IEEE P2020 Automotive Image Quality Standard Workshop was held at Leopard Imaging

The IEEE P2020 Automotive Image Quality Standard Workshop was held at Leopard Imaging, Fremont, California on 25-26 January, immediately after the nearby Electronic Imaging 2024 symposium. This hosted a total of 60 participants for 2 days, with 20 in-person participants and 40 online participants.

After 8 years of considerable collaboration, innovation, and experimentation, it was voted on 25 January during the workshop to submit the 300-page technical draft for final publication to the IEEE. This is a considerable achievement and will lead to better regulation of consequential imaging systems. Future enhancements were also proposed, including the development of more information-theoretic tools for image quality assessment, to address emerging deep learning computer vision perspectives on image content.

The IEEE‐SA P2020 working group on automotive imaging standards was co-founded 8 years ago by UL/D2ICE's Patrick Denny to address the considerable ambiguity in the measurement of image quality of automotive imaging systems, both human and computer vision-based. An associated white paper outlines the goals, achievements, rationale, and plans of the subgroup, which has started to work on the development of a new standard. Image quality plays a crucial role for both automotive viewing and automotive computer vision applications and today’s image evaluation approaches do not necessarily meet the needs of such applications.

Currently, there is not a consistent approach within the industry to measure automotive image quality. The IEEE P2020 working group is attempting to remedy these deficiencies by connecting people in the field, identifying gaps in existing standards, and working to address these by creating a coherent set of key performance indicators by which camera systems and components may be evaluated in a manner consistent with their intended use.