检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering, ICBAIE 2021

作者： Huiming, Yu Fuxin, Xu Central South University School of Physics and Electronics Changsha410083 China

ISBN: (纸本)9780738131221

As an important branch in the field of machine vision, target detection and recognition technology have important applications in various fields. In view of the fact that the general target detection and recognition model does not perform well in remote sensing images, and there're large amount of different size targets need to be recognized. On the basis of Mask R-CNN model, one of the classic target detection and recognition model, this paper proposes A target recognition and detection method that integrates data enhancement processing and improves the Mask R-CNN backbone network FPN to RFP. When inputting image data, perform random enhancement processing on the data, randomly cut the image, and randomly merge;when extracting features, improve the FPN in the original Mask R-CNN model to RFP to make the extracted features better Reflecting the original picture information, experiments have shown that this model has a good performance in fine-grained target recognition in remote sensing images. On the same data set, its evaluation indicators are superior to other comparison algorithms in all aspects. © 2021 IEEE.

关键词： remote sensing

来源：评论

学校读者我要写书评

暂无评论

Learning to Reduce Information Bottleneck for Object Detection in Aerial images

引用

IEEE GEOSCIENCE AND remote sensing LETTERS 2023年 20卷 1页

作者： Shen, Yuchen Zhang, Dong Song, Zhihao Jiang, Xuesong Ye, Qiaolin Nanjing Forestry Univ Coll Informat Sci & Technol Nanjing 210037 Jiangsu Peoples R China Hong Kong Univ Sci & Technol Dept CSE Hong Kong Peoples R China Nanjing Forestry Univ Coll Mech & Elect Engn Nanjing 210037 Jiangsu Peoples R China Nanjing Xiaozhuang Univ Key Lab Intelligent Informat Proc Nanjing 211171 Jiangsu Peoples R China

Object detection in aerial images is a critical and essential task in the fields of geoscience and remote sensing. Despite the popularity of computer vision methods in detecting objects, these methods have been faced with significant limitations of aerial images such as appearance occlusion and variable object sizes. In this letter, we explore the limitations of conventional neck networks in object detection by analyzing information bottlenecks. We propose an enhanced neck network to address the information deficiency issue in current neck networks. Our proposed neck network, which serves as a bridge between the backbone network and the head network, comprises a global semantic network (GSNet) and a feature fusion refinement module (FRM). The GSNet is designed to perceive contextual surroundings and propagate discriminative knowledge through a bidirectional global pattern. The FRM is developed to exploit different levels of features to capture comprehensive location information. We validate the efficacy and efficiency of our approach through experiments conducted on two challenging datasets, DOTA and HRSC2016. Our method outperforms existing approaches in terms of accuracy and complexity, demonstrating the superiority of our proposed method.

关键词： Neck Feature extraction Kernel Task analysis Semantics Object detection Location awareness Aerial image processing information bottleneck object detection remote sensing scene recognition

来源：评论

学校读者我要写书评

暂无评论

MORPHOLOGICAL TEXTURE DESCRIPTION FOR HYPERSPECTRAL imageS: pattern SPECTRUM 11

MORPHOLOGICAL TEXTURE DESCRIPTION FOR HYPERSPECTRAL IMAGES: ...

引用

11th Workshop on Hyperspectral Imaging and Signal processing - Evolution in remote sensing (WHISPERS)

作者： Deborah, H. Richard, N. Norwegian Univ Sci & Technol Dept Comp Sci Teknologivn 22 Gjovik Norway Univ Poitiers Lab XLIM JRU CNRS 7252 Futuroscope France

ISBN: (纸本)9781665436014

A metrological extension of morphological granulometry for the hyperspectral domain is introduced in this work. This development is enabled by the latest study of a suitable ordering relation for hyperspectral images. With granulometry as a texture descriptor, a suitable similarity measure for it is also introduced. In addition to providing validation experiments to the extension, a preliminary result in a texture discrimination task can also be found in this work.

关键词： Texture mathematical morphology pattern spectrum hyperspectral

来源：评论

学校读者我要写书评

暂无评论

A COMPARATIVE STUDY OF SEVERAL SLFN-BASED CLASSIFICATION ALGORITHMS FOR URBAN AND RURAL LAND USE 24

A COMPARATIVE STUDY OF SEVERAL SLFN-BASED CLASSIFICATION ALG...

引用

24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow

作者： Lin, Yi Xie, Guangshun Zhang, Tinghui Yu, Jie Zhang, Hanchao Cai, Hanging Tongji Univ Coll Surveying & Geoinformat Shanghai 200092 Peoples R China Minist Nat Resources Key Lab Surveying & Mapping Sci & Geospatial Info Beijing 100036 Peoples R China Univ Stuttgart Inst Geodesy D-70174 Stuttgart Germany

In the study of urban sustainable development, accurate classification of land use has become an important basis for monitoring urban dynamic changes. Hence it is necessary to develop the appropriate recognition model for urban-rural land use. Although deep learning algorithms have become a research hotspot in image classification tasks in recent years, and many good results have been achieved. But other machine learning algorithms are not going away. Compared deep learning with machine learning, there are some advantages and disadvantages in data dependence, hardware dependence, feature processing, problem solving methods, execution time, and interpretability, etc. Especially in the classification for remote sensing images, the continuous research and development of traditional machine learning algorithms is still of great significance. In this paper, the performances of several SLFN-based classification algorithms were studied and compared, including ELM, RBF K-ELM, mixed K-ELM, A-ELM and SVM. Extreme Learning Machine (ELM) is a new algorithm for single-hidden-layer feedforward neural network (SLFN). It has simple structure, fast speed and is easy to train. In some applications, however, standard ELM is prone to be overfitting and its performance will be affected seriously when outliers exist. In order to explore the performance of ELM and its improved algorithm for urban-rural land use classification, comparative experiments between three improved ELM algorithms (RBF K-ELM, mixed K-ELM and A-ELM), ELM and SVM with image data from several study areas were performed, and the classification accuracy and efficiency were analysed. The results show that the three improved ELM algorithms perform better than the standard ELM and SVM both in overall accuracy and Kappa coefficient. However, it is worth noting that the computation efficiency of RBF K-ELM and mixed K-ELM decreases greatly with larger image, the time cost is much more than other algorithms. Compared with othe

关键词： remote-sensing image classification land use extreme learning machine kernel function A-ELM machine learning

来源：评论

学校读者我要写书评

暂无评论

Using the improved mask R-CNN and Softer-NMS for target segmentation of remote sensing image 4

Using the improved mask R-CNN and Softer-NMS for target segm...

引用

4th International Conference on pattern recognition and Artificial Intelligence, PRAI 2021

作者： Wang, Yiwen Rao, Yunbo Huang, Cheng Yang, Yang Huang, Yuanyuan He, Qixue School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Sichuan Institute of Computer Sciences Chengdu China School of Cybersecurity Chengdu University of Information Technology Chengdu China Chengdu Information Technology of the Chinese Academy of Sciences Co. Ltd Chengdu China

ISBN: (纸本)9781665413220

Recently, the combination of remote sensing image processing and deep learning methods is an increasingly popular trend. In this paper, we combine the existing instance segmentation model Mask R-CNN and the target detection algorithm Softer-NMS, and propose a model based on the improved Mask R-CNN. The model can capture the edges well, thereby segmenting the target more accurately. The experimental results also verify the effectiveness of our method. Compared with the prototype Mask R-CNN, our method improves the overall segmentation accuracy, and the loss function of the mask branch and the loss function of the candidate frame of the RPN drop faster than the original model. Incidentally, there is also a good improvement in the accuracy of detection. © 2021 IEEE.

关键词： remote sensing

来源：评论

学校读者我要写书评

暂无评论

A proposal learning strategy on CNN architectures for targets classification 6

A proposal learning strategy on CNN architectures for target...

引用

6th International Conference on Advanced Technologies for Signal and image processing, ATSIP 2022

作者： Toumi, Abdelmalek Cexus, Jean-Christophe Khenchaf, Ali Umr Cnrs 6285 Ensta Bretagne Lab-STICC 2 Rue François Verny Brest Cedex 9 29806 France

ISBN: (纸本)9781665451161

Synthetic Aperture Radar (SAR) imagery has a great potential in remote sensing field in order to maintain aerial, land and maritime surveillance. To improve this potential for several goals, Machine Learning (ML) techniques are used for effective and efficient classification of remotely sensed imagery. The strengths of machine learning include the capacity to handle data of high dimensionality with several modality and to map classes with very complex and varied *** focus in this paper on the ship classification from SAR imagery using a deep learning algorithms with transfer leaning mechanisms. To improve the recognition performances, several learning strategies are proposed. We illustrate these issues through applying a transfer learning on deep learning ship classification with several learning strategies. We used in this work especially no huge labelled dataset available for training. The aim is thus to see how to leverage knowledge from models pre-trained on other tasks (source tasks) and use them for target classification (target task). © 2022 IEEE.

关键词： remote sensing

来源：评论

学校读者我要写书评

暂无评论

The First Challenge on Moving Object Detection and Tracking in Satellite Videos: Methods and Results 26

The First Challenge on Moving Object Detection and Tracking ...

引用

26th International Conference on pattern recognition / 8th International Workshop on image Mining - Theory and Applications (IMTA)

作者： Guo, Yulan Yin, Qian Hu, Qingyong Zhang, Feng Xiao, Chao Zhang, Ye Wang, Hanyun Dai, Chenguang Yang, Jian Zhou, Zhuang Guo, Weilong Qi, Xiyu Tu, Kelong Xu, Cong Zhu, Shudan Chen, Lai Lin, Bin Xue, Chaocan Zheng, Jinlei Qin, Limei Li, Ying Zhao, Manqi Ruan, Lu Cui, Mingpeng Ding, Guanchen Jiang, Guangwei Chen, Zhenzhong Sun, Yuhan Cao, Kaiyang Kong, Lingyu Chen, Shaodong Zhao, Zhicheng Shen, Qin Liu, Lei Li, Chenglong Xiao, Yun Natl Univ Def Technol Changsha Peoples R China Univ Oxford Oxford England Informat Engn Univ Zhengzhou Peoples R China Chinese Acad Sci Technol & Engn Ctr Space Utilizat Beijing Peoples R China Chinese Acad Sci Key Lab Space Utilizat Beijing Peoples R China China Univ Geosci Wuhan Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Beijing Peoples R China Southwest Jiaotong Univ Chengdu Peoples R China Guilin Univ Technol Guilin Peoples R China Northwestern Polytech Univ Xian Peoples R China Wuhan Univ Sch Remote Sensing & Informat Engn Wuhan Peoples R China Wuhan Univ Wuhan Peoples R China Anhui Univ Hefei Peoples R China

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

In this paper, we briefly summarize the first challenge on moving object detection and tracking in satellite videos (SatVideoDT). This challenge has three tracks related to satellite video analysis, including moving object detection (Track 1), single object tracking (Track 2), and multiple-object tracking (Track 3). 123, 89, and 70 participants successfully registered, while 37, 42, and 29 teams submitted their final results on the test datasets for Tracks 1-3, respectively. The top-performing methods and their results in each track are described with details. This challenge establishes a new benchmark for satellite video analysis.

关键词： Satellites Object detection Benchmark testing pattern recognition Object tracking Videos

来源：评论

学校读者我要写书评

暂无评论

Proceedings of the 2022 11th International Conference on Computing and pattern recognition, ICCPR 2022

Proceedings of the 2022 11th International Conference on Com...

引用

11th International Conference on Computing and pattern recognition, ICCPR 2022

ISBN: (纸本)9781450397056

The proceedings contain 98 papers. The topics discussed include: multi-scale channel attention for Chinese scene text recognition;recognition of human walking motion using a wearable camera;an efficient lightweight spatio-temporal attention module for action recognition;rice disease recognition and feature visualization using a convolutional neural network;vehicle re-identification based on multi-scale attention feature fusion;improving pedestrian attribute recognition with dual adaptive fusion attention;coordinate attention-enabled ship object detection with electro-optical image;few-shot object detection via refining eigenspace;object detection algorithm based on coordinate attention and context feature enhancement;Swin transformer with multi-scale residual attention for semantic segmentation of remote sensing images;drivable area segmentation in unstructured roads for autonomous vehicles based on multi-sensor fusion;and a brief comparison of deep learning methods for semantic segmentation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Graph Regularisation for Guided Super-Resolution

Learning Graph Regularisation for Guided Super-Resolution

引用

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

作者： de Lutio, Riccardo Becker, Alexander D'Aronco, Stefano Russo, Stefania Wegner, Jan D. Schindler, Konrad Swiss Fed Inst Technol EcoVis Lab Photogrammetry & Remote Sensing Zurich Switzerland Univ Zurich Inst Computat Sci Zurich Switzerland

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

We introduce a novel formulation for guided super-resolution. Its core is a differentiable optimisation layer that operates on a learned affinity graph. The learned graph potentials make it possible to leverage rich contextual information from the guide image, while the explicit graph optimisation within the architecture guarantees rigorous fidelity of the high-resolution target to the low-resolution source. With the decision to employ the source as a constraint rather than only as an input to the prediction, our method differs from state-of-the-art deep architectures for guided super-resolution, which produce targets that, when downsampled, will only approximately reproduce the source. This is not only theoretically appealing, but also produces crisper;more natural-looking images. A key property of our method is that, although the graph connectivity is restricted to the Axel lattice, the associated edge potentials are learned with a deep feature extractor and can encode rich context information over large receptive fields. By taking advantage of the sparse graph connectivity, it becomes possible to propagate gradients through the optimisation layer and learn the edge potentials from data. We extensively evaluate our method on several datasets, and consistently outperform recent baselines in terms of quantitative reconstruction errors, while also delivering visually sharper outputs. Moreover, we demonstrate that our method generalises particularly well to new datasets not seen during training.

关键词： Deep learning Training Superresolution Optimization methods Lattices Computer architecture Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Feature Level Multi-Sensor Information Fusion Strategy for Land Region Classification

A Feature Level Multi-Sensor Information Fusion Strategy for...

引用

IEEE Applied imagery pattern recognition Workshop (AIPR)

作者： Schierl, Jonathan Asari, Vijayan Singer, Nina Aspiras, Theus Stokes, Andrew Keaffaber, Brett Van Rynbach, Andre Decker, Kevin Rabb, David Univ Dayton Vis Lab Dept Elect & Comp Engn Dayton OH 45469 USA US Air Force Res Lab Dayton OH USA Def Engn Corp Dayton OH USA

ISBN: (纸本)9781665424714

Deep learning has seen success in image recognition and classification in remote sensing research areas. Specifically, it is capable of classifying land coverage by its usage, such as determining if a plot of land is a residential area, industrial area, forest, etc. This is useful for quickly parsing datasets for surveillance applications and also for autonomously categorizing municipal land for urban planning. However, current methods learn and classify based on a single data stream (EO) and consequentially a single set of features. Our approach for land classification, LandNet, uses a feature-level fusion approach of both EO and LiDAR data in a deep learning classification system. In our approach, we use an aerial dataset of geo-registered scenes captured by both EO and LiDAR sensors. We propose a deep-learning based feature-level fusion framework for integrating information extracted from 2D and 3D data. In our preliminary testing, we observed that this proposed network is a more effective approach as it employs feature sets of multiple sensors, and it outperforms each of the individual modalities.

关键词： lidar aerial imagery fusion point clouds 3D processing deep learning remote sensing GIS mapping geospatial intelligence computer vision machine learning wide area surveillance automatic target recognition scene understanding classification transfer learning

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：