Camera enabled IoT devices such as smart cameras, capture images after a trigger (such as motion sensing) and ship them to the cloud for further processing to detect intruders, face recognition and so on. This approach can lead to higher power, latency and privacy concerns as compared to processing the images on device. Our solutions allow data extraction using Neural Networks on the device to preserve privacy, reduce latency, power and bandwidth leading to savings in operational cost.
We work closely with partners to design and prototype platforms designed to perform typical CV tasks in the 1mW range, which is an order of magnitude less than most solutions. Such a low power envelope is achieved by detailed understanding of the use case followed by tightly coupled hardware/software co-design. As a result, our solutions are capable of running on coin cells, solar or other energy harvesting devices to enable indefinitely long and maintenance free operation.
Embedded vision tends to be rather application specific, we would be happy to discuss your specific application. The best way to contact us is via email at: firstname.lastname@example.org. You may also reach us at (+1) 858 437 9852.
5621 Palmer Way, Suite A,
Carlsbad, CA 92010, USA