Circle Recognition - Grayscale Image

Example Results

Run this section's example code [Source Code/06.cv_lite/3.grayscale_find_circles.py]

This section uses the cv_lite extension module to implement circle detection. It captures images in real time using a camera and draws a circular outline for annotation after detecting circular objects.

The average frame rate of this section's examples is around 15 frames per second. The specific frame rate depends on the actual detection scenario.

Code Explanation

Code Snippet Explanation

Importing Modules

import time, os, sys, gc
from machine import Pin
from media.sensor import * # Camera interface
from media.display import * # Display interface
from media.media import * # Media manager
import _thread
import cv_lite # cv_lite extension module (contains circle detection functions)
import ulab.numpy as np # NumPy-like ndarray for MicroPython

These modules provide the functionality required for camera control, image display, memory management, and Hough circle detection.

Set image size

xxxxxxxxxx
image_shape = [480, 640] # Height x Width

Define the image resolution to 480x640 (height x width). The camera and display module will be initialized based on this size.

Initialize the camera

xxxxxxxxxx
sensor = Sensor(id=2, width=1280, height=720, fps=90)
sensor.reset()
sensor.set_framesize(width=image_shape[1], height=image_shape[0])
sensor.set_pixformat(Sensor.GRAYSCALE)  # Set to grayscale image output / Grayscale mode

• Initialize the camera, set the resolution to 1280x720 and the frame rate to 90 FPS.
• Resize the output frame to 640x480 and set it to grayscale mode (single-channel image, saves memory and computing resources, suitable for Hough circle detection).

Initialize the display module

xxxxxxxxxx
Display.init(Display.ST7701, width=image_shape[1], height=image_shape[0], to_ide=True, quality=50)

Initialize the display module, use the ST7701 driver chip, and the resolution is consistent with the image size. to_ide=True means that the image will be transmitted to the IDE for virtual display at the same time, and quality=50 sets the image transmission quality.

Initialize the media manager and start the camera

xxxxxxxxxx
MediaManager.init()
sensor.run()

Initialize the media resource manager and start the camera to start capturing the image stream.

Setting Hough Circle Detection Parameters

xxxxxxxxxx
 Color Block Recognition - Color Image
Circle Recognition - Color Image