Risk Ranked Recall: Collision Safety Metric for Object Detection Systems in Autonomous Vehicles
arXiv:2106.04146 · doi:10.1109/MECO52532.2021.9460196
Abstract
Commonly used metrics for evaluation of object detection systems (precision, recall, mAP) do not give complete information about their suitability of use in safety critical tasks, like obstacle detection for collision avoidance in Autonomous Vehicles (AV). This work introduces the Risk Ranked Recall () metrics for object detection systems. The metrics categorize objects within three ranks. Ranks are assigned based on an objective cyber-physical model for the risk of collision. Recall is measured for each rank.
arXiv commentCyber-Physical Systems and Internet-of-Things 2021
Cited by in corpus (4)
- Verifiable Obstacle Detection
- Evaluating Object (mis)Detection from a Safety and Reliability Perspective: Discussion and Measures
- Perception Simplex: Verifiable Collision Avoidance in Autonomous Vehicles Amidst Obstacle Detection Faults
- Synergistic Perception and Control Simplex for Verifiable Safe Vertical Landing