BiFA-YOLO: A Novel YOLO-Based Method for Arbitrary-Oriented Ship Detection in High-Resolution SAR Images

Sun, Zhongzhen; Leng, Xiangguang; Yu, Lei; Xiong, Boli; Ji, Kefeng; Kuang, Gangyao

doi:10.3390/rs13214209

Cited by 135 publications

(64 citation statements)

References 60 publications

(71 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be seen that after the 20th epoch, the mAP of the all models has been stable. The mAP value of SAFFPest in this paper compared with FasterRCNN [35] , RetinaNet [36] , CP-FCOS [37], VFNet and BiFA-YOLO [38] increased by 33.7%, 6.5%, 4.5%, 2.9% and 2%, respectively. In addition, Figure 13(a) and Figure 13(b) provide confusion matrix diagrams under the VFNet and SAFFPest, which can further illustrate the effectiveness and feasibility of SAFFPest.…”

Section: Experimental Environmentmentioning

confidence: 71%

A Self-Attention Feature Fusion Model for Rice Pest Detection

Wang

Zhang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

To address the problem that existing deep learning methods are not sufficiently accurate to detect rice pests with changeable shapes or similar appearances, a self-attention feature fusion model for rice pest detection (SAFFPest) was proposed. The model was based on VarifocalNet. First, a deformable convolution module was added to the feature extraction network, to improve the feature extraction ability of pests with changeable shapes. Second, by obtaining the balance features of multiple feature maps, the selfattention mechanism was introduced to refine the balance feature, in order to better restore the semantic information of some pests with similar appearances. Subsequently, the group normalization method was used to replace the batch normalization method in the original model, to reduce the impact of batch size on model training. The IP102 rice pest dataset was used to train and verify this model. The experimental results showed that the model can accurately detect nine kinds of rice pests, such as rice leaf rollers and rice leaf caterpillars. Compared with FasterRCNN, RetinaNet, CP-FCOS, VFNet and BiFA-YOLO, the mean average precision of the model improved by 33.7%, 6.5%, 4.5%, 2.9% and 2% respectively.

show abstract

Section: Experimental Environmentmentioning

confidence: 71%

A Self-Attention Feature Fusion Model for Rice Pest Detection

Wang

Zhang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Hyperparameters λ 1 , λ 2 and λ 3 are default settings as {1, 1, 1}. The bounding box regression loss function is calculated by Complete Intersection over Union (CIoU), the confidence loss function and classification loss function are calculated by Binary Cross Entropy With Logits Loss (BCEWithLogit-sLoss) [34]. BCEWithLogitsLoss formula is as follows:…”

Section: Trainingmentioning

confidence: 99%

A Lightweight Object Detection Method in Aerial Images Based on Dense Feature Fusion Path Aggregation Network

Zhou

Rao

et al. 2022

IJGI

View full text Add to dashboard Cite

In recent years, significant progress has been obtained in object detection using Convolutional Neural Networks (CNNs). However, owing to the particularity of Remote Sensing Images (RSIs), common object detection methods are not well suited for RSIs. Aiming at the difficulties in RSIs, this paper proposes an object detection method based on the Dense Feature Fusion Path Aggregation Network (DFF-PANet). Firstly, for better improving the detection performance of small and medium-sized instances, we propose Feature Reuse Module (FRM), which can integrate semantic and location information contained in feature maps; this module can reuse feature maps in the backbone to enhance the detection capability of small and medium-sized instances. After that, we design the DFF-PANet, which can help feature information extracted from the backbone to be fused more efficiently, and thus cope with the problem of external interference factors. We performed experiments on the Dataset of Object deTection in Aerial images (DOTA) dataset and the HRSC2016 dataset; the accuracy reached 71.5% mAP, which exceeds most object detectors of one-stage and two-stages at present. Meanwhile, the size of our model is only 9.2 M, which satisfies the requirement of being lightweight. The experimental results demonstrate that our method not only has better detection accuracy but also maintains high efficiency in RSIs.

show abstract

“…The literature [41] used two new deep learning-based networks namely BCL-UNet and MGG-UNet, which can detect and segment buildings and roads very well. For the characteristics of high-resolution SAR ship images, Sun et al [42] proposed a detector based on bi-directional feature fusion and angular classification (BiFA-YOLO), which can be adapted to SAR ships of arbitrary orientation. Yang et al [43] proposed a model named Rotation Dense Feature Pyramid Networks, which can effectively detect ships in different scenes such as ocean and port.…”

Section: Related Workmentioning

confidence: 99%

“…For the characteristics of high‐resolution SAR ship images, Sun et al. [42] proposed a detector based on bi‐directional feature fusion and angular classification (BiFA‐YOLO), which can be adapted to SAR ships of arbitrary orientation. Yang et al.…”

Section: Related Workmentioning

confidence: 99%

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

Sun

Huo

2022

IET Signal Processing

View full text Add to dashboard Cite

In recent years, the maritime industry is developing rapidly, which poses great challenges for intelligent ship navigation systems to achieve accurate ship classification. To cope with this problem, a Recurrent Attention Convolutional Neural Network (RA‐CNN) is proposed, which is fused with multiple feature regions for ship classification. The proposed model has three scale layers, each of which contains a classification network VGG‐19 and a localisation head Attention Proposal Network (APN). First, the Scale Dependent Pooling algorithm is integrated with VGG‐19 to reduce the impact of over‐pooling and improve the classification performance of small ships. Second, the APN incorporates the Joint Clustering algorithm to generate multiple independent feature regions; thus, the whole model can make full use of the global information in ship recognition. In the meantime, the Feature Regions Optimisation method is designed to solve the overfitting problem and reduce the overlap rate of multiple feature regions. Finally, a novel loss function is defined to cross‐train VGG‐19 and APN, which accelerates the convergence process. The experimental results show that the classification accuracy of the authors’ proposed method reaches 90.2%, which has a 6% improvement over the baseline RA‐CNN. Both classification accuracy and robustness are improved by a large margin compared to those of other compared models.

show abstract

BiFA-YOLO: A Novel YOLO-Based Method for Arbitrary-Oriented Ship Detection in High-Resolution SAR Images

Cited by 135 publications

References 60 publications

A Self-Attention Feature Fusion Model for Rice Pest Detection

A Self-Attention Feature Fusion Model for Rice Pest Detection

A Lightweight Object Detection Method in Aerial Images Based on Dense Feature Fusion Path Aggregation Network

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

Contact Info

Product

Resources

About