Resource limited hardware-based stereo matching for high-speed vision system
Fredrik Ekstrand, Carl Ahlberg, Mikael Ekström, Lars Asplund, Giacomo Spampinato · 2011
This paper proposes a 1-dimensional implementation of area-based stereo matching with minimal resource utilization. It achieves an acceptable disparity map without the use of expensive resources. The matching accuracy for the approach can in some extent even outperform that of its 2-dimensional counterpart. Additionally, as it excels in terms of frame rate and resource utilization, it is highly suitable for real-time stereo-vision systems.