A small target detection method combining attention mechanism and feature fusion

Abstract

To solve the problem that the features of small targets in the image are difficult to extract and lead to missed detection, a small target detection method combining attention mechanism and feature fusion was proposed based on the single shot multi-box detector (SSD) model. Firstly, ResNet50 was used as the feature extraction backbone network to solve the problem of insufficient feature extraction capability caused by the gradient correlation decay of the original network. Then, an attention mechanism module was added to the low-level feature extraction layer information, the learning ability of low-level feature was improved. Finally, the low-level features and high-level semantic information were cascaded and fused to make full use of the correlation information between different feature maps. The experimental results show that the average detection accuracy of the improved model for small targets reaches 51.1%, which is 9.3% higher than that before the improvement. The improved model has higher detection accuracy for small targets.