We have designed and implemented a system for real-time detection of 2-D im
age features on a reconfigurable computer based on Field Programmable Gate
Arrays (FPGA's). We envision this device as the front-end of a system able
to track image features in real-time vision applications like autonomous ve
hicle navigation and "structure from motion". The algorithm employed to sel
ect good features is inspired by the method of Tomasi and Kanade. Compared
to the original method, the algorithm that we have devised does not require
any floating point or transcendental operations, and maps efficiently into
a highly pipelined architecture, well suited to be implemented in FPGA tec
hnology. We have implemented the algorithm on a low-cost reconfigurable com
puter equipped with video decoder and encoder interfaces. Reliable operatio
n has been observed on an image stream generated by a standard NTSC commerc
ial video camera at 30 Hz on different scenes and under different light con
ditions. This result compares favorably to the implementation of the same a
lgorithm on a system based on the TI C80 DSP, able to process at most 5 fra
mes/second.