Real-Time Detection and Tracking of Traffic Sign in Video Sequences for Autonomous Mobile Robot

This paper proposes a navigation algorithm that allows mobile robots that participate in different missions to move in unknown environment. The algorithm uses data from the sonar or from the infrared sensors mounted on the robots and data from the video camera with which the robots are equipped. Using the video camera the robots will be able to detect and classify different traffic signs that can help the robots to arrive the target points safely and in a short time. The algorithm includes a convolutional neural network with six layers to classify the traffic signs. Several simulations were run on the nRobotic platform developed at the "Politehnica" University of Timisoara, Romania, to validate the new algorithm. The simulation scenarios illustrate attractive mechatronics applications concerning the behaviors of robots in unknown environments in the presence of multiple traffic signs.

show abstract

Real-Time Detection and Tracking of Traffic Sign in Video Sequences for Autonomous Mobile Robot

Cited by 2 publications

References 11 publications

On feature selection in network flow based traffic sign tracking models

On feature selection in network flow based traffic sign tracking models

Nrobotic mobile robot navigation using traffic signs in unknown indoor environments

Contact Info

Product

Resources

About