Device, method and non-transitory computer readable storage medium for detecting object

A device for detecting objects, wherein the device comprises:

• an image acquiring circuit, acquiring an image having pixels and generating a plurality of image blocks, in which each of the image blocks corresponds to one of the pixels;
• an image transforming circuit comprising:
• N filtering circuits having N corresponding filtering parameters for filtering a specific image block of the image blocks to generate N filtering results, in which the N filtering parameters gradually enhance the blurriness of the specific image block, wherein N is an integer greater than 1;
• N RMSE computing circuits, computing N RMSE values, in which M is an integer from 2 to N, the first RMSE value is computed according to the first filtering result and the specific image block with no filtering, and the M-th RMSE value is computed according to the M-th and the (M−1)-th filtering results;
• and
• a slope computing circuit, computing a slope of an approximate line according to the RMSE values as the blurriness value of the specific image block;
• and
• an in-focus object detecting circuit, comparing each of the blurriness values with a threshold value to detect corresponding pixels which are parts of a sharp object and further detect an in-focus object.

A non-transitory computer readable storage medium to store a computer program to execute a method for detecting objects used in a device for detecting objects, wherein the method comprises:

• acquiring an image having pixels;
• generating a plurality of image blocks, in which each of the image blocks corresponds to one of the pixels;
• filtering, a specific image block of the image blocks by using N filtering parameters to generate N filtering results, in which the N filtering parameters gradually enhance the blurriness of the specific image block, wherein N is an integer greater than 1;
• computing N root mean square error (RMSE) values, in which M is an integer from 2 to N, the first RMSE value is computed according to the first filtering result and the specific image block with no filtering, and the M-th RMSE value is computed according, to the M-th and the (M−1)-th filtering results;
• computing a slope of an approximate line according to the RMSE values as the blurriness value of the specific image block;
• repeating the above steps to generate the blurriness values of all of the image blocks correspond to the pixels;
• and
• comparing each of the blurriness values with a threshold value to detect corresponding pixels which are parts of a sharp object and further detect an in-focus object.