Merge pull request ndleah#265 from kevin-291/object-detection

Object detection

Object_Detection/README.md

@@ -0,0 +1,31 @@
+![Star Badge](https://img.shields.io/static/v1?label=%F0%9F%8C%9F&message=If%20Useful&style=style=flat&color=BC4E99)
+![Open Source Love](https://badges.frapsoft.com/os/v1/open-source.svg?v=103)
+
+# Object Detection
+
+
+## 🛠️ Description
+
+This folder contains a Python script for a real-time object detection application using the YOLOv9 model from Ultralytics. The application uses the default camera (webcam) for video input and displays detected objects with bounding boxes, including labels of the detected object and their probability.
+
+## ⚙️ Languages or Frameworks Used
+
+Open Command Prompt and use the following command to install the required modules:
+``` bash
+pip install -r requirements.txt
+```
+
+## 🌟 How to run
+
+You can run the program using the following command
+``` bash
+python object-detection.py
+```
+
+## 📺 Demo
+<p align="center">
+<img src="image.png" width=40% height=40%>
+
+## 🤖 Author
+
+[Kevin Cherian George](https://github.com/kevin-291)

Object_Detection/object-detection.py

@@ -0,0 +1,65 @@
+import cv2
+import torch
+from ultralytics import YOLO
+
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+def main():
+
+    # Load YOLOv9 model
+    model = YOLO('yolov9c.pt')
+    model.to(device)
+
+    # Initialize video capture (0 for default camera)
+    cap = cv2.VideoCapture(0)
+
+    # Check if the video capture device is opened
+    if not cap.isOpened():
+        print("Error: Could not open video capture device")
+        return
+
+    while True:
+        # Capture frame-by-frame
+        ret, frame = cap.read()
+
+        if not ret:
+            print("Error: Could not read frame")
+            break
+
+        # Use YOLOv9 model to make predictions
+        results = model(frame)
+
+        # Process the results
+        for result in results:
+            # Loop through each detected object
+            for box in result.boxes:
+                # Get coordinates and class label
+                x1, y1, x2, y2 = box.xyxy[0]
+                label_id = int(box.cls[0].item())
+                confidence = box.conf[0].item()
+
+                # Get the class label from YOLO model
+                class_label = model.names[label_id]
+
+                # Create the label text
+                label_text = f"{class_label}: {confidence:.2f}"
+
+                # Draw bounding box on the frame
+                cv2.rectangle(frame, (int(x1), int(y1)), (int(x2), int(y2)), (0, 255, 0), 2)
+
+                # Draw the label text on the frame above the bounding box
+                cv2.putText(frame, label_text, (int(x1), int(y1) - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 1)
+
+        # Display the frame with bounding boxes and labels
+        cv2.imshow('Real-Time Object Detection', frame)
+
+        # Exit the loop if the user presses 'q'
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    # Release the video capture device and close the window
+    cap.release()
+    cv2.destroyAllWindows()
+
+if __name__ == "__main__":
+    main()

Object_Detection/requirements.txt

@@ -0,0 +1,2 @@
+ultralytics>=8.0.100
+opencv-python>=4.5.5.62