Hardware Implementation of FAST Algorithm for Mobile Applications

Simple inexpensive cameras are often built in small devices such as mobile phones or mp3 players. Besides the usual image recording, other ways of their use have been proposed which usually involve intensive image processing. In such processing, corner detection is often found as a preliminary operation. Many corner detection algorithms have been introduced, but due to their computational complexity very few are suitable for real-time applications. One of novel approaches to corner detection is the so called FAST algorithm which is specially optimized for speed. However, on simple and slow devices even this algorithm can be too slow and energy consuming when executed on the in-built processor. In this paper we present hardware implementation of FAST algorithm, capable of processing images at constant speed of one pixel per clock. The results showed that nearly forty times faster corner detection could be achieved on mobile object detection and localization application, if the existing software detector is replaced by our hardware module.