Based on ARM+FPGA heterogeneous development board, according to the contents of the following file, you can know the functions supported by myir-image-full system, which supports OpenCV, so there is no need to install related driver packages in particular, saving a lot of things.
02. Mil ARM+FPGA based heterogeneous development board software evaluation guide
This article introduces the basic operations of Python, in the documentation 10.1 Development language support.
03. Mill based on ARM+FPGA development board process path
/usr/share/OpenCV/samples//usr/share/opencv4/samples/python/
There are some python programs in the file directory.
04. Mill image recognition development based on ARM+FPGA development board
1. Use reference images
The picture above is a simulated answer sheet, the same as the actual answer sheet theory, the details may need to change. The normal answer sheet collects more data. 2. Source code 1) Source code screenshot
2) Source code paste
#! /usr/bin/env python3
“” ”
Created on Thu Sep 30 07:53:41 2021
“” ”
PYTHON 2/3 COMPATIBILITY
from future import print_function
import numpy as np
import cv2
img = cv2.imread(‘b.jpg’)
cv2.imshow(“orginal”,img)
gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
cv2.imshow(“gray”,gray)
gaussian = cv2.GaussianBlur(gray, (5, 5), 0)
cv2.imshow(“gaussian”,gaussian)
Edged = cv2. Canny (gaussian, 50200)
cv2.imshow(“edged”,edged)
cts, hierarchy = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours(img, cts, -1, (0,0,255), 3)
cv2.imshow(“img”,img)
cv2.waitKey()
cv2.destroyAllWindows()
3. Code image upload