| Skill Level | Area of Focus | Operating System | Platform/Hardware |
|---|---|---|---|
| Advanced | Computer Vision, Facial Recognition, Embedded, Security, Smart Cities | Linux | DragonBoard 410c |
This project utilizes the power of the DragonBoard™ 410c from Arrow Electronics to run a facial recognition application, utilizing libraries like Caffe2 and OpenCV.
Objective
The main goal of the project is to demonstrate the power of the DragonBoard 410c to run a modern computer vision application for facial detection and recognition. Using powerful libraries like Caffe2 and OpenCV, the software finds faces in the image and use a DNN to classify the person.
Materials Required / Parts List / Tools
- DragonBoard 410c boards
- 12V wall adapter
- Micro SD Card (16GB)
- Logitech C920 Webcam
- USB Keyboard
- HDMI Monitor
Source Code / Source Examples / Application Executable
Build / Assembly Instructions
The build instructions can be found in the README file in the GitLab link. Basically, you have to build the libs and install the application on the board.
Usage Instructions
Setup the webcam to scan your environment and find faces. Run the project as described in the GitLab link. The application will show a screenshot in the monitor periodically and will mark the faces detected with a bounding box. Names of recognized people are shown in the screen, and new people are tagged as unknown.
Contributors
| Name | Title/Company |
|---|---|
| Augusto | Qualcomm IoT Reference Center - FACENS |
| Felipe | Qualcomm IoT Reference Center - FACENS |
| Lucas Max | Qualcomm IoT Reference Center - FACENS |
| Lucas Mendes | Qualcomm IoT Reference Center - FACENS |
| Luccas Schardt | Qualcomm IoT Reference Center - FACENS |