A research team headed by Dr. Eugenio Culurciello, associate professor of engineering at Yale University, has developed a field programmable gate array (FPGA) processor that has been specifically designed for artificial vision. It operates about 100 times faster than a laptop computer, effectively bringing supercomputing power to synthetic vision. A system using this FPGA would be capable of analysing full-motion video in real-time. It could simultaneously monitor multiple video streams, looking for certain objects or behaviours with clear possibilities for UAS applications.
There is a need for a vision system that is capable of performing the same task as that of a human vision system such as spotting and identifying objects in real-time motion. Such a system can complement a human operator, thereby reducing the need for human monitoring.
It can be trained to recognise any object in real-time, either from scratch or in an unsupervised manner. Vision is taught with the help of convolutional neural networks or ConvNets – multistage neural networks that can model the way the brains visual processing area creates invariance to size and position to identify the objects.
The researchers have developed a general-purpose system that can be programmed like a standard PC, based on a runtime reconfigurable 2D grid of computing elements with reconfiguration capabilities, somewhat similar to those of an FPGA. The major difference is that the reconfiguration can be done at runtime, allowing very diverse computations to be performed on the grid. The FPGAs are custom-made for this system and are superior to any CPU (central processing unit) or GPU (graphics processing unit). The FPGA that is used in this system is substantially more efficient.
According to Dr. Eugenio Culurciello, custom designed FPGAs will always outperform general purpose ICs for specific tasks since custom-made FPGAs require only about 10 watts, and within a few years will have the capability to dissipate just 1 watt.
For further information, read the full article in SA Instrumentation & Control – The Official Journal of the SAIMC, and an interview with Dr. Culuciello in Next Big Future