Stereo Matching Algorithm Using Population-Based Incremental Learning on GPU

Abstract

To solve the general problems of genetic algorithms applied in stereo matching, two measures are proposed. Firstly, the strategy of the simplified population-based incremental learning (PBIL) is adopted to decrease the problems in memory consumption and searching inefficiency, as well as a scheme controlling the distance of neighbors for disparity smoothness is inserted to obtain a wide-area consistency of disparities. In addition, an alternative version of the proposed algorithm without using a probability vector is also presented for simpler set-ups. Secondly, to decrease the running time further, a model of the proposed algorithm which can be run on programmable graphics-hardware (GPU) is newly given. The algorithms are implemented on the CPU as well as the GPU and evaluated by experiments. The experimental results show the proposed algorithm has better performance than traditional BMA methods with a deliberate relaxation and its modified version in both running speed and stability. The comparison in computation times for the algorithm both on GPU and CPU shows that the former has more speed-up than the latter, the bigger the image size is.

GPGPU Implementation of a Genetic Algorithm for Stereo Refinement

“…A similar system to the one herein proposed is presented in [8]. In this work, a genetic algorithm for stereo matching is also implemented in GPU.…”

Untitled

“…Problems solved by PGA on GPGPU are Medical Image Registration [23], Feature Selection, Electrical Circuit Synthesis and Data Mining [24], SAT Problems [25], Function Optimization [26], Benchmark Problems [27], [28], [29], Texture-Rendering [30], One-MAX Problem [31], Quadratic Assignment Problems [32], Non-convex Mixed Integer Non-Linear Programming (MINLP) and Non-convex Non Linear Programming (NLP) Problems [33], Cellular Automata Rules Acceleration [34], Stereo Matching [35], Data Mining [36], Drug discovery [37], Gaming Application [38]…”

Genetic Algorithm for Stereo Correspondence with a Novel Fitness Function and Occlusion Handling

“…Recently, (Dai et al, 2008) use an adaptive crossover and mutation while their fitness function do not include any smoothing term. Finally, (Zhang et al, 2009) use a pyramidal propagation stratagem for solution representation and (Nie et al, 2009) implement a stereo correspondence genetic algorithm in GPU for performance enhancement. Genetic algorithms have also been used for matching sparse features, for instance in (Issa et al, 2002) a genetic algorithm is employed to match edges.…”