Title :
Reinforcing the reliability of pedestrian detection in far-infrared sensing
Author :
Meis, Urban ; Oberlander, Matthias ; Ritter, Werner
Author_Institution :
Dept. RIC-AP, DaimlerChrysler AG, Ulm, Germany
Abstract :
In this contribution we describe a method to improve the reliability of monocular far-infrared pedestrian detection. In contrast to many other solutions using heuristic approaches, we use a statistical approach, i.e., a pixel classification for head detection in comparison with a classifier for body detection to investigate the performance of pedestrian detection. Using a head detector leads to a significant improvement in the detection precision and promises further advantages in combination with a body detector.
Keywords :
image classification; image segmentation; image sensors; object detection; statistics; body detection; body detector; far infrared sensing; head detection; head detector; heuristic method; monocular far infrared pedestrian detection; pixel classification; reliability; statistical method; Cameras; Detectors; Infrared heating; Layout; Magnetic heads; Night vision; Object detection; Roads; Sensor systems; Thermal sensors;
Conference_Titel :
Intelligent Vehicles Symposium, 2004 IEEE
Print_ISBN :
0-7803-8310-9
DOI :
10.1109/IVS.2004.1336483
