检索结果-南通市图书馆

Deep graph cut network for weakly-supervised semantic segmentation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2021年第3期64卷 57-68页

作者： Jiapei FENG Xinggang WANG Wenyu LIU School of Electronic Information and Communications Huazhong University of Science and Technology

The scarcity of fully-annotated data becomes the biggest obstacle that prevents many deep learning approaches from widely applied. Weakly-supervised visual learning which can utilize inexact annotations is developed rapidly to remedy such a situation. In this paper, we study the weakly-supervised task achieving pixel-level semantic segmentation only with image-level labels as supervision. Different from other methods,our approach tries to transform the weakly-supervised visual learning problem into a semi-supervised visual learning problem and then utilizes semi-supervised learning methods to solve it. Utilizing this transformation,we can adopt effective semi-supervised methods to perform transductive learning with context *** the semi-supervised learning module, we propose to use the graph cut algorithm to label more supervision from the activation seeds generated from a classification network. The generated labels can provide the segmentation model with effective supervision information; moreover, the graph cut module can benefit from features extracted by the segmentation model. Then, each of them updates and optimizes the other iteratively until convergence. Experiment results on PASCAL VOC and COCO benchmarks demonstrate the effectiveness of the proposed deep graph cut algorithm for weakly-supervised semantic segmentation.

关键词： semantic segmentation weakly-supervised learning semi-supervised learning graph cut

Optimal CNN-based semantic segmentation model of cutting slope images

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Structural and Civil Engineering 2022年第4期16卷 414-433页

作者： Mansheng LIN Shuai TENG Gongfa CHEN Jianbing LV Zhongyu HAO School of Civil and Transportation Engineering Guangdong University of TechnologyGuangzhou 510006China JSTI Group Guangdong Inspection and Certification Co.Ltd Nanjing 210000China

This paper utilizes three popular semantic segmentation networks,specifically DeepLab v3+,fully convolutional network(FCN),and U-Net to qualitively analyze and identify the key components of cutting slope images in complex scenes and achieve rapid image-based slope *** elements of cutting slope images are divided into 7 *** order to determine the best algorithm for pixel level classification of cutting slope images,the networks are compared from three aspects:a)different neural networks,b)different feature extractors,and c)2 different optimization *** is found that DeepLab v3+with Resnet18 and Sgdm performs best,FCN 32s with Sgdm takes the second,and U-Net with Adam ranks *** paper also analyzes the segmentation strategies of the three networks in terms of feature map *** show that the contour generated by DeepLab v3+(combined with Resnet18 and Sgdm)is closest to the ground truth,while the resulting contour of U-Net(combined with Adam)is closest to the input images.

关键词： slope damage image recognition semantic segmentation feature map visualizations

维普期刊数据库

A semantic segmentation-based underwater acoustic image transmission framework for cooperative SLAM

在线全文

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2024年第3期33卷 339-351页

作者： Jiaxu Li Guangyao Han Shuai Chang Xiaomei Fu School of Marine Science and Technology Tianjin UniversityTianjin 300072China

With the development of underwater sonar detection technology,simultaneous localization and mapping(SLAM)approach has attracted much attention in underwater navigation field in recent *** the weak detection ability of a single vehicle limits the SLAM performance in wide ***,cooperative SLAM using multiple vehicles has become an important research *** key factor of cooperative SLAM is timely and efficient sonar image transmission among underwater ***,the limited bandwidth of underwater acoustic channels contradicts a large amount of sonar image *** is essential to compress the images before ***,deep neural networks have great value in image compression by virtue of the powerful learning ability of neural networks,but the existing sonar image compression methods based on neural network usually focus on the pixel-level information without the semantic-level *** this paper,we propose a novel underwater acoustic transmission scheme called UAT-SSIC that includes semantic segmentation-based sonar image compression(SSIC)framework and the joint source-channel codec,to improve the accuracy of the semantic information of the reconstructed sonar image at the *** SSIC framework consists of Auto-Encoder structure-based sonar image compression network,which is measured by a semantic segmentation network's *** that sonar images have the characteristics of blurred target edges,the semantic segmentation network used a special dilated convolution neural network(DiCNN)to enhance segmentation accuracy by expanding the range of receptive *** joint source-channel codec with unequal error protection is proposed that adjusts the power level of the transmitted data,which deal with sonar image transmission error caused by the serious underwater acoustic *** results demonstrate that our method preserves more semantic information,with advantages over existing methods at the sa

关键词： semantic segmentation Sonar image transmission Learning-based compression

维普期刊数据库

Navigation algorithm based on semantic segmentation in wheat fields using an RGB-D camera

在线全文

学校读者我要写书评

暂无评论

Information Processing in Agriculture 2023年第4期10卷 475-490页

作者： Yan Song Feiyang Xu Qi Yao Jialin Liu Shuai Yang School of Engineering Anhui Agricultural UniversityHefei 230036PR China Anhui Provincial Engineering Laboratory of Intelligent Agricultural Machinery Hefei 230036PR China

Determining the navigation line is critical for the automatic navigation of agricultural robots in the *** this research,considering a wheat field as the typical scenario,a novel navigation line extraction algorithm based on semantic segmentation is *** data containing horizontal parallax,height,and grayscale information(HHG)is constructed by combining re-encoded depth data and red-green-blue(RGB)*** HHG,RGB,and depth data are used to achieve scene recognition and navigation line extraction for a wheat *** method includes two main ***,the semantic segmentation of the wheat,ground,and background are performed using a fully convolutional network(FCN).Second,the navigation line is fitted in the camera coordinate system on the basis of the semantic segmentation result and the principle of camera pinhole *** segmentation model is trained using 508 randomly selected images from a data set,and the model is tested on 199 *** labelled data are used as the reference benchmark,the mean intersection over union(mIoU)of the HHG data is greater than 95%,which is the highest among the three types of *** semantic segmentation methods based on the RGB and HHG data show higher navigation line extraction accuracy rates(with the absolute value of the angle deviation less than 5)than the compared *** mean and standard deviation of the angle deviation of the two methods are within 0.1and 2.0,while the mean and standard deviation of the distance deviation are less than 30 mm and 60 mm,*** values meet the basic requirements of agricultural machinery field *** novelty of this work is the proposal of a navigation line extraction algorithm based on semantic segmentation in wheat *** method is high in accuracy and robustness to interference from crop occlusion.

关键词： Fully convolutional network Navigation line extraction semantic segmentation Visual navigation

CGNet:cross-guidance network for semantic segmentation

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2020年第2期63卷 49-64页

作者： Zhijie ZHANG Yanwei PANG School of Electrical and Information Engineering Tianjin University

semantic segmentation is a fundamental task in image analysis. The issue of semantic segmentation is to extract discriminative features for distinguishing different objects and recognizing hard ***, most existing methods have limitations on resolving this problem. To tackle this problem, we identify the contributions of the edge and saliency information for segmentation and present a novel end-to-end network, termed cross-guidance network(CGNet) to leverage them to benefit the semantic segmentation. The edge and saliency detection network are unified into the CGNet, and model the intrinsic information among them, guiding the process of extracting discriminative features. Specifically, the CGNet attempts to extract segmentation, edge, and salient features, simultaneously. Then it transfers them into the cross-guidance module(CGM) to generate the pre-knowledge features based on the modeled information, optimizing the context feature extraction process. The proposed approach is extensively evaluated on PASCAL VOC 2012,PASCAL-Person-Part, and Cityscapes, and achieves state-of-the-art performance, demonstrating the superiority of the proposed approach.

关键词： semantic segmentation fully convolutional networks pyramid network edge detection saliency detection cross-guidance

Class-conditional domain adaptation for semantic segmentation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2024年第5期10卷 1013-1030页

作者： Yue Wang Yuke Li James H.Elder Runmin Wu Huchuan Lu School of Information and Communication Engineering Dalian University of TechnologyDalian 116024China School of Computer Science Wuhan UniversityWuhan 430072China Department of Electrical Engineering and Computer Science York UniversityToronto M3J 1P3Canada Department of Computer Science the University of Hong KongHong Kong 999077China

semantic segmentation is an important sub-task for many ***,pixel-level ground-truth labeling is costly,and there is a tendency to overfit to training data,thereby limiting the generalization *** domain adaptation can potentially address these problems by allowing systems trained on labelled datasets from the source domain(including less expensive synthetic domain)to be adapted to a novel target *** conventional approach involves automatic extraction and alignment of the representations of source and target domains *** limitation of this approach is that it tends to neglect the differences between classes:representations of certain classes can be more easily extracted and aligned between the source and target domains than others,limiting the adaptation over all ***,we address:this problem by introducing a Class-Conditional Domain Adaptation(CCDA)*** incorporates a class-conditional multi-scale discriminator and class-conditional losses for both segmentation and ***,they measure the segmentation,shift the domain in a classconditional manner,and equalize the loss over *** results demonstrate that the performance of our CCDA method matches,and in some cases,surpasses that of state-of-the-art methods.

关键词： domain adaptation generative adversarial networks semantic segmentation cityscapes

Dual context prior and refined prediction for semantic segmentation

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Geo-Spatial Information Science 2021年第2期24卷 228-240,I0004页

作者： Long Chen Jiajie Liu Han Li Wujing Zhan Baoding Zhou Qingquan Li School of Data and Computer Science Sun Yat-sen UniversityGuangzhouChina Guangdong Key Laboratory of Urban Informatics Shenzhen UniversityShenzhenChina Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ) Shenzhen UniversityShenzhenChina Civil and Transportation Engineering Shenzhen UniversityShenzhenChina

Recently,the focus of semantic segmentation research has shifted to the aggregation of context prior and refined boundary.A typical network adopts context aggregation modules to extract rich semantic *** also utilizes top-down connection and skips connections for refining boundary *** it still remains disadvantage,an obvious fact is that the problem of false segmentation occurs as the object has very different *** fusion of weak semantic and low-level features leads to context prior *** tackle the issue,we propose a simple yet effective network,which integrates dual context prior and spatial propagation-dubbed *** extends two mainstreams of current segmentation researches:(1)Designing a dual context prior module,which pays attention to context prior again with a shortcut connection.(2)The network can inherently learn semantic aware affinity values for each pixel and refine the *** will present detailed comparisons,which perform on PASCAL VOC 2012 and *** result demonstrates the validation of our approach.

关键词： Deep learning semantic segmentation linear spatial propagation context information

FISS GAN:A Generative Adversarial Network for Foggy Image semantic segmentation

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2021年第8期8卷 1428-1439页

作者： Kunhua Liu Zihao Ye Hongyan Guo Dongpu Cao Long Chen Fei-Yue Wang School of Computer Science and Engineering Sun Yat-sen UniversityGuangzhou 510006China State Key Laboratory of Automotive Simulation and Control and the Department of Control Science and Engineering Jilin University(Campus Nanling)Changchun 130025China Mechanical and Mechatronics Engineering Department at the University of Waterloo 200 University Avenue West WaterlooON N2L 3G1Canada State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China

Because pixel values of foggy images are irregularly higher than those of images captured in normal weather(clear images),it is difficult to extract and express their *** method has previously been developed to directly explore the relationship between foggy images and semantic segmentation *** investigated this relationship and propose a generative adversarial network(GAN)for foggy image semantic segmentation(FISS GAN),which contains two parts:an edge GAN and a semantic segmentation *** edge GAN is designed to generate edge information from foggy images to provide auxiliary information to the semantic segmentation *** semantic segmentation GAN is designed to extract and express the texture of foggy images and generate semantic segmentation *** on foggy cityscapes datasets and foggy driving datasets indicated that FISS GAN achieved state-of-the-art performance.

关键词： Edge GAN foggy images foggy image semantic segmentation GAN semantic segmentation

维普期刊数据库

Point attention network for point cloud semantic segmentation

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2022年第9期65卷 99-112页

作者： Dayong REN Zhengyi WU Jiawei LI Piaopiao YU Jie GUO Mingqiang WEI Yanwen GUO National Key Lab for Novel Software Technology Nanjing University School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics

We address the point cloud semantic segmentation problem through modeling long-range dependencies based on the self-attention mechanism. Existing semantic segmentation models generally focus on local feature aggregation. By comparison, we propose a point attention network(PA-Net) to selectively extract local features with long-range dependencies. We specially devise two complementary attention modules for the point cloud semantic segmentation task. The attention modules adaptively integrate the semantic inter-dependencies with long-range dependencies. Our point attention module adaptively integrates local features of the last layer of the encoder with a weighted sum of the long-range dependency features. Regardless of the distance of similar features, they are all correlated with each other. Meanwhile, the feature attention module adaptively integrates inter-dependent feature maps among all local features in the last layer of the encoder. Extensive results prove that our two attention modules together improve the performance of semantic segmentation on point clouds. We achieve better semantic segmentation performance on two benchmark point cloud datasets(i.e., S3DIS and Scan Net). Particularly, the Io U on 11 semantic categories of S3DIS is significantly boosted.

关键词： point cloud semantic segmentation self-attention mechanism deep learning long-range dependencies

同方期刊数据库