Changes

A new C++ application was written to apply the inference to the frames captured from an the image sensor ([https://cdn.sparkfun.com/datasheets/Sensors/LightImaging/OV5640_datasheet.pdf OV5640]) of a [https://www.nxp.com/part/MINISASTOCSI#/ camera module], instead of images retrieved from files. It uses OpenCV 4.2.0 to control the image sensor camera and to pre-process the frames. Like version 2, inference run on NPU, so only the fully-quantized model was tested with the version 3 application.

The following image shows the execution of the third version of the classifier on the embedded platform. The image sensor is pointed at a red apple which is correctly classified with 98% confidence. Note that with this image sensorcamera, the frame rate is capped at 30 fps.