检索结果-内蒙古大学图书馆

15th International Conference on Ubiquitous Information Management and Communication (IMCOM)

作者： Song, Mingue Kim, Yanggon Towson Univ Dept Comp & Informat Sci Towson MD 21252 USA

ISBN: (纸本)9781665423182

Medical image analysis is consistently being researched in the computer vision in that it captures potential symptoms and enables more delicate diagnosis of patients. Based on the development of medical equipment such as optical coherence tomography(OCT) and magnetic resonance imaging(MRI), it is possible to analyze medical data with clearer and higher resolution than before. However, there are still many data that have limitations in manually diagnosis by human. Moreover, identifying the extent of the damaged retinal layer also remains one of the most challenging tasks since the damaged layer not only contains too many invisible layers, but it is too small. Normal OCT data has smooth layers while age-related macular degeneration(AMD) or diabetic macular edema(DME), which are classified as abnormal, has layers that are damaged by bleeding. The precise regional classification is required for the diagnosis and prescription of the damaged layers and a new approach to effectively training an irregular layer of abnormal data is also needed. Hence, this paper proposes an OCT data manipulation method as a preprocessing step to improve training boundaries of regional layers. The preprocessed data were generated by manual range using the proposed method and applied to the encoder-decoder networks, SegNet and Unet. The experiment shows that the preprocessed datasets were trained much faster than the original and the optimized range was also confirmed through comparison the results of preprocessed dataset by each range.

关键词： OCT Segmentation Preprocessing encoder-decoder networks Deep learning

来源：评论

学校读者我要写书评

暂无评论

Influence of decoder size for binary segmentation tasks in medical imaging

Influence of decoder size for binary segmentation tasks in m...

引用

Medical Imaging Conference - Image Processing

作者： van der Putten, Joost van der Sommen, Fons de With, Peter H. N. Eindhoven Univ Technol Eindhoven Netherlands

ISBN: (纸本)9781510633940

Symmetric design of encoder-decoder networks is common in deep learning. For almost all segmentation problems, the output segmentation is vastly less complex compared to the input image. However, the effect of the size of the decoder on segmentation performance has not been investigated in literature. This work investigates the effect of reducing decoder size on binary segmentation performance in a medical imaging application. To this end, we propose a methodology to reduce the size of the decoder in encoder-decoder networks, where residual skip connections are employed in combination with a 1 x 1 convolution instead of concatenations (as employed by U-Net) to achieve models with asymmetric design. The results on the ISIC2017 data set show that the amount of trainable parameters in the decoder can be reduced by up to a factor 100 compared to standard U-Net, while retaining segmentation performance. Additionally, the reduced amount of trainable decoder parameters in the proposed models leads to inference times up to 3 times faster compared to standard U-Net.

关键词： skin lesions binary segmentation encoder-decoder networks model optimization

来源：评论

学校读者我要写书评

暂无评论

Learning Geometric Features for Improving the Automatic Detection of Citrus Plantation Rows in UAV Images

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2022年 19卷

作者： Cue La Rosa, Laura Elena Oliveira, Dario A. B. Zortea, Maciel Gemignani, Bruno Holtz Feitosa, Raul Queiroz IBM Res BR-22290240 Rio De Janeiro Brazil Pontifical Catholic Univ Rio de Janeiro Dept Elect Engn BR-22451900 Rio De Janeiro Brazil 3DGEO BR-80320200 Curitiba Parana Brazil

Unmanned aerial vehicles (UAVs) allow on-demand imaging of orchards at an unprecedented level of detail. The automated detection of plantation rows in the images helps in the successive analysis steps, such as the detection of individual fruit trees and planting gaps, aiding producers with inventory and planting operations. Citrus trees can be planted in curved rows that form intricate geometric patterns in aerial images, requiring robust detection approaches. While deep learning methods rank among state-of-the-art methods for segmenting images with particular geometrical patterns, they struggle to hold their performance when testing data differs much from training data (e.g., image intensity differences, image artifacts, vegetation characteristics, and landscape conditions). In this letter, we propose a method to learn geometric features of orchards in UAV images and use them to improve the detection of plantation rows. First, we train a detection encoder-decoder network (DetED) to segment planting rows in RGB images. Then, with labeled data, we train an encoder-decoder correction network (CorrED) that learns to map binary masks with spurious row segmentation geometries into corrected ones. Finally, we use the CorrED network to fix geometric inconsistencies in DetED outcome. Our experiments with commercial plantations of orange trees show that the proposed CorrED postprocessing can restore missing segments of plantation rows and improve detection accuracy in testing data.

关键词： Image segmentation Geometry Vegetation Training Testing Decoding Feature extraction encoder-decoder networks geometric patterns plantation rows detection postprocessing

来源：评论

学校读者我要写书评

暂无评论

Contextual ensemble network for semantic segmentation

引用

PATTERN RECOGNITION 2022年 122卷

作者： Zhou, Quan Wu, Xiaofu Zhang, Suofei Kang, Bin Ge, Zongyuan Latecki, Longin Jan Nanjing Univ Posts & Telecommun Natl Engn Res Ctr Commun & Networking Nanjing 21003 Peoples R China Nanjing Univ Posts & Telecommun Dept Internet Things Nanjing 21003 Peoples R China Monash Univ Monash eRes Ctr Melbourne Vic Australia Temple Univ Dept Comp & Informat Sci Philadelphia PA 19122 USA

Recently, exploring features from different layers in fully convolutional networks (FCNs) has gained sub-stantial attention to capture context information for semantic segmentation. This paper presents a novel encoder-decoder architecture, called contextual ensemble network (CENet), for semantic segmentation, where the contextual cues are aggregated via densely usampling the convolutional features of deep layer to the shallow deconvolutional layers. The proposed CENet is trained in terms of end-to-end segmenta-tion to match the resolution of input image, and allows us to fully explore contextual features through ensemble of dense deconvolutions. We evaluate our CENet on two widely-used semantic segmentation datasets: PASCAL VOC 2012 and CityScapes. The experimental results demonstrate our CENet achieves superior performance with respect to recent state-of-the-art results. Furthermore, we also evaluate CENet on MS COCO dataset and ISBI 2012 dataset for the task of instance segmentation and biological segmen-tation, respectively. The experimental results show that CENet obtains promising results on these two datasets. (c) 2021 Elsevier Ltd. All rights reserved.

关键词： Ensemble deconvolution Semantic segmentation FCNs Context aggregation encoder-decoder networks

来源：评论

学校读者我要写书评

暂无评论

Real-time Travel Time Estimation with Sparse Reliable Surveillance Information

引用

PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT 2020年第1期4卷 1-23页

作者： Zhang, Wen Wang, Yang Xie, Xike Ge, Chuancai Liu, Hengchang Univ Sci & Technol China Hefei Anhui Peoples R China Univ Elect Sci & Technol China Chengdu Sichuan Peoples R China

Origin-destination (OD) travel time estimation is of paramount importance for applications such as intelligent transportation. In this work, we propose a new solution for OD travel time estimation, with road surveillance camera data. The surveillance information supports accurate and reliable observations at camera-equipped intersections, but is associated with missing and incomplete surveillance records at the camera-free intersections. To overcome this, we propose a modified version of multi-layer graph convolutional networks. The camera surveillance data is used to extract the traffic flow of each intersection, the extracted information serves as the input of the multi-layer GCN based model, based on which the real-time traffic status can be predicted. To enhance the estimation accuracy, we address the effects of various features for the travel time estimation with encoder-decoder networks and embedding techniques. We further improve the generalization of our model by using multi-task learning. Extensive experiments on real datasets are done to verify the effectiveness of our proposals.

关键词： travel time multi-layer graph convolutional networks encoder-decoder networks embedding

来源：评论

学校读者我要写书评

暂无评论

A Sequence-to-Sequence Approach for Remaining Useful Lifetime Estimation Using Attention-augmented Bidirectional LSTM

引用

INTELLIGENT SYSTEMS WITH APPLICATIONS 2021年 10-11卷

作者： Bin Shah, Sayed Rafay Chadha, Gavneet Singh Schwung, Andreas Ding, Steven X. South Westphalia Univ Appl Sci Dept Automat Technol Luebecker Ring 2 D-59494 Soest Germany Univ Duisburg Essen Dept Automat Control & Complex Syst Bismarckstr 81 D-47057 Duisburg Germany

We propose a novel sequence-to-sequence prediction approach for the estimation of the remaining useful lifetime (RUL) of technical components. The approach is based on deep recurrent neural network structures, namely bidirectional Long Short Term Memory (LSTM) networks, which we augment with an attention mechanism to allow for a more fine-grained information flow between the input and output sequence. Using the base architecture as a reference, we experiment with various forms of attention mechanisms as well as different forms of additional input embeddings. Further, we analyse the impact of the sequence length on the estimation quality. We apply our approach to the well known C-MAPSS data set previously serving as a benchmark dataset for RUL prediction. We obtain state of the art results on the data set and provide a thorough hyperparameter study that underlines, that more simple but well tuned architecture can achieve comparable or better performance than highly complex architectures. (c) 2021 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license ( http://***/licenses/by-nc-nd/4.0/ )

关键词： Remaining useful lifetime estimation encoder-decoder networks Bidirectional long-short term memory Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Class-level Aware Network for Human Parsing

Class-level Aware Network for Human Parsing

引用

作者： Jiayi Yin Weibin Liu Weiwei Xing Yuan Xiao Institute of Information Science Beijing Jiaotong University School of Software Engineering Beijing Jiaotong University Bidding and Purchasing Management Center Renmin University of China

Having shown great performance in human parsing, convolutional neural networks(CNNs) come with much computation budget. In this paper, a novel class-level aware network(CANet), which employs an asymmetric encoder-decoder architecture, is presented to achieve reliable human parsing results in a memory friendly *** achieve the trade-off between speed and accuracy in human parsing, we design group-split-bottleneck(GS-bt) block, where group convolution and channel split are utilized in the residual block. In decoder network, the attention pyramid pooling module(APPM) is proposed to recovering the details of human parsing. Moreover, a multi-class classification branch is developed to extract class-level information and revise human parsing results. Compared to current models, our model has less parameters and experiments demonstrate that the proposed CANet can reach state-of-the-art results on PASCAL-Person-Part dataset.

关键词： human parsing encoder-decoder networks CNN

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Regularization Approach to Colonoscopic Polyp Detection Using a Cascaded Structure of encoder-decoders

引用

INTERNATIONAL JOURNAL OF FUZZY SYSTEMS 2019年第7期21卷 2091-2101页

作者： Hwang, Maxwell Wang, Da Jiang, Wei-Cheng Pan, Xiang Fu, Dongliang Hwang, Kao-Shing Ding, Kefeng Zhejiang Univ Sch Med Affiliated Hosp 2 Dept Colorectal Surg Hangzhou Zhejiang Peoples R China Zhejiang Univ Affiliated Hosp 2 China Natl Minist Educ Canc InstKey Lab Canc Prevent & Intervent Hangzhou Zhejiang Peoples R China Zhejiang Univ Affiliated Hosp 2 Key Lab Mol Biol Med Sci Sch Med Hangzhou Zhejiang Peoples R China Tunghai Univ Dept Elect Engn Taichung Taiwan Natl Sun Yat Sen Univ Dept Elect Engn Kaohsiung Taiwan

This research aims to segment colonoscopic images by automatically extracting polyp features by exploiting the strengths of convolution neural networks (CNN). The proposed model employs deep learning and adaptive regularization techniques. The model is structurally composed of two cascaded encoder-decoder networks, each of which is constructed by four CNN layers and two full connection layers. The front model is built on backpropagation learning for segmenting a colonoscopic polyp image. The output images from the precedent hetero-encoder are regarded as corrupted labeled images, especially during the time period close to the end of learning, and are selectively fed into the successive auto-encoder for denoising learning to enhance its discriminative power and relieve the problem of a lack of labeled data for medical image tasks. The performance of the proposed model can be further improved by a simple fuzzy logic approach setting the regularization parameter in the loss function. The proposed method utilizes features learned from some open medical datasets and our own collected dataset. The performance of the proposed architecture is compared with a state-of-the-art network. The evaluation shows the performances of the proposed method are consistent across all the datasets and often outperform the state-of-art model.

关键词： Convolution neural networks encoder-decoder networks Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Multi-task learning for the segmentation of organs at risk with label dependence

引用

MEDICAL IMAGE ANALYSIS 2020年 61卷 101666页

作者： He, Tao Hu, Junjie Song, Ying Guo, Jixiang Yi, Zhang Sichuan Univ Coll Comp Sci Machine Intelligence Lab Chengdu 610065 Peoples R China West China Hosp China Dept Radiotherapy Nanchong Peoples R China

Automatic segmentation of organs at risk is crucial to aid diagnoses and remains a challenging task in medical image analysis domain. To perform the segmentation, we use multi-task learning (MTL) to accurately determine the contour of organs at risk in CT images. We train an encoder-decoder network for two tasks in parallel. The main task is the segmentation of organs, entailing a pixel-level classification in the CT images, and the auxiliary task is the multi-label classification of organs, entailing an image-level multi-label classification of the CT images. To boost the performance of the multi-label classification, we propose a weighted mean cross entropy loss function for the network training, where the weights are the global conditional probability between two organs. Based on MTL, we optimize the false positive filtering (FPF) algorithm to decrease the number of falsely segmented organ pixels in the CT images. Specifically, we propose a dynamic threshold selection (DTS) strategy to prevent true positive rates from decreasing when using the FPF algorithm. We validate these methods on the public ISBI 2019 segmentation of thoracic organs at risk (SegTHOR) challenge dataset and a private medical organ dataset. The experimental results show that networks using our proposed methods outperform basic encoder-decoder networks without increasing the training time complexity. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Segmentation of organs at risk encoder-decoder networks Label dependence Multi-label classification

来源：评论

学校读者我要写书评

暂无评论

AGLNet: Towards real-time semantic segmentation of self-driving images via attention-guided lightweight network

引用

APPLIED SOFT COMPUTING 2020年 96卷

作者： Zhou, Quan Wang, Yu Fan, Yawen Wu, Xiaofu Zhang, Suofei Kang, Bin Latecki, Longin Jan Nanjing Univ Posts & Telecommun Natl Engn Res Ctr Commun & Networking Nanjing 21003 Peoples R China Nanjing Univ Posts & Telecommun Dept Internet Things Nanjing 21003 Peoples R China Temple Univ Dept Comp & Informat Sci Philadelphia PA 19122 USA

The extensive computational burden limits the usage of convolutional neural networks (CNNs) in edge devices for image semantic segmentation, which plays a significant role in many real-world applications, such as augmented reality, robotics, and self-driving. To address this problem, this paper presents an attention-guided lightweight network, namely AGLNet, which employs an encoder-decoder architecture for real-time semantic segmentation. Specifically, the encoder adopts a novel residual module to abstract feature representations, where two new operations, channel split and shuffle, are utilized to greatly reduce computation cost while maintaining higher segmentation accuracy. On the other hand, instead of using complicated dilated convolution and artificially designed architecture, two types of attention mechanism are subsequently employed in the decoder to upsample features to match input resolution. Specifically, a factorized attention pyramid module (FAPM) is used to explore hierarchical spatial attention from high-level output, still remaining fewer model parameters. To delineate object shapes and boundaries, a global attention upsample module (GAUM) is adopted as global guidance for high-level features. The comprehensive experiments demonstrate that our approach achieves state-of-the-art results in terms of speed and accuracy on three self-driving datasets: CityScapes, CamVid, and Mapillary Vistas. AGLNet achieves 71.3%, 69.4%, and 30.7% mean IoU on these datasets with only 1.12M model parameters. Our method also achieves 52 FPS, 90 FPS, and 53 FPS inference speed, respectively, using a single GTX 1080Ti GPU. Our code is open-source and available at https://***/xiaoyufenfei/Efficient-Segmentation-networks. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Robot vision Self-driving Real-time semantic segmentation Convolutional neural networks encoder-decoder networks

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：