Revision history [back]

@Eric Song. Yes, you can do that Snippet:

kernel_height = cv2.getGaussianKernel(frame.shape[0], frame.shape[0] / 2)
Kernel_width = cv2.getGaussianKernel(frame.shape[1], frame.shape[1] / 2)
w_h = np.dot(kernel_heigh,  np.transpose(Kernel_width))
m = 1  / np.max(w_h)

You can change value int or float / 2

@Eric Song. Yes, you can do that Snippet:that:

kernel_height = cv2.getGaussianKernel(frame.shape[0], frame.shape[0] / 2)
Kernel_width = cv2.getGaussianKernel(frame.shape[1], frame.shape[1] / 2)
w_h = np.dot(kernel_heigh,  np.transpose(Kernel_width))
m = 1  / np.max(w_h)

You can change value int or float / 2