Open Access

ARTICLE

Ship Detection and Recognition Based on Improved YOLOv7

Wei Wu¹, Xiulai Li², Zhuhua Hu¹, Xiaozhang Liu^3,*

1 School of Information and Communication Engineering, Hainan University, Haikou, 570228, China
2 School of Cyberspace Security, Hainan University, Haikou, 570228, China
3 School of Computer Science and Technology, Hainan University, Haikou, 570228, China

* Corresponding Author: Xiaozhang Liu. Email:

(This article belongs to this Special Issue: AI Powered Human-centric Computing with Cloud and Edge)

Computers, Materials & Continua 2023, 76(1), 489-498. https://doi.org/10.32604/cmc.2023.039929

Received 24 February 2023; Accepted 18 April 2023; Issue published 08 June 2023

Abstract

In this paper, an advanced YOLOv7 model is proposed to tackle the challenges associated with ship detection and recognition tasks, such as the irregular shapes and varying sizes of ships. The improved model replaces the fixed anchor boxes utilized in conventional YOLOv7 models with a set of more suitable anchor boxes specifically designed based on the size distribution of ships in the dataset. This paper also introduces a novel multi-scale feature fusion module, which comprises Path Aggregation Network (PAN) modules, enabling the efficient capture of ship features across different scales. Furthermore, data preprocessing is enhanced through the application of data augmentation techniques, including random rotation, scaling, and cropping, which serve to bolster data diversity and robustness. The distribution of positive and negative samples in the dataset is balanced using random sampling, ensuring a more accurate representation of real-world scenarios. Comprehensive experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art approaches in terms of both detection accuracy and robustness, highlighting the potential of the improved YOLOv7 model for practical applications in the maritime domain.

---

Keywords

---