An image processing apparatus: obtains a captured image captured by the image capturing apparatus after an orientation adjustment is performed by using a first target image generated based on a three-dimensional model of a structure in an image capturing region; determines a correction amount for correcting a difference between an orientation of the image capturing apparatus and a target orientation based on the first target image and the obtained captured image; and corrects the captured image by using the correction amount. The corrected captured image can be used as a second target image for further adjusting the posture of the imaging device.