Real-Time Object Detection Using OpenCV and Deep Learning

This project demonstrates a real-time object detection system built using OpenCV, Python, and pre-trained deep learning models such as YOLO and SSD MobileNet. The goal is to detect objects from a webcam feed or video in real-time with high accuracy.

---

🔧 Technologies Used

• Python
• OpenCV
• Pre-trained YOLOv3 and SSD MobileNet models
• NumPy
• Deep Neural Networks (DNN) module from OpenCV

---

📦 How It Works

1. Load a pre-trained object detection model (e.g., YOLOv3 or SSD).
2. Read frames from the webcam or a video file.
3. Process each frame through the deep learning model.
4. Display bounding boxes and class labels for detected objects.
5. Run smoothly in real time.

---

▶️ Example Use Case

A webcam can identify multiple objects like "person", "car", "bottle", or "dog" and display them with labels and confidence scores — useful for surveillance, automation, or robotics.

---

🗂️ Files Included

• object_detection.py: Main Python script for detection.
• yolov3.cfg & yolov3.weights: Model configuration and weights.
• coco.names: Label file with class names.

---

📁 Dataset and Model Links

• COCO Dataset
• YOLOv3 Weights
• YOLOv3 Config

---

🚀 How to Run

1. Clone the repo:

   git clone https://github.com/Augustine0077/Object-Detection
   cd Object-Detection
   

Download model weights and config and place them in the project folder.

Run the detection:

bash
Copy
Edit
python object_detection.py

A window will open showing real-time detection.

📬 Connect with Me
GitHub: github.com/Augustine0077
LinkedIn: linkedin.com/in/augustine-shaji

📄 License
This project is licensed under the MIT License.