Due to the small size, high resolution, and complex background, small object detection has become a difficult point in computer vision. Making full use of high-resolution features and reducing information loss in the process of information propagation is of great significance to improve small object detection. In this article, to achieve the above two points, this work proposes a small object detection network based on multiple feature enhancement and feature fusion based on RetinaNet (MFEFNet). First, this work designs a densely connected dilated convolutions to adequately extract high-resolution features from C2. Then, this work utilizes subpixel convolution to avoid the loss of channel information caused by channel dimension reduction in the lateral connection. Finally, this article introduces a bidirectional fusion feature pyramid structure to shorten the propagation path of high-resolution features and reduce the loss of high-resolution features. Experiments show that our proposed MFEFNet achieves stable performance gains in object detection task. Specifically, the improved method improves RetinaNet from 34.4AP to 36.2AP on the challenging MS COCO dataset, and especially achieves excellent results in small object detection with an improvement of 2.9%.

Concrete is the most widely used material in civil engineering, but due to its inherent brittleness, the generation of cracks easily occurs. Crack healing is an effective method for restoring the mechanical properties of concrete and improving its durability. Of all the current concrete crack healing methods, microbial-induced calcium carbonate precipitation technology is an incredibly promising crack self-healing strategy that has received widespread attention in the field of concrete crack repair. As the biological self-healing agent has difficulty resisting the high alkali and high calcium environment in concrete, protection is required when it is used in concrete cracks.