High-Speed Range Estimation Based on Intensity Gradient Analysis

Abstract

The Intensity Gradient Analysis (IGA) Algorithm obtains depth estimates by analyzing temporal intensity gradients arising from image displacements induced by known camera motion. By using intensity gradients, IGA completely avoids the computationally expensive feature extraction and correspondence steps of conventional approaches and is therefore very fast. Extensive experimentation has been done using IGA, with a strong emphasis on the issues associated with real-world implementation. These issues include the non-ideal nature of conventional CCD sensors, the effects of imaging geometry and the effects of uncertainties in knowledge of the cameras motion parameters on the perceptual capabilities of an IGA-based depth recovery system. The purpose of this work is two-fold. First and foremost it is to present the algorithm itself. IGA is an accurate, vision-based depth recovery algorithm that requires a fraction of the computational effort required by existing techniques. The second is the fact that IGA represents a concrete example of how the so-called Active Vision paradigm can be used to simplify a complex task.