RT info:eu-repo/semantics/article
T1 Pedestrian detection using a MEMS acoustic array mounted on a moving vehicle
A1 Izquierdo Fuente, Alberto
A1 Val Puente, Lara del
A1 Villacorta Calvo, Juan José
K1 Pedestrian detection
K1 MEMS microphone array
K1 Onboard system
K1 Moving vehicle
AB Automatic pedestrian detection in a vehicle is of vital importance in Advanced Driver Assistance Systems (ADAS). Sensors currently used are based on cameras, radars and lidars, whose performance is degraded in environments with reduced visibility: night, smoke, fog, etc. This paper has validated the use of an active array of 150 MEMS (Micro-Electro Mechanical Systems) microphones incorporated into a conventional car moving in real urban traffic conditions, with the system working in real time, at a rate of 8 detections per second. Together with beamforming, Constant False Alarm Rate (CFAR) detection and lane detection algorithms, a crucial algorithm has been incorporated for the proper performance of the system that discriminates the detections of objects or pedestrians generated by the system from the false alarms generated by road imperfections, such as bumps, cracks, etc. Based on 6000 captures, performed with the car moving at 30 km/h, which is the typical speed limit in urban environments, it has been possible to detect pedestrians positioned at a distance from the car varying between 5 and 20 m, with a detection probability of 0.91 and a false alarm probability of 0.01. The results obtained have validated the effectiveness of using active acoustic arrays in the field of pedestrian detection and position estimation from moving cars in urban environments. The fusion of the presented system with the systems currently used for this purpose, would significantly improve the performance of pedestrian detection systems interacting with AEB (Automatic Emergency Breaking) systems, extending their operability to environments with reduced visibility, and resulting in the reduction in the number of possible collisions with pedestrians, thus increasing their safety.
PB Elsevier
SN 0924-4247
YR 2024
FD 2024
LK https://uvadoc.uva.es/handle/10324/73116
UL https://uvadoc.uva.es/handle/10324/73116
LA eng
NO Sensors and Actuators A: Physical, octubre 2024, vol. 376, 115586
NO Producción Científica
DS UVaDOC
RD 15-ene-2025