检索结果-内蒙古大学图书馆

Semi-supervised Counting of Grape Berries in the Field Based on Density Mutual Exclusion

Plant Phenomics 2023年第4期5卷 825-835页

作者： Yanan Li Yuling Tang Yifei Liu Dingrun Zheng School of Computer Science and Engineering School of Artificial IntelligenceWuhan Institute of TechnologyWuhan 430205China Hubei Key Laboratory of Intelligent Robot Wuhan Institute of TechnologyWuhan 430073China

Automated counting of grape berries has become one of the most important tasks in grape yield ***,dense distribution of berries and the severe occlusion between berries bring great challenges to counting algorithm based on deep *** collection of data required for model training is also a tedious and expensive *** address these issues and cost-effectively count grape berries,a semi-supervised counting of grape berries in the field based on density mutual exclusion(CDMENet)is *** algorithm uses VGG16 as the backbone to extract image *** tasks based on density mutual exclusion are *** tasks exploit the spatial distribution pattern of grape berries in density levels to make full use of unlabeled *** addition,a density difference loss is *** feature representation is enhanced by amplifying the difference of features between different density *** experimental results on the field grape berry dataset show that CDMENet achieves less counting *** with the state of the arts,coefficient of determination(R^(2))is improved by 6.10%,and mean absolute error and root mean square error are reduced by 49.36%and 54.08%,*** code is available at.

关键词： Grape mutual backbone

来源：评论

学校读者我要写书评

暂无评论

Bionic Muscle Control with Adaptive Stiffness for Bionic Parallel Mechanism

引用

Journal of Bionic Engineering 2023年第2期20卷 598-611页

作者： Yaguang Zhu Ruyue Li Zhipeng Song The Key Laboratory of Road Construction Technology and Equipment of MOE Chang’an UniversityXi’an710064China Shanghai Collaborative Innovation Center of Intelligent Manufacturing Robot Technology for Large Components Shanghai201620China

As the torso is critical to the coordinated movement and flexibility of vertebrates,a 6-(Degree of Freedom)DOF bionic parallel torso with noteworthy motion space was designed in our previous *** improve the compliance of the parallel mechanism,a pair of virtual muscle models is constructed on both sides of the rotating joints of each link of the mechanism,and a bionic muscle control algorithm is *** analyzing the control parameters of the muscle model,dynamic characteristics similar to those of biological muscle are *** adaptive stiffness control is proposed to adaptively adjust the stiffness coefficient with the change in the external load of the parallel *** attitude closed-loop control can effectively keep the attitude angle unchanged when the position of the moving platform *** simulations and experiments are undertaken to validate compliant movements and the flexibility and adaptability of the parallel mechanism.

关键词： Bionic mechanism Compliance control Muscle model Stiffness adaptation Dura-rate integral learning

来源：评论

学校读者我要写书评

暂无评论

DSSNet: a transformer-based network for dense scene text detection and recognition in complex environments 5

DSSNet: a transformer-based network for dense scene text det...

引用

5th International Conference on Signal Processing and Computer Science, SPCS 2024

作者： Li, Jing Zhou, Huabing College of Computer Science and Engineering Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan China

ISBN: (数字)9781510686731

ISBN: (纸本)9781510686724

This paper presents a novel approach for dense scene text detection called DSSNet (Dense Script Spotter Network). The network leverages ResNet and FPN for feature extraction, employing multi-scale feature fusion and Transformer-based feature processing to enhance text recognition across varying sizes. The method generates text instance shapes using Bézier central curves and performs text recognition by integrating positional query information. Experimental results on the DSTD1500 and ICDAR2015 datasets demonstrate that DSSNet outperforms existing methods in terms of text localization accuracy, recognition accuracy, and annotation flexibility. © 2025 SPIE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A SAR Denoising Network Based on Generative Adversarial Learning 6

A SAR Denoising Network Based on Generative Adversarial Lear...

引用

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

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

ISBN: (纸本)9798350315301

Synthetic Aperture Radar (SAR) images are critical in microwave remote sensing and are used for resource exploration and target location. However, due to the principle of coherent imaging, SAR images are often interfered by speckle noise, which reduces image quality. It is necessary to remove noise but retain details. We are committed to improving the network structure to increase the diversity and authenticity of generated images. Inspired by Se-Res-Unet, we fuse generative adversarial networks for SAR image denoising and named the model SAR-RsuGan. In it, the generator and the discriminator compete with each other to generate high-quality images. We use synthetic SAR images for training and compare with other methods to obtain the best performance. © 2023 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

A Vital Signs intelligent Detection Framework of FMCW MIMO Radar Based on 3-D Beamforming and Muli-site Fusion of Heartbeat Signals 2

A Vital Signs Intelligent Detection Framework of FMCW MIMO R...

引用

2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

作者： Wang, Zijia Gong, Pengcheng Wuhan Institute of Technology Wuhan China The Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9798331515669

This paper presents a framework for frequency modulated continuous wave (FMCW) multiple input multiple output (MIMO) radar non-contact vital sign monitoring to achieve accurate heart rate (HR) in low SNR environments. The framework consists of two main parts. The first part includes a 3-D cardiac beamformer based on heartbeat signal quality, which is a beamformer composed of the distance dimension, azimuth and zenith angles. Proposed a new beamformer method and combined with the heart signal quality evaluation model to focus the radar array beam on the human heart to improve the signal quality. The second part proposed the multipart signal fusion (MSF) method, which fuses the reflection intensity of different parts of the trunk to improve the signal-to-noise ratio, thereby improving the performance of BR and HR. Finally, the HR and BR signals are separated by filter. © 2024 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

MaskBEV: Mask of Accurate 2D Object to Optimize Multi-view 3D Object Detection 3

MaskBEV: Mask of Accurate 2D Object to Optimize Multi-view 3...

引用

3rd International Conference on Machine Learning and Computer Application, ICMLCA 2022

作者： Hao, Xiaoxing Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan China

ISBN: (纸本)9781510664814

As a key part of autonomous driving technology, 3D object detection in Bird-Eye-View(BEV) view is designed to accurately detect road conditions based on multiple sensor inputs. However, current 3D detection methods are usually biased towards the acquisition of depth information. There is a strong correlation between 2D object detection and 3D object detection in BEV, especially the latest 2D detection has high robustness and accuracy in complex environments. To the end, this paper proposes a 3D object detection algorithm with object feature enhencement, which reasonably uses mask generated by 2D object detection as prior information and facilitates object extraction in BEV. In particular, in order to amplify the difference between the target and the background, we first designed the Data Preparation Module(DPM) to convert the 2D detection results into a binary target mask which completely separates the target from the background. Then, an Object Enhencement Module (OEM) is designed to enhence the contrast and texture details between the object and background. Finally, we propose Channel Interaction Module(CIM) considering the correlation between multi-channel features, which fully allocates the weights between channels. In this way, MaskBEV-Tiny scores 34.0% mAP and 41.1% NDS on the nuScenes val set which surpasses BEVDet-Tiny by a largin of 2.9% mAP and 2.0% NDS. © 2023 SPIE.

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

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

Infrared and Visible Image Fusion Based on Region Semantic Discrimination Optimization 5

Infrared and Visible Image Fusion Based on Region Semantic D...

引用

5th International Seminar on Artificial Intelligence, Networking and Information technology, AINIT 2024

作者： Li, Juan Zhou, Huabing College of Computer Science and Engineering Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan China

ISBN: (纸本)9798350385557

The fusion of infrared and visible images holds significant application value in military, security, environmental monitoring, and other fields. However, infrared images exhibit distinct target features, while visible images contain clear texture details. The fused image should preserve the corresponding features of the infrared or visible source images based on different semantic regions. In this study, based on the semantic discrimination network module, we propose a generative adversarial network with dual discriminators to improve the fusion effect of infrared and visible images. This method extracts semantic information from images through a semantic segmentation network and combines no-reference image quality assessment and entropy to estimate the information content in each semantic object, thereby guiding the fusion process. Experimental results demonstrate that this method can effectively achieve the fusion of infrared and visible images, achieving significant improvements in feature preservation. © 2024 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

GeoSAM: A Sampling and Attention Mechanism for Cross-View Geo-Localisation 6

GeoSAM: A Sampling and Attention Mechanism for Cross-View Ge...

引用

6th International Conference on Frontier Technologies of Information and Computer, ICFTIC 2024

作者： Wu, Fan Zhou, Huabing College of Computer Science and Engineering Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan China

ISBN: (纸本)9798331541750

Cross-view geo-localisation aims to match street-view images with satellite images, but this task remains challenging due to significant appearance and viewpoint discrepancies. This paper proposes a novel framework, GeoSAM, which enhances feature alignment and matching accuracy by integrating a dynamic sampling strategy and attention mechanism. GeoSAM employs a dual-branch network with Convolutional Block Attention Modules (CBAM) to strengthen feature extraction for both street-view and satellite-view images. Furthermore, the framework incorporates a dynamic hard negative sampling strategy, combining geographic proximity and visual similarity, to ensure robustness in contrastive learning. Experiments on the CVUSA dataset demonstrate that GeoSAM significantly outperforms existing methods in terms of Top-1 accuracy and recall, offering an efficient and generalisable solution for cross-view geo-localisation tasks. © 2024 IEEE.

关键词： Image matching

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：