|
1 |
| -This is a [Next.js](https://nextjs.org/) project bootstrapped with [`create-next-app`](https://github.com/vercel/next.js/tree/canary/packages/create-next-app). |
| 1 | +# 🎥 Real-Time Computer Vision in WebGL with TensorFlow.js |
2 | 2 |
|
3 |
| -## Getting Started |
| 3 | +Overview |
4 | 4 |
|
5 |
| -First, run the development server: |
| 5 | +This project demonstrates the power of running computer vision models directly in the browser using TensorFlow.js (tfjs) and WebGL. It features implementations of the YOLO and COCO-SSD models for object detection, all processed on the client side. This approach drastically reduces server costs by limiting API requests to only when detections occur, making it ideal for businesses and developers looking for efficient and cost-effective computer vision solutions. |
| 6 | + |
| 7 | +Features |
| 8 | + |
| 9 | +- Real-time Object Detection: Runs YOLO and COCO-SSD models in WebGL directly in the browser. |
| 10 | +- Cost-Efficient: Reduces the need for continuous server communication, cutting down on cloud computing and bandwidth costs. |
| 11 | +- Flexible Notifications: Sends alerts via Telegram, email, WhatsApp, SMS, or any other platform of your choice. |
| 12 | +- User-Friendly Interface: Easily create a canvas to define detection zones and select models and labels. |
| 13 | + |
| 14 | +Open Source: Contribute, customize, and build upon this project. |
| 15 | +Demo |
| 16 | + |
| 17 | +[](https://www.youtube.com/watch?v=fO3A9giDCVk) |
| 18 | + |
| 19 | + |
| 20 | +Getting Started |
| 21 | +Prerequisites |
| 22 | +Node.js |
| 23 | +npm or yarn |
| 24 | +Installation |
| 25 | +Clone the repository: |
6 | 26 |
|
7 | 27 | ```bash
|
8 |
| -npm run dev |
9 |
| -# or |
10 |
| -yarn dev |
11 |
| -# or |
12 |
| -pnpm dev |
13 |
| -# or |
14 |
| -bun dev |
| 28 | +Copier le code |
| 29 | +git clone <https://github.com/your-username/your-repo-name.git> |
| 30 | +cd your-repo-name |
15 | 31 | ```
|
16 | 32 |
|
17 |
| -Open [http://localhost:3000](http://localhost:3000) with your browser to see the result. |
| 33 | +Install dependencies: |
18 | 34 |
|
19 |
| -You can start editing the page by modifying `app/page.tsx`. The page auto-updates as you edit the file. |
| 35 | +```bash |
| 36 | +Copier le code |
| 37 | +npm install |
| 38 | +``` |
20 | 39 |
|
21 |
| -This project uses [`next/font`](https://nextjs.org/docs/basic-features/font-optimization) to automatically optimize and load Inter, a custom Google Font. |
| 40 | +Run the application: |
22 | 41 |
|
23 |
| -## Learn More |
| 42 | +```bash |
| 43 | +Copier le code |
| 44 | +npm start |
| 45 | +``` |
| 46 | + |
| 47 | +This will start a local development server and open the app in your default web browser. |
| 48 | + |
| 49 | +Usage |
| 50 | + |
| 51 | +- Select the detection model (YOLO or COCO-SSD). |
| 52 | +- Define the detection zone on the canvas. |
| 53 | +- Run the detection and receive notifications through your chosen platform. |
| 54 | + |
| 55 | +Configuration |
| 56 | +Telegram Integration: To receive notifications via Telegram, you need to set up a bot and get your bot token and chat ID. Configure these in the .env file. |
| 57 | + |
| 58 | +```bash |
| 59 | +Copier le code |
| 60 | +TELEGRAM_BOT_TOKEN=your_bot_token |
| 61 | +TELEGRAM_CHAT_ID=your_chat_id |
| 62 | +``` |
24 | 63 |
|
25 |
| -To learn more about Next.js, take a look at the following resources: |
| 64 | +Custom Models and Labels: You can add custom models and labels by modifying the models/ and labels/ directories. |
26 | 65 |
|
27 |
| -- [Next.js Documentation](https://nextjs.org/docs) - learn about Next.js features and API. |
28 |
| -- [Learn Next.js](https://nextjs.org/learn) - an interactive Next.js tutorial. |
| 66 | +Roadmap |
29 | 67 |
|
30 |
| -You can check out [the Next.js GitHub repository](https://github.com/vercel/next.js/) - your feedback and contributions are welcome! |
| 68 | +- Add more pre-trained models. |
| 69 | +- Implement support for additional notification platforms (e.g., Slack, Microsoft Teams). |
| 70 | +- Improve UI/UX for easier model and zone selection. |
31 | 71 |
|
32 |
| -## Deploy on Vercel |
| 72 | +Contributing |
| 73 | +Contributions are welcome! Please fork this repository and submit a pull request with your changes. For major changes, please open an issue to discuss what you would like to change. |
33 | 74 |
|
34 |
| -The easiest way to deploy your Next.js app is to use the [Vercel Platform](https://vercel.com/new?utm_medium=default-template&filter=next.js&utm_source=create-next-app&utm_campaign=create-next-app-readme) from the creators of Next.js. |
| 75 | +License |
| 76 | +This project is licensed under the MIT License - see the LICENSE file for details. |
35 | 77 |
|
36 |
| -Check out our [Next.js deployment documentation](https://nextjs.org/docs/deployment) for more details. |
| 78 | +Contact |
| 79 | +For questions or feedback, please contact Your Name. |
0 commit comments