Image analysis method and apparatus, computer device, and readable storage medium

An image analysis method for distinguishing in a ground area a lawn region from a non-lawn region, the lawn region being a working region and the non-lawn region being a non-working region, so that an intelligent lawn mower may work in the lawn region and avoid working in the non-lawn region, the method comprising:

• obtaining a saturation channel image and a value channel image according to an original image of the ground area;
• obtaining a relative deviation value image based on the saturation channel image and the value channel image, wherein the relative deviation value image represents relative deviations between saturation and value;
• extracting several contours from the relative deviation value image;
• determining target parameter values corresponding to each contour;
• and
• determining according to analysis results of the target parameter values corresponding to each contour whether a non-working region exists in the original image wherein the intelligent lawn mower avoids working in the non-working region based on the determination that the non-working region exists in the original image,
• wherein the step of obtaining the relative deviation value image based on the saturation channel image and the value channel image comprises:
• obtaining the relative deviation value image by using the following formula:
• dMat
• =
• sMat
• -
• vMat
• sMat
• +
• vMat
• *
• 2
• ⁢
• 5
• ⁢
• 5
• wherein dMat is the relative deviation value image, sMat is the saturation channel image, and vMat is the value channel image.