You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Update README with comprehensive project documentation
Extensively revamp the README.md to provide clearer project structure and
better documentation. Major changes include:
- Add clear overview and key features sections
- Include detailed application descriptions with usage examples
- Expand installation guide with prerequisites
- Add supported devices and hardware compatibility list
- Improve FAQ section with better organization
- Add architecture diagram and community support information
- Update formatting and layout for better readability
The updated documentation makes it easier for new users to understand and
get started with DeepCamera while providing comprehensive technical details
for advanced users.
DeepCamera transforms traditional surveillance cameras and CCTV/NVR systems into intelligent monitoring solutions using advanced machine learning technologies. It provides:
29
+
30
+
- Open-source facial recognition for intrusion detection
31
+
- Fall detection capabilities
32
+
- Smart parking lot monitoring
33
+
- Local inference engine for privacy and performance
34
+
35
+
SharpAI-hub is the cloud platform that enables rapid deployment of AI applications to your CCTV cameras and edge devices.
36
+
37
+
## ✨ Key Features
38
+
39
+
### 🤖 Advanced AI Capabilities
40
+
- Facial Recognition
41
+
- Person Re-identification (RE-ID)
42
+
- Parking Space Management
43
+
- Fall Detection
44
+
- More features in development
45
+
46
+
### 📊 Professional ML Pipeline
47
+
- Feature clustering with Milvus vector database
48
+
- Data labeling with Labelstudio
49
+
- Comprehensive model training workflow
50
+
51
+
### 💻 Edge AI Development
52
+
- Containerized AI frameworks
53
+
- Browser-based desktop environment
54
+
- No VNC client installation needed
55
+
31
56
DeepCamera empowers your traditional surveillance cameras and CCTV/NVR with machine learning technologies.
32
57
It provides open source facial recognition based intrusion detection, fall detection and parking lot monitoring with the inference engine on your local device.
33
58
@@ -50,6 +75,95 @@ SharpAI-hub is the cloud hosting for AI applications which help you deploy AI ap
50
75
- desktop in docker with web vnc client, so you don't need even install vnc client
51
76
</details>
52
77
78
+
## 🚀 Applications
79
+
80
+
### 1. Person Recognition for Intruder Detection
81
+
Advanced intruder detection using self-supervised person recognition (REID) technology. [Source code](https://github.com/SharpAI/DeepCamera/blob/master/src/yolov7_reid/src/detector_cpu.py)
82
+
83
+
**Key Technologies:**
84
+
- Yolov7 Tiny (COCO pretrained) for person detection
85
+
- FastReID ResNet50 for feature extraction
86
+
- Milvus vector database for self-supervised learning
87
+
- Integration with Home-Assistant for smart home automation
88
+
89
+
```bash
90
+
pip3 install sharpai-hub
91
+
sharpai-cli yolov7_reid start
92
+
```
93
+
94
+
### 2. Local Facial Recognition
95
+
Secure, locally-deployed facial recognition system for intruder detection. All data stays on your device.
96
+
```bash
97
+
sharpai-cli local_deepcamera start
98
+
```
99
+
100
+
### 3. Cloud-Based Facial Recognition
101
+
Free cloud-powered facial recognition system:
102
+
```bash
103
+
sharpai-cli login
104
+
sharpai-cli device register
105
+
sharpai-cli deepcamera start
106
+
```
107
+
108
+
### 4. Screen Monitor for Child Safety
109
+
Monitor laptop screens using AI-powered feature extraction and local storage. Perfect for ensuring online safety for kids and teens.
110
+
```bash
111
+
sharpai-cli screen_monitor start
112
+
```
113
+
114
+
### 5. Basic Person Detection
115
+
Simple and efficient person detection system:
116
+
```bash
117
+
sharpai-cli yolov7_person_detector start
118
+
```
119
+
120
+
## 📦 Installation Guide
121
+
122
+
### Prerequisites
123
+
- Docker (Latest version)
124
+
- Python (v3.6 - v3.10)
125
+
- Internet connection for initial setup
126
+
127
+
### Quick Start
128
+
1. Install SharpAI-Hub:
129
+
```bash
130
+
pip3 install sharpai-hub
131
+
```
132
+
133
+
2. Start desired application (example using yolov7_reid):
134
+
```bash
135
+
sharpai-cli yolov7_reid start
136
+
```
137
+
138
+
### Important URLs
139
+
- Docker Desktop UI: http://localhost:8000
140
+
- Home-Assistant: http://localhost:8123
141
+
- Labelstudio: http://localhost:8080
142
+
143
+
<details>
144
+
<summary><h3>📱 Supported Devices</h3></summary>
145
+
146
+
#### Edge AI Hardware
147
+
- Nvidia Jetson
148
+
- Nano (ReComputer j1010)
149
+
- Xavier AGX
150
+
- Single Board Computers
151
+
- Raspberry Pi 4GB/8GB
152
+
- Desktop/Laptop
153
+
- MacOS
154
+
- Windows
155
+
- Ubuntu
156
+
- MCU Cameras
157
+
- ESP32 CAM
158
+
- ESP32-S3-Eye
159
+
160
+
#### Compatible Cameras
161
+
- RTSP Cameras (Lorex/Amrest/DoorBell)
162
+
- Blink Camera
163
+
- IMOU Camera
164
+
- Google Nest (Indoor/Outdoor)
165
+
</details>
166
+
53
167
# Application 1: Self-supervised person recognition(REID) for intruder detection
54
168
SharpAI yolov7_reid is an open source python application leverages AI technologies to detect intruder with traditional surveillance camera. Source code is [here](https://github.com/SharpAI/DeepCamera/blob/master/src/yolov7_reid/src/detector_cpu.py)
55
169
It leverages Yolov7 as person detector, FastReID for person feature extraction, Milvus the local vector database for self-supervised learning to identity unseen person, Labelstudio to host image locally and for further usage such as label data and train your own classifier. It also integrates with Home-Assistant to empower smart home with AI technology.
0 commit comments