A Defective Bolt Detection Model With Attention-Based RoI Fusion and Cascaded Classification Network

In unmanned aerial vehicle (UAV) transmission line inspection images, the detection of defective small-size objects such as bolts on towers is important and challenging. Although using multiscale features of deep neural networks has improved the performance, it is still inadequate in mining fine-grained associations between multiscale features and dealing with the high similarity between normal and defective bolts. Therefore, this article proposes an improved defective bolt detection model mixed attention RoI fusion (MARF)-cascaded classification network (CCN), based on region of interest (RoI) feature fusion and CCN. First, a MARF network is built to adaptively compute fine-grained weights for features at different scales of the feature pyramid network (FPN) and enhances the difference between foreground and background. Second, CCN is designed to divide the original classification results into more easily identifiable categories based on morphological features, which are rectified via a secondary classifier to reduce false detection. Third, this article defines atypical defects based on occurrence frequency and utilizes Focal Loss to address the resulting imbalanced classification loss. Experiments show that MARF-CCN improves the average precision (AP) of defective bolts by 14.33%-84.40% compared with the commonly used models.