WebCam Motion Detector program in Python ?

A WebCam Motion Detector analyzes images from your webcam to detect movement and logs the time intervals when motion occurs. This program uses computer vision techniques to compare frames and identify changes.

Required Libraries

Install the required libraries using pip ?

pip install opencv-python pandas

How Motion Detection Works

Complete Motion Detector Code

# Import required libraries
import cv2
import pandas as pd
import time
from datetime import datetime

# Initialize variables
still_image = None
motion_list = [None, None]
time_list = []

# Initialize DataFrame with start and end time columns
df = pd.DataFrame(columns=["Start", "End"])

# Capture video from webcam (0 = default camera)
video = cv2.VideoCapture(0)

print("Motion detector started. Press 'q' to quit.")

while True:
    # Read frame from video
    check, frame = video.read()
    motion = 0

    # Convert to grayscale and apply Gaussian blur
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    gray = cv2.GaussianBlur(gray, (21, 21), 0)
    
    # Set first frame as reference background
    if still_image is None:
        still_image = gray
        continue

    # Calculate difference between background and current frame
    diff_frame = cv2.absdiff(still_image, gray)

    # Apply threshold to get binary image
    thresh_frame = cv2.threshold(diff_frame, 25, 255, cv2.THRESH_BINARY)[1]
    thresh_frame = cv2.dilate(thresh_frame, None, iterations=2)
    
    # Find contours of moving objects
    contours, hierarchy = cv2.findContours(thresh_frame.copy(),
                                         cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
    
    # Check each contour for significant motion
    for contour in contours:
        if cv2.contourArea(contour) < 10000:
            continue
        motion = 1
        (x, y, w, h) = cv2.boundingRect(contour)
        cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 3)

    # Track motion status
    motion_list.append(motion)
    motion_list = motion_list[-2:]

    # Record start time of motion
    if motion_list[-1] == 1 and motion_list[-2] == 0:
        time_list.append(datetime.now())

    # Record end time of motion
    if motion_list[-1] == 0 and motion_list[-2] == 1:
        time_list.append(datetime.now())

    # Display frames
    cv2.imshow("Grayscale Frame", gray)
    cv2.imshow("Threshold Frame", thresh_frame)
    cv2.imshow("Motion Detection", frame)

    # Press 'q' to quit
    key = cv2.waitKey(1)
    if key == ord('q'):
        if motion == 1:
            time_list.append(datetime.now())
        break

# Save motion time intervals to DataFrame
for i in range(0, len(time_list), 2):
    if i + 1 < len(time_list):
        new_row = pd.DataFrame({"Start": [time_list[i]], "End": [time_list[i + 1]]})
        df = pd.concat([df, new_row], ignore_index=True)

# Save to CSV file
df.to_csv("motion_detection_log.csv", index=False)
print(f"Motion log saved with {len(df)} motion events")

# Cleanup
video.release()
cv2.destroyAllWindows()

Key Features

• Background Subtraction: Compares current frame with a reference background
• Noise Reduction: Uses Gaussian blur to reduce camera noise
• Contour Detection: Identifies moving objects and draws bounding boxes
• Time Logging: Records start and end times of motion events
• CSV Export: Saves motion data for analysis

Sample Output

The program displays three windows: grayscale view, threshold binary image, and colored frame with motion rectangles. The CSV file contains motion timestamps ?

Start,End
2024-02-21 18:08:35.791487,2024-02-21 18:10:59.718005
2024-02-21 18:15:22.456123,2024-02-21 18:16:45.789456

Customization Options

Conclusion

This motion detector uses OpenCV's background subtraction and contour detection to identify movement. Adjust the threshold and contour area parameters to fine-tune sensitivity for your specific use case.