how to do object identification using webcam on Neural Compute Stick 2?

[JAVIERJOSE_A_Intel]

Hi rizwan_ahmed,

Thanks for reaching out.

The Open Model Zoo repository includes optimized deep learning models and a set of demos to expedite the development of high-performance deep learning inference applications.

There you can use the Object Detection for SSD C++ Demo or Object Detection for YOLO V3 C++ Demo that supports video and camera inputs.

Also, you need to check the compatibility between pre-trained models, demos and devices here.

Regards,

Javier A. 

Intel Customer Support Technician 

A Contingent Worker at Intel 

[rizwan_ahmed]

Thank you so much for the reply but i wanted to implement the object identification on raspberry Pi and i think That YOLO can't be implemented on Raspberry Pi because of its Low Processing Power. Can you guide me that how can i use my NCS 2 For Object Identification on Raspberry Pi using Pi camera or USB cam?

Again Thank you so much for your response and i hope that this time you will respond faster than earlier.

[JAVIERJOSE_A_Intel]

Hi rizwan_ahmed,

If you want to use an NCS 2 to inference a model on a Raspberry Pi, you need to use the OpenVINO™ toolkit for Raspbian* OS.

It includes the Inference Engine and the MYRIAD plugins. You can use it with the Intel® Movidius™ Neural Compute Stick (Intel® NCS) or the Intel® Neural Compute Stick 2 plugged in one of the USB ports.

As mentioned in my previous message, you can use the object detection samples from Open Model Zoo repository and check the compatibility between pre-trained models, demos and devices.

You can check the official installation guide of OpenVINO™ toolkit for Raspbian* OS here.

Regards,

Javier A. 

Intel Customer Support Technician 

A Contingent Worker at Intel