YOLO-Object-Detection

🎯 Real-Time Object Detection using YOLOv9 and OpenCV

This project demonstrates real-time object detection using the YOLOv9 deep learning model integrated with OpenCV. It captures live video from a webcam, detects multiple objects using pre-trained YOLOv9 weights, and displays annotated frames in real-time with bounding boxes and labels. It also tracks the count of each detected object and saves it to a Python file.

---

🚀 Features

• Real-time object detection using YOLOv9
• Live webcam input with OpenCV
• CUDA GPU acceleration support
• Displays object labels and confidence scores
• Tracks and logs object count in a Python dictionary

---

🛠️ Technologies Used

• Python
• OpenCV
• PyTorch
• Ultralytics YOLOv9
• Collections (defaultdict)

---

🧾 Requirements

Install dependencies using pip:

pip install torch torchvision torchaudio opencv-python ultralytics

⚠️ Make sure your system supports CUDA if using GPU.

---

▶️ How to Run

1. Clone this repository:

git clone https://github.com/your-username/YOLOv9-Object-Detection.git
cd YOLOv9-Object-Detection

2. Place your yolov9c.pt weight file in the root directory.

3. Run the detection script:

python detect.py

Press q to stop detection. The object counts will be saved to count.py.

---

🖼️ Demo

---

📁 Output File

After running, a file named count.py will be generated with a dictionary like:

object_counts = {
    'person': 5,
    'car': 2,
    'dog': 1,
}

---

👩‍💻 Author

Akanksha 📧 akankshaprashar5244@gmail.com

---

📜 License

This project is licensed under the MIT License.