ITSC 2025 Paper Abstract

Paper WE-LA-T4.3

CORNEJO-URQUIETA, Galia-Fabiola (Ampere SOftware Technologies), Grandvalet, Yves (CNRS/UTC), Moreau, Julien (University of technology of Compiègne (UTC)), Ibanez Guzman, Javier (Renault S.A.S,), Camarda, Federico (Heudiasyc Laboratory)

Perception Metrics for Intelligent Vehicles: An Application-Focused Evaluation

Scheduled for presentation during the Regular Session "S04c-Intelligent Perception and Detection Technologies for Connected Mobility" (WE-LA-T4), Wednesday, November 19, 2025, 16:40−17:00, Surfers Paradise 1

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 19, 2025

Keywords Real-time Object Detection and Tracking for Dynamic Traffic Environments, Deep Learning for Scene Understanding and Semantic Segmentation in Autonomous Vehicles, Safety Verification and Validation Methods for Autonomous Vehicle Technologies

Abstract

Modern passenger vehicles increasingly rely on video cameras within Advanced Driver Assistance Systems (ADAS) and Automated Driving (AD) technologies to perceive their surroundings and make decisions. These perception systems, largely based on machine learning, face typical challenges of data-driven approaches. As their role in safety-critical scenarios grows, uncertainty quantification has gained significant attention to better characterize both the perceived environment and the confidence in these perceptions. Benchmarking these methods from a application point of view becomes crucial for their deployment. In this context, robust metrics are critical to evaluate how well an intelligent vehicle’s perception system performs. This paper investigates the relationship between conventional computer vision metrics and those required for ADAS/AD applications, when characterizing perception system from an application point of view. It presents experimental results that reveal alignments and mismatches between standard computer vision measures and the demands of ADAS/AD use cases. Finally, it demonstrates how adopting a unified perspective on metrics can: (1) provide deeper insights into perception system performance, and (2) guide the selection of appropriate evaluation criteria to enhance the deployment of machine learning algorithms in intelligent vehicle perception.