Visibility of road hazards in thermal, visible, and sensor-fused night-time imagery

Sensor fusion combines the output of multiple imaging sensors within a sing le composite display. Ideally, a fused image will retain important spatial information provided by individual input images, and will convey useful spa tial or chromatic emergent information derived from the contrast between in put images. The present experiment assessed the potential benefits of senso r fusion as a method of enhancing drivers' night-time detection of road haz ards. Observers were asked to detect a pedestrian within thermal and visibl e images of a night-time scene, and within chromatic and achromatic renderi ngs created by sensor fusion of grayscale thermal and visible images. Resul ts indicated that fusion can both improve spatial image content, and can ef fectively embellish spatial content with emergent chromatic information. Th e benefits of both sensor fusion and of color rendering, however, were inco nsistent, varying substantially with quality of input images submitted for fusion. (C) 2000 Elsevier Science Ltd. All rights reserved.