Ebook: High-Speed Range Estimation Based on Intensity Gradient Analysis

A fast and reasonably accurate perception of the environment is essential for successful navigation of an autonomous agent. Although many modes of sensing are applicable to this task and have been used, vision remains the most appealing due to its passive nature, good range, and resolution. Most vision techniques to recover depth for navigation use stereo. In the last few years, researchers have started studying techniques to combine stereo with the motion of the camera. Skifstad's dissertation proposes a new approach to recover depth information using known camera motion. This approach results in a robust technique for fast estimation of distances to objects in an image using only one translating camera. A very interesting aspect of the approach pursued by Skifstad is the method used to bypass the most difficult and computationally expensive step in using stereo or similar approaches for the vision-based depth esti­ mation. The correspondence problem has been the focus of research in most stereo approaches. Skifstad trades the correspondence problem for the known translational motion by using the fact that it is easier to detect single pixel disparities in a sequence of images rather than arbitrary disparities after two frames. A very attractive feature of this approach is that the computations required to detect single pixel disparities are local and hence can be easily parallelized. Another useful feature of the approach, particularly in naviga­ tion applications, is that the closer objects are detected earlier.

---

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.

---

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.
Content:
Front Matter....Pages i-x
Introduction....Pages 1-4
Approaches to the Depth Recovery Problem....Pages 5-23
Depth Recovery....Pages 25-33
Theoretical Basis for IGA....Pages 35-44
Intensity Gradient Analysis....Pages 45-54
Implementation Issues....Pages 55-86
Fixed Disparity Surfaces....Pages 87-110
Experiments....Pages 111-144
An Application: Vision-Guided Navigation Using IGA....Pages 145-169
Conclusion....Pages 171-174
Back Matter....Pages 175-182

---

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.
Content:
Front Matter....Pages i-x
Introduction....Pages 1-4
Approaches to the Depth Recovery Problem....Pages 5-23
Depth Recovery....Pages 25-33
Theoretical Basis for IGA....Pages 35-44
Intensity Gradient Analysis....Pages 45-54
Implementation Issues....Pages 55-86
Fixed Disparity Surfaces....Pages 87-110
Experiments....Pages 111-144
An Application: Vision-Guided Navigation Using IGA....Pages 145-169
Conclusion....Pages 171-174
Back Matter....Pages 175-182
....