Autoware Traffic Light Recognition without Vector Map
If I use region-tlr-mxnet or region_tlr_ssd in autoware, is Vector map containing traffic light information still mandatory?
ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | ros @ Robotics Stack Exchange |
If I use region-tlr-mxnet or region_tlr_ssd in autoware, is Vector map containing traffic light information still mandatory?
You will still need vector map information to do traffic light information.
region_tlr_mxnet and region_tlr_ssd are meant to only do color recognition of the traffic light, and traffic light detection can only be done using feat_proj nodes.
Technically speaking, region_tlr_ssd can detect position of traffic light in the image. However, current implementation expects output from feat_proj to as a trigger to do recognition.
Asked: 2020-03-19 03:51:19 -0500
Seen: 302 times
Last updated: Mar 19 '20
Is there a way to know which version of Autoware is running?
How to change the vision algorithm(yolov3 to yolov4) in autoware.ai?
In which version of Autoware the Gazebo Catvehicle simulation is supported?
How to know how to import a message ?
For frame [velodyne]: Frame [velodyne] does not exist
Why does TF use strictly a tree?
Problem with ros::Rate sleep function