Towards Robust Full-speed FPGA-based Stereo-matching on the GIMME Platform

This paper presents GIMME (General Image Multiview Manipulation Engine), a highly flexible reconfigurable standalone mobile two-camera vision platform with stereo-vision capability. GIMME relies on reconfigurable hardware (FPGA) to perform application-specific low to medium-level imageprocessing at video-rate. A high-speed stereo-matching approach combining segmentation and 1D SAD for high accuracy and unlimited disparity range at minimal resource utilization is presented. Thanks to its compact design, low power consumption and standardized interfaces (power and communication), GIMME is an ideal vision platform for autonomous and mobile robot applications.