A new technique for robot vision in autonomous underwater vehicles using the color shift in underwater imaging
Jones, Jake A.
MetadataShow full item record
Developing a technique for underwater robot vision is a key factor in establishing autonomy in underwater vehicles. A new technique is developed and demonstrated to depict an underwater scene in three dimensions (3D) for use in underwater robot vision. This technique uses passive lighting and the optical properties of water to approximate distances between objects in a scene. Beer's Law is used to describe the change in intensity that light at different wavelengths experiences as it travels through water. If the intensities can be measured, then Beer's Law provides sufficient information to estimate the unknown distance. Applying the equation pixel by pixel to compare two images produces distances from the camera to everything in the image. A shift in color caused by the uneven absorption by each wavelength is similar to comparing the intensities. The color shift produces a relative distance between objects in the scene rather than distances from the camera to the objects. This relative distance may be combined with other techniques to determine the distances from each pixel to the camera.
RightsThis publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.
Showing items related by title, author, creator and subject.
Moeller, Michelle L. (Monterey, CA; Naval Postgraduate School, 2021-06);A low-light, underwater, charge coupled device (CCD) video camera with a unique lens was evaluated in near-zero surface lux for operational use at night as a function of depth in the ocean. The goal is real-time video for ...
Finite element modeling and long-wave infrared imaging for detection and identification of buried objects Tilley, Heather P. (Monterey, California: Naval Postgraduate School, 2017-12);Detection of buried improvised explosive devices (IED) represents a complex threat to U.S. forces. This thesis explores the potential use of infrared images combined with finite element models to detect buried objects in ...
Lai, Wee Leong (Monterey, California: Naval Postgraduate School, 2017-09);In a GPS-denied environment, one of the possible selections for navigating an unmanned ground vehicle (UGV) is through real-time visual odometry. To navigate in such an environment, the UGV needs to be able to detect, ...