AILDP: a research on ship number recognition technology for complex scenarios
Abstract With the rapid growth of global maritime trade and the increasingly urgent need for maritime surveillance and security management, fast and accurate identification of vessels has become a crucial aspect. The task of ship number recognition mainly faces two challenges: first, the ship number...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-03-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-025-01820-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract With the rapid growth of global maritime trade and the increasingly urgent need for maritime surveillance and security management, fast and accurate identification of vessels has become a crucial aspect. The task of ship number recognition mainly faces two challenges: first, the ship number is usually located in different parts of the hull, and due to the shooting distance, the size of the ship number can vary greatly on different vessels, making automated recognition complex. Second, adverse weather conditions and complex sea surface environments may affect the accuracy of visual recognition. To address the above issues, we produce a private dataset containing 2436 images of ships in a variety of scenarios and propose an algorithm (AILDP) for interactive feature learning and adaptive enhancement to tackle multiple challenges in ship number recognition. Firstly, in the detection phase, for the problem of varying size and position in the ship number recognition task, the detection effect is optimized by a module (AIFI_LPE) that combines feature interaction and learned position encoding. Secondly, to deal with the issues of blurring and occlusion of ship numbers due to ship movement or bad weather, a module (C2f_IRMB_DRB) is proposed that can capture high-quality features while weighing the computational effort when processing low-quality images. After detection, the results are divided into two categories: clear ship number and low-quality ship number. In order to save computational resources, only the low-quality images are first subjected to preliminary image enhancement processing, and then the Thin Plate Spline (TPS) is introduced in the recognition part based on the framework of PaddleOCRv4 and combined with the feature extraction and enhancement module to adjust the spatial features of the images to ensure that both types of ship number images can be accurately processed in the feature extraction and recognition process. Experimental results show that the AILDP can improve the accuracy of ship number recognition, with the precision, recall, and mAP0.5 for ship number detection increased to 95.7%, 94.5%, and 94.8%. The Character_accuracy of the recognition task can reach 95.23%. |
|---|---|
| ISSN: | 2199-4536 2198-6053 |