摘要 |
Disclosed are a method and apparatus for detecting an object based on shape similarity. The apparatus for detecting an object according to the present invention comprises: a pre-processing unit configured to pre-process an input image and then divide the input image into blocks having a predetermined size; a first feature extraction unit configured to extract, as a first feature, a histogram of oriented gradients (HOG) representing a frequency distribution of gradient vectors with respect to the blocks of the input image; a second feature extraction unit configured to extract a second feature which is based on shape similarity of each block by using left-right symmetry of an object included in the input image; and an object determination unit configured to determine a target object corresponding to the first and second features with reference to pre-learned data. |