It might have to do with government restrictions on devices that can be used for targeting people – the Panasonic GridEYE is considered a “controlled device” here in the USA. I was going to do a product based on it (i.e. it can tell you how many people are in a room) but the usage restrictions made it too difficult to sell.
So, I just open-sourced the project
http://bit.ly/1clb03r
and people can build their own if they want to try it out.
 Quantized Neural Networks for FPGA InferenceSponsored by Intel Implementing a low precision network in FPGA hardware for efficient inferencing provides numerous advantages when it comes to meeting demanding specifications. The increased flexibility allows optimization of throughput, overall power consumption, resource usage, device size, TOPs/watt, and deterministic latency. These are important benefits where scaling and efficiency are inherent requirements of the application. |
