主要问题在于 ROI 选择事件以及当前如何调用它。当前的实现不是动态的，这意味着我们无法可视化我们正在尝试选择的 ROI。此外，我们甚至在选择 ROI 之前就已经开始处理。
选择 ROI 的正确方法是，一旦我们捕获了第一帧，注册鼠标单击事件并使用 imshow 和 waitKey(n) 无限期地可视化该帧，直到按下某个特定键。或者，我们可以通过使用waitKey(0)（未测试）在没有无限循环的情况下实现相同的效果。
在这个阶段，我们应该能够绘制所需的 ROI 矩形。这里的关键因素是必须通过使用无限循环或waitKey(0) 来停止执行。仅仅注册活动是不够的。完成 ROI 选择后，继续执行其余代码。
一些建议如下：
- 尽可能避免使用全局变量
- 为 ROI 选择创建单独的窗口，然后将其丢弃
- 为每个单独的任务创建单独的函数
以下是完整代码，演示了正确使用鼠标点击事件来选择视频处理的 ROI：
import numpy as np
import cv2
import matplotlib.pyplot as plt
ORIGINAL_WINDOW_TITLE = 'Original'
FIRST_FRAME_WINDOW_TITLE = 'First Frame'
DIFFERENCE_WINDOW_TITLE = 'Difference'
canvas = None
drawing = False # true if mouse is pressed
#Retrieve first frame
def initialize_camera(cap):
_, frame = cap.read()
return frame
# mouse callback function
def mouse_draw_rect(event,x,y,flags, params):
global drawing, canvas
if drawing:
canvas = params[0].copy()
if event == cv2.EVENT_LBUTTONDOWN:
drawing = True
params.append((x,y)) #Save first point
elif event == cv2.EVENT_MOUSEMOVE:
if drawing:
cv2.rectangle(canvas, params[1],(x,y),(0,255,0),2)
elif event == cv2.EVENT_LBUTTONUP:
drawing = False
params.append((x,y)) #Save second point
cv2.rectangle(canvas,params[1],params[2],(0,255,0),2)
def select_roi(frame):
global canvas
canvas = frame.copy()
params = [frame]
ROI_SELECTION_WINDOW = 'Select ROI'
cv2.namedWindow(ROI_SELECTION_WINDOW)
cv2.setMouseCallback(ROI_SELECTION_WINDOW, mouse_draw_rect, params)
roi_selected = False
while True:
cv2.imshow(ROI_SELECTION_WINDOW, canvas)
key = cv2.waitKey(10)
#Press Enter to break the loop
if key == 13:
break;
cv2.destroyWindow(ROI_SELECTION_WINDOW)
roi_selected = (3 == len(params))
if roi_selected:
p1 = params[1]
p2 = params[2]
if (p1[0] == p2[0]) and (p1[1] == p2[1]):
roi_selected = False
#Use whole frame if ROI has not been selected
if not roi_selected:
print('ROI Not Selected. Using Full Frame')
p1 = (0,0)
p2 = (frame.shape[1] - 1, frame.shape[0] -1)
return roi_selected, p1, p2
if __name__ == '__main__':
cap = cv2.VideoCapture(0)
#Grab first frame
first_frame = initialize_camera(cap)
#Select ROI for processing. Hit Enter after drawing the rectangle to finalize selection
roi_selected, point1, point2 = select_roi(first_frame)
#Grab ROI of first frame
first_frame_roi = first_frame[point1[1]:point2[1], point1[0]:point2[0], :]
#An empty image of full size just for visualization of difference
difference_image_canvas = np.zeros_like(first_frame)
while cap.isOpened():
ret, frame = cap.read()
if ret:
#ROI of current frame
roi = frame[point1[1]:point2[1], point1[0]:point2[0], :]
difference = cv2.absdiff(first_frame_roi, roi)
difference = cv2.GaussianBlur(difference, (3, 3), 0)
_, difference = cv2.threshold(difference, 18, 255, cv2.THRESH_BINARY)
#Overlay computed difference image onto the whole image for visualization
difference_image_canvas[point1[1]:point2[1], point1[0]:point2[0], :] = difference.copy()
cv2.imshow(FIRST_FRAME_WINDOW_TITLE, first_frame)
cv2.imshow(ORIGINAL_WINDOW_TITLE, frame)
cv2.imshow(DIFFERENCE_WINDOW_TITLE, difference_image_canvas)
key = cv2.waitKey(30) & 0xff
if key == 27:
break
else:
break
cap.release()
cv2.destroyAllWindows()
专业提示：
有时，在初始化相机时，根据房间内的环境光，需要一些时间来预热。您可以考虑跳过一些初始帧，让相机从初始化阶段稳定下来。可以通过在上述代码中定义initialize_camera函数来完成，如下：
def initialize_camera(cap):
for i in range(0,60): #Skip first 60 frames
_, frame = cap.read()
return frame