CDVA/VCM: Language for Intelligent and Autonomous Vehicles

Abstract

Intelligent transportation is a complex system that involves the interaction of connected technologies, including Smart Sensors, Intelligent and Autonomous Vehicles, High Precision Maps, and 5G. The coordination of all these machines mandates a common language that serves as a protocol for intelligent machines to communicate. International standards serves as the global protocol to satisfy industry needs at the product level. MPEG-CDVA is the official ISO standard for search and retrieval applications by providing Compact Descriptors for Video Analysis (CDVA). It is robust and enables efficient implementations on embedded systems. CDVA is the first generation language for images/videos. MPEG-VCM is developing advanced features beyond CDVA to the new generation as Video Coding for Machines (VCM). With the wide availability of low-power AI chips, CDVA and VCM are ready to deploy and serve as the language for intelligent and autonomous vehicles. In this paper, we demonstrate the use of the SuperCDVA and Closed Captioning CDVA algorithms for intelligent and autonomous vehicles. Concepts are borrowed from the Super Characters algorithm in Natural Language Processing. In order for intelligent and autonomous vehicles to understand events on the road, the CDVA vectors are organized into an image to represent the story of the video.