如何在特定 x/y 像素坐标的 cv2s 关键点检测中定义掩码？

如何解决如何在特定 x/y 像素坐标的 cv2s 关键点检测中定义掩码？

我需要有关掩码参数的帮助，以将关键点检测应用于特定的感兴趣区域。如何在 np.array 中定义具有 x/y 范围的区域？

import numpy as np
import cv2 as cv

img = cv.imread('test_img.jpg')

gray = cv.cvtColor(img,cv.COLOR_BGR2GRAY)
gray2 = np.float32(gray)
print(img.shape)

max_corners = 20
quality_level = 8 / 100
min_distance = 7

###################?????????????################
mask = ???
# how to define the mask with specific x/y pixel coordinates? 

corners = cv.goodFeaturesToTrack(gray2,max_corners,quality_level,min_distance,mask)
#print(corners)
corners = np.int0(corners)
for i in corners:
    x,y = i.ravel()
    cv.circle(img,(x,y),2,(0,255,0),-1)

cv.imshow('Detection Test',img)
cv.waitKey(0)
cv.destroyAllWindows()