Motion Detection

This tutorial is specific to CM5; it cannot be used directly in CM4.

1. Experiment Objective

To learn how to use the Rider-Pi's camera and screen to create a motion statistics health assistant. The counting here mainly involves tracking the detected human motion movements.

2. Experiment Steps

Enter the Rider-Pi system, terminate the main Rider-Pi program, and enter "ip (where IP is the Rider-Pi's IP):8888" in your browser. After logging in, enter the password "yahboom".

Then log in and navigate to the path cd /home/pi/Rider-pi_class/5.AI Visual Recognition Course/19. Motion detection and run mian.ipynb.

Finally, run the program.

3. Experimental Phenomena

1. After the program runs, select the movement to be detected using the button in the upper right corner of the screen. The detectable movements are as follows:

• Squat
• Push-up
• Sit-up
• Bicep curl
• Lateral raise
• Overhead press
• Leg raise
• Knee raise
• Left knee press
• Right knee press

2. After selecting the corresponding mode/function, press the button in the upper left corner of the screen to start the movement statistics.

3. To change the detected motion, restart the program and select the mode again.

4. Experimental source code analysis

xxxxxxxxxx
while True:
    frame = picam2.capture_array()
    processed_frame, current_angle, keypoints = pose_processor.process_frame(frame, exercise_type)
    
    # 将OpenCV图像转为PIL图像 # Convert OpenCV images to PIL images
    pil_img = Image.fromarray(cv2.cvtColor(processed_frame, cv2.COLOR_BGR2RGB))
    draw = ImageDraw.Draw(pil_img)
           
    current_count = exercise_counter.counter
    
    # 计算文本位置 Calculate text position
    text_width = draw.textlength(display_text, font=pil_font)
    count_width = draw.textlength(str(current_count), font=pil_font)
    right_margin = 5
    text_x = processed_frame.shape[1] - text_width - right_margin
    count_x = processed_frame.shape[1] - count_width - right_margin
    
    # 绘制文本 Drawing Text
    draw.text((text_x, 30), display_text, font=pil_font, fill=(0, 255, 0))
    draw.text((count_x, 60), str(current_count), font=pil_font, fill=(0, 255, 0))
    
    # 转换回OpenCV格式 Convert back to OpenCV format
    processed_frame = cv2.cvtColor(np.array(pil_img), cv2.COLOR_RGB2BGR)
    
    image_widget.value = bgr8_to_jpeg(myimg)
​
    if button.press_b():
        break
​

This while loop is the main business logic for motion detection. It exits the detection by detecting the button in the lower left corner of the screen.