The invention relates to the technical field of
train monitoring, and discloses a metro
bogie bolt looseness detection method based on multi-dimensional visual combined driving, which comprises the following steps: acquiring bolt two-dimensional image data and bolt three-dimensional image data of a key part of a metro
bogie; performing data enhancement on the two-dimensional image data of the bolt, inputting the two-dimensional image data into a BOLT-YOLO bolt detection model to identify key parts of the subway
bogie, outputting a bolt image containing the key parts, and
numbering each key part; obtaining an independent bolt area image, inputting the image into the Unet semantic segmentation
network model to identify two sections of bolt anti-loosening lines, and judging the loosening state through the angle change of the anti-loosening lines and the bolts; if the two-dimensional image information is insufficient, a three-dimensional
point cloud model of the bolt is generated, and whether the bolt exceeds an error range or not is judged through accurate registration and datum plane
height difference calculation; according to the method, the abnormal state of the
train bolt can be detected in real time, the detection precision is improved, and the
resource utilization rate is reduced.