Adaptive Filtering of 4-D Light Field Images for Depth-Based Image Enhancement

A novel method is described for adaptive filtering of light fields to enhance objects at a given depth. Using the frequency domain of an epipolar-plane image (EPI) to select the minimum and maximum depths of an object of interest (OOI) allows greater selectivity over traditional methods and the ability to re-focus a light field as the scene changes. This method is executed on real light fields, where depth information is extracted and used for depth filtering. A light field video is used to show that as an OOI moves to varying depths in a scene, the performance of a fixed-depth filter decreases when compared to an adaptive-depth filter. This method is shown to be robust in an environment where an OOI is moving to different depths in relation to the camera, and has implications in tasks where objects must be identified by their depth, such as in robotics or autonomous vehicles.