The purpose of this project is to create an application to demonstrate how an Intel Neural Compute Stick can accelerate inference on edge devices such as raspberry pi using OpenVINO toolkit and following Intel’s workflow.
Constructions sites are busy places and can constitute a very dangerous environment when many contractors are working at the same time, especially when they are not using appropriate personal protective equipment (PPE), the system described in this document detects whether workers are wearing appropriate PPEs or not running Tiny-YOLOv3 on a raspberry Pi with an Intel Neural Computer Stick 2 to accelerate the inference process.
The pre-trained model can be downloaded from the following links in the format provided by OpenVino:
- tiny_yolo_IR_500000_FP16.xml
- tiny_yolo_IR_500000_FP16.bin
- tiny_yolo_IR_500000_FP32.bin
- tiny_yolo_IR_500000_FP32.xml
- https://github.com/thtrieu/darkflow
- https://github.com/tzutalin/labelImg
- https://github.com/srp-31/Data-Augmentation-for-Object-Detection-YOLO-
- https://github.com/Jumabek/darknet_scripts
- https://github.com/mystic123/tensorflow-yolo-v3
- https://github.com/PINTO0309/OpenVINO-YoloV3 <-- The most important.
- https://github.com/thtrieu/darkflow