Ship images detection and classification based on convolutional neural network with multiple feature regions

Xu, Zhijing; Sun, Jiuwu; Huo, Yuhao

doi:10.1049/sil2.12104

Cited by 6 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Li et al [29] who developed a novel method to extract sea ice cover using Sentinel-1 data based on the support vector machine (SVM). Xu et al [30] proposed a Recurrent Attention Convolutional Neural Network (RA-CNN) to classify different ships. In this paper, the fusion of remote sensing and optical images is used to take advantage of the complementary strengths.…”

Section: Discussionmentioning

confidence: 99%

Multi-Scale Polar Object Detection Based on Computer Vision

Ding,

Zeng,

Zhou

et al. 2023

Water

View full text Add to dashboard Cite

When ships navigate in polar regions, they may collide with ice masses, which may cause structural damage and endanger the safety of their occupants. Therefore, it is essential to promptly detect sea ice, icebergs, and passing ships. However, individual data sources have limits and should be combined and integrated to obtain more thorough information. A polar multi-target local-scale dataset with five categories was constructed. Sea ice, icebergs, ice melt ponds, icebreakers, and inter-ice channels were identified by a single-shot detector (SSD), with a final mAP value of 70.19%. A remote sensing sea ice dataset with 15,948 labels was constructed. The You Only Look Once (YOLOv5) model was improved with Squeeze-and-Excitation Networks (SE), Funnel Activation (FReLU), Fast Spatial Pyramid Pooling, and Cross Stage Partial Network (SPPCSPC-F). In the detection stage, a slicing operation was performed on remote sensing images to detect small targets. Simulated sea ice data were included to verify the model’s generalization ability. Then, the improved model was trained and evaluated in an ablation experiment. The mAP, recall (R), and precision (P) values of the improved YOLOv5 were 75.3%, 70.3, and 75.4%, with value increases of 3.5%, 3.4%, and 1.9%, respectively, compared to the original model. The improved YOLOv5 was also compared with other models such as YOLOv3, Faster-RCNN, and YOLOv4-tiny. The results indicated that the performance of the proposed model surpassed those of the other conventional models. This study achieved the detection of multiple targets on different scales in a polar region and realized data fusion, avoiding the limitations of using a single data source, and provides a method to support polar ship path planning.

show abstract

Section: Discussionmentioning

confidence: 99%

Multi-Scale Polar Object Detection Based on Computer Vision

Ding,

Zeng,

Zhou

et al. 2023

Water

View full text Add to dashboard Cite

show abstract

“…They highlighted how data augmentation and fine-tuning of the VGG architecture contributed to improved model performance. [33] leveraged VGG, ResNet, DenseNet, AlexNet, and various other CNN variants for ship classification. Their self-collected dataset comprised 2,635 internet images, categorised into eight target categories, covering both civilian and non-civilian ships.…”

Section: Literature Reviewmentioning

confidence: 99%

Explainable Deep Learning to Classify Royal Navy Ships

Baesens,

Adams,

Pacheco-Ruiz

et al. 2024

IEEE Access

View full text Add to dashboard Cite

We research how deep learning convolutional neural networks can be used to to automatically classify the unique data set of black-and-white naval ships images from the Wright and Logan photographic collection held by the National Museum of the Royal Navy. We contrast various types of deep learning methods: pretrained models such as ConvNeXt, ResNet and EfficientNet, and ConvMixer. We also thoroughly investigate the impact of data preprocessing and externally obtained images on model performance. Finally, we research how the models estimated can be made transparent using visually appealing interpretability techniques such as Grad-CAM. We find that ConvNeXt has the best performance for our data set achieving an accuracy of 79.62% for 0-notch classification and an impressive 94.86% for 1-notch classification. The results indicate the importance of appropriate image preprocessing. Image segmentation combined with soft augmentation significantly contributes to model performance. We consider this research to be original in several aspects. Notably, it distinguishes itself through the uniqueness of the acquired dataset. Additionally, its distinctiveness extends to the analytical modeling pipeline, which encompasses a comprehensive range of modeling steps, including data preprocessing (incorporating external data, image segmentation, and image augmentation) and the use of deep learning techniques such as ConvNeXt, ResNet, EfficientNet, and ConvMixer. Furthermore, the research employs explanatory tools like Grad-CAM to enhance model interpretability and usability. We believe the proposed methodology offers lots of potential for documenting historic image collections.

show abstract

“…Kang et al [38] designed a deeply layered network consisting of a region proposal network (RPN) with a high network resolution and an object detection network with upper and lower features to improve the detection performance of small ships. In addition, Xu et al [39] proposed a recurrent attention convolutional neural network (RA-CNN), which integrates multiple characteristic layers, with each layer containing a localization head attention proposal network (APN). Through this approach the convergence process is accelerated, and the overlap rate of multiple feature regions is reduced.…”

Section: Related Workmentioning

confidence: 99%