检索结果-内蒙古大学图书馆

Biomedical image segmentation algorithm based on dense atrous convolution

MATHEMATICAL BIOSCIENCES AND ENGINEERING 2024年第3期21卷 4351-4369页

作者： Li, Hong'an Liu, Man Fan, Jiangwen Liu, Qingfang Xian Univ Sci & Technol Coll Comp Sci & Technol Xian 710054 Peoples R China Shijiazhuang Posts & Telecommun Tech Coll Informat Ctr Ctr Management Shijiazhuang 050021 Peoples R China Beihang Univ State Key Lab Virtual Real Technol & Syst Beijing 100191 Peoples R China

Biomedical images have complex tissue structures, and there are great differences between images of the same part of different individuals. Although deep learning methods have made some progress in automatic segmentation of biomedical images, the segmentation accuracy is relatively low for biomedical images with significant changes in segmentation targets, and there are also problems of missegmentation and missed segmentation. To address these challenges, we proposed a biomedical image segmentation method based on dense atrous convolution. First, we added a dense atrous convolution module (DAC) between the encoding and decoding paths of the U -Net network. This module was based on the inception structure and atrous convolution design, which can effectively capture multi -scale features of images. Second, we introduced a dense residual pooling module to detect multi -scale features in images by connecting residual pooling blocks of different sizes. Finally, in the decoding part of the network, we adopted an attention mechanism to suppress background interference by enhancing the weight of the target area. These modules work together to improve the accuracy and robustness of biomedical image segmentation. The experimental results showed that compared to mainstream segmentation networks, our segmentation model exhibited stronger segmentation ability when processing biomedical images with multiple -shaped targets. At the same time, this model can significantly reduce the phenomenon of missed segmentation and missegmentation, improve segmentation accuracy, and make the segmentation results closer to the real situation.

关键词： biomedical image segmentation deep learning dense atrous convolution dense residual pooling multi-scale features attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A lightweight deep learning model for real-time rectangle NdFeB surface defect detection with high accuracy on a global scale

引用

JOURNAL OF real-time image processing 2025年第1期22卷 1-13页

作者： Huang, Lin Yuan, Heping Chen, Shuixuan Zhou, Bo Guo, Yihuang Xiamen Univ Technol Sch Mech & Automot Engn Xiamen 361024 Fujian Peoples R China Anjierui Robot Co LTD Gen Managers Off Xiamen 361023 Fujian Peoples R China

To solve the problem that it is difficult to detect dynamic tiny square neodymium-iron-boron (NdFeB) surface defects in the case of limited computing resources, this paper proposes a square NdFeB magnet surface defect detection method based on the YOLO (YOLOv8-FCW) lightweight network. Initially, the lightweight global adaptive feature enhancement module (DFNet) network is used as the backbone feature extraction net-work. By customizing the depth of the feature matrix and reducing unnecessary branch structures, the model complexity is reduced while enhancing the network's ability to extract multi-scale feature information. Subsequently, the deformable convolution module (DCNv3) is utilized to acquire twice downsampling feature maps without information loss, aiming to expand the receptive field for small-sized defects. Finally, to further improve detection accuracy, the Wise-IOU (WIOU) v3 bounding box loss function is introduced to focus on the samples that are difficult to identify and reduce the gradient penalty for low-quality samples. The experimental results show that the YOLOv8-FCW algorithm achieves a mean Average Precision (mAP@0.5) of 78.6% on the rectangle NdFeB magnet dataset, with a model parameter quantity and computational cost reduction of 33.2% and 24.7%, respectively compared with the baseline, and requires less computational resources for higher detection accuracy compared to other mainstream object detection algorithms. Finally, the model was deployed to industrial Automated Optical Inspection (AOI) devices using TensorRT. This deployment reduced the inference time for a single image to 2.7 ms and increased speed by 6.6 times, enabling dynamic micro-detection of surface defects in square NdFeB.

关键词： Defect detection NdFeB magnet YOLOv8 Lightweight network DFNet TensoRT

来源：评论

学校读者我要写书评

暂无评论

deep learning for real-time Satellite Pose Estimation on Tensor processing Units

引用

JOURNAL OF SPACECRAFT AND ROCKETS 2023年第3期60卷 1034-1038页

作者： Lotti, Alessandro Modenini, Dario Tortora, Paolo Saponara, Massimiliano Perino, Maria A. Univ Bologna Dept Ind Engn Alma Mater Studiorum I-47121 Forli Italy Univ di Bologna Interdept Ctr Ind Res Aerosp Alma Mater Studiorum I-47121 Forli Italy Thales Alenia Space Italia Nav & Control Dept I-10146 Turin Italy Thales Alenia Space Italia Space Econ Explorat & Int Network I-10146 Turin Italy

来源：评论

学校读者我要写书评

暂无评论

PDSE-YOLOv8: a lightweight detection method for internal defects in asphalt roads

引用

SIGNAL image AND VIDEO processing 2024年第12期18卷 8925-8936页

作者： Li, Ning Zhang, Wenliang Liu, Zhaoxu Liu, Kaifeng Wang, Junjie Zhang, Fan Ocean Univ China Dept Civil Engn Qingdao 266100 Peoples R China Shandong Hispeed Grp Co Ltd Innovat Res Inst Jinan 250014 Peoples R China Shandong Hispeed Engn Test CO LTD Jinan 250014 Peoples R China BIM Res Inst China Construct Engn Div 8 Shanghai 200112 Peoples R China

Ground penetrating radar (GPR) is an effective tool for detecting internal defects in asphalt roads due to its non-destructive nature and high resolution. However, detecting defects in GPR images remains challenging, as existing models lack sufficient accuracy and are often complex and redundant. To address these issues, a lightweight real-time detection method based on ground-penetrating radar is proposed in this study. First, a field GPR image dataset of asphalt roads was collected and constructed. To address the limited defect sample data acquired by GPR, an efficient copy-and-paste augmentation method was employed. This method involved copying and pasting defect samples in GPR images while incorporating random scale jitter and position migration operations to generate a sufficient number of real defect samples. Second, the C2f-DSConv module and the SE attention mechanism were designed and introduced based on the YOLOv8 network to improve detection accuracy in the complex background environment of GPR images. Finally, a channel pruning strategy was used to prune the improved YOLOv8 network, reducing model complexity while maintaining detection accuracy. The final model achieves an average detection accuracy of 90.9% and a detection speed of 140.9 FPS. The results show that the proposed method combines both detection accuracy and real-time performance, further advancing the engineering application of internal defect detection in asphalt roads.

关键词： image processing deep learning algorithm Asphalt pavement Internal defect Channel pruning Ground penetrating radar (GPR)

来源：评论

学校读者我要写书评

暂无评论

SST-YOLOv5s: advancing real-time blood cell object detection through multi-headed attention mechanism

引用

SIGNAL image AND VIDEO processing 2025年第3期19卷 1-17页

作者： Zhang, Mingyu Chen, Jiaqing Xiamen Univ Wang Yanan Inst Studies Econ Xiamen 361005 Peoples R China Wuhan Univ Technol Coll Math & Stat Wuhan 430070 Peoples R China

An important method of diagnosing diseases in medicine is the examination of blood samples in which the blood cells in the blood sample are examined. To address the challenges of detecting small and variable blood cells in real-time, we introduce a small-target Swin Transformer YOLOv5s model named SST-YOLOv5s in this study. Based on YOLOv5s, the small object detection layer is added to enhance the feature extraction capability of YOLOv5s and improve the detection of small targets in the dataset. In this way, the C3 module is replaced by the Swin Transformer Blocks, which enhances the extraction of global information from the model as well as speeds up the computation of the model. Subsequently, considering the need for the testing speed of the model, Simplify Optimal Transport Assignment is used in this research to reduce the testing time of the model greatly. The experimental results demonstrate that compared with the baseline model of YOLOv5s, the SST-YOLOv5s model achieves a mAP0.5 of 93.0%, a mAP0.5:0.95 of 60.4%, and a Latency of 0.6. To the best of our knowledge, SST-YOLOv5s is the first YOLOv5s to add Swin Transformer and SimOTA to a small-target detection head and use it to detect cells and further proves that SST-YOLOv5s can be better applied in practical medical applications.

关键词： deep learning Medical image process Blood cell YOLOv5s Object detection

来源：评论

学校读者我要写书评

暂无评论

The functionality and features of AI automated detector and counter, Oto-BaCTM for bagworm census in oil palm plantation

引用

INDIAN JOURNAL OF ENGINEERING AND MATERIALS SCIENCES 2024年第6期31卷 914-921页

作者： Ahmad, Mohd Najib Shariff, Abdul Rashid Mohamed Moslim, Ramle Malaysian Palm Oil Board PersiaranInst 6 Bandar BaruBangi Kajang 43600 Selangor Malaysia Univ Putra Malaysia Fac Engn Serdang 43400 Selangor Malaysia

In Malaysia, the bagworm species Metisa plana Walker (Lepidoptera: Psychidae) has been recognized as one of the major insect pests attacking oil palm. Bagworm attacks, if left untreated, have contributed to up to 43% yield loss, and in 2020, the loss of fresh fruit bunches due to these attacks has been chronicled at approximately RM 180 million. Due to this critical situation, it has become compulsory to frequently monitor bagworm infestations in affected areas. Manual census methods, involving the counting of bagworm populations on fronds, have often yielded imprecise data due to human errors, such as overestimating or fabricating data, which have hindered the planning of effective control actions in infested areas. Recognizing the necessity for improved census operations and outcomes, this technology has aimed to create and implement a specialized machine vision system incorporating image processing algorithms tailored to its functions. The device, known as the Automated Bagworm Counter or trademarked as Oto-BaC (TM), has stood as the world's inaugural prototype in its category. The software has been configured to operate through Graphic processing Unit (GPU) computation with the TensorFlow/Teano library, utilizing a trained dataset. Oto-BaC (TM) has employed a standard camera and self-designed deep learning (DL) algorithms, encompassing motion tracking and false color analysis, to identify both living and deceased larvae and pupae of M. plana. It has further tallied the respective populations of living and deceased larvae and pupae per frond, classifying them into three primary groups or sizes. This automated device has proven to be straightforward, precise, and user-friendly for bagworm detection and counting on palm leaflets. The technology has relied on advanced deep learning with Faster R-CNN methodology for real-time object detection. Although the instrument has not undergone enumeration testing, it has been crafted to augment bagworm counting efficiency in

关键词： AI automated counter Bagworm infestations Census deep learning Precise

来源：评论

学校读者我要写书评

暂无评论

Batched-image detection model and deployment method for tunnel lining defects using line-scan cameras based on experiments study

引用

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY 2023年 142卷

作者： Qin, Shaojie Qi, Taiyue Lei, Bo Huang, Xiaodong Minist Educ Key Lab Transportat Tunnel Engn Chengdu Peoples R China Southwest Jiaotong Univ Sch Civil Engn Chengdu Peoples R China Guangzhou Metro Construct Management Co Ltd Guangzhou Peoples R China

High-performance line-scan cameras are highly accurate and efficient for tunnel detection, however, the exponential growth of image data creates new challenges for real-time image processing. The inference speed of existing tunnel detection algorithms is insufficient for massive amounts of image data, and traditional data structures limit the parallelism of the detection system, thereby reducing the speed of image processing. In this study, a deep learning (DL) network is developed for real-time tunnel defect detection based on the you only look once (YOLO) family. The network includes innovative defect feature-extraction modules, optimization of the network architecture, and improvement of the decoupling heads to increase defect detection accuracy and efficiency. Furthermore, we developed critical technologies for real-time detection. First, our method employs a deployment method for DL networks based on TensorRT, which enables our network to be applied directly to C++ image acquisition programs away from the traditional DL frameworks. The proposed line-scan data structure enables the raw images to be fed into the neural network in batches, which, combined with the simultaneous technique of image acquisition, detection, and storage, significantly increases the efficiency of realtime detection. The paper demonstrates the advantages of the proposed model and hardware system through an experiment study. The test results indicate that the mean average precision and F1-score of our network were 86.07% and 84.53%, respectively, while it had 21.42 M parameters. Combined with the proposed storage strategy, a recall rate of more than 90% was achieved for defect detection. Moreover, batch image processing method has a significant advantage in terms of inference speed, with 243.9 FPS in PyTorch, 381.46 FPS in TensorRT, and 305.3 FPS in real-time detection, which is five times faster than existing defect-detection models. This study significantly increases the efficiency of tu

关键词： Tunnel defect detection real -time detection Machine vision YOLO TensorRT Structural health monitoring

来源：评论

学校读者我要写书评

暂无评论

MS-DETR: a real-time multi-scale detection transformer for PCB defect detection

引用

SIGNAL image AND VIDEO processing 2025年第3期19卷 1-15页

作者： Ji, Li Huang, Chaohang Li, Haiwei Han, Wenjie Yi, Leiye Shenyang Aerosp Univ Minist Educ Coll Mech & Elect Engn Key Lab Rapid Dev & Mfg Technol Aircraft Shenyang Peoples R China Shenyang Aircraft Corp Shenyang Peoples R China

Surface defects on printed circuit boards degrade product quality and impact device performance, stability, and reliability. Accurately identifying these defects amidst a complex background is challenging due to the compact PCB layout. To address this, we propose the Multi-Scale Detection Transformer (MS-DETR), designed to enhance detection accuracy while maintaining efficiency for resource-constrained environments. MS-DETR introduces a Multi-Stage Convolution module to replace traditional convolution layers, enhancing feature extraction for small objects while reducing model complexity. The Slim-Scale Adaptive Fusion architecture, incorporating Ghost Squeeze-and-Excitation Convolution and Scale Adaptive Fusion modules, reduces network computation and enhances semantic information extraction. Additionally, integrating high-frequency and low-frequency (Hilo) information improves fine-grained feature extraction and focuses on critical features, while Inner Generalized Intersection over Union optimizes the loss function to accelerate convergence and enhance detection accuracy. Experimental results on a PCB defect dataset and a self-constructed dataset show that MS-DETR achieves a mean Average Precision of 96.90%, reducing arithmetic operations by 11.7 GFLOPs and parameter count by 5.9 M compared to real-time Detection Transformer, while maintaining a detection speed of 115 frames per second. These attributes make MS-DETR suitable for edge systems or embedded devices, balancing accuracy, computational cost, and speed effectively.

关键词： deep learning real-time detection transformer Printed circuit board Defect detection Small object detection

来源：评论

学校读者我要写书评

暂无评论

deep learning solutions for audio event detection in a swine barn using environmental audio and weak labels

引用

APPLIED INTELLIGENCE 2025年第7期55卷 1-12页

作者： Souza, Andre Moreira Kobayashi, Livia Lissa Tassoni, Lucas Andrietta Garbossa, Cesar Augusto Pospissil Ventura, Ricardo Vieira de Sousa, Elaine Parros Machado Univ Sao Paulo Inst Math & Comp Sci ICMC Ave Trabalhador Sao Carlense400 Ctr BR-13566590 Sao Carlos SP Brazil Univ Sao Paulo Sch Vet Med & Anim Sci FMVZ Ave Duque Caxias Norte 225 BR-13635900 Pirassununga SP Brazil

The increasing demand for animal protein products has led to the emergence of Precision Livestock Farming (PLF) and the adoption of sensing technologies, big data solutions, and Machine learning (ML) methods in modern livestock farming. At the same time, the audio signal processing field has undergone notable advancements in recent years, transitioning from traditional techniques to more sophisticated ML approaches, with open challenges in detecting and classifying complex, low-quality, and overlapping sounds in real-world scenarios. In this paper, we evaluate deep learning methods, conceived from computer vision to attention-based approaches, for Audio Event Detection (AED) on a novel audio dataset from a swine farming environment with challenging characteristics, such as weak annotations and high amounts of noise. The primary purpose of our study is to prospect effective AED solutions for the development of tools for auditing livestock farms, which could be used to improve animal welfare. Our results show that, despite inherent limitations in the dataset's size, class imbalance, and sound quality, Convolutional Neural Network (CNN) and attention-based architectures are respectively effective and promising for detecting complex audio events. Further research may explore avenues for optimizing model performance in similar, real-life datasets while simultaneously amplifying annotated events and reducing annotation costs, thereby enhancing the broader applicability of AED methods in diverse audio processing scenarios.

关键词： AED Audio classification Machine learning Computer vision Precision livestock farming Weak annotations

来源：评论

学校读者我要写书评

暂无评论

Automated Recognition of Hand Gestures From Multichannel EMG Sensor Data Using time-Frequency Domain deep learning for IoT Applications

IEEE SENSORS LETTERS

引用

IEEE SENSORS LETTERS 2024年第6期8卷 1页

作者： Mohapatra, Amlan deep Aggarwal, Amol Tripathy, Rajesh Kumar BITS Pilani Dept Elect & Elect Engn Hyderabad Campus Hyderabad 500078 India BITS Pilani Dept Pharm Pilani Campus Pilani 333031 India

The automated recognition of hand gestures from multicha- nnel electromyogram (MEMG) sensor data is essential for human-computer interaction, prosthetic control, rehabilitation, and biometric-related applications. This letter proposes a time-frequency domain deep neural network (TFDDNN)-based approach to recognize hand gestures using MEMG recordings. The MEMG recordings are segmented into frames, and the average of all channel information (mean EMG signal) for each frame is evaluated. The continuous wavelet transform is applied to the mean EMG signal to obtain the joint time-frequency representation (TFR). The TFR-based image of the mean EMG signal is used as the input to a deep representation learning network (DRLN) model to recognize hand gestures. Two publicly available databases are utilized to evaluate the performance of the proposed TFDDNN approach. The results show that the proposed TFDDNN has obtained overall accuracy values of 92.73% and 80.33% using MEMG signals from database 1 and database 2 for multiclass-based recognition of hand gestures. The suggested DRLN model has demonstrated higher accuracy for automated hand gesture recognition than existing deep-learning-based methods. We have deployed the proposed TFDDNN approach in a web application for Internet of Things (IoT)-enabled real-time recognition of hand gestures using MEMG sensor data.

关键词： Databases Electromyography Solid modeling Sensors Recording Continuous wavelet transforms Gesture recognition Sensor signal processing accuracy continuous wavelet transform (CWT) deep representation learning electromyogram (EMG) hand gestures Internet of Things (IoT)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：