检索结果-内蒙古大学图书馆

2023 International conference on image, Signal processing, and pattern recognition, ISPP 2023

作者： Miao, Sheng Qu, Yu Liu, Xirong College of Geodesy and Geomatics Shandong University of Science and Technology Qingdao China

ISBN: (纸本)9781510666351

Landslide as a natural disaster, it is important to obtain accurate information of landslide spatial distribution. The current method of landslide extraction is mainly based on the spectral features, spatial structure and texture features of landslides on remote sensing images, which is difficult to accurately extract the spatial distribution of landslides for surface structures with similar spectral features (bare soil, villages, exposed rocks, roads, water bodies, etc.) and does not make full use of local spatial information features and causes loss of landslide boundary information. To address the above problems, this paper proposes a method to extract landslides based on the fusion of local spatial information with multi-temporal image differences. The high-resolution images before and after the landslide are used to calculate the difference images, extract each band and combine the temporal difference images to combine the bands and use them as input features for deep learning. The ASPP module is introduced to the U-net network model for expanding the local spatial information perception field, enhancing the preservation of landslide boundary information, and guiding the attention mechanism of feature downsampling for extracting multi-scale contextual information. The evaluation shows that the method can ensure the detection error of landslide area range is less than 8.6%, the extraction accuracy is more than 95%, and the Kappa is 0.90. The experimental results prove the feasibility and accuracy of the method in rainfall landslide detection. © 2023 SPIE.

关键词： Landslides

来源：评论

学校读者我要写书评

暂无评论

Research on the integration of transformer network in High-Resolution remote sensing imagery road extraction network

Research on the integration of transformer network in High-R...

引用

2024 International conference on Advanced image processing Technology, AIPT 2024

作者： Wang, Ziyan Ran, Da School of Space Information Space Engineering University Beijing China

ISBN: (纸本)9781510682542

In order to overcome the strong local perception and weak global perception characteristics of traditional convolutional neural networks (CNNs), this paper proposes a multi-spectral guided CNN-Transformer hybrid road extraction model (M2SA-MSNet) which introduces a multi-scale multi-head attention mechanism so as to capture long-range dependencies in the encoding stage. Experimental results suggest that, compared to the current state-of-the-art road extraction methods, M2SA-MSNet achieves better recognition performance and exhibits good accuracy and completeness in road extraction. © 2024 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep density estimation based on multi-spectral remote sensing data for in-field crop yield forecasting

Deep density estimation based on multi-spectral remote sensi...

引用

IEEE/CVF conference on Computer Vision and pattern recognition (CVPR)

作者： Baghdasaryan, Liana Melikbekyan, Razmik Dolmajain, Arthur Hobbs, Jennifer Intelinair Inc Yerevan Armenia Intelinair Inc Chicago IL USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Yield forecasting has been a central task in computational agriculture because of its impact on agricultural management from the individual farmer to the government level. With advances in remote sensing technology, computational processing power, and machine learning, the ability to forecast yield has improved substantially over the past years. However, most previous work has been done leveraging low-resolution satellite imagery and forecasting yield at the region, county, or occasionally farm-level. In this work, we use high-resolution aerial imagery and output from high-precision harvesters to predict in-field harvest values for corn-raising farms in the US Midwest. By using the harvester information, we are able to cast the problem of yield-forecasting as a density estimation problem and predict a harvest rate, in bushels/acre, at every pixel in the field image. This approach provides the farmer with a detailed view of which areas of the farm may be performing poorly so he can make the appropriate management decisions in addition to providing an improved prediction of total yield. We evaluate both traditional machine learning approaches with hand-crafted features alongside deep learning methods. We demonstrate the superiority of our pixel-level approach based on an encoder-decoder framework which produces a 5.41% MAPE at the field-level.

关键词： Deep learning Satellites conferences Government Estimation Crops pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-domain Vision based Sign Language recognition based on Auto Labeled Hand Tracking Data Learning 28

Multi-domain Vision based Sign Language Recognition based on...

引用

conference on image and Signal processing for remote sensing XXVIII

作者： Lee, Junha Won, Hong-In Kim, Min Young Kim, Byeong Hak Kyungpook Natl Univ KNU 80 Daehakro Daegu South Korea Korea Inst Ind Technol KITECH 15 Jisiksanneop Ro Gyongsan South Korea

ISBN: (纸本)9781510655386;9781510655379

remote operating and autonomous systems are widely applied in various fields, and the development of technology for human machine interface and communication is strongly demanded. In order to overcome the limitations of the conventional keyboard and tablet devices, various vision sensors and state-of-the-art artificial intelligence image processing techniques are used to recognize hand gestures. In this study, we propose a method for recognizing a reference sign language using auto labeled AI model training datasets. This study can be applied to the remote control interfaces for drivers to vehicles, person to home appliances, and garners to entertainment contents and remote character input technology for the metaverse environment.

关键词： remote sensing human machine interface machine learning deep learning hand tracking sign language recognition multi-domain sensing object detection

来源：评论

学校读者我要写书评

暂无评论

Sparse and Complete Latent Organization for Geospatial Semantic Segmentation

Sparse and Complete Latent Organization for Geospatial Seman...

引用

IEEE/CVF conference on Computer Vision and pattern recognition (CVPR)

作者： Yang, Fengyu Ma, Chenyang Univ Michigan Ann Arbor MI 48109 USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Geospatial semantic segmentation on remote sensing images suffers from large intra-class variance in both foreground and background classes. First, foreground objects are tiny in the remote sensing images and are represented by only a few pixels, which leads to large foreground intraclass variance and undermines the discrimination between foreground classes (issue firstly considered in this work). Second, background class contains complex context, which results in false alarms due to large background intra-class variance. To alleviate these two issues, we construct a sparse and complete latent structure via prototypes. In particular, to enhance the sparsity of the latent space, we design a prototypical contrastive learning to have prototypes of the same category clustering together and prototypes of different categories to be far away from each other. Also, we strengthen the completeness of the latent space by modeling all foreground categories and hardest (nearest) background objects. We further design a patch shuffle augmentation for remote sensing images with complicated contexts. Our augmentation encourages the semantic information of an object to he correlated only to the limited context within the patch that is specific to its category, which further reduces large intra-class variance. We conduct extensive evaluations on a large scale remote sensing dataset, showing our approach significantly outperforms state-of-the-art methods by a large margin.

关键词： image segmentation Computer vision Computational modeling Semantics Prototypes Organizations Geospatial analysis

来源：评论

学校读者我要写书评

暂无评论

Real-Time Person Identification by Video image Based on YOLOv2 and VGG 16 Networks

引用

AUTOMATION AND remote CONTROL 2022年第10期83卷 1567-1575页

作者： Bobkov, A. V. Aung, Kh. Bauman Moscow State Tech Univ Moscow 105005 Russia

This paper deals with the problem of video-based face recognition. Nowadays, facial recognition methods have made a big step forward, but video-based recognition with its poor quality, difficult lighting conditions, and real-time requirements is still a difficult and unfinished *** paper uses the apparatus of convolutional networks for various stages of processing: for capturing and detecting a face, for constructing a feature vector, and finally for recognition. All algorithms are implemented and studied in the Matlab environment to simplify their further export to embedded applications.

关键词： VGG16 convolutional neural network face recognition YOLOv2 object detection algorithm deep learning face database

来源：评论

学校读者我要写书评

暂无评论

APPLeNet: Visual Attention Parameterized Prompt Learning for Few-Shot remote sensing image Generalization using CLIP

APPLeNet: Visual Attention Parameterized Prompt Learning for...

引用

2023 IEEE/CVF conference on Computer Vision and pattern recognition Workshops, CVPRW 2023

作者： Singha, Mainak Jha, Ankit Solanki, Bhupendra Bose, Shirsha Banerjee, Biplab Indian Institute of Technology Bombay India Technical University of Munich Germany

ISBN: (纸本)9798350302493

In recent years, the success of large-scale vision-language models (VLMs) such as CLIP has led to their increased usage in various computer vision tasks. These models enable zero-shot inference through carefully crafted instructional text prompts without task-specific supervision. However, the potential of VLMs for generalization tasks in remote sensing (RS) has not been fully realized. To address this research gap, we propose a novel image-conditioned prompt learning strategy called the Visual Attention Parameterized Prompts Learning Network (APPLeNet). APPLeNet emphasizes the importance of multi-scale feature learning in RS scene classification and disentangles visual style and content primitives for domain generalization tasks. To achieve this, APPLeNet combines visual content features obtained from different layers of the vision encoder and style properties obtained from feature statistics of domain-specific batches. An attention-driven injection module is further introduced to generate visual tokens from this information. We also introduce an anti-correlation regularizer to ensure discrimination among the token embeddings, as this visual information is combined with the textual tokens. To validate APPLeNet, we curated four available RS benchmarks and introduced experimental protocols and datasets for three domain generalization tasks. Our results consistently outperform the relevant literature and code is available at https://***/mainaksingha01/APPLeNet © 2023 IEEE.

关键词： remote sensing

来源：评论

学校读者我要写书评

暂无评论

Application of remote sensing image processing for Classification and recognition 15

Application of Remote Sensing Image Processing for Classific...

引用

15th IEEE International conference on Advanced Infocomm Technology, ICAIT 2023

作者： Shi, Xiaolong Huang, Dan Li, Wenjie Wang, Xianjie College of Computer Science and Engineering Chongqing University of Technology Chongqing China China Research and Development Academy of Machinery Equipment Beijing China Chongqing High-tech Zone Pegasus Innovation Institute Chongqing University of Technology Chongqing China

ISBN: (纸本)9798350314120

Aiming at the difficulties in object detection and recognition in remote sensing images caused by high background complexity, large scale variations of targets, and the presence of numerous small objects, an improved method for remote sensing image object detection based on YOLOv7-tiny is proposed. This method combines the loss function based on normalized Gaussian Wasserstein distance (NWD) with the CIoU loss function to address the problem of sensitivity to positional deviation of small objects by IoU-Loss. The addition of a global attention mechanism (GAM) in the backbone network reduces information diffusion and enhances the interaction at the global dimension to mitigate the interference of complex backgrounds in remote sensing images on the model, enabling the model to focus on the feature extraction of the desired targets. Finally, the coupled detection head (Coupled Head) of the model is replaced with a decoupled detection head (Decoupled Head), allowing the classification and regression tasks to output from different branches to achieve decoupling and avoid the decrease in detection accuracy caused by conflicts between classification and regression. The experimental results of this method on the public dataset DIOR achieved 88.73% accuracy, which is an improvement of 1.78% compared to the unimproved method's accuracy of 86.95%. Furthermore, compared to other researchers' methods tested on DIOR, the proposed method also shows improvement, thus validating its effectiveness. © 2023 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Semi-automatic Labeling of Satellite images Using Texture Features and Hough Circle Transformation

引用

SN Computer Science 2024年第5期5卷 1-12页

作者： Sundari, L. K. Sowmya Mallikarjuna, M.K. Halakeri, Pooja Hebbar, Ramachandra School of CIT REVA University Bangalore India RRSC –South Bangalore India

In order to extract valuable ground information from images, supervised classification is an extensively adopted technique. However, it has a substantial downside in that choosing and labeling training samples requires a lot of time and resources. Fortunately, recent developments in automatic information indexing have produced encouraging this development makes it possible to develop an automated method for labelling training samples as opposed to relying just on human interpretation. In this research paper, we present a unique technique for the automated recognition and annotation of training data for high-resolution image classification which will identify tree and non-tree. The proposed methodology consists of methods like pre-processing to enhance the quality, identifying features where distinctive characteristics are extracted from the images, applying NDVI a fundamental vegetation index which quantifies the presence of healthy vegetation, applying a 7*7 mask, spatial filter to enhance specific features in the image, image subtraction to highlights discrepancies between images and Hough circle transformation a robust method for circular shape detection to identify circular patterns associated with tree canopies detecting tree region. The proposed sampling methodology has been assessed using a series of high-resolution remote sensing images. The results indicate that the proposed method can reliably generate a large number of samples and can achieve satisfactory results when used with various classifiers. This research makes a significant contribution to high-resolution image classification by automating the labeling of training data, with a particular emphasis on tree identification. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： NDVI pattern spatial filters remote sensing Texture analysis Very high-resolution images

来源：评论

学校读者我要写书评

暂无评论

4th International conference on Advances in Computational Science and Engineering, ICACSE 2023

4th International Conference on Advances in Computational Sc...

引用

4th International conference on Advances in Computational Science and Engineering, ICACSE 2023

ISBN: (纸本)9789819729760

The proceedings contain 52 papers. The special focus in this conference is on Advances in Computational Science and Engineering. The topics include: Sensitivity Analysis on Absorber Column as Hydrogen Gas Purification Unit Using Aspen Plus;use that Pinky on the ‘A’ Key: A Finger-Key Identification Module for a Touch Typing Trainer;Accelerating Density-Based Spatial Clustering of Applications with Noise (DBSCAN) Using Vincenty’s Inverse Method on CUDA;procedural Modeling for Sustainable Urban Development and Planning: A Blender Plugin for 3D Modeling of Philippine Cities;estimating Orangutans Population Size in Sabah Rainforest in Malaysia Using Spatial Modelling;multilayer Gaussian Feature Extraction Algorithm for Sky image Classification;face Expression recognition: A Survey on Hyperparameter Optimization;Enhancing Low Light image Classification Using MADPIP Approach;a Robust Multiple Adaptive Derivative Face recognition System on Pose and Illumination;performance Comparison of Convolutional Neural Network Deep Learning Architectures for remote sensing image Segmentation;revolutionizing Human–Computer Interaction: Unraveling the Power of Deep Learning Convolutional Neural Networks in Face recognition;Multiple Adaptive Derivative Passive image processing Approach to Unsharp Masking Restoration for CNN on Low Light images;data-Driven Insights for Strengthening Information Security Awareness in Higher Education Institutions;Determining Motivational Factors for Retention and Course Completion Among Filipino MOOC Learners: A Thematic Analysis;development of Kansei-Based Visualization pattern for E-Learning Website;augmented Reality in Education: Transformative Innovations and Immersive Learning Experiences;classification of Game Mechanics: A Brief Review;challenges and Issues in Team Gamer Loyalty for Massively Multiplayer Online Game;optimizing Cloud-Based Educational Services for Enhanced Learning in Higher Education Institutions;biomarker Identification for Lung Canc

关键词：

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：