Water Video Analysis

Many image processing and computer vision applications have difficulty dealing with a nonstatic background such as water waves, but this particular dynamic scene actually contains enough information to reveal much more than a static scene. In this paper, we propose a method to determine real world scale as well as other factors, including wave height, sea state, and wind speed, from uncalibrated water video. We do this by using low level image processing tools to extract a spatial frequency spectrum from individual frames of the video and temporal frequencies from the time dimension of the video, and applying known physics of water waves to find the high level properties of the scene. An example is presented to demonstrate and validate the process. © 2004 IEEE