检索结果-内蒙古大学图书馆

BFBE-Net: deep bilateral fusion and bilateral embedded network for real-time semantic segmentation

JOURNAL OF ELECTRONIC IMAGING 2023年第4期32卷 043031-043031页

作者： Hou, Zhiqiang Cheng, Minjie Dai, Nan Ma, Sugang Yang, Xiaobao Fan, Jiulun Xian Univ Posts & Telecommun Inst Comp Xian Peoples R China Xian Univ Posts & Telecommun Shaanxi Key Lab Network Data Anal & Intelligent P Xian Peoples R China

Real-time semantic segmentation has been challenging, and the fusion of features from different branches remains crucial to improvement. The two-branch structure has shown promising results in real-time semantic segmentation. However, upsampling feature maps from the semantic branch to match the detail branch leads to a loss of object feature information and compromises segmentation accuracy. We propose a deep bilateral fusion and bilateral embedded network (BFBE-Net) based on the encoder-decoder structure for real-time semantic segmentation to address these issues. The BFBE-Net adopts a two-branch design in the encoder, with a top-down fusion module and a bottom-up fusion module designed to integrate multi-scale context information in the channel dimension, and assigns different weights to detailed information and semantic information to enhance information characteristics. In the decoder, a bilateral embedded attention module under the guidance of spatial and channel attention integrates semantic and spatial features, gradually upsampling feature maps to reduce the loss of feature information. In addition, an enhanced aggregation pyramid pooling module is designed to efficiently extract contextual information by combining depth-wise asymmetric convolution. The proposed algorithm is evaluated on two benchmark datasets, Cityscapes and CamVid, achieving 78.5% mean intersection over union (mIoU) at 82 frames per second (FPS) on the Cityscapes test set and 79.2% mIoU at 131 FPS on the CamVid test set. The proposed BFBE-Net not only improves segmentation accuracy but also ensures real-time performance.

关键词： real-time semantic segmentation convolutional neural network encoder-decoder structure two-branch structure feature fusion

来源：评论

学校读者我要写书评

暂无评论

SSLIDE: SOUND SOURCE LOCALIZATION FOR INDOORS BASED ON DEEP LEARNING

SSLIDE: SOUND SOURCE LOCALIZATION FOR INDOORS BASED ON DEEP ...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Wu, Yifan Ayyalasomayajula, Roshan Bianco, Michael J. Bharadia, Dinesh Gerstoft, Peter Univ Calif San Diego La Jolla CA 92093 USA

ISBN: (纸本)9781728176055

This paper presents SSLIDE, Sound Source Localization for Indoors using DEep learning, which applies deep neural networks (DNNs) with encoder-decoder structure to localize sound sources with random positions in a continuous space. The spatial features of sound signals received by each microphone are extracted and represented as likelihood surfaces for the sound source locations in each point. Our DNN consists of an encoder network followed by two decoders. The encoder obtains a compressed representation of the input likelihoods. One decoder resolves the multipath caused by reverberation, and the other decoder estimates the source location. Experiments based on both the simulated and experimental data show that our method can not only outperform multiple signal classification (MUSIC), steered response power with phase transform (SRP-PHAT), sparse Bayesian learning (SBL), and a competing convolutional neural network (CNN) approach in the reverberant environment but also achieve a good generalization performance.

关键词： Indoor sound source localization multipath encoder-decoder structure deep neural networks

来源：评论

学校读者我要写书评

暂无评论

MatTrip: Multi-functional Attention-based Neural Network for Semantic Travel Route Recommendation

MatTrip: Multi-functional Attention-based Neural Network for...

引用

IEEE International Conference on Web Services (ICWS) / IEEE World Congress on Services (IEEE SERVICES)

作者： Yang, Chenxiao Zhang, Jiale Gao, Xiaofeng Chen, Guihai Shanghai Jiao Tong Univ MoE Key Lab Artificial Intelligence Dept Comp Sci & Engn Shanghai Peoples R China

ISBN: (纸本)9781665416818

Travel route recommendation aims to recommend a sequence of point of interests (POIs) for visitors based on their personal interests. Previous studies utilize user interest features and POI spatial information to provide travel route recommendation service. However, most of them fail to consider the implicit information in user traveling patterns, which is the key to improve recommendation quality. Additionally, few deep learning based travel route recommendation systems provide comprehensive trip planning functionalities, which is critical to improve the user experience. To alleviate these two problems, we propose a multi-functional attention-based neural network for route recommendation (named MatTrip). We first introduce an encoder-decoder structure with a novel dual bi-directional LSTM encoder as the sequence generation model to learn other users' traveling records and generates a semantic travel route based on user preference and geographical features of start/end POI. Next, multiple user-specific functionalities are supported in MatTrip by grid beam search. The functionalities include weather dependency, POI opening hours, restricted sequence length, mandatory POIs, and dynamic route revision. In addition, MatTrip adopts an online learning approach to learn from user deviation behaviors to improve recommendation performance. Experiments on two real-world datasets show that our model achieves a 20.98% improvement in performance, compared with state-of-arts.

关键词： Travel Route Recommendation POI Recommendation encoder-decoder structure Grid Beam Search

来源：评论

学校读者我要写书评

暂无评论

Progressive Guidance Edge Perception Network for Semantic Segmentation of Remote-Sensing Images

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2022年 19卷

作者： Pan, Shaoming Tao, Yulong Chen, Xiaoshu Chong, Yanwen Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430079 Peoples R China

Remarkable improvements have been seen in the semantic segmentation of remote-sensing images. As an effective structure to aggregate shallow information and deep information, encoder-decoder structure has been widely used in many state-of-the-art models, but it possesses two drawbacks that have not been fully addressed. On the one hand, encoder-decoder structure fuses the features obtained from shallow and deep layers directly;despite harvesting some detailed information, it also brings in noisy features owing to the poor discriminant ability of the shallow layers. On the other hand, existing encoder-decoder structure merely fuses the high-level information generated by the last layer of encoder once, which neglects its guidance ability to the feature aggregation process in the decoder. In this letter, we first propose an edge perception module (EPM) to eliminate the noisy features in the shallow information, as well as enhance features' structural information. And then, we generate the most suitable guidance information adaptively for different stages in the decoder through high-level information module (HIM). Finally, we apply the guidance information to achieve feature aggregation in the feature aggregation module (FAM). Combined with EPM, HIM, and FAM, our proposed model achieves 89.5% overall accuracy (OA) on the challenging ISPRS Vaihingen test set, which is the new state-of-the-art in the semantic segmentation of remote-sensing images.

关键词： Semantics Convolution Noise measurement Remote sensing Image segmentation Feature extraction Decoding encoder-decoder structure high-level information noisy features remote-sensing images semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Synergistic data fusion of satellite observations and in-situ measurements for hourly PM2.5 estimation based on hierarchical geospatial long short-term memory

引用

ATMOSPHERIC ENVIRONMENT 2022年 286卷

作者： Yu, Xinyu Wong, Man Sing Liu, Chun-Ho Zhu, Rui Hong Kong Polytech Univ Dept Land Surveying & Geo Informat Hong Kong Peoples R China Hong Kong Polytech Univ Res Inst Land & Space Hong Kong Peoples R China Univ Hong Kong Dept Mech Engn Hong Kong Peoples R China

PM2.5 as a primary air pollutant has adverse effects on the environment and public health. The air quality monitoring stations are distributed sparsely and unevenly, making it difficult to provide continuous and precise regional measurements, which can be supplemented by satellite observations. However, most satellite-based approaches for air pollution estimation are difficult to extract the spatio-temporal dependencies effectively, leading to lower accuracy in long-term prediction and assessment of episodic changes. To fill this gap, a hierarchical geospatial long short-term memory method (HG-LSTM) by considering the geospatial autocorrelation was proposed for hourly PM2.5 estimation with 2-km spatial resolution in Yangtze River Delta (YRD) urban agglomeration. The superior accuracy of the HG-LSTM is compared with other models via the site-based and year-based cross-validation (CV) tests, indicating geospatial autocorrelation exerts non-negligible impacts on the PM2.5 estimation. The estimations are consistent with the in-situ observations with site-based CV R-2 of 0.88. The deviations less than 10 mu g/m(3) account for over 80%. The PM2.5 spatiotemporal characteristics in the YRD reveal that PM2.5 concentrations are higher in the morning and decline significantly in the afternoon. As well, elevated PM2.5 values are accumulated in the northern regions of the study area. Although the prediction accuracy decreases as the augment of prediction timesteps, the results can still be useful to detect air pollution changes in the near future. Overall, the HG-LSTM model can estimate hourly PM2.5 concentrations accurately and seamlessly, which is beneficial for air pollution monitoring and environmental protection strategy formation.

关键词： PM2.5 HG-LSTM Geospatial autocorrelation encoder-decoder structure

来源：评论

学校读者我要写书评

暂无评论

Strip Attention Networks for Road Extraction

引用

REMOTE SENSING 2022年第18期14卷 4516-4516页

作者： Huan, Hai Sheng, Yu Zhang, Yi Liu, Yuan Nanjing Univ Informat Sci & Technol Sch Artificial Intelligence Nanjing 210044 Peoples R China Nanjing Univ Informat Sci & Technol Sch Elect & Informat Engn Nanjing 210044 Peoples R China Nanjing Nanji Intelligent Agr Machinery Technol R Nanjing 210008 Peoples R China

In recent years, deep learning methods have been widely used for road extraction in remote sensing images. However, the existing deep learning semantic segmentation networks generally show poor continuity in road segmentation due to the high-class similarity between roads and buildings surrounding roads in remote sensing images, and the existence of shadows and occlusion. To deal with this problem, this paper proposes strip attention networks (SANet) for extracting roads in remote sensing images. Firstly, a strip attention module (SAM) is designed to extract the contextual information and spatial position information of the roads. Secondly, a channel attention fusion module (CAF) is designed to fuse low-level features and high-level features. The network is trained and tested using the CITY-OSM dataset, DeepGlobe road extraction dataset, and CHN6-CUG dataset. The test results indicate that SANet exhibits excellent road segmentation performance and can better solve the problem of poor road segmentation continuity compared with other networks.

关键词： remote sensing image road extraction attention module encoder-decoder structure

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation using Light Attention Mechanism 15

Semantic Segmentation using Light Attention Mechanism

引用

15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) / 15th International Conference on Computer Vision Theory and Applications (VISAPP)

作者： Hiramatsu, Yuki Hotta, Kazuhiro Meijo Univ Nagoya Aichi Japan

ISBN: (纸本)9789897584022

Semantic segmentation using convolutional neural networks (CNN) can be applied to various fields such as automatic driving. Semantic segmentation is pixel-wise class classification, and various methods using CNN have been proposed. We introduce a light attention mechanism to the encoder-decoder network. The network that introduced a light attention mechanism pays attention to features extracted during training, emphasizes the features judged to be effective for training and suppresses the features judged to be irrelevant for each pixel. As a result, training can be performed by focusing on only necessary features. We evaluated the proposed method using the CamVid dataset and obtained higher accuracy than conventional segmentation methods.

关键词： Semantic Segmentation Attention Mechanism encoder-decoder structure

来源：评论

学校读者我要写书评

暂无评论

Multi-path connected network for medical image segmentation

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2020年 71卷 102852-102852页

作者： Wang, Dan Hu, Guoqing Lyu, Chengzhi South China Univ Technol Sch Mech & Automot Engn Guangzhou Peoples R China

In recent years, deep learning has been successfully applied to medical image segmentation. However, as the network extends deeper, the consecutive downsampling operations will lead to more loss of spatial information. In addition, the limited data and diverse targets increase the difficulty for medical image segmentation. To address these issues, we propose a multi-path connected network (MCNet) for medical segmentation problems. It integrates multiple paths generated by pyramid pooling into the encoding phase to preserve semantic information and spatial details. We utilize multi-scale feature extractor block (MFE block) in the encoder to obtain large and multi-scale receptive fields. We evaluated MCNet on three medical datasets with different image modalities. The experimental results show that our method achieves better performance than the state-of-the-art approaches. Our model has strong feature learning ability and is robust to capture different scale targets. It can achieve satisfactory results while using only 0.98 million (M) parameters. (c) 2020 Elsevier Inc. All rights reserved.

关键词： Medical image segmentation Multi-path connections Convolutional neural networks encoder-decoder structure

来源：评论

学校读者我要写书评

暂无评论

Depth image super-resolution using correlation-controlled color guidance and multi-scale symmetric network

引用

PATTERN RECOGNITION 2020年 107卷 107513-107513页

作者： Li, Tao Lin, Hongwei Dong, Xiucheng Zhang, Xiaohua Xihua Univ Sch Elect Engn & Elect Informat Chengdu 610039 Peoples R China Northwest Minzu Univ Coll Elect Engn Lanzhou 730000 Peoples R China Hiroshima Inst Technol Dept Informat Syst & Management Hiroshima 7315193 Japan

Depth image super-resolution (DISR) is an effective solution to improve the quality of depth images captured by real world low-cost cameras. In this paper, we propose a multi-scale symmetric network with the correlation-controlled color guidance block (CCGB) for DISR. The proposed network consists of two multi-scale sub-networks to respectively provide guidance and estimate depth. A symmetric unit (SU), which is a mini-encoder-decoder structure with residual learning, is designed and used as a basic network atom. The encoder part in SU aims to extract essential features, while the decoder part works to restore edge details. The way the SU processes information matches well with the textureless and sharpedge characteristics of depth images. The two sub-networks present a high-level symmetric structure connected by dense guidance links in between. Based on the correlation analyses between the two subnetworks, each guidance link will transfer information trough a CCGB designed to implement channel-wise re-weighting mechanism. The accurate color guidance from CCGB helps avoiding artifacts introduced by non-co-occurrence of depth discontinuities and color edges. Experimental results demonstrate the superiority of the proposed method over several state-of-the-art DISR works. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Depth image super-resolution Deep convolutional neural network encoder-decoder structure Color guidance Channel correlation

来源：评论

学校读者我要写书评

暂无评论

An Integrated Deep Neural Network Approach for Large-Scale Water Quality Time Series Prediction

An Integrated Deep Neural Network Approach for Large-Scale W...

引用

IEEE International Conference on Systems, Man and Cybernetics (SMC)

作者： Dong, QuanXi Lin, YongZhe Bi, Jing Yuan, Haitao Beijing Univ Technol Fac Informat Technol Beijing Peoples R China Beijing Jiaotong Univ Sch Software Engn Beijing Peoples R China New Jersey Inst Technol Dept Elect & Comp Engn Newark NJ 07102 USA

ISBN: (纸本)9781728145693

The prediction of water quality has great significance for the management of water environment and the protection of water resources. Traditional water quality prediction methods are relatively simple, and linear models are often used to predict water quality. However, such models limit the accuracy of prediction and lack the analysis of nonlinear characteristics of water quality. In addition, due to the complex water environment, the water quality time series has large noise, which makes it difficult for traditional models to effectively predict water quality indicators under complex environmental conditions. To solve this problem, this work proposes an integrated prediction method that combines Savitzky-Golay filter with Long Short-Term Memory (LSTM)-based encoder-decoder neural network to predict water quality at the next time interval. In this approach, the water quality time series is first smoothed by Savitzky-Golay filter, and LSTM can extract valid information from complex time series. Based on them, an integrated model is for the first time established and can well characterize statistical characteristics. Experimental results demonstrate that it achieves better prediction results than some typical prediction methods.

关键词： Water quality prediction LSTM encoder-decoder structure Savitzky-Golay filter water environment

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：