Convolutional Neural Network Based Multi-Band Ship Target Recognition with Feature Fusion

Feng, 刘峰 Liu; Tongsheng, 沈同圣 Shen; Xin-xing, 马新星 Ma

doi:10.3788/aos201737.1015002

Cited by 5 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SSD model based on the decision-level method is used to detect the infrared images and the visible images [1]. The feature-level fusion method is proposed to fuse the images of different wave bands and classify the targets [2]. This single fusion method can show the rich detail information of the visible images.…”

Section: Introductionmentioning

confidence: 99%

Multi-source target detection based on pixel-level fusion and decision-level fusion

Lei,

Liu,

et al. 2023

3rd International Conference on Laser, Optics, and Optoelectronic Technology (LOPET 2023)

View full text Add to dashboard Cite

In this paper, we focus on the problem of the visible images and the infrared images fusion detection. Aiming at the incomplete target information obtained by the single wave band target detection algorithm, an improved DenseFuse pixel-level fusion detection model CLHE-DenseFuse-Mask R-CNN is designed to fuse the information of the visible images and the infrared images. In order to solve the problem of the information loss caused by a single fusion method, a multi-source target detection model Mask R-CNN based on the pixel-level fusion and the decision-level fusion MF-Mask R-CNN is proposed. The experimental results show that the multi-fusion target detection model MF-Mask R-CNN significantly improves the detection accuracy of the targets.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-source target detection based on pixel-level fusion and decision-level fusion

Lei,

Liu,

et al. 2023

3rd International Conference on Laser, Optics, and Optoelectronic Technology (LOPET 2023)

View full text Add to dashboard Cite

show abstract

“…However, it can only perform separate training and testing for visible or infrared images, without integration between results from visible and infrared images. Liu et al [16] proposes a fusion recognition method based on CNN. The method designs a sensible network model to extract features of three band images and effectively fuse them.…”

Section: Introductionmentioning

confidence: 99%

Ship Classification Based on Attention Mechanism and Multi-Scale Convolutional Neural Network for Visible and Infrared Images

et al. 2020

View full text Add to dashboard Cite

Visible image quality is very susceptible to changes in illumination, and there are limitations in ship classification using images acquired by a single sensor. This study proposes a ship classification method based on an attention mechanism and multi-scale convolutional neural network (MSCNN) for visible and infrared images. First, the features of visible and infrared images are extracted by a two-stream symmetric multi-scale convolutional neural network module, and then concatenated to make full use of the complementary features present in multi-modal images. After that, the attention mechanism is applied to the concatenated fusion features to emphasize local details areas in the feature map, aiming to further improve feature representation capability of the model. Lastly, attention weights and the original concatenated fusion features are added element by element and fed into fully connected layers and Softmax output layer for final classification output. Effectiveness of the proposed method is verified on a visible and infrared spectra (VAIS) dataset, which shows 93.81% accuracy in classification results. Compared with other state-of-the-art methods, the proposed method could extract features more effectively and has better overall classification performance.

show abstract

Overview of Deep Convolutional Neural Network Approaches for Satellite Remote Sensing Ship Monitoring Technology

Chen

Fan

2020

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

Remote sensing (RS) monitoring of ships has important significance in both military and civilian fields. The RS ship detection aims to locate the position of the ship in the remote sensing image and extract its characteristics. Traditional ship target detection algorithms cannot meet the demands for speed and precision of SAR remote sensing and optical remote sensing data. With the development of artificial intelligence technology, the target detection technology such as deep learning algorithms has made significant progress in RS ship detection. Deep learning has become a heated topic in research. This paper has analyzed and summarized previous researches on the application of deep learning algorithms in ship detection technologies based on SAR and optical remote sensing images in recent years and has provided suggestions for future studies. In the future, deep learning-based technologies for RS ship detection will use more data, such as data from multiple sensors in multiple channels. Deep neural networks will also include more rules and specialized knowledge. Its structure will become more complicated and eventually develop into a neural network like the human brain.

show abstract

Convolutional Neural Network Based Multi-Band Ship Target Recognition with Feature Fusion

Cited by 5 publications

References 0 publications

Multi-source target detection based on pixel-level fusion and decision-level fusion

Multi-source target detection based on pixel-level fusion and decision-level fusion

Ship Classification Based on Attention Mechanism and Multi-Scale Convolutional Neural Network for Visible and Infrared Images

Overview of Deep Convolutional Neural Network Approaches for Satellite Remote Sensing Ship Monitoring Technology

Contact Info

Product

Resources

About