Machine Vision Technology Development

Experiment 1 - Opening USB Camera

cd OPENCV # Open OPENCV package
sudo python3 ./camera_display.py # Run py file
Terminal displays:
At this time, the Linux system will display the camera's real-time video. We need to test the keys under the window focus, the effect is as follows:
#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""
Camera capture program
Function: Open camera and display real-time video, supports multiple functions
"""

import cv2
import numpy as np
import sys
import os
import time
import argparse
from datetime import datetime

def main():
    """
    Main function: Open camera and display real-time video
    """
    # Parse command line arguments
    parser = argparse.ArgumentParser(description='Camera real-time display program')
    parser.add_argument('--width', type=int, default=1280, help='Display window width')
    parser.add_argument('--height', type=int, default=720, help='Display window height')
    args = parser.parse_args()

    # Open default camera (usually 0, if multiple cameras try 1, 2, etc.)
    cap = cv2.VideoCapture(0)

    # Check if camera opened successfully
    if not cap.isOpened():
        print("Error: Unable to open camera")
        sys.exit(1)

    # Set camera resolution
    cap.set(cv2.CAP_PROP_FRAME_WIDTH, args.width)
    cap.set(cv2.CAP_PROP_FRAME_HEIGHT, args.height)

    # Create a resizable window
    cv2.namedWindow('Camera', cv2.WINDOW_NORMAL)
    cv2.resizeWindow('Camera', args.width, args.height)

    print("Camera opened successfully")
    print(f"Window size set to: {args.width}x{args.height}")
    print("Key instructions:")
    print("- 'q': Exit program")
    print("- 'g': Toggle grayscale/color mode")
    print("- 'b': Apply blur effect")
    print("- 'e': Apply edge detection")
    print("- 'n': Restore normal mode")
    print("- 's': Save current frame as image")
    print("- '+': Increase window size")
    print("- '-': Decrease window size")

    # Default settings
    gray_mode = False
    blur_mode = False
    edge_mode = False
    window_width = args.width
    window_height = args.height

    # Create directory for saving images
    save_dir = "captured_images"
    if not os.path.exists(save_dir):
        os.makedirs(save_dir)

    # Loop to read camera frames
    while True:
        # Read a frame
        ret, frame = cap.read()

        # If failed to read, exit loop
        if not ret:
            print("Error: Unable to read camera frame")
            break

        # Process image
        if gray_mode:
            # Convert to grayscale
            processed_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
            # Convert back to three channels for text display
            display_frame = cv2.cvtColor(processed_frame, cv2.COLOR_GRAY2BGR)
            mode_text = "Gray Mode"
        else:
            processed_frame = frame.copy()
            display_frame = processed_frame
            mode_text = "Color Mode"

        # Apply additional effects
        if blur_mode:
            processed_frame = cv2.GaussianBlur(processed_frame, (15, 15), 0)
            display_frame = processed_frame
            mode_text += " + Blur"

        if edge_mode and gray_mode:
            # Edge detection requires grayscale image
            processed_frame = cv2.Canny(processed_frame, 100, 200)
            # Convert back to three channels for text display
            display_frame = cv2.cvtColor(processed_frame, cv2.COLOR_GRAY2BGR)
            mode_text += " + Edge"
        elif edge_mode:
            # If not grayscale mode, convert to grayscale first then do edge detection
            edges = cv2.Canny(cv2.cvtColor(processed_frame, cv2.COLOR_BGR2GRAY), 100, 200)
            # Overlay edges on original image
            display_frame = processed_frame.copy()
            display_frame[edges > 0] = [0, 255, 255]  # Yellow edges
            mode_text += " + Edge"

        # Add mode text
        cv2.putText(display_frame, mode_text, (10, 30),
                    cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 0, 255), 2)

        # Display image
        cv2.imshow('Camera', display_frame)

        # Wait for key press, exit if 'q' is pressed
        key = cv2.waitKey(1) & 0xFF
        if key == ord('q'):
            print("User exited program")
            break
        elif key == ord('g'):
            # Toggle grayscale/color mode
            gray_mode = not gray_mode
            print("Switched to", "grayscale mode" if gray_mode else "color mode")
        elif key == ord('b'):
            # Toggle blur effect
            blur_mode = not blur_mode
            print("Blur effect:", "on" if blur_mode else "off")
        elif key == ord('e'):
            # Toggle edge detection
            edge_mode = not edge_mode
            print("Edge detection:", "on" if edge_mode else "off")
        elif key == ord('n'):
            # Restore normal mode
            gray_mode = False
            blur_mode = False
            edge_mode = False
            print("Restored to normal mode")
        elif key == ord('s'):
            # Save current frame
            timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
            filename = os.path.join(save_dir, f"capture_{timestamp}.jpg")
            cv2.imwrite(filename, frame)
            print(f"Image saved: {filename}")

    # Release camera resources
    cap.release()
    # Close all OpenCV windows
    cv2.destroyAllWindows()
    print("Program exited")

if __name__ == "__main__":
    try:
        main()
    except Exception as e:
        print(f"Program error: {e}")
        sys.exit(1)