Depth from Scattering

Light power is a ected when it crosses the atmosphere; there is a simple, albeit non-linear, relationship between the radiance of an image at any given wavelength and the distance between object and viewer. This phenomenon is called atmospheric scattering and has been extensively studied by physicists and meterologists. We present the rst analysis of this phenomenon from an image understanding perspective: we investigate a group of techniques for extraction of depth cues solely from the analysis of atmospheric scattering e ects in images. Depth from scattering techniques are discussed for indoor and outdoor environments, and experimental tests with real images are presented. We have found that depth cues in outdoor scenes can be recovered with surprising accuracy and can be used as an additional information source for autonomous vehicles.

• Type: Conference
• Year: 1997
• Where: CVPR
• Authors: Fabio Gagliardi Cozman, Eric Krotkov
• Keywords: Atmospheric Scattering, Computer Vision, CVPR 1997, Depth Cues, Image Understanding Perspective