Study on semi-global matching algorithm extended for multi baseline matching and parallel processing method based on GPU

This paper extended semi-global matching algorithm into multi baseline matching to improve matching reliability, especially studies kernel function optimization strategies and GPU threads’ executing scheme of matching cost cube computing and aggregating, and realized its fine granularity parallel processing based on GPU. The experiment results using three UCD aerial images based on Tesla C2050 GPU showed that MVLL’s semi-global optimize algorithm can improve matching effectiveness and productiveness.