This software has been designed to detect water bodies that are out in the open on cross-country terrain at close range (out to 30 meters), using imagery acquired from a stereo pair of color cameras mounted on a terrestrial, unmanned ground vehicle (UGV). This detector exploits the fact that the color variation across water bodies is generally larger and more uniform than that of other naturally occurring types of terrain, such as soil and vegetation. Non-traversable water bodies, such as large puddles, ponds, and lakes, are detected based on color variation, image intensity variance, image intensity gradient, size, and shape.
At ranges beyond 20 meters, water bodies out in the open can be indirectly detected by detecting reflections of the sky below the horizon in color imagery. But at closer range, the color coming out of a water body dominates sky reflections, and the water cue from sky reflections is of marginal use. Since there may be times during UGV autonomous navigation when a water body does not come into a perception system’s field of view until it is at close range, the ability to detect water bodies at close range is critical. Factors that influence the perceived color of a water body at close range are the amount and type of sediment in the water, the water’s depth, and the angle of incidence to the water body. Developing a single model of the mixture ratio of light reflected off the water surface (to the camera) to light coming out of the water body (to the camera) for all water bodies would be fairly difficult. Instead, this software detects close water bodies based on local terrain features and the natural, uniform change in color that occurs across the surface from the leading edge to the trailing edge.
From a water body’s leading edge to the trailing edge, brightness and saturation levels tend to increase, with saturation content changing at a faster rate than the brightness content. For all the pixels on a water body, a plot of brightness/saturation vs. incidence angle is fairly linear with high slope. Fortuitously, this slope tends to be higher for water than other naturally occurring terrain. This phenomenology was exploited here to develop software that detects water bodies at close range. First, candidate water regions are identified in image space by locating regions having low texture. Next, the color changes are evaluated across each candidate water region to locate those consistent with water. Finally, an ellipse fit is performed on remaining candidate water regions and size and aspect ratio filtering is applied to prune regions that geometrically are not likely to be water.
This work was done by Arturo L. Rankin of Caltech for NASA’s Jet Propulsion Laboratory.
In accordance with Public Law 96-517, the contractor has elected to retain title to this invention. Inquiries concerning rights for its commercial use should be addressed to:
Innovative Technology Assets Management
JPL
Mail Stop 202-233
4800 Oak Grove Drive
Pasadena, CA 91109-8099
E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
NPO-47088
This Brief includes a Technical Support Package (TSP).
Water Detection Based on Color Variation
(reference NPO-47088) is currently available for download from the TSP library.
Don't have an account?
Overview
The document titled "Water Detection Based on Color Variation" is a Technical Support Package developed by the California Institute of Technology under the sponsorship of NASA. It focuses on enhancing the capabilities of unmanned ground vehicles (UGVs) in detecting water and mud across various terrains and conditions, which is crucial for autonomous navigation.
The primary goal of the Robotics Collaborative Technology Alliances (RCTA) Water and Mud Detection task is to create a robust classifier that can accurately identify water and mud hazards, enabling UGVs to plan safe paths during operations both day and night. The document discusses previous work (NPO47092) that successfully developed software for detecting water bodies at mid to far ranges, utilizing sky reflections as a significant cue. This method demonstrated effectiveness in identifying large water puddles from distances of 15 to 60 meters.
However, the document highlights the challenges faced when detecting water bodies at close range. At these distances, the color of the water becomes the dominant cue, overshadowing the sky reflections that are useful at greater distances. The authors present an algorithm designed to detect water bodies in open areas at close range, where traditional methods may fail.
The document includes theoretical analyses, such as the fraction of incident power reflected from an air/water interface as a function of incidence angle and distance. It notes that high reflection coefficients occur only at large incidence angles and that the effectiveness of detection diminishes for look-ahead distances less than 18 meters. This is particularly relevant for pure water, and the impact of sediment concentration is acknowledged as outside the scope of the current work.
Visual aids, including plots and images, illustrate the variation in color across a water body as the range decreases, emphasizing the importance of color analysis in close-range detection. The document concludes by underscoring the significance of robust water detection for UGVs, as failures due to water damage can lead to costly repairs and resource diversion during critical missions.
Overall, this Technical Support Package provides valuable insights into the development of advanced detection algorithms and the challenges of water detection in autonomous navigation, contributing to the broader field of robotics and military applications.
