Station building defect identification and detection method, system and device and storage medium

The invention discloses a station building defect identification and detection method, system and device and a storage medium. The method comprises the following steps: acquiring online video data of a station building; the video stream of the online video data is converted into frames through OpenCV, and online frame images are obtained; the online frame image is preprocessed; inputting the preprocessed online frame image into the trained defect recognition model to obtain a defect recognition result; according to the method, a BAM attention mechanism is fused in a convolutional network feature extraction stage, and meanwhile, PSPNet global pooling is used for carrying out weighted fusion on feature channels after pyramid pooling so as to reserve more important feature information, so that the perception capability on details is relatively high, the station building anomaly detection precision is improved, and the method is suitable for popularization and application. And the method has relatively high resea