multiple tracks

  • Track with multi-object tracker

​

Generating Driving Scenarios and Modeling Sensors

 

Objective: Create driving scenarios and synthetic radar/camera sensor detections interactively to test automated driving perception algorithms.

​

  • Overview of Driving Scenario Designer

  • Create scenarios with roads, actors and sensors

  • Simulate and visualize scenario

  • Generate detections and export scenarios

  • Test algorithms with scenarios