Lightweight Feature Fusion for Single Shot Multibox Floater Detection

A lightweight feature fusion SSD for USV (unmanned surface vessel) platforms with limited memory is proposed in this paper. Firstly, MobileNetV2 is used to replace VGG to reduce parameter redundancy and improve speed without compromising accuracy. Secondly, a lightweight feature fusion module is utilized to improve accuracy for small targets. On the Flow dataset the average accuracy of the network proposed in this paper is improved by nearly 10%, parameters and GFLOPs is reduced by nearly 50% and 90%, respectively. What’s more, the FPS meets the real-time detection requirements. This approach is considered suitable for real-time target detection on USV with limited memory resources.