Abstract: Autonomous vehicles using Artificial Intelligence (AI) technologies requires various sensors such as radars, lidar, ultrasonic, etc. to have the human visual perception in monitoring the road. Wide angle camera is often used for better coverage and experience for view. Those sensors generate massive amount of data that could be processed with the cloud computing through the wireless communication. The cloud computing may not be a feasible solution, as for real- time detection systems. In this work, we examine the implementation of the deep-learning and real-time object detection on the edge devices that is connected to the wide-angle camera. This system can achieve real-time object detection with a latency of less than 0.2 ms. This model also helps to mitigate the distortion that is introduced by the wide-angle camera. Detection system will be able to warn user of his or her surrounding road conditions.
Keywords: Artificial Intelligence, Deep-Learning, Edge Computing, Real-time Object Detection.
|
DOI:
10.17148/IJARCCE.2022.115193