RPFNet: Recurrent Pyramid Frequency Feature Fusion Network for Instance Segmentation in Side-Scan Sonar Images

Wang, Zhen; Zhang, Shanwen; Zhang, Chuanlei; Wang, Buhong

doi:10.1109/jstars.2023.3266383

Cited by 8 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This segmentation roughly locates the diver's target and generates a region of interest (ROI). Wang et al [37] had constructed a novel recurrent pyramid frequency feature fusion network (RPFNet) by enhancing and fusing the different frequency characteristics of SSS images, using the residual structure and attention mechanism which effectively extracted fine-grained features, reduced background information interference, and improved nonlinear feature representation capabilities.…”

Section: Application Of Frequency Domain For Sss Imagesmentioning

confidence: 99%

“…Some methods have borrowed the concept of frequency to make some attempts: Zhu et al [36] to separate the acoustically highlighted area from the surrounding environment based on frequency analysis. Wang et al [37] had constructed a novel network by enhancing and fusing the different frequency characteristics of SSS images. However, by its very nature, frequency domain conversion is not used to obtain characteristic information.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

D2MFNet: a Dual-Domain Multi-Frequency Network for Side-Scan Sonar Image Detection

Wang,

Zhang,

et al. 2023

Preprint

View full text Add to dashboard Cite

The utilization of side-scan sonar (SSS) technology plays a pivotal role in ensuring the safety of underwater environments and facilitating the discovery of aquatic resources during daily production activities. Within this field, the use of SSS images for seabed target detection has gained widespread recognition. However, many existing detection approaches primarily concentrate on tracking the evolution path of optical image object detection tasks, resulting in complex structures and limited versatility. To tackle this issue, we introduce a pioneering Dual-Domain Multi-Frequency Network (D2MFNet) meticulously crafted to harness the distinct characteristics of SSS image detection. To maximize the information extracted from SSS images across various frequency ranges, we introduce a novel method for calculating the information flow of target ranges and propose a Multi-Frequency Combined Attention Mechanism (MFCAM). This mechanism amplifies the relevance of dual-domain features across different channels. Moreover, recognizing that SSS images can provide richer insights after frequency domain conversion, we introduce a Dual-Domain Feature Pyramid Network D2FPN. By incorporating frequency domain information representation, D2FPN significantly augments the depth and breadth of feature information in underwater small datasets. Our methods are seamlessly designed for integration into existing networks, offering plug-and-play functionality with substantial performance enhancements. We have conducted extensive experiments to validate the efficacy of our proposed techniques, and the results showcase their state-of-the-art performance. We will make our code and models publicly available at https://dagshub.com/estrellaww00/D2MFNet.

show abstract

Section: Application Of Frequency Domain For Sss Imagesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

D2MFNet: a Dual-Domain Multi-Frequency Network for Side-Scan Sonar Image Detection

Wang,

Zhang,

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

An Automatic Framework for Nasal Esthetic Assessment by ResNet Convolutional Neural Network

Ashoori,

Zoroofi,

Sadeghi

2024

J Digit Imaging. Inform. med.

View full text Add to dashboard Cite

Nasal base aesthetics is an interesting and challenging issue that attracts the attention of researchers in recent years. With that insight, in this study, we propose a novel automatic framework (AF) for evaluating the nasal base which can be useful to improve the symmetry in rhinoplasty and reconstruction. The introduced AF includes a hybrid model for nasal base landmarks recognition and a combined model for predicting nasal base symmetry. The proposed state-of-the-art nasal base landmark detection model is trained on the nasal base images for comprehensive qualitative and quantitative assessments. Then, the deep convolutional neural networks (CNN) and multi-layer perceptron neural network (MLP) models are integrated by concatenating their last hidden layer to evaluate the nasal base symmetry based on geometry features and tiled images of the nasal base. This study explores the concept of data augmentation by applying the methods motivated via commonly used image augmentation techniques. According to the experimental findings, the results of the AF are closely related to the otolaryngologists’ ratings and are useful for preoperative planning, intraoperative decision-making, and postoperative assessment. Furthermore, the visualization indicates that the proposed AF is capable of predicting the nasal base symmetry and capturing asymmetry areas to facilitate semantic predictions. The codes are accessible at https://github.com/AshooriMaryam/Nasal-Aesthetic-Assessment-Deep-learning.

show abstract

A novel target detection method with dual‐domain multi‐frequency feature in side‐scan sonar images

Wang,

Zhang,

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

Side‐scan sonar (SSS) detection is a key method in underwater environmental security and subsea resource development. However, many detection approaches primarily concentrate on tracking the evolution path of optical image object detection tasks when using acoustic images, resulting in complex structures and limited versatility. To tackle this issue, we introduce a pioneering dual‐domain multi‐frequency network (D2MFNet) meticulously crafted to harness the distinct characteristics of SSS image detection. In D2MFNet, a novel method for optimizing and improving the detection sensitivity in different frequency ranges called multi‐frequency combined attention mechanism (MFCAM) is proposed. This mechanism amplifies the relevance of dual‐domain features across different channels and spaces. Moreover, we introduce a dual‐domain feature pyramid network (D2FPN) significantly augments the depth and breadth of feature information in underwater small datasets. The methods offer plug‐and‐play functionality with substantial performance enhancements. Extensive experiments are conducted to validate the efficacy of the proposed techniques, and the results showcase their state‐of‐the‐art performance. MFCAM improves the mAP by 16.9% in the KLSG dataset and 15.5% in the SCTD dataset. The mAP of D2FPN was improved by 8.4% in the KLSG dataset and by 9.8% in the SCTD dataset. The code and models will be publicly available at https://dagshub.com/estrellaww00/D2MFNet.

show abstract

RPFNet: Recurrent Pyramid Frequency Feature Fusion Network for Instance Segmentation in Side-Scan Sonar Images

Cited by 8 publications

References 48 publications

D2MFNet: a Dual-Domain Multi-Frequency Network for Side-Scan Sonar Image Detection

D2MFNet: a Dual-Domain Multi-Frequency Network for Side-Scan Sonar Image Detection

An Automatic Framework for Nasal Esthetic Assessment by ResNet Convolutional Neural Network

A novel target detection method with dual‐domain multi‐frequency feature in side‐scan sonar images

Contact Info

Product

Resources

About