Xin Wen

Dr. Xin Wen

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 July 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
XWXin Wen
Xin Wen
WJWang Jian
Wang Jian
CCchensheng cheng
chensheng cheng
FZFeihu Zhang
Feihu Zhang
Guang PanGuang Pan
Guang Pan
Side-scan sonar plays a crucial role in underwater exploration, and the autonomous detection of side-scan sonar images is vital for detecting unknown underwater environments. However, due to the complexity of the underwater environment, the presence of a few highlighted areas on the targets, blurred feature details, and difficulty in collecting data from side-scan sonar, achieving high-precision autonomous target recognition in side-scan sonar images is challenging. This article addresses this problem by improving the You Only Look Once v7 (YOLOv7) model to achieve high-precision object detection in side-scan sonar images. Firstly, given that side-scan sonar images contain large areas of irrelevant information, this paper introduces the Swin-Transformer for dynamic attention and global modeling, which enhances the model’s focus on the target regions. Secondly, the Convolutional Block Attention Module (CBAM) is utilized to further improve feature representation and enhance the neural network model’s accuracy. Lastly, to address the uncertainty of geometric features in side-scan sonar target features, this paper innovatively incorporates a feature scaling factor into the YOLOv7 model. The experiment initially verified the necessity of attention mechanisms in the public dataset. Subsequently, experiments on our side-scan sonar (SSS) image dataset show that the improved YOLOv7 model has 87.9% and 49.23% in its average accuracy (mAP0.5) and (mAP0.5:0.95), respectively. These results are 9.28% and 8.41% higher than the YOLOv7 model. The improved YOLOv7 algorithm proposed in this paper has great potential for object detection and the recognition of side-scan sonar images.

29 September 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
CCchensheng cheng
chensheng cheng
XHXujia Hou
Xujia Hou
XWXin Wen
Xin Wen
Weidong LiuWeidong Liu
Weidong Liu
FZFeihu Zhang
Feihu Zhang
Underwater target detection technology plays a crucial role in the autonomous exploration of underwater vehicles. In recent years, significant progress has been made in the field of target detection through the application of artificial intelligence technology. Effectively applying AI techniques to underwater target detection is a highly promising area of research. However, the difficulty and high cost of underwater acoustic data collection have led to a severe lack of data, greatly restricting the development of deep-learning-based target detection methods. The present study is the first to utilize diffusion models for generating underwater acoustic data, thereby effectively addressing the issue of poor detection performance arising from the scarcity of underwater acoustic data. Firstly, we place iron cylinders and cones underwater (simulating small preset targets such as mines). Subsequently, we employ an autonomous underwater vehicle (AUV) equipped with side-scan sonar (SSS) to obtain underwater target data. The collected target data are augmented using the denoising diffusion probabilistic model (DDPM). Finally, the augmented data are used to train an improved YOLOv7 model, and its detection performance is evaluated on a test set. The results demonstrate the effectiveness of the proposed method in generating similar data and overcoming the challenge of limited training sample data. Compared to models trained solely on the original data, the model trained with augmented data shows a mean average precision (mAP) improvement of approximately 30% across various mainstream detection networks. Additionally, compared to the original model, the improved YOLOv7 model proposed in this study exhibits a 2% increase in mAP on the underwater dataset.

20 May 2024 in IEEE Journal of Oceanic Engineering
Verified
Journal Article
Closed access
XWXin Wen
Xin Wen
FZFeihu Zhang
Feihu Zhang
CCChensheng Cheng
Chensheng Cheng
XHXujia Hou
Xujia Hou
Guang PanGuang Pan
Guang Pan
Side-scan sonar (SSS) plays a crucial role in underwater exploration. Autonomous analysis of SSS images is vital for detecting unknown targets in underwater environments. However, due to the complexity of the underwater environment, few highlighted areas of the target, blurred feature details, and the difficulty of collecting data from SSS, achieving high-precision autonomous target recognition in SSS images is challenging. This article solves this problem by improving the You Only Look Once v7 (YOLOv7) model to achieve high-precision object detection in SSS images. First, we enhance and enlarge real and experimental images using the denoising–diffusion model to establish a self-made SSS image data set, as there are data pictures of the detection target in the SSS images obtained from real experiments. Since the SSS image has large areas without targets, this article introduces a vision transformer (ViT) for dynamic attention and global modeling, which improves the model's weight in the target region. Second, the convolutional block attention module is adopted to further improve the feature expression ability and reduce floating-point operations. Finally, this article uses Scylla-Intersection over Union as the loss function to increase the accuracy of the model's inference. Experiments on the SSS image data set demonstrate that the improved YOLOv7 model outperforms other technologies, with an average accuracy (mAP0.5) and (mAP0.5:0.95) of 78.00% and 48.11%, respectively. These results are 3.47% and 2.9% higher than the YOLOv7 model. The improved YOLOv7 algorithm proposed in this article has great potential for object detection and recognition of SSS images.

Verified
Journal Article
Open access
PDF file
CCchensheng cheng
chensheng cheng
XHXujia Hou
Xujia Hou
CWCan Wang
Can Wang
XWXin Wen
Xin Wen
Weidong LiuWeidong Liu
Weidong Liu
FZFeihu Zhang
Feihu Zhang
Accurate underwater target detection is crucial for the operation of autonomous underwater vehicles (AUVs), enhancing their environmental awareness and target search and rescue capabilities. Current deep learning-based detection models are typically large, requiring substantial storage and computational resources. However, the limited space on AUVs poses significant challenges for deploying these models on the embedded processors. Therefore, research on model compression is of great practical importance, aiming to reduce model parameters and computational load without significantly sacrificing accuracy. To address the challenge of deploying large detection models, this paper introduces an automated pruning method based on dependency graphs and successfully implements efficient pruning on the YOLOv7 model. To mitigate the accuracy degradation caused by extensive pruning, we design a hybrid distillation method that combines output-based and feature-based distillation techniques, thereby improving the detection accuracy of the pruned model. Finally, we deploy the compressed model on an embedded processor within an AUV to evaluate its performance. Multiple experiments confirm the effectiveness of our proposed method in practical applications.

20 May 2025 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
XWXin Wen
Xin Wen
CCChensheng Cheng
Chensheng Cheng
LLLu Li
Lu Li
FZFeihu Zhang
Feihu Zhang
GPGuang Pan
Guang Pan

Verified
Journal Article
Open access
PDF file
DYDianyu Yang
Dianyu Yang
JYJingfeng Yu
Jingfeng Yu
CWCan Wang
Can Wang
CCChensheng Cheng
Chensheng Cheng
GPGuang Pan
Guang Pan
FZFeihu Zhang
Feihu Zhang
In the realm of underwater environment detection, achieving information matching stands as a pivotal step, forming an indispensable component for collaborative detection and research in areas such as distributed mapping. Nevertheless, the progress in studying the matching of underwater side-scan sonar images has been hindered by challenges including low image quality, intricate features, and susceptibility to distortion in commonly used side-scan sonar images. This article presents a comprehensive overview of the advancements in underwater sonar image processing. Building upon the novel SchemaNet image topological structure extraction model, we introduce a feature matching model grounded in side-scan sonar images. The proposed approach employs a semantic segmentation network as a teacher model to distill the DeiT model during training, extracting the attention matrix of intermediate layer outputs. This emulates SchemaNet’s transformation method, enabling the acquisition of high-dimensional topological structure features from the image. Subsequently, utilizing a real side-scan sonar dataset and augmenting data, we formulate a matching dataset and train the model using a graph neural network. The resulting model demonstrates effective performance in side-scan sonar image matching tasks. These research findings bear significance for underwater detection and target recognition and can offer valuable insights and references for image processing in diverse domains.