lguzzon-scratchbook / DeepCamera

Open source AI-powered video surveillance on embedded Linux/Android with ARM GPU/NPU support, featuring face recognition, human shape recognition(ReID), etc. The world's first AutoML Deep Learning edge AI platform.

What's SharpAI DeepCamera

Deep Learning video processing surveillance on ARM GPU for face recognition and much more on the way. Turn digital camera into AI-powered camera. Production level platform for edge AI using ARM GPU/NPU, leveraging AutoML. The first world-class Edge AI full stack platform for developer/kids/home/SMB/enterprise/cloud, baking by community.

Full stack system for the deep learning edge computing devices, espeicailly set-up-box off the shell with image burning or Android apk installation.

Data labeling on Mobile, no data scientist involed

Automatically train/deploy model for edge device(Embedded/Android/X86 system)

Power efficient, Easy scalable, Production ready, Mobile first

Feature List

• High accurate Face Recognition
• Face Detection
• Inference on ARM Mali GPU
• Support Android TF Lite(GPU/CPU/NPU)
• Support open source embedded linux
• Control from mobile application
• Management System for devices
• Push Notification to Mobile Device
• Object Detection
• Distributed System based on celery
• Plugin to process video by Shinobi CCTV
• Application on Android to decode video with hw acc
• Motion Detection with Android GPU
• Lable and train from Mobile to Edge Device

Supported Device

• Raspberry Pi
• X86 (Linux/Ubuntu, Mac OS X, Windows(not tested) through Docker)
• Rockchip RK3399 (Linux, set-up-box H96 Max)
• Rockchip RK3288 (Android, set-up-box)
• Samsung 7420 (Android, Mobile)
• Rockchip RK3399 (Android RockPro64 doc release soon)
• Linux/Android Has OpenCL

Supported Camera

• Dahua Camera
• Hikvision Camera
• Shinobi CCTV Supported Devices
• Screen Captured from Android Camera preview application

Slack Channel

Click to join sharpai slack channel

Demo

How to Run DeepCamera From Source Code

1. Generate/Get Serial No

Android

After install Launcher(Modified Termux), the serial_no will be placed: /data/data/com.termux/files/home/.ro_serialno

Linux/MacOS

Get your Mac Address(1e:20:34:10:24:21)

cd DeepCamera
echo 1e2034102421 > docker/workaipython/ro_serialno

2. Then generate text type QR code with serial_no you just got

QR code Generator En
QR code Generator Chn

3. How to Run DeepCamera on Edge Device

3.1 Run on Android(5.1+ aarch64)

3.2 Run on Rockchip RK3399 with linux/docker

3.2.1 Use prebuilt docker images

git clone https://github.com/SharpAI/DeepCamera
cd DeepCamera/docker  
sudo ./run-deepeye-prebuilt.sh start

3.3 Run on Rockchip RK3288 with Android 5.1

3.4 Run on X86 Laptop Docker

3.4.1 Use prebuilt docker images

git clone https://github.com/SharpAI/DeepCamera -b pc_version
cd DeepCamera/docker
sudo ./run-deepeye-x86.sh start #make sure Serial No is in docker/workaipython/ro_serialno

3.4.2 Build docker images on your local machine

git clone https://github.com/SharpAI/ImageBuilder-DeepLearning -b android_porting
cd ImageBuilder-DeepLearning/Docker-DeepEye/workai/
./build_x86_dockers.sh

Then run DeepCamera, will use local docker images

git clone https://github.com/SharpAI/DeepCamera
cd DeepCamera/docker
docker-compose -f docker-compose-x86.yml up

3.5 Run on Raspberry Pi

4. Link to Your Camera

4.1 Linux/Docker System

Then you need to follow Shinobi's document to add camera. or click to see our tutorial

Shinobi login page(device_ip:8080):
username: [e-mail]
password: SharpAI2018

You can also turn Mac Camera into RTSP camera(not tested)

4.2 Android(Dahua SDK Configure)

Code is here

4.3 Android screen capture

Code is here

4.4 Android(RTSP url config)

Comming soon

Survey: Do you want to have Dev Kit for easily startup

We are considering to provide full set of development kit to easy the setup effort you may face to. Please thumb up if you want one

How it works from end user's point of view, green parts are done if using Dev Kit

How to configure on Mobile APP

How to deploy server on your server

Call For Help

• Documents, A LOT OF DOCUMENTS, we already deploy our deep camera in industry leading company but we don't have extra resource to build up community friendly documents.
• Tutorial on youtube, we can build up some of them, only if with your help, we can success together.
• Translation, we did deploy our production in China, much of our resource is in Chinese, need your help to translate, especially the Mobile APP built with Meteor https://github.com/SharpAI/mobile_app_server (need i18n selection based on system language)
• Remove unused code/project in https://github.com/SharpAI/mobile_app_server
• PR, more than welcome, anything :)
• Meetup hosts, in Silicon Valley

APIs doc for app server

Click to see APIs document

App User Guide

Click for user guide