A HiL Test Bench for Monocular Vision Sensors and Its Applications in Camera-Only AEBs

This paper presents a HiL test bench specifically designed for closed-loop testing of the monocular-vision based ADAS sensors, whereby the animated pictures of the virtual scene is calibrated and projected onto a 120-degree circular screen, such that the camera sensor installed has the same vision as the observation of the real-world scene. A high-fidelity AEBs model is established and deployed in the real-time target of the HiL system, making intervention decisions based on the instance-level detection information transmitted from the physical sensor. By referring to the 2018 edition of the C-NCAP testing protocol, the HiL tests of the rear-end collision scenarios is performed to investigate the performance and characteristics of the longitudinal-motion sensing of the sensor sample under test. By comparing and analyzing the differences between the measured data and the ground truth, the sensor’s visual-perceptual capabilities with respect to accuracy and delays are evaluated in the presence of emergency braking of the subject and the leading vehicles. Finally, the matching and optimization solution is offered for performance enhancement of the camera-only AEBs using this monocular vision sensor.