检索结果-内蒙古大学图书馆

Deep convolutional neural networks for semantic segmentation of cracks

STRUCTURAL CONTROL & HEALTH MONITORING 2022年第1期29卷 e2850-e2850页

作者： Wang, Jia-Ji Liu, Yu-Fei Nie, Xin Mo, Y. L. Tsinghua Univ Dept Civil Engn Beijing 100084 Peoples R China Univ Houston Dept Civil & Environm Engn Houston TX 77204 USA

A large crack detection dataset of 2446 manually labeled images is established to cover a wide range of noise and to evaluate the performance of end-to-end deep convolutional networks in detecting cracking. Five state-of-the-art end-to-end deep computer vision architectures for semantic segmentation are trained and evaluated, including Fully Convolutional Network (FCN), Global Convolutional Network (GCN), Pyramid Scene Parsing Network (PSPNet), UPerNet, and DeepLabv3+. For the backbones, the VGG, ResNet, and DenseNet are adopted. Based on the comparison of test set metrics, DeepLabv3+ with the ResNet101 backbone achieved the highest IoU of 0.6298, the highest recall of 0.6834, and the highest F1 score of 0.7732. The influence of database choice and image noise on crack detection performance is reported. Based on the comparison of predicted images, UperNet with ResNet101 backbone shows the highest performance for images with shadings, while DeepLabv3+ with ResNet101 backbone shows the best performance for images with blemishes. The research outcome can provide reference for the application of fast and accurate detection of cracks in civil engineering.

关键词： computer vision convolutional neural network crack deep learning encoder-decoder semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Asymmetric cross-modal activation network for RGB-T salient object detection

引用

KNOWLEDGE-BASED SYSTEMS 2022年 258卷

作者： Xu, Chang Li, Qingwu Zhou, Qingkai Jiang, Xiongbiao Yu, Dabing Zhou, Yaqin Hohai Univ Coll Internet Things Engn Changzhou 213022 Jiangsu Peoples R China Hohai Univ Jiangsu Key Lab Power Transmiss & Distribut Equipm Changzhou 213022 Jiangsu Peoples R China

RGB-thermal salient object detection (RGB-T SOD) has unique advantages in terms of handling challenging scenes with cluttered backgrounds, low illumination, and low contrast. However, because they do not consider the significant differences between different imaging mechanisms and inherent characteristics of thermal images, existing RGB-T SOD methods are generally unable to handle diverse feature fusion demands and may yield unsatisfactory performance. To overcome this problem and achieve more effective RGB-T SOD, we propose an asymmetric cross-modal activation network to exploit the interactions of modality-specific features based on an asymmetric feature fusion strategy. Specifically, a two-stream asymmetric feature aggregation encoder module is proposed to fuse multimodality features adaptively and extract complementary information. The self-attention of multimodality features is leveraged to guide cross-modal interactions, which can propagate long-range contextual dependencies and extract effective saliency cues. Furthermore, a multitask decoder is proposed to achieve SOD and thermal image reconstruction in a unified framework. Salient objects can be located and segmented accurately based on reconstructed high-resolution feature representations. Extensive experiments on public RGB-T and RGB-D SOD datasets demonstrate the superiority of the proposed network and ablation experiments highlight the effectiveness of each component. Our code and saliency maps are available at: ***/xanxuso/ACMANet.(c) 2022 Elsevier B.V. All rights reserved.

关键词： RGB-T salient object detection Multimodality Feature fusion encoder-decoder Long-range dependence

来源：评论

学校读者我要写书评

暂无评论

Stroke constrained attention network for online handwritten mathematical expression recognition

引用

PATTERN RECOGNITION 2021年 119卷 108047-108047页

作者： Wang, Jiaming Du, Jun Zhang, Jianshu Wang, Bin Ren, Bo Univ Sci & Technol China Natl Engn Lab Speech & Language Informat Proc Hefei Anhui Peoples R China Tencent Youtu Lab Shenzhen Peoples R China

In this paper, we propose a novel stroke constrained attention network (SCAN) which treats stroke as the basic unit for encoder-decoder based online handwritten mathematical expression recognition (HMER). Unlike previous methods which use trace points or image pixels as basic units, SCAN makes full use of stroke-level information for better alignment and representation. The proposed SCAN can be adopted in both single-modal (online or offline) and multi-modal HMER. For single-modal HMER, SCAN first employs a CNN-GRU encoder to extract point-level features from input traces in online mode and employs a CNN encoder to extract pixel-level features from input images in offline mode, then use stroke constrained information to convert them into online and offline stroke-level features. Using stroke-level features can explicitly group points or pixels belonging to the same stroke, therefore reduces the difficulty of symbol segmentation and recognition via the decoder with attention mechanism. For multi-modal HMER, other than fusing multi-modal information in decoder, SCAN can also fuse multi-modal information in encoder by utilizing the stroke based alignments between online and offline modalities. The encoder fusion is a better way for combining multi-modal information as it implements the information interaction one step before the decoder fusion so that the advantages of multiple modalities can be exploited earlier and more adequately. Besides, we propose an approach combining the encoder fusion and decoder fusion, namely encoder-decoder fusion, which can further improve the performance. Evaluated on a benchmark published by CROHME competition, the proposed SCAN achieves the state-of-the-art performance. Furthermore, by conducting experiments on an additional task: online handwritten Chinese character recognition (HCCR), we demonstrate the generality of our proposed method. (c) 2021 Elsevier Ltd. All rights reserved.

关键词： Stroke-level information Multi-modal fusion encoder-decoder Attention mechanism Handwritten mathematical expression recognition

来源：评论

学校读者我要写书评

暂无评论

Attention-Based Convolutional LSTM for Describing Video

引用

IEEE ACCESS 2020年 8卷 133713-133724页

作者： Liu, Zhongyu Chen, Tian Ding, Enjie Liu, Yafeng Yu, Wanli China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221008 Jiangsu Peoples R China China Univ Min & Technol IOT Percept Mine Res Ctr Xuzhou 221000 Jiangsu Peoples R China Univ Bremen Inst Electrodynam & Microelect D-28359 Bremen Germany

Video description technique has been widely used in the computer community for many applications. The typical approaches are mainly based on the encode-decode framework: the fixed-length video representation vectors are extracted by the encoder using the upper layer output of pre-trained convolutional neural networks (CNNs);The decoder uses the recurrent neural networks to generate a textual sentence. However, the upper layers of convolutional neural networks contain low-resolution, semantically strong, while the lower layers contain high-resolution, semantically weak features. In the existing method, the multi-scale information of CNNs is hardly considered to be used in the video description. Ignoring this information will lead to the problem that the video description is not detailed and comprehensive. This paper applies the hierarchical convolutional long short-term memory (ConvLSTM) in the encode-decode framework to conduct feature extraction of the upper and lower layers in CNNs. Moreover, multiple network structures are designed to explore the Spatio-temporal feature extraction performance of ConvLSTM, which can approach the optimal accuracy in the three-layer ConvLSTM. In order to efficiently improve the language quality of video description, the attention mechanism focuses on visual feature output by ConvLSTM. The extensive experimental results demonstrate that the proposed method outperforms the existing approaches.

关键词： Feature extraction Visualization Decoding Task analysis Semantics Recurrent neural networks Convolution Video description long short-term memory encoder-decoder attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Dual temporal attention mechanism-based convolutional LSTM model for industrial dynamic soft sensor

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2024年第11期35卷 115103-115103页

作者： Cui, Jiarui Shi, Yuyu Huang, Jian Yang, Xu Gao, Jingjing Li, Qing Univ Sci & Technol Beijing Sch Automat & Elect Engn Beijing Peoples R China Univ Sci & Technol Beijing Shunde Innovat Sch Foshan Peoples R China

Deep learning is an appropriate methodology for modeling complex industrial data in the field of soft sensors, owing to its powerful feature representation capability. Given the nonlinear and dynamic nature of the process industry, the key challenge for soft sensor technology is to effectively mine dynamic information from long sequences and accurately extract features of relevance to quality. A dual temporal attention mechanism-based convolutional long short-term memory network (DTA-ConvLSTM) under an encoder-decoder framework is proposed as a soft sensor model to acquire quality-relevant dynamic features from serial data. Considering different influences of process variables for prediction at multiple time steps and various locations, ConvLSTM and temporal self-attention mechanism are utilized as the encoder to adaptively fuse spatiotemporal features and capture long-term dynamic properties of process in order to capture the trends of industrial variables. Furthermore, a quality-driven temporal attention mechanism is employed throughout the decoding process to dynamically select relevant features to more accurately track quality changes. The encoder-decoder model meticulously analyses the interactions between process and quality variables by incorporating dual-sequence dynamic information to improve the prediction performance. The validity and superiority of the DTA-ConvLSTM model was validated on two industrial case studies of the debutanizer column and sulfur recovery unit. Compared to the traditional LSTM model, the proposed model demonstrated a substantial improvement with the accuracy R2 up to 97.3% and 94.9% and the root mean square error reducing to 0.122 and 0.022.

关键词： dual temporal attention mechanism LSTM encoder-decoder convolutional layer soft sensor

来源：评论

学校读者我要写书评

暂无评论

Leaf vein segmentation with self-supervision

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2022年 203卷

作者： Li, Lei Hu, Wenzheng Lu, Jiang Zhang, Changshui Tsinghua Univ Inst Artificial Intelligence Beijing Natl Res Ctr Informat Sci & Technol BNRist State Key Lab Intelligent Technol & SystTsinghua Beijing Peoples R China Tsinghua Univ State Key Lab Automot Safety & Energy Beijing Peoples R China China Marine Dev & Res Ctr CMDRC Beijing Peoples R China Kuaishou Technol Co Ltd Beijing Peoples R China

The leaf vein, often viewed as the fingerprint of the leaf, is an important characteristic used to identify plant species. Leaf vein segmentation aims to extract the vein features and obtain the vein architectures from leaf images. Unlike the general semantic or instance segmentation focusing on the block and object level, the leaf vein segmentation is fine and it focuses on the internal details inside the mesophyll, whose color is indistinguishable, making this task difficult. To tackle this problem, we utilize the particularities of leaf veins, namely continuity and branching, and propose a Confidence Refining Vein Network (CoRE-Net) to segment leaf veins by handling the intersections, breakpoints, and blurred boundaries of veins to enhance segment prediction. Moreover, the proposed network only needs a few labeled samples to warm start, and then the whole network can converge without any annotated labels. Meanwhile, we collect and release the first leaf vein dataset, Leaf Vein Dataset 2021 (LVD2021). The proposed framework achieves mean Intersection over Union at 71.02% and mean Dice at 79.76% on LVD2021, which outperforms its counterparts in different settings, demonstrating the effectiveness of our framework.

关键词： Leaf vein segmentation Computer vision Self-supervision encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Sketch2Photo: Synthesizing photo-realistic images from sketches via global contexts

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第PartA期117卷

作者： Liu, Heng Xu, Yao Chen, Feng Anhui Univ Technol Maanshan 243032 Peoples R China Anhui Engn Res Ctr Intelligent Applicat & Secur In Maanshan 243032 Peoples R China

Sketch-to-image synthesis aims to generate realistic images that match the input sketches or edge maps exactly. Most known sketch-to-image synthesis methods use various generative adversarial networks (GANs) that are trained with numerous pairs of sketches and real images. Because of the convolution locality, the low-level layers of the generators in these GANs lack global perception ability, causing feature maps derived from them easily to overlook global cues. Since the global receptive field is crucial for acquiring the non-local structures and features of sketches, the absence of global contexts will impact the generation of high-quality images. Some recent models turn to self-attention to construct global dependencies. However, they are not viable for large feature maps for the quadratic computational complexity concerning the size of feature maps. To address these problems, in this work, we propose Sketch2Photo - a new image synthesis approach that can capture global contexts as well as local features to generate photo-realistic images from weak or partial sketches or edge maps. We employ fast Fourier convolution (FFC) residual blocks to create global receptive fields in the bottom layers of the network and incorporate Swin Transformer block (STB) units to obtain long-range global contexts for large-size feature maps efficiently. We also present an improved spatial attention pooling (ISAP) module to relax the strict alignment requirements between incomplete sketches and generated images. Quantitative and qualitative experiments on multiple public datasets demonstrate the superiority of the proposed approach over many other sketch-to-image synthesis methods. The project code is available at https://***/hengliusky/Skecth2Photo.

关键词： Sketch-based image synthesis Fast Fourier convolution Swin transformer encoder-decoder Global contexts

来源：评论

学校读者我要写书评

暂无评论

A Transformer-Based Bridge Structural Response Prediction Framework

引用

SENSORS 2022年第8期22卷 3100页

作者： Li, Ziqi Li, Dongsheng Sun, Tianshu Dalian Univ Technol Sch Civil Engn Dalian 116024 Peoples R China

Structural response prediction with desirable accuracy is considerably essential for the health monitoring of bridges. However, it appears to be difficult in accurately extracting structural response features on account of complex on-site environment and noise disturbance, resulting in poor prediction accuracy of the response values. To address this issue, a Transformer-based bridge structural response prediction framework was proposed in this paper. The framework contains multi-layer encoder modules and attention modules that can precisely capture the history-dependent features in time-series data. The effectiveness of the proposed method was validated with the use of six-month strain response data of a concrete bridge, and the results are also compared with those of the most commonly used Long Short-Term Memory (LSTM)-based structural response prediction framework. The analysis indicated that the proposed method was effective in predicting structural response, with the prediction error less than 50% of the LSTM-based framework. The proposed method can be applied in damage diagnosis and disaster warning of bridges.

关键词： bridge structural response prediction transformer deep learning structural health monitoring encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Improved Short-term Dense Bottleneck network for efficient scene analysis

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 2023年第1期235卷

作者： Singha, Tanmay Pham, Duc-Son Krishna, Aneesh Curtin Univ Perth WA 6102 Australia

Visual scene understanding mainly depends on pixel-wise classification obtained from a deep convolutional neural network. However, existing semantic segmentation models often face difficulties in real-time appli-cations due to their large network architecture. Although there are real-time semantic segmentation models available, their shallow backbone can degrade the performance considerably. This paper introduces SDBNetV2, a lightweight semantic segmentation model designed to improve real-time performance without increasing computational costs. A key contribution is a novel Short-term Dense Bottleneck (SDB) module in the encoder, which provides varied field-of-views to capture different geometrical objects in a complex scene. Additionally, we propose dense feature refinement and improved semantic aggregation modules at the decoder end to enhance contextualization and object localization. We evaluate the proposed model's performance on several indoor and outdoor datasets in structured and unstructured environments. The results show that SDBNetV2 achieves superior segmentation performance over other real-time models with less than 2 million parameters.

关键词： Semantic segmentation Convolutional neural network Scene understanding Real-time Machine learning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Exploration of dual-attention mechanism-based deep learning for multi-step-ahead flood probabilistic forecasting

引用

JOURNAL OF HYDROLOGY 2023年第PartB期622卷

作者： Cui, Zhen Guo, Shenglian Zhou, Yanlai Wang, Jun Wuhan Univ State Key Lab Water Resources & Hydropower Engn Sc Wuhan 430072 Peoples R China

In order to improve the flood forecasting accuracy and reflect the forecast uncertainty information in the Three Gorges Reservoir (TGR) interval-basin in China, this study integrates the feature and temporal dual-attention (DA) mechanism and recursive encoder-decoder (RED) structure into the long short-term memory (LSTM) neural network to develop a DA-LSTM-RED model. The feature attention acts on the input variables of the encoder, and the temporal attention mechanism acts on the hidden layer states extracted by the LSTM neural network during encoding process, prompting the proposed model to extract critical input information among different types and moments of input variables to improve the multi-step-ahead flood forecasting accuracy. Second, the copula-based Hydrological Uncertainty Processor (copula-HUP) is used to quantify the forecast uncertainty of the proposed model meanwhile creating multi-step-ahead flood probabilistic forecasts. Combining the long-term 6 h hydrologic data series of the Xiangjiaba-TGR interval-basin and the forecasted precipitation from the European Centre for Medium-Range Weather Forecasts (ECMWF), the effectiveness of the proposed model, the effect of forecast precipitation on multi-step-ahead flood forecasting, and the effect of different copula functions on the probabilistic forecast of copula-HUP are investigated, respectively. The results show that the DALSTM-RED model can effectively improve the forecasting accuracy for long forecast horizons (3-7d) compared to the LSTM-RED model, and the average absolute error metrics are reduced by 10%-17%. Meanwhile, the proposed model can identify input variables with a high correlation with the target output variables, which improves the interpretability of deep learning to a certain extent. The Student copula-HUP has the lowest RB and CRPS metrics than the Frank and Gaussian copula-HUP, which can better quantify the DA-LSTM-RED model's forecast uncertainty. Therefore, combining the proposed mo

关键词： Dual-attention mechanism encoder-decoder Deep learning Hydrological uncertainty processor Copula function Probabilistic forecasting

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：