ReBiDet: An Enhanced Ship Detection Model Utilizing ReDet and Bi-Directional Feature Fusion

To enhance ship detection accuracy in the presence of complex scenes and significant variations in object scales, this study introduces three enhancements to ReDet, resulting in a more powerful ship detection model called rotation-equivariant bidirectional feature fusion detector (ReBiDet). Firstly,...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences 2023-06, Vol.13 (12), p.7080
Main Authors: Yan, Zexin, Li, Zhongbo, Xie, Yongqiang, Li, Chengyang, Li, Shaonan, Sun, Fangwei
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
artificial intelligence
bi-directional feature fusion
Clustering
Datasets
Deep learning
Detectors
Efficiency
feature pyramid network
Localization
Neural networks
Remote sensing
remote sensing images
Rotation
Samplers
Satellites
Semantics
ship detection
Ships
Task complexity
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To enhance ship detection accuracy in the presence of complex scenes and significant variations in object scales, this study introduces three enhancements to ReDet, resulting in a more powerful ship detection model called rotation-equivariant bidirectional feature fusion detector (ReBiDet). Firstly, the feature pyramid network (FPN) structure in ReDet is substituted with a rotation-equivariant bidirectional feature fusion feature pyramid network (ReBiFPN) to effectively capture and enrich multiscale feature information. Secondly, K-means clustering is utilized to group the aspect ratios of ground truth boxes in the dataset and adjust the anchor size settings accordingly. Lastly, the difficult positive reinforcement learning (DPRL) sampler is employed instead of the random sampler to address the scale imbalance issue between objects and backgrounds in the dataset, enabling the model to prioritize challenging positive examples. Through numerous experiments conducted on the HRSC2016 and DOTA remote sensing image datasets, the effectiveness of the proposed improvements in handling complex environments and small object detection tasks is validated. The ReBiDet model demonstrates state-of-the-art performance in remote sensing object detection tasks. Compared to the ReDet model and other advanced models, our ReBiDet achieves mAP improvements of 3.20, 0.42, and 1.16 on HRSC2016, DOTA-v1.0, and DOTA-v1.5, respectively, with only a slight increase of 0.82 million computational parameters.
ISSN:2076-3417
2076-3417
DOI:10.3390/app13127080