Multi-scale feature fusion convolutional neural network for surface damage detection in retired steel shafts

The detection of surface damage is an important part of the process before remanufacturing retired steel shaft (RSS). Traditional damage detection is mainly done manually, which is time-consuming and error-prone. In recent years, computer vision methods have been introduced into the community of surface damage detection. However, some advanced typical object detection methods perform poorly in the detection of surface damage on RSS due to the complex surface background and rich diversity of damage patterns and scales. To address these issues, we propose a Faster-RCNN-based surface damage detection method for RSS. To improve the adaptability of the network, we endow it with a feature pyramid network (FPN) as well as adaptable multi-scale information modifications to the region proposal network (RPN). In this paper, a detailed study of an FPN-based feature extraction network and the multi-scale object detection network is conducted. Experimental results show that our method improves the mAP score by 8.9% compared with the original Faster-RCNN for surface damage detection of RSS, and the average detection accuracy for small objects is improved by 18.2%. Compared with the current advanced object detection methods, our method is more advantageous for the detection of multi-scale objects.