The evaluation of visual perception systems for autonomous vehicles (AVs) is challenging for developing AV technologies. Enlightened by current studies on human-like AV control, assessing the similarity of visual attention between AVs and human drivers becomes one of the potential means for the evaluation of AV technologies. This work proposes a human-like evaluation framework for the visual perception system of AVs, based on human visual attention benchmarks derived from expert human drivers' eye gaze data. We first create a perceptual benchmark by standardizing the gaze data from different expert human drivers. Then, we extract the features from the hidden layers of different AV perception algorithms. Finally, a human-like evaluation index is proposed to quantify the differences between chauffeured vehicles and AVs. The proposed human-like evaluation framework is of help for the development of AV system testing and evaluation by assessing the visual perception of AVs under various driving scenarios.
Human-Like Evaluation of Visual Perception System for Autonomous Vehicles Based on Human Visual Attention
24.09.2023
584966 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Driver Visual Focus of Attention Estimation in Autonomous Vehicles
British Library Conference Proceedings | 2020
|Driver Visual Focus of Attention Estimation in Autonomous Vehicles
SAE Technical Papers | 2020
|Driver Visual Focus of Attention Estimation in Autonomous Vehicles
British Library Conference Proceedings | 2020
|Automatic thresholding based on human visual perception
British Library Online Contents | 1993
|