Two-stage ship detection at long distances based on deep learning and slicing technique

Ship detection over long distances is crucial for the visual perception of intelligent ships. Since traditional image processing-based methods are not robust, deep learning-based image recognition methods can automatically obtain the features of small ships. However, due to the limited pixels of shi...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2024-11, Vol.19 (11), p.e0313145
Main Authors: Gong, Yanfeng, Chen, Zihao, Tan, Jiawan, Yin, Chaozhong, Deng, Wen
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Analysis
Artificial intelligence
Biology and Life Sciences
Computer and Information Sciences
Deep Learning
Earth Sciences
Engineering and Technology
Forecasts and trends
Humans
Image processing
Image Processing, Computer-Assisted - methods
Information processing
Innovations
Machine learning
Methods
Neural networks
Object recognition
Pixels
Remote sensing
Research and Analysis Methods
Ships
Social Sciences
Technology application
Visual discrimination learning
Visual perception
Water waves
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Ship detection over long distances is crucial for the visual perception of intelligent ships. Since traditional image processing-based methods are not robust, deep learning-based image recognition methods can automatically obtain the features of small ships. However, due to the limited pixels of ships over long distances, accurate features of such ships are difficult to obtain. To address this, a two-stage object detection method that combines the advantages of traditional and deep-learning methods is proposed. In the first stage, an object detection model for the sea-sky line (SSL) region is trained to select a potential region of ships. In the second stage, another object detection model for ships is trained using sliced patches containing ships. When testing, the SSL region is first detected using the trained 8th version of You Only Look Once (YOLOv8). Then, the SSL region detected is divided into several overlapping patches using the slicing technique, and another trained YOLOv8 is applied to detect ships. The experimental results showed that our method achieved 85% average precision when the intersection over union is 0.5 (AP50), and a detection speed of 75 ms per image with a pixel size of 1080×640. The code is available at https://github.com/gongyanfeng/PaperCode.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0313145