FSFADet: Arbitrary-Oriented Ship Detection for SAR Images Based on Feature Separation and Feature Alignment

Zhu, Ming; Hu, Guoping; Li, Shuai; Zhou, Hao; Wang, Shiqiang

doi:10.1007/s11063-022-10753-5

Cited by 7 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For calculating loss for RCNN, two different losses, each for one branch, are used for weight updating. The first loss is for class prediction, which can be calculated as in Equations ( 9)- (11).…”

Section: The Frcnn Methodsmentioning

confidence: 99%

“…It shows high accuracy with the help of three essential components: residual blocks, bounding box regression, and intersection over union, which are responsible for detecting, predicting, and locating, respectively. In [11], YOLO v2 was implemented to detect ships in marine environments with feature separation and feature alignment, which outperforms conventional neural networks with deeper layers. However, the number of parameters handled was still increased.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Aggregate Channel Features and Fast Regions CNN Approach for Classification of Ship and Iceberg

Sethu Ramasubiramanian,

Sivasubramaniyan,

Peer Mohamed

2023

Applied Sciences

View full text Add to dashboard Cite

Detection and classification of icebergs and ships in synthetic aperture radar (SAR) images play a vital role in marine surveillance systems even though available adaptive threshold methods give satisfying results on detection and classification for ships and icebergs, including techniques of convolutional neural networks (CNNs), but need more accuracy and precision. An efficient and accurate method was developed to detect and classify the ship and icebergs. Hence, the research method proposed locating and classifying both ships and icebergs in a given SAR image with the help of deep learning (DL) and non-DL methods. A non-DL method utilized here was the aggregate channel features (ACF) detector, which extracts region proposals from huge SAR images. The DL object detector called fast regions CNN (FRCNN) detects objects accurately from the result of ACF since the ACF method avoids unwanted regions. The novelty of this study was that ACF-FRCNN concentrates only on accurately classifying ships and icebergs. The proposed ACF-FRCNN method gave a better performance in terms of loss (18.32%), accuracy (96.34%), recall (98.32%), precision (95.97%), and the F1 score (97.13%). Compared to other conventional methods, the combined effect of ACF and FRCNN increased the speed and quality of the detection of ships and icebergs. Thus, the ACF-FRCNN method is considered a novel method for over 75 × 75 resolution ship and iceberg SAR images.

show abstract

Section: The Frcnn Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Aggregate Channel Features and Fast Regions CNN Approach for Classification of Ship and Iceberg

Sethu Ramasubiramanian,

Sivasubramaniyan,

Peer Mohamed

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…where Y xyc represents the value of Gaussian function, and a and b are the super parameters used to adjust the weights of nonsymmetric samples in Focal Loss function. Smooth L1 Loss (Zhu et al, 2022) is used to calculate the loss function of length, width and offset of the measured object, including:…”

Section: Centernet Networkmentioning

confidence: 99%

“…Smooth L1 Loss (Zhu et al , 2022) is used to calculate the loss function of length, width and offset of the measured object, including: …”

Section: Metal Workpiece Target Detection Algorithmmentioning

confidence: 99%

A 6DOF pose measurement method for metal casts object based on stereo vision sensor

Wan,

Hu,

Liu

et al. 2024

View full text Add to dashboard Cite

Purpose Presently, 6 Degree of Freedom (6DOF) visual pose measurement methods enjoy popularity in the industrial sector. However, challenges persist in accurately measuring the visual pose of blank and rough metal casts. Therefore, this paper introduces a 6DOF pose measurement method utilizing stereo vision, and aims to the 6DOF pose measurement of blank and rough metal casts. Design/methodology/approach This paper studies the 6DOF pose measurement of metal casts from three aspects: sample enhancement of industrial objects, optimization of detector and attention mechanism. Virtual reality technology is used for sample enhancement of metal casts, which solves the problem of large-scale sample sampling in industrial application. The method also includes a novel deep learning detector that uses multiple key points on the object surface as regression objects to detect industrial objects with rotation characteristics. By introducing a mixed paths attention module, the detection accuracy of the detector and the convergence speed of the training are improved. Findings The experimental results show that the proposed method has a better detection effect for metal casts with smaller size scaling and rotation characteristics. Originality/value A method for 6DOF pose measurement of industrial objects is proposed, which realizes the pose measurement and grasping of metal blanks and rough machined casts by industrial robots.

show abstract

“…Most of the traditional ship detection methods are based on synthetic aperture radar (SAR) images [23,24], which is an active microwave earth observation device with all-weather, all-day operation and a certain penetration capability to the ground. It can obtain images of ship similar to optical photographs.…”

Section: Related Workmentioning

confidence: 99%

An Improved Ship Classification Method Based on YOLOv7 Model with Attention Mechanism

Cen

Feng

Liu

et al. 2023

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Deep learning (DL) is widely used in ship detection, but there are still some problems in the effective classification, such as inaccurate object feature extraction and inconspicuous feature information in deep layers. To address these problems, we propose a YOLOv7-residual convolutional block attention module (YOLOv7-RCBAM) by combining the convolutional attention mechanism and residual connections to the YOLOv7. First, to accelerate the training speed, the parameters in the backbone network of the pretrained model are frozen by using transfer learning, and the model is fine-tuned for training. Second, to enhance the information relevance of channel dimensional features, an attention mechanism with residual connectivity is adopted. Finally, a feature fusion attention mechanism is introduced to improve the effective feature extraction. The effectiveness of the proposed method is fully validated on the SeaShips dataset. The results show that the YOLOv7-RCBAM model achieves better performance with a 97.59% in mAP and effectively extracts object feature in deep layers. Meanwhile, the YOLOv7-RCBAM model can accurately locate ship in complex environments with darkness and noise with the mAP reaching 96.13% to achieve effective ship classification detection.

show abstract

FSFADet: Arbitrary-Oriented Ship Detection for SAR Images Based on Feature Separation and Feature Alignment

Cited by 7 publications

References 20 publications

Aggregate Channel Features and Fast Regions CNN Approach for Classification of Ship and Iceberg

Aggregate Channel Features and Fast Regions CNN Approach for Classification of Ship and Iceberg

A 6DOF pose measurement method for metal casts object based on stereo vision sensor

An Improved Ship Classification Method Based on YOLOv7 Model with Attention Mechanism

Contact Info

Product

Resources

About