What's SharpAI DeepCamera

This is a unique repository in many ways. It’s a deep learning model open sourced to protect your privacy. The entire DeepCamera concept is based on automated machine learning (AutoML). So you don’t even need any programming experience to train a new model.

DeepCamera works on Android devices. You can integrate the code with surveillance cameras as well. There’s a LOT you can do with DeepCamera’s code, including:

• Face recognition
• Face Detection
• Control from mobile application
• Object detection
• Motion detection
• Human ReID (Recognition based on human shape)

And a whole host of other things. Building your own AI-powered model has never been this easy!

Quick Evaluation on Android

Slack Channel

Click to join sharpai slack channel

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/tested Device

• MediaTek MTK6797 (Android, Mobile/Tablet)
• Huawei Kirin 960/970/980 （Android, Mobile/Tablet)
• Samsung 7420 (Android, Mobile)
• Raspberry Pi
• X86 (Linux/Ubuntu, Mac OS X, Windows(not tested) through Docker)
• Rockchip RK3399 (Linux, set-up-box H96 Max)
• Rockchip RK3399 (Android, RockPro64)
• Rockchip RK3288 (Android, set-up-box)
• ARM 64bit devices

Supported Camera

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

Demo

How to develop on SharpAI DeepCamera

You can develop on SharpAI DeepCamera almost on every devices.

How to Run DeepCamera on 64-bit Android From Source Code

How to Run DeepCamera on 32-bit Android

Run on Raspberry Pi

Run on Embedded Linux with docker (Rockchip RK3399)

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

Run on X86 Laptop Docker

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

It is even possible to integrate with your Surveilance Camera

Through Shinobi (if you install DeepCamera through Docker)

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

Shinobi login page(device_ip:8080):
username: user@sharpaibox.com
password: SharpAI2018

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

Through Dahua SDK (if you install DeepCamera on Android)

Code is here

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, Chinese Version

Application in English(Beta Test)

Android: https://www.pgyer.com/app/install/0e87e08c72a232e8f39a6a7c76222038
iOS: https://testflight.apple.com/join/8LXGgu3q

How to deploy server on your server

APIs doc for app server

Click to see APIs document

App User Guide

Click for user guide

Contributions

This project contains source code or library dependencies from the follow projects:

• Tensorflow available at: https://github.com/tensorflow/tensorflow Apache License 2.0
• MXNet available at: https://github.com/apache/incubator-mxnet Apache License 2.0
• TVM available at: https://github.com/dmlc/tvm Apache License 2.0
• Shinobi project available at: https://gitlab.com/Shinobi-Systems/Shinobi/ Copyright (c) 2018 Shinobi Systems
• Termux project available at: https://github.com/termux/termux-app GPLv3/Apache License 2.0
• Insightface project available at: https://github.com/deepinsight/insightface MIT License
• Easyrs project available at: https://github.com/silvaren/easyrs MIT License
• Nodejs: https://nodejs.org Copyright Node.js contributors. All rights reserved.
• Python: https://www.python.org Python 2.7 license
• Gcc for termux with fortran scipy etc: https://github.com/its-pointless/gcc_termux
• RembrandtAndroid project available at https://github.com/imgly/RembrandtAndroid
• Great English-writing introduction on analyticsvidhya