检索结果-内蒙古大学图书馆

2022 International Conference on Automation, robotics and Computer Engineering, ICARCE 2022

作者： Zhang, Siqing Liu, Xiaoquan Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan China

ISBN: (纸本)9781665475488

Range gated 3D imaging is widely used in space imaging, distance measurement, automatic driving and other application scenarios. A range gated 3D imaging system based on neural network is proposed. The system inputs three range gated images through convolutional neural network, and then outputs a depth map. A single convolutional neural network is proposed to process range gated images, and a multi-scale loss function is used. The test results on the real data set of outdoor driving show that the model trained on the GPU(graphics processing unit) in this paper realizes range gated 3D imaging. © 2022 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Feature-Driven Super-Resolution for Object Detection 5

Feature-Driven Super-Resolution for Object Detection

引用

5th International Conference on Control, robotics and Cybernetics, CRC 2020

作者： Wang, Bin Lu, Tao Zhang, Yanduo Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan China

ISBN: (数字)9781728186245

ISBN: (纸本)9781728186245

Although some convolutional neural networks (CNNs) based super-resolution (SR) algorithms yield good visual performances on single images recently. Most of them focus on perfect perceptual quality but ignore specific needs of subsequent detection task. This paper proposes a simple but powerful feature-driven super-resolution (FDSR) to improve the detection performance of low-resolution (LR) images. First, the proposed method uses feature-domain prior which extracts from an existing detector backbone to guide the high-resolution (HR) image reconstruction. Then, with the aligned features, FDSR updates SR parameters for better detection performance. Comparing with some state-of-the-art SR algorithms with scale factor 4, FDSR outperforms the detection performance mAP on MS COCO validation and VOC2007 test datasets, and with good generalization to other detection networks. © 2020 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition Based on Wasserstein Distance Fusion of Audiovisual Features 6

Emotion Recognition Based on Wasserstein Distance Fusion of ...

引用

6th International Conference on robotics, Control and Automation Engineering, RCAE 2023

作者： Ai, Nianxin Zhang, Shuiping Yi, Niannian Ma, Zhiwei Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan China

ISBN: (纸本)9798350315301

The task of multimodal emotion recognition aims to discern human emotions by utilizing both speech and facial expressions. Given the significance of complementarity between different modal sources, fusion has emerged as a prominent area of research in multimodal emotion recognition. However, when merging multiple modalities, two distinct challenges arise: the high dimensionality of feature vectors and redundancy of information. Furthermore, this complexity introduces intricacies into the data. To address these challenges, we introduce a model based on the Wasserstein distance. This model extracts meaningful features from each modality by minimizing the Wasserstein distance, reducing information redundancy through the selection of these meaningful features. Subsequently, the effective features from both modalities are integrated, partially mitigating the high dimensionality of the feature data and simplifying it. Finally, a classification task is applied to the integrated effective features to determine the ultimate emotional category. Experimental results conducted on the RA VDESS dataset demonstrate that our model outperforms post-fusion models by achieving an accuracy 3.7 % higher, reaching an impressive accuracy rate of 85.2%. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Research on Landslide Detection in Remote Sensing Image Based on Improved Faster-RCNN 2

Research on Landslide Detection in Remote Sensing Image Base...

引用

2nd International Conference on Computer, Control and robotics, ICCCR 2022

作者： Zhang, DanFeng Zhang, ShuiPing Wang, HaiHui Ai, XinNian Yi, NianNian Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan China

ISBN: (纸本)9781665466745

The application of base on deep learning remote sensing image landslide detection has become a trend. In view of the, large difference in the scale of landslide objects and the very important characteristics of the shallow layer of the landslide object, we modified the original Faster RCNN. First compare the average accuracy values of different network models, and select the network ResNet50 with deeper layers, and then integrated into Feature Pyramid Network (FPN) on the basis of ResNet50, Fusion of FPN structure with RPN and Fast RCNN. Finally, it is verified on the public landslide dataset in BiJie City, Guizhou Province, China, and the average accuracy of the obtained model is 87.10%, which is 16.9% higher than the 70.20% of VGG16. Contrast experiments with different anchor ratios and different hyperparameters in the FPN part are carried out, and the generated results are analyzed and compared. The experimental results show that the proposed method has good robustness and high accuracy for the detection of landslide objects, in remote sensing images, which can provide a technical reference for further research on landslide detection in remote sensing images. © 2022 IEEE.

关键词： Landslides

来源：评论

学校读者我要写书评

暂无评论

Degradation Prior Guided Scene Text Image Super-Resolution 4

Degradation Prior Guided Scene Text Image Super-Resolution

引用

4th International Conference on Frontiers technology of Information and Computer, ICFTIC 2022

作者： Yang, Hang Zhou, Huabing Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan China

ISBN: (纸本)9798350321951

Scene text image super-resolution (STISR) aims to increase the resolution and restore text details in low-resolution (LR) text images. Recently, significant improvements have been achieved by deep learning-based methods with the assistance of the real-world dataset. However, most existing STISR networks have been substantially deeper to extract deep features while ignoring the native degradation prior information in LR images. In this paper, we propose a novel Degradation Prior Guided Super-Resolution (DPGSR) Network for STISR task. Specifically, a degradation prior (DP) encoder is designed to capture the degradation prior, which is injected to the image reconstruction process. Meanwhile, a degradation prior aware loss function is introduced to constraint the encoder training. Comprehensive experiments on the benchmark TextZoom dataset demonstrate that our DPGSR method can improve text recognition accuracy significantly and strengthen the image quality in terms of PSNR/SSIM metrics. Our approach is superior to the existing baseline and other methods in the trade-off between text recognition accuracy and image quality metrics. © 2022 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Scene Text Image Super-Resolution via Anchor Point Guided and Efficient Transformer 5

Scene Text Image Super-Resolution via Anchor Point Guided an...

引用

5th International Conference on Frontiers technology of Information and Computer, ICFTIC 2023

作者： Xiong, Wenfei Shi, Xiaoqian Yang, Hang Zhou, Huabing Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9798350309034

Scene text image super-resolution (STISR) aims to restoring textual details within low-resolution (LR) text images, producing high-resolution (HR) images that closely align with human perception. However, current state-of-the-art methods lack a comprehensive approach to modeling text images, resulting in an unsatisfactory balance between improving image quality and enhancing downstream task performance in STISR. In this paper, we propose a novel STISR framework (ATSR) via Anchor Point Guided and Efficient Transformer. We comprehensively analyze text images from three perspectives: local features within characters, character-level features, and image-level global features. Specifically, we propose Anchor Point Guided Pixel Attention (APGPA) to establish the invariance characteristics of characters. To ensure accurate characters restoration, we introduce a text recognition operator as a prior constraint on the character features of the generated text image. Additionally, recognizing the significance of global features for image quality and subsequent text recognition tasks, we present the Efficient Text Super-Resolution Transformer (ETSRT), a module that efficiently reconstructs images by leveraging visual and semantic information from the context. Our approach outperforms the existing baseline as demonstrated by numerous experiments. © 2023 IEEE.

关键词： anchor point efficient Transformer scene text image super-resolution

来源：评论

学校读者我要写书评

暂无评论

Study on Decentralization of Spherical Amphibious Multi-robot Control System Based on Smart Contract and Blockchain

引用

Journal of Bionic Engineering 2021年第6期18卷 1317-1330页

作者： Shuxiang Guo Sheng Cao Jian Guo Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems and Intelligent Robot Laboratory Tianjin University of TechnologyBinshui Xidao Extension 391Tianjin300384China Intelligent Mechanical Systems Engineering Department Faculty of Engineering Kagawa UniversityTakamatsuKagawaJapan

With the development of intelligent bionic robots and the improvement of military application,a single robot cannot meet the requirements of the tasks of the current *** more complex tasks require not only that the robot be able to pass through the field barriers and the amphibious environment,but also that the robot be able to collaborate in a multi-robot ***,research on the multi-robot control system of spherical amphibious robots is very ***,the main research on amphibious robots is to improve the functions of a single robot,in the absence of the study of the multi-robot control *** systems primarily use a centralized control *** the transfer of central node can be achieved,there is still a problem of Byzantine fault tolerance in military applications,that is,when the amphibious multi-robot system is invaded by the *** central node may not only fail to accomplish the task,but also lose control of other robots,with severe *** solve the above problems,this paper proposed a decentralized method of spherical amphibious multi-robot control system based on blockchain ***,the point-to-point information network based on long range radio technology of low power wide area network was set up,we designed the blockchain system for embedded application environment and the decentralized hardware and software architecture of multi-robot control *** this basis,the consensus plugin,smart contract and decentralized multi-robot control algorithm were designed to achieve *** experimental results of consensus of spherical amphibious multi-robot showed the effectiveness of the decentralization.

关键词： Amphibious robot Blockchain Smart contract Control system Decentralization

来源：评论

学校读者我要写书评

暂无评论

Registration of Lithium Battery x-ray Images Based on an Improved RANSAC Algorithm 21

Registration of Lithium Battery x-ray Images Based on an Imp...

引用

5th International Conference on Electronic Information technology and Computer Engineering, EITCE 2021

作者： DIng, Chang Chen, Deng Hubei Province Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9781450384322

Image registration and stitching are required in the defect detection of lithium batteries. However, existing image registration methods will suffer from a large number of mismatches caused by similar textures and structures in lithium battery x-ray images. In order to address the problem, we propose an improved RANSAC (random sample consensus, RANSAC) algorithm, which is optimized based on the structure characteristics of lithium battery. When solving the relationship model, this method calculates the matching quality of the matching pair based on the longitudinal pixel distance of the matching pair, and then eliminates the wrong matching point pairs according to the matching quality of the matching pair, thereby reducing the number of mismatched pairs. Experiments show that the algorithm proposed in this paper can eliminate obvious mismatched pairs, and the registration accuracy of lithium battery X-ray digital images is improved by 20.5% on average. © 2021 ACM.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Network for Person Search 4

Context-Aware Network for Person Search

引用

4th International Conference on robotics and Computer Vision, ICRCV 2022

作者： Gu, Yu Lu, Tao Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan Hubei China

ISBN: (数字)9781665481700

ISBN: (纸本)9781665481700

The key to effective person search is aiming to localize the pedestrians and obtain the discriminative embeddings representation for person ReID from numerous surveillance scene images. And the existing one-step anchor-free methods can achieve a trade-off between speed and accuracy, but it can not fully exploit the contextual feature information of search context, resulting in undesirable localization. To alleviate this issue, we propose a Context-Aware Network for Person Search (CANPS) to delve into the high-level contextual information. In CANPS, firstly, context encoder is proposed to bridge the gap between the feature maps, achieved by distributing rich contextual information to prediction head layers. Second, we design the malleable center sampling strategy to reasonably expose sample region and focus on the centroid feature representations. What's more, we design above components in a trainable bag-of-freebies manner, so that real-time person search can greatly improve the accuracy without increasing extra inference cost. Extensive experiments show that the approach we proposed can outperform current state-of-the-art methods in public CUHK-SYSU datasets. © 2022 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Pose Estimation of Six-axis Industrial robots Based on Deep Learning 21

Pose Estimation of Six-axis Industrial Robots Based on Deep ...

引用

5th International Conference on Electronic Information technology and Computer Engineering, EITCE 2021

作者： Yang, Yichen Wei, Wei Chen, Deng Hubei Province Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9781450384322

Industrial robot pose estimation has important applications in industrial robot safety detection and abnormal pose analysis. Aiming at the current problems of low accuracy of industrial robot pose estimation, this paper proposes a pose estimation method of six-axis industrial robots based on deep learning. Firstly, this paper uses the object detection method to detect the six joint axes of the industrial robot, and then the detected results are converted into the pose of the industrial robot. Additionally, this paper constructs an image dataset for industrial robot pose. Our method lays the foundation for industrial robot safety detection and abnormal pose analysis. The experimental results on the self-constructed dataset show that our method can accurately estimate the pose of the industrial robot, and the mean average precision (mAP) is 82.98%. It also outperforms previous industrial robot pose estimation methods by a significant margin of 29.98% performance gain. © 2021 ACM.

关键词： Industrial robots

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：