检索结果-南通市图书馆

Triple-Branch Asymmetric Network for real-time semantic segmentation of Road Scenes

Instrumentation 2024年第2期11卷 72-82页

作者： Yazhi Zhang Xuguang Zhang Hui Yu The Communication Engineering Department Hangzhou Dianzi UniversityZhejiang 310020China The School of Creative Technologies University of PorsmouthUK

As the field of autonomous driving evolves, real-time semantic segmentation has become a crucial part of computer vision tasks. However, most existing methods use lightweight convolution to reduce the computational effort, resulting in lower accuracy. To address this problem, we construct TBANet, a network with an encoder-decoder structure for efficient feature extraction. In the encoder part, the TBA module is designed to extract details and the ETBA module is used to learn semantic representations in a high-dimensional space. In the decoder part, we design a combination of multiple upsampling methods to aggregate features with less computational overhead. We validate the efficiency of TBANet on the Cityscapes dataset. It achieves 75.1% mean Intersection over Union(mIoU) with only 2.07 million parameters and can reach 90.3 Frames Per Second(FPS).

关键词： encoder-decoder architecture lightweight convolution real-time semantic segmentation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

DuFNet:Dual Flow Network of real-time semantic segmentation for Unmanned Driving Application of Internet of Things

引用

Computer Modeling in Engineering & Sciences 2023年第7期136卷 223-239页

作者： Tao Duan Yue Liu Jingze Li Zhichao Lian d Qianmu Li School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing210094China School of Cyberspace Security Nanjing University of Science and TechnologyWuxi320200China

The application of unmanned driving in the Internet of Things is one of the concrete manifestations of the application of artificial intelligence *** semantic segmentation can help the unmanned driving system by achieving road accessibility *** segmentation is also a challenging technology for image understanding and scene *** focused on the challenging task of real-time semantic segmentation in this *** this paper,we proposed a novel fast architecture for real-time semantic segmentation named *** from the existing work of Bilateral segmentation Network(BiSeNet),DuFNet proposes a novel semantic Information Flow(SIF)structure for context information and a novel Fringe Information Flow(FIF)structure for spatial *** also proposed two kinds of SIF with cascaded and paralleled structures,*** SIF encodes the input stage by stage in the ResNet18 backbone and provides context information for the feature *** from previous stages usually contain rich low-level details but high-level semantics for later *** convolutions embed in Parallel SIF aggregate the corresponding features among different stages and generate a powerful global context representation with less computational *** FIF consists of a pooling layer and an upsampling operator followed by projection convolution *** concise component provides more spatial details for the *** with BiSeNet,our work achieved faster speed and comparable performance with 72.34%mIoU accuracy and 78 FPS on Cityscapes Dataset based on the ResNet18 backbone.

关键词： real-time semantic segmentation convolutional neural network feature fusion unmanned driving fringe information flow

来源：

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

Distilling the Long-Range Knowledge for real-time semantic segmentation

Distilling the Long-Range Knowledge for Real-Time Semantic S...

引用

第40届中国控制会议

作者： Yunnan Wang Meng Cai Jianxun Li Department of Automation Shanghai Jiao Tong University Luoyang Institute of Electro-Optical Equipment AVIC

Deep convolutional networks have achieved great success in semantic ***,existing semantic segmentation networks are difficult to achieve an ideal balance between accuracy and *** tackle this dilemma,the key idea of this paper is to design a two-part knowledge distillation framework to improve the accuracy of real-time networks,including separated distillation and long-range *** distillation treats semantic segmentation as an independent pixel classification task,aiming to align logits between a cumbersome teacher network and a lightweight student *** extract the long-range knowledge from the scene,the similarity attention map is defined as knowledge,which is transfered from teacher to student through the long-range *** framework proposed in this paper improves the accuracy of real-time networks on Cityscapes and Fisheye datasets by 2.7% and 1.7%,*** distilled network is tested on NVIDIA Xavier embedded platform with speed of *** will be available here:https://***/WangYunnan/real-time-semantic-segmentation.

关键词： real-time semantic segmentation Long-Range Knowledge Embedded Platform

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

SPSSNet: a real-time network for image semantic segmentation

引用

Frontiers of Information Technology & Electronic Engineering 2020年第12期21卷 1770-1782页

作者： Saqib MAMOON Muhammad Arslan MANZOOR Fa-en ZHANG Zakir ALI Jian-feng LU School of Computer Science and Engineering Nanjing University of Science&TechnologyNanjing 210094China Alnnovation Beijing 100080China

Although deep neural networks(DNNs)have achieved great success in semantic segmentation tasks,it is still challenging for real-time applications.A large number of feature channels,parameters,and floating-point operations make the network sluggish and computationally heavy,which is not desirable for real-time tasks such as robotics and autonomous *** approaches,however,usually sacrifice spatial resolution to achieve inference speed in real time,resulting in poor *** this paper,we propose a light-weight stage-pooling semantic segmentation network(SPSSN),which can efficiently reuse the paramount features from early layers at multiple stages,at different spatial *** takes input of full resolution 2048×1024 pixels,uses only 1.42×10~6 parameters,yields 69.4%m Io U accuracy without pre-training,and obtains an inference speed of 59 frames/s on the Cityscapes *** can run directly on mobile devices in real time,due to its light-weight *** demonstrate the effectiveness of the proposed network,we compare our results with those of state-of-the-art networks.

关键词： real-time semantic segmentation Stage-pooling Feature reuse

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

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：