Active Stereo Vision with High Resolution on an FPGA

Abstract

We present a novel FPGA based active stereo vision system, tailored for the use in a mobile 3D stereo camera. For the generation of a single 3D map the matching algorithm is based on a correlation approach, where multiple stereo image pairs instead of a single one are processed to guarantee an improved depth resolution. To efficiently handle the large amounts of incoming image data we adapt the algorithm to the underlying FPGA structures, e.g. by making use of pipelining and parallelization.Experiments demonstrate that our approach provides high-quality 3D maps at least three times more energy-efficient (5.5 fps/W) than comparable approaches executed on CPU and GPU platforms. Implemented on a Xilinx Zynq-7030 SoC our system provides a computation speed of 12.2 fps, at a resolution of 1.3 megapixel and a 128 pixel disparity search space. As such it outperforms the currently best passive stereo systems of the Middlebury Stereo Evaluation in terms of speed and accuracy. The presented approach is therefore well suited for mobile applications, that require a highly accurate and energy-efficient active stereo vision system.