Lug piece breakage detection method for high-speed rail overhead line system supporting device based on HOG features and two-dimensional Gabor wavelet transformation

The invention discloses a lug piece breakage detection method for a high-speed rail overhead line system supporting device based on HOG features and two-dimensional Gabor wavelet transformation. According to the method, a rotating double-lug lug piece breakage failure is detected. The method comprises the following steps that a positive and negative sample library of a rotating double-lug body is built firstly; the HOG features of a positive and negative sample are extracted, and a feature descriptor of the sample is generated; on the basis of an AdaBoost algorithm, a Cascade classifier is trained, the trained classifier is utilized for carrying out classification and identification on an area where the rotating double-lug body in an image is located and an area where a non-rotating double-lug body in the image is located, and positioning of the rotating double-lug body in the image is completed; finally, the two-dimensional Gabor wavelet transformation is utilized for screening edge information of the rotating double-lug image, and therefore identification on fault cracks caused by the lug piece breakage failure is carried out. According to the method, a lug piece where the breakage failure happens can be accurately identified in a complex overhead line system hanging device image, and compared with a method of manual screening, the detection efficiency can be greatly improved.