Abstract
Unmanned surface vehicles (USVs) have been extensively used in various dangerous maritime tasks. Vision-based sea surface object detection algorithms can improve the environment perception abilities of USVs. In recent years, the object detection algorithms based on neural networks have greatly enhanced the accuracy and speed of object detection. However, the balance between speed and accuracy is a difficulty in the application of object detection algorithms for USVs. Most of the existing object detection algorithms have limited performance when they are applied in the object detection technology for USVs. Therefore, a sea surface object detection algorithm based on You Only Look Once v4 (YOLO v4) was proposed. Reverse Depthwise Separable Convolution (RDSC) was developed and applied to the backbone network and feature fusion network of YOLO v4. The number of weights of the improved YOLO v4 is reduced by more than 40% compared with the original number. A large number of ablation experiments were conducted on the improved YOLO v4 in the sea ship dataset SeaShips and a buoy dataset SeaBuoys. The experimental results showed that the detection speed of the improved YOLO v4 increased by more than 20%, and mAP increased by 1.78% and 0.95%, respectively, in the two datasets. The improved YOLO v4 effectively improved the speed and accuracy in the sea surface object detection task. The improved YOLO v4 algorithm fused with RDSC has a smaller network size and better real-time performance. It can be easily applied in the hardware platforms with weak computing power and has shown great application potential in the sea surface object detection.
Highlights
In recent years, marine economy has played an increasingly important role in the economic development of countries
In order to analyze the impact of Reverse Depthwise Separable Convolution (RDSC) on You Only Look Once v4 (YOLO v4) more comprehensively, on the basis of the original YOLO v4, all convolutions were replaced with RDSCs, and another scheme was proposed for comparison, where all convolutions were replaced with DCSs
Based on the engineering application of real-time sea surface object detection of unmanned surface vehicles (USVs), the network structure of YOLO v4 was improved in this paper, and experiments were conducted in SeaShips and SeaBuoys datasets
Summary
Marine economy has played an increasingly important role in the economic development of countries. Many related research focuses on adding different components to industry-leading object detection algorithms, or increasing the volume of the network structure to achieve good detection results, improve accuracy or speed. Not too many components are added to YOLO v4 or expand the network volume but the complexity of the network model is reduced while ensuring accuracy, which is of great significance for the sea surface object detection of USVs with weak performance of the computing hardware platform. The main contributions of this paper are as follows: (1) RDSC was applied to the backbone network and feature fusion network of YOLO v4, which greatly improves the detection speed of YOLO v4, and enhances accuracy at the same time.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
