检索结果-内蒙古大学图书馆

Network model to optimize the process of green environmental features and urban building recognition based on lightweight image search system

引用

SOFT COMPUTING 2023年 1-11页

作者： Huang, Haibo Taiyuan Univ Dept Architecture & Environm Engn Taiyuan 123456 Shanxi Peoples R China

To promote the development of a green environment, it is necessary to build a friendly environment for green travel and increase the use of green resources. Methods based on remote sensing image processing and feature analysis have become one of the main ways to obtain ground information, and have been widely used and promoted. Therefore, ground targets the accuracy of object recognition and features have been significantly improved. In the lightweight image of the city, the terrain occupies almost 80% of the buildings and roads. Urban buildings play an important role in supporting the operation, management and planning of the city. An important technology for the construction of digital towns in the future is the city. Building identification, therefore, the research of building identification is more important in the development of the city. With the widespread application of artificial intelligence deep learning and the popularization of smart technologies, the digital images generated by the Internet and mobile smart terminals have exponentially increased. image data provides users with a comfortable experience and convenient services, but it also brings many challenges. How to filter out the photos we are interested in from a large amount of image data and find the content we need is a data difficulty. In computer vision research, image search systems can solve the problem of searching for the same content in many digital images. This paper applies deep learning and lightweight images to search systems to promote the development of urban building recognition.

关键词： Network model Deep learning Lightweight image Search system image data City building recognition

来源：评论

学校读者我要写书评

暂无评论

ViTs for SITS: Vision Transformers for Satellite image Time Series

ViTs for SITS: Vision Transformers for Satellite Image Time ...

引用

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

作者： Tarasiou, Michail Chavez, Erik Zafeiriou, Stefanos Imperial Coll London London England

ISBN: (纸本)9798350301298

In this paper we introduce the Temporo-Spatial Vision Transformer (TSViT), a fully-attentional model for general Satellite image Time Series (SITS) processing based on the Vision Transformer (ViT). TSViT splits a SITS record into non-overlapping patches in space and time which are tokenized and subsequently processed by a factorized temporo-spatial encoder. We argue, that in contrast to natural images, a temporal-then-spatial factorization is more intuitive for SITS processing and present experimental evidence for this claim. Additionally, we enhance the model's discriminative power by introducing two novel mechanisms for acquisition-time-specific temporal positional encodings and multiple learnable class tokens. The effect of all novel design choices is evaluated through an extensive ablation study. Our proposed architecture achieves state-of-the-art performance, surpassing previous approaches by a significant margin in three publicly available SITS semantic segmentation and classification datasets. All model, training and evaluation codes can be found at https://***/michaeltrs/DeepSatModels.

关键词： Photogrammetry and remote sensing

来源：评论

学校读者我要写书评

暂无评论

Bridging remote Sensors with Multisensor Geospatial Foundation Models

Bridging Remote Sensors with Multisensor Geospatial Foundati...

引用

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

作者： Han, Boran Zhang, Shuai Shi, Xingjian Reichstein, Markus Amazon Web Serv Seattle WA 98109 USA Boson AI Santa Clara CA USA Max Planck Inst Biogeochem Jena Germany

ISBN: (纸本)9798350353006

In the realm of geospatial analysis, the diversity of remote sensors, encompassing both optical and microwave technologies, offers a wealth of distinct observational capabilities. Recognizing this, we present msGFM, a multisensor geospatial foundation model that effectively unifies data from four key sensor modalities. This integration spans an expansive dataset of two million multisensor images. ms-GFM is uniquely adept at handling both paired and unpaired sensor data. For data originating from identical geolocations, our model employs an innovative cross-sensor pre-training approach in masked image modeling, enabling the synthesis of joint representations from diverse sensors. ms-GFM, incorporating four remote sensors, upholds strong performance, forming a comprehensive model adaptable to various sensor types. msGFM has demonstrated enhanced proficiency in a range of both single-sensor and multisensor downstream tasks. These include scene classification, segmentation, cloud removal, and pan-sharpening. A key discovery of our research is that representations derived from natural images are not always compatible with the distinct characteristics of geospatial remote sensors, underscoring the limitations of existing representations in this field. Our work can serve as a guide for developing multisensor geospatial pretraining models, paving the way for more advanced geospatial capabilities. Code can be found at https://***/boranhan/Geospatial_Foundation_Models

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral image Classification Based on Capsule Network

引用

Chinese Journal of Electronics 2022年第1期31卷 146-154页

作者： MA Qiaoyu ZHANG Xin ZHANG Chunlei ZHOU Heng School of Science China University of Geosciences (Beijing) School of Statistics Beijing Normal University Beijing Zhongdi Runde Petroleum Technology Co. Ltd.

The conventional convolutional neural network performs not well enough in the ground objects classification because of its insufficient ability in maintaining sensitive spectral information and characterizing the covariance of spatial structure, resulting from the narrow sensitive frequency band and complex spatial structure with diversity of hyperspectral remote sensing data which caused more serious phenomena of "same material, different spectra" and "different material, same spectra".Therefore, an improved capsule network is proposed and introduced into hyperspectral image target recognition. A convolution structure combining shallow features and multi-scale depth features is put forward to reduce the phenomena of "different material, same spectra" firstly,and then the diversity of the spatial structure is expressed by the capsule vector and sub-capsule division in channel wise, so that the averaging effect of the convolution process is weakened in the spectral domain and the spatial domain to reduce the phenomena of "same material, different spectra". By comparing the experimental results on the hyperspectral data sets such as Indian Pines,Salinas, Tea Tree and Xiongan, the capsule network shows strong spatial structure expression ability, flexible deep and shallow feature fusion ability in multi-scale, and its accuracy in target recognition is better than that of conventional convolutional neural networks, so it is suitable for the recognition of complex targets in hyperspectral images.

关键词： spectral domain spatial domain hyperspectral imaging different spectra insufficient ability complex targets geophysical image processing convolution process neural nets image classification object detection hyperspectral remote sensing data capsule vector shallow features hyperspectral image target recognition multiscale feature extraction geophysical signal processing flexible deep feature fusion ability shallow feature fusion ability convolution structure narrow sensitive frequency band strong spatial structure expression ability improved capsule network hyperspectral images serious phenomena complex spatial structure hyperspectral image classification sub-capsule division hyperspectral data sets remote sensing conventional convolutional neural network different material sensitive spectral information

来源：评论

学校读者我要写书评

暂无评论

RTMDet-R2: An Improved Real-Time Rotated Object Detector 6th

RTMDet-R2: An Improved Real-Time Rotated Object Detector

引用

6th Chinese Conference on pattern recognition and Computer Vision (PRCV)

作者： Xiang, Haifeng Jing, Naifeng Jiang, Jianfei Guo, Hongbo Sheng, Weiguang Mao, Zhigang Wang, Qin Shanghai Jiao Tong Univ Shanghai Peoples R China

ISBN: (纸本)9789819985548;9789819985555

Object detection in remote sensing images is challenging due to the absence of visible features and variations in object orientation. Efficient detection of objects in such images can be achieved using rotated object detectors that utilize oriented bounding boxes. However, existing rotated object detectors often struggle to maintain high accuracy while processing high-resolution remote sensing images in real time. In this paper, we present RTMDet-R2, an improved real-time rotated object detector. RTMDet-R2 incorporates an enhanced path PAFPN to effectively fuse multi-level features and employs a task interaction decouple head to alleviate the imbalance between regression and classification tasks. To further enhance performance, we propose the ProbIoU-aware dynamic label assignment strategy, which enables efficient and accurate label assignment during the training. As a result, RTMDet-R2-m and RTMDet-R2-l achieve 79.10% and 79.46% mAP, respectively, on the DOTA 1.0 dataset using single-scale training and testing, outperforming the majority of other rotated object detectors. Moreover, RTMDet-R2-s and RTMDet-R2-t achieve 78.43% and 77.27% mAP, respectively, while achieving inference frame rates of 175 and 181 FPS at a resolution of 1024 x 1024 on an RTX 3090 GPU with TensorRT and FP16-precision. Furthermore, RTMDet-R2-t achieves 90.63/97.44% mAP on the HRSC2016 dataset. The code and models are available at https://***/Zeba-Xie/RTMDet-R2.

关键词： remote sensing images Object Detection Rotated Object Detection Feature Fusion Label Assignment

来源：评论

学校读者我要写书评

暂无评论

Research on Key Technologies for Realistic 3D Modeling of Ancient Buildings 24

Research on Key Technologies for Realistic 3D Modeling of An...

引用

1st International Conference on image processing Machine Learning and pattern recognition

作者： Wang, Jiangtao Li, Huan Yin, Jinghui Gao, Suyuan Yan, Pengkun China Coal Aerial Photogrammetry & Remote Sensing Xian Peoples R China

ISBN: (纸本)9798400707032

This article takes ancient architecture in Shaanxi Province as the research object. Based on laser 3D scanning technology, the seamless integration of point cloud data and GIS data of individual buildings is completed through unmanned aerial vehicles and RTK, forming a process of spatial data acquisition based on ancient architecture. The key technologies include oblique photography mesh model acquisition, laser point cloud model acquisition, and parameterized 3D model generation. By using dynamic uniform light and color processing to tilt aerial photography images, the color effect of the images is improved, and a high-precision Mesh model is generated using the ContextCapture system. At the same time, scientific and reasonable denoising methods are adopted to process laser point cloud data, ensuring the quality of the point cloud. In model generation, texture compression algorithm is applied to optimize OBJ data, improve texture mapping utilization and model loading efficiency. In the end, the fusion of multi-source data successfully produced real-life 3D models of five ancient buildings, including the Big Wild Goose Pagoda and Bell Tower, providing technical support for the digital protection and dissemination of cultural heritage.

关键词： Ancient architecture Data fusion Dealistic 3D technology

来源：评论

学校读者我要写书评

暂无评论

Application of Band Combination in Landslide Identification of remote sensing images Driven by Deep Learning 2

Application of Band Combination in Landslide Identification ...

引用

2nd International Conference on image processing, Computer Vision and Machine Learning, ICICML 2023

作者： Yang, Tianyu Xu, Weijie Hua, Yu Chengdu University of Technology College of Computer Science and Cyber Security Oxford Brookes College Chengdu China

ISBN: (纸本)9798350331417

With the frequent occurrence of geological disasters, landslide identification has become an important research problem. In recent years, with the application and research of deep learning in the fields of computer vision and remote sensing image analysis, deep learning has become a popular method for landslide identification research because of its excellent feature extraction and pattern recognition capabilities. In this paper, we add new bands reflecting vegetation and water of landslide factors to the original bands of remote sensing image samples by linear combination of bands, and conduct two sets of comparison experiments on Unet and Swin-Unet to verify that adding band features can help improve landslide identification accuracy. The experimental results show that the experimental group with additional band features has a numerical improvement in landslide identification accuracy, with F1-score as the evaluation index, the Unet experimental group has a 2.29% improvement and the Swin-Unet experimental group has a 1.78% improvement. The results of this paper have implications for the subsequent application of bands combination of landslide factor features in remote sensing landslide identification driven by deep learning methods. © 2023 IEEE.

关键词： deep learning landslide identification linear combination of bands remote sensing

来源：评论

学校读者我要写书评

暂无评论

Global Contextual Learning Network for Multisource remote sensing image Fusion 2

Global Contextual Learning Network for Multisource Remote Se...

引用

2nd International Conference on pattern recognition, Machine Vision and Intelligent Algorithms, PRMVIA 2024

作者： Duan, Puhong Xie, Zhuojun Lu, Xukun Kang, Xudong Hunan University School of Robotics Changsha China Hunan University College of Electrical and Information Engineering Changsha China

ISBN: (纸本)9798350389746

Multisource remote sensing image fusion aims to combine the complementary advantage of different modalities for fine-grained classification. Current multisource image fusion methods are based on a patch-by-patch learning paradigm, which requires high computational burden. In addition, how to combine different attributes is still a challenging issue. In this article, a global contextual learning network (GCLNet) is studied for multisource remote sensing image fusion. In GCLNet, an encoder-decoder convolutional network is proposed to draw global spectral-spatial information, which can significantly reduce the computing cost. Furthermore, a contextual attention feature fusion module is designed to connect coarse-to-fine features between encoder and decoder. Experiments on Augsburg and Yellow River datasets reveal that the proposed GCLNet obtains promising results in the light of classification result and inference speed compared to other advanced fusion methods. © 2024 IEEE.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

DBDAN: Dual-Branch Dynamic Attention Network for Semantic Segmentation of remote sensing images 6th

DBDAN: Dual-Branch Dynamic Attention Network for Semantic Se...

引用

6th Chinese Conference on pattern recognition and Computer Vision (PRCV)

作者： Che, Rui Ma, Xiaowen Hong, Tingfeng Wang, Xinyu Feng, Tian Zhang, Wei Zhejiang Univ Sch Software Technol Hangzhou 310027 Peoples R China Zhejiang Univ Innovat Ctr Yangtze River Delta Jiaxing 314103 Peoples R China

ISBN: (纸本)9789819984619;9789819984626

Attention mechanism is capable to capture long-range dependence. However, its independent calculation of correlations can hardly consider the complex background of remote sensing images, which causes noisy and ambiguous attention weights. To address this issue, we design a correlation attention module (CAM) to enhance appropriate correlations and suppress erroneous ones by seeking consensus among all correlation vectors, which facilitates feature aggregation. Simultaneously, we introduce the CAM into a local dynamic attention (LDA) branch and a global dynamic attention (GDA) branch to obtain the information on local texture details and global context, respectively. In addition, considering the different demands of complex and diverse geographical objects for both local texture details and global context, we devise a dynamic weighting mechanism to adaptively adjust the contributions of both branches, thereby constructing a more discriminative feature representation. Experimental results on three datasets suggest that the proposed dual-branch dynamic attention network (DBDAN), which integrates the CAM and both branches, can considerably improve the performance for semantic segmentation of remote sensing images and outperform representative state-of-the-art methods.

关键词： remote sensing Semantic Segmentation Attention Mechanism Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Grassland botanical species identification based on MTMF model

Grassland botanical species identification based on MTMF mod...

引用

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

作者： Huang, Mengge Wang, Xinhong Ma, Lingling Ouyang, Guangzhou Liu, Wei Zhu, Xiaohua Niu, Yifang Tang, Lingli Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Key Laboratory of Quantitative Remote Sensing Information Technology Chinese Academy of Sciences Beijing100094 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Science Beijing100049 China Institute of Botany Chinese Academy of Sciences Beijing100093 China

ISBN: (纸本)9781510666351

Grassland plays an important role in regional economic development and terrestrial ecosystem security. remote sensing technology is fast, efficient and low cost. The use of remote sensing technology to discriminate grassland species is an important way to monitor the population dynamics and botanical community succession in grassland. Such information is conducive to the timely and accurate detection of changes in the grassland ecological environment and provides an important reference for the scientific management of grassland ecosystems and the construction of an ecologically aware civilization. In this paper, based on the UAV hyperspectral remote sensing image of natural grassland in Inner Mongolia and the linear spectral mixture model, the MTMF (mixture tuned matched filtering) model was used for grass species identification, and the results were verified with FVC (fractional vegetation cover) estimation. The results showed that this method could achieve effective identification and extraction of the dominant species of Leymus chinensis in the study area. © 2023 SPIE.

关键词： Unmanned aerial vehicles (UAV)

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：