Vision Apps User Guide
Dempster-Shafer Enabled Lidar Occupancy Grid Map Application

Introduction

This application generates a dynamic occupancy grid map indicating free space versus occupied space around the vehicle, using automotive grade Velodyne Lidar. Dempster- shafer algorithm is employed for handling the dynamics in the scene. The generated OGMAP is then used as input to a parking/free space detection algorithm block to generate a final map with different regions (free space parkable free space) marked. Localization of the vehicle in the maps is provided by an Inertial Navigation System (INS) combining GPS (Global Positioning System) and IMU (Inertial Measurement Unit).

The application makes use of the below application libraries,

  1. Applib for OGMap Generation using Lidar

Supported plaforms

Platform Linux x86_64 Linux+RTOS mode QNX+RTOS mode SoC
Support N0 YES NO J721e

Data flow

vx_app_lidar_ogmap_data_flow_ds.png

Steps to run the application

  1. Boot the EVM up.
  2. Run the following commands:
    source /opt/vision_apps/vision_apps_init.sh
    /opt/vision_apps/run_ptk_demo.sh
    Pick option 4 for Lidar Dempster-Shafer OG map application.

Sample Output

Shown below is an example output visualization showing the Lidar DS OGMAP.

vx_app_lidar_ogmap_ds_out.png