high performance computing on graphics processing units: hgpu.org

In recent years, it can be observed that there is a gradual increase in the number of researchers and projects involved with the development of omnidirectional vision systems for various applications. The primary factors, which contributed towards this positive trend, are the availability of inexpensive and high resolution vision sensors, robust and fast computers and the advantages of using such systems over perspective vision systems. In this paper, a novel variable multibaseline omnidirectional stereovision system is presented. The proposed algorithm is implemented on the GPU based on the Nvidia CUDA libraries and subsequently, this paper will provide details of the automatic baseline selection process. Finally, results of the multibaseline stereovision algorithm based on voxel voting will be illustrated and discussed. In addition, possible research directions suggested by this approach will also be discussed.