Sea Surface Object Detection Algorithm Based on YOLO v4 Fused with Reverse Depthwise Separable Convolution (RDSC) for USV

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.

A Study on Small-Scale Ship Detection Based on Attention Mechanism

“…To demonstrate its effectiveness, the proposed local attention module has been combined with other approaches. The local attention module was added to C1, P1, and N1 of PANet [28], and the local attention module was added to the SPP module of CSPDarknet [30]. Compared with the initial method, the network-detection performance can be further improved by adding an attention module, the results of which are presented in Table 3.…”

A Lightweight Sea Surface Object Detection Network for Unmanned Surface Vehicles

“…Some object detection algorithms based on deep learning have been successfully employed in USVs to detect sea surface objects. Tao Liu et al [18] proposed a sea surface object detection algorithm based on YOLO v4. They introduced the module of Reverse Depthwise Separable Convolution [19] to reduce the number of weights.…”

High-Speed Maritime Object Detection Scheme for the Protection of the Aid to Navigation

“…The CNN (Convolution Neural Network) takes the same role as do human eyes in the recent deep learning-based image recognition technologies and it is simply available to recognize various marine floating objects (i.e. ships and buoys) [19] as shown in Fig. 12.…”