obtaining a detection image and a marked image, the marked image being obtained by marking objects in the detection image;

applying an image segmentation model to segment a first segmented image from the detection image, the detection image being a street view image, the image segmentation model comprising a feature extraction model and a classification model, the feature extraction model being used to extract features of the objects in the detection image, and the classification model being used to up-sample the detection image, determine types of the objects in the detection image, and output the first segmented image, wherein a size of the detection image is same as a size of the marked image, and a size of the first segmented image is smaller than the size of the detection image;

correcting the first segmented image according to the marked image to obtain a second segmented image, comprising: setting a scale factor; and performing a super-resolution processing on the first segmented image according to the scale factor and the marked image to obtain the second segmented image, comprising generating a reference image according to the scale factor and the size of the first segmented image, initial RGB values of all pixels in the reference image being same; setting RGB values for first pixels in the reference image according to the first segmented image; setting RGB values for second pixels other than the first pixels in the reference image according to the RGB values of the first pixels and the marked image; and using the reference image as the second segmented image after the RGB values of all pixels in the reference image are set; and

adjusting a size of the second segmented image to obtain an adjusted segmented image, and using the adjusted segmented image as a standard segmented image of the detection image.