Week 12: Motion Detection

Week 12: Motion Detection#

Laboratory 9
Last updated Jan 5, 2023

00. Content #

Mathematics

Vector fields

Programming Skills

Function and modules

Embedded Systems

Thonny and Micropython

0. Required Hardware #

Microcontroller: Raspberry Pi Pico
Breadboard
USB connector
Camera

Write your name and email below:

Name: me

Email: me @purdue.edu

You may work in groups of 2-3 for this lab.

Groupmate(s):

import numpy as np
import matplotlib.pyplot as plt
import cv2

1. Detecting Motion #

During the previous lab, you learned how to display the optical flow between the frames of a video and how to set up a camera using the Raspberry Pi Pico. For this lab, we will be focusing on using the camera and analyzing the video that it provides.

Set up your camera using the instructions from last week’s lab. After it is set up, try Exercise 1 using what you learned last week. As a reminder, OpenCV is used for images and videos in Python, so remember to make use of this. You may want to look up commands to help during this lab.

If you run into significant hardware issues, use the test video from Lab 7.

Rerun the following cells as you did in the previous lab:

import time
import serial
from serial.tools import list_ports

PICO_HWID = "2E8A"


def get_pico_port():
    pico_ports = list(list_ports.grep(PICO_HWID))
    if len(pico_ports) == 0:
        raise Exception(
            "No Raspberry Pi Pico was detected. Check to make sure it is plugged in, and that no other programs are accessing it"
        )
    return pico_ports[0].device


print("Here are all the serial devices detected:")
for port in list_ports.comports():
    print(port.device, port.hwid)

port = get_pico_port()
print(f"\nselected port {port} as most likely to have a raspberry pi pico")

buffer = bytearray(96 * 96)
img = np.zeros(shape=(96, 96), dtype="uint8")

with serial.Serial(port, timeout=1) as s:
    s.read_until(b"\x55\xAA")
    s.readinto(buffer)
    img.flat[::-1] = buffer

plt.imshow(img, cmap="gray")
plt.show()

%matplotlib widget

fig, ax = plt.subplots()
render = ax.imshow(img, cmap='gray')
plt.show(block=False)

try:
    with serial.Serial(port, timeout=1) as s:
        while True:
            s.read_until(b"\x55\xAA")
            s.readinto(buffer)
            img.flat[::-1] = buffer
            render.set_data(img)
            fig.canvas.draw()
except KeyboardInterrupt:
    pass

Remember that when you are done, you will have to hit the Interrupt Kernel button, which can found at the top of the screen (the stop symbol) or under Kernel.

Exercise 1 #

Part 1

Recall the previous lab on optical flow. Can you think of a (mathematical) rule to tell when an object enters the camera’s view?

Hint: Are there any values that would be high/low when there is motion?

Write Answers for Exercise 1 Part 1 Below

Part 2

Using your camera, detect motion in real time (or near real time). You can use any method to do this, whether it be Farneback’s algorithm to determine the differences between frames, your answer to Exercise 1 Part 1, or anything else you can think of. Decide how to display that movement has been detected on the camera, such as having Python print a statement.

Display all code you wrote either by copying and pasting or reading in and printing Python file contents.

Write Answers for Exercise 1 Part 2 Below

Exercise 2 #

Analyze the camera feed in real time and display which direction the movement is occurring in. This can be limited to up, down, right, left.

Hint: Compare neighboring frames and determine where there are significant differences between them.

Part 1

Display all code you wrote either by copying and pasting or reading in and printing Python file contents.

Write Answers for Exercise 2 Part 1 Below