检索结果-内蒙古大学图书馆

Automatic Meter Reading from UAV Inspection Photos in the Substation by Combining YOLOv5s and DeeplabV3+

SENSORS 2022年第18期22卷 7090-7090页

作者： Deng, Guanghong Huang, Tongbin Lin, Baihao Liu, Hongkai Yang, Rui Jing, Wenlong Guangzhou iMapCloud Intelligent Technol Co Ltd Guangzhou 510095 Peoples R China Guangdong Acad Sci Guangzhou Inst Geog Guangdong Prov Engn Lab Geog Spatiotemporal Big D Key Lab Guangdong Utilizat Remote Sensing & Geog Guangzhou 510070 Peoples R China

The combination of unmanned aerial vehicles (UAVs) and artificial intelligence is significant and is a key topic in recent substation inspection applications;and meter reading is one of the challenging tasks. This paper proposes a method based on the combination of YOLOv5s object detection and Deeplabv3+ image segmentation to obtain meter readings through the post-processing of segmented images. Firstly, YOLOv5s was introduced to detect the meter dial area and the meter was classified. Following this, the detected and classified images were passed to the image segmentation algorithm. The backbone network of the Deeplabv3+ algorithm was improved by using the MobileNetv2 network, and the model size was reduced on the premise that the effective extraction of tick marks and pointers was ensured. To account for the inaccurate reading of the meter, the divided pointer and scale area were corroded first, and then the concentric circle sampling method was used to flatten the circular dial area into a rectangular area. Several analog meter readings were calculated by flattening the area scale distance. The experimental results show that the mean average precision of 50 (mAP50) of the YOLOv5s model with this method in this data set reached 99.58%, that the single detection speed reached 22.2 ms, and that the mean intersection over union (mIoU) of the image segmentation model reached 78.92%, 76.15%, 79.12%, 81.17%, and 75.73%, respectively. The single segmentation speed reached 35.1 ms. At the same time, the effects of various commonly used detection and segmentation algorithms on the recognition of meter readings were compared. The results show that the method in this paper significantly improved the accuracy and practicability of substation meter reading detection in complex situations.

关键词： object detection image segmentation YOLOv5s Deeplabv3+ meter reading

来源：评论

学校读者我要写书评

暂无评论

Seasonal inundation dynamics and water balance of the Mara Wetland, Tanzania based on multi-temporal Sentinel-2 image classification

引用

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION 2022年 109卷

作者： Kool, Juliette Lhermitte, Stef Hrachowitz, Markus Bregoli, Francesco McClain, Michael E. Delft Univ Technol Dept Water Management Bldg 23Stevinweg 1 NL-2628 CN Delft Netherlands Delft Univ Technol Dept Geosci & Remote Sensing Bldg 23Stevinweg 1 NL-2628 CN Delft Netherlands IHE Delft Inst Water Educ Dept Water Resources & Ecosyst Westvest 7 NL-2611 AX Delft Netherlands Radboud Univ Nijmegen Dept Environm Sci Heyendaalseweg 135 NL-6525 AJ Nijmegen Netherlands

Anthropogenic hydrologic alternations are a threat to flood dependent wetland ecosystems like The Mara Wetland in Tanzania, which plays an important role in regulating the quality, timing and magnitude of the flow of water into Lake Victoria and provides natural resources and habitat for a variety of species. Baseline information on the spatiotemporal dynamics of the seasonal inundation is critical to manage potential threats such as dam construction and local climate change, but is challenging to acquire due to the heterogeneity of the landscape caused by the interspersion of open water and emergent vegetation. In this study, intra- and inter-annual inundation pattern of the Mara Wetland are reproduced for 2017-2019 using remotely sensed data. A Random Forest (RF) algorithm is trained bi-seasonally, using eight Sentinel-2 bands, five water- and vegetation-indices and a Digital Surface Model (DSM) to classify the land cover of the wetland region in a semi-automated way, by processing a total of 73 Sentinel-2 scenes based on wet- and dry-state training images for 2017. The scenes are classified into seven classes;three wetland- and four dryland-classes. The overall classification accuracy achieved (based on an independent validation set) is 98.6%. The inundation extents are used in combination with available hydrological field-data to estimate the water balance. The seasonal expansion and contraction of the wetland follows a consistent bi-modal regime, and the results from the water balance affirm the importance of river-flow during the dry-season and local precipitation for the seasonal fluctuations in water-availability.

关键词： Wetlands remote sensing Sentinel-2 Ecosystem Services Hydrology Lake Victoria

来源：评论

学校读者我要写书评

暂无评论

Fire Detection based on Smoke image using Convolutional Neural Network (CNN) 4

Fire Detection based on Smoke Image using Convolutional Neur...

引用

4th International Conference on Cybernetics and Intelligent System, ICORIS 2022

作者： Zulkarnain, Jefri Pahlevi, Mohammad Rezza Astica, Yustikamasy Pangestuti, Widi Kusrini, Kusrini Amikom University Yogyakarta Magister of Informatics Engineering Yogyakarta Indonesia

ISBN: (纸本)9781665453950

Forest fire is a natural disaster that is difficult to control and has a very wide scope that threatens forest ecosystems [1]. In Indonesia itself, forest area decreases every year, one of the causes of the reduction in forest area in Indonesia is forest fires and illegal logging. On this basis, a remote fire detection system is designed and can monitor large forest areas so that problems caused by fires can be minimized. The existing technology in computer vision is a combination of image processing and pattern recognition. The results show that the convolutional neural network has good performance in the field of image processing and obtains architectural optimization in its area. In the smoke image detection research, the accuracy results are very good, namely 99.72% using the Convolutional Neural Network method. © 2022 IEEE.

关键词： Smoke

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence and Machine Learning in Optical Information processing: introduction to the feature issue

引用

APPLIED OPTICS 2022年第7期61卷 AIML1-AIML1页

作者： Iftekharuddin, Khan Preza, Chrysanthe Awwal, Abdul Ahad S. Zelinski, Michael E. Old Dominion Univ 5115 Hampton Blvd Norfolk VA 23529 USA Univ Memphis 3720 Alumni Ave Memphis TN 38152 USA Lawrence Livermore Natl Lab Livermore CA 94550 USA

This special feature issue covers the intersection of topical areas in artificial intelligence (AI)/machine learning (ML) and optics. The papers broadly span the current state-of-the-art advances in areas including image recognition, signal and image processing, machine inspection/vision and automotive as well as areas of traditional optical sensing, interferometry and imaging. (C) 2022 Optica Publishing Group

关键词： image processing image recognition Interferometry Object detection Optical sensing pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Compact Deep Color Features for remote sensing Scene Classification

引用

NEURAL processing LETTERS 2021年第2期53卷 1523-1544页

作者： Anwer, Rao Muhammad Khan, Fahad Shahbaz Laaksonen, Jorma Incept Inst Artificial Intelligence Abu Dhabi U Arab Emirates Aalto Univ Dept Informat & Comp Sci Sch Sci Espoo Finland

Aerial scene classification is a challenging problem in understanding high-resolution remote sensing images. Most recent aerial scene classification approaches are based on Convolutional Neural Networks (CNNs). These CNN models are trained on a large amount of labeled data and the de facto practice is to use RGB patches as input to the networks. However, the importance of color within the deep learning framework is yet to be investigated for aerial scene classification. In this work, we investigate the fusion of several deep color models, trained using color representations, for aerial scene classification. We show that combining several deep color models significantly improves the recognition performance compared to using the RGB network alone. This improvement in classification performance is, however, achieved at the cost of a high-dimensional final image representation. We propose to use an information theoretic compression approach to counter this issue, leading to a compact deep color feature set without any significant loss in accuracy. Comprehensive experiments are performed on five remote sensing scene classification benchmarks: UC-Merced with 21 scene classes, WHU-RS19 with 19 scene types, RSSCN7 with 7 categories, AID with 30 aerial scene classes, and NWPU-RESISC45 with 45 categories. Our results clearly demonstrate that the fusion of deep color features always improves the overall classification performance compared to the standard RGB deep features. On the large-scale NWPU-RESISC45 dataset, our deep color features provide a significant absolute gain of 4.3% over the standard RGB deep features.

关键词： remote sensing Deep learning Scene classification Color features Feature compression

来源：评论

学校读者我要写书评

暂无评论

image Classification via Multi-branch Position Attention Network 3rd

Image Classification via Multi-branch Position Attention Ne...

引用

3rd International Conference on pattern recognition and Artificial Intelligence, ICPRAI 2022

作者： Zhang, Ke Yang, Jun Yuan, Kun Wei, Qing-Song Chen, Si-Bao State Grid Power Research Institute Hefei230086 China School of Information Science and Technology University of Science and Technology of China Hefei230026 China School of Computer Science and Technology Anhui University Hefei230601 China

ISBN: (纸本)9783031090363

image classification is a hot spot in the field of pattern recognition and artificial intelligence. When there are apparent inter-class similarity and intra-class diversity, such as in the area of remote sensing, image classification becomes very challenge. With the continuous development of convolutional neural networks, a major breakthrough has been made in image classification. Although good performance have been achieved, there is still some room for improvement. First, in addition to global information, local features are crucial to image classification. Second, minimizing/maximizing the distance from the same/different classes allows the key points in image classification to be given full attention. In this paper, we propose an image classification method which is named multi-branch position attention network (MBPANet). We design a channel attention module containing position information, called Position Channel Attention Module (PCAM), and synthesize a new attention module Position Spatial Attention Module (PSAM) with a spatial attention module Local Spatial Attention Module (LSAM). The features obtained by the attention weighting method not only obtain local neighborhood semantic information but also contain global semantic information. Extensive experiments on three benchmark datasets show that our approach outperforms state-of-the-art methods. © 2022, Springer Nature Switzerland AG.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Joint Token and Feature Alignment Framework for Text-Based Person Search

引用

IEEE SIGNAL processing LETTERS 2022年 29卷 2238-2242页

作者： Li, Shangze Lu, Andong Huang, Yan Li, Chenglong Wang, Liang Anhui Univ Sch Comp Sci & Technol Anhui Prov Key Lab Multimodal Cognit Computat Hefei 230601 Peoples R China Anhui Univ Sch Artificial Intelligence Informat Mat & Intelligent Sensing Lab Anhui Prov Anhui Prov Key Lab Multimodal Cognit Computat Hefei 230601 Peoples R China Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing 100190 Peoples R China

Text-based person search is a challenging cross-modal retrieval task. Existing works reduce the inter-modality and intra-class gaps by aligning local features extracted from image and text modalities, which easily lead to mismatching problems due to the lack of annotation information. Besides, it is sub-optimal to reduce two gaps simultaneously in the same feature space. This work proposes a novel joint token and feature alignment framework to reduce the inter-modality and intra-class gaps progressively. Specifically, we first build a dual-path feature learning network to extract features and conduct feature alignment to reduce the inter-modality gap. Second, we design a text generation module to generate token sequences using visual features, and then token alignment is performed to reduce the intra-class gap. Last, a fusion interaction module is introduced to further eliminate the modality heterogeneity using the strategy of multi-stage feature fusion. Extensive experiments on the CUHK-PEDES dataset demonstrate the effectiveness of our model, which significantly outperforms previous state-of-the-art methods.

关键词： Feature extraction Visualization Representation learning Logic gates image reconstruction Transformers Training Cross-modal generation feature alignment text-based person search token alignment transformer

来源：评论

学校读者我要写书评

暂无评论

An Improved Infrared and Visible image Fusion Using an Adaptive Contrast Enhancement Method and Deep Learning Network with Transfer Learning

引用

remote sensing 2022年第4期14卷 939页

作者： Bhutto, Jameel Ahmed Tian, Lianfang Du, Qiliang Sun, Zhengzheng Yu, Lubin Soomro, Toufique Ahmed South China Univ & Technol Sch Automat Sci & Engn Guangzhou 510640 Peoples R China Southern Marine Sci & Engn Guangdong Lab Zhuhai Zhuhai 519080 Peoples R China Minist Nat Resources Key Lab Marine Environm Survey Technol & Applicat Guangzhou 510300 Peoples R China Quaid E Awam Univ Sci & Technol Elect Engn Dept Nawabshah 67480 Pakistan

Deep learning (DL) has achieved significant attention in the field of infrared (IR) and visible (VI) image fusion, and several attempts have been made to enhance the quality of the final fused image. It produces better results than conventional methods;however, the captured image cannot acquire useful information due to environments with poor lighting, fog, dense smoke, haze, and the noise generated by sensors. This paper proposes an adaptive fuzzy-based preprocessing enhancement method that automatically enhances the contrast of images with adaptive parameter calculation. The enhanced images are then decomposed into base and detail layers by anisotropic diffusion-based edge-preserving filters that remove noise while smoothing the edges. The detailed parts are fed into four convolutional layers of the VGG-19 network through transfer learning to extract features maps. These features maps are fused by multiple fusion strategies to obtain the final fused detailed layer. The base parts are fused by the PCA method to preserve the energy information. Experimental results reveal that our proposed method achieves state-of-the-art performance compared with existing fusion methods in a subjective evaluation through the visual experience of experts and statistical tests. Moreover, the objective assessment parameters are conducted by various parameters (FMI, SSIMa, API, EN, Q(F)(AB), and N-F(AB)) which were used in the comparison method. The proposed method achieves 0.2651 to 0.3951, 0.5827 to 0.8469, 56.3710 to 71.9081, 4.0117 to 7.9907, and 0.6538 to 0.8727 gain for FMI, SSIMa, API, EN, and Q(F)(AB), respectively. At the same time, the proposed method has more noise reduction (0.3049 to 0.0021) that further justifies the efficacy of the proposed method than conventional methods.

关键词： deep learning image fusion computer vision pattern recognition machine learning

来源：评论

学校读者我要写书评

暂无评论

Swin Transformer with Multi-Scale Residual Attention for Semantic Segmentation of remote sensing images 22

Swin Transformer with Multi-Scale Residual Attention for Sem...

引用

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

作者： Yuanyang Lin Da-han Wang Yun Wu Shunzhi Zhu Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen University of Technology China

ISBN: (纸本)9781450397056

Semantic segmentation of remote sensing images usually faces the problems of unbalanced foreground-background, large variation of object scales, and significant similarity of different classes. The FCN-based fully convolutional encoder-decoder architecture seems to have become the standard for semantic segmentation, and this architecture is also prevalent in remote sensing images. However, because of the limitations of CNN, the encoder cannot obtain global contextual information, which is extraordinarily important to the semantic segmentation of remote sensing images. By contrast, in this paper, the CNN-based encoder is replaced by Swin Transformer to obtain rich global contextual information. Besides, for the CNN-based decoder, we propose a multi-level connection module (MLCM) to fuse high-level and low-level semantic information to help feature maps obtain more semantic information and use a multi-scale upsample module (MSUM) to join the upsampling process to recover the resolution of images better to get segmentation results preferably. The experimental results on the ISPRS Vaihingen and Potsdam datasets demonstrate the effectiveness of our proposed method.

关键词： Dilated Convolution Semantic Segmentation remote sensing Swin Transformer

来源：评论

学校读者我要写书评

暂无评论

remote sensing image Super-Resolution via Efficient Non-Local Feature Extraction Strategy 23

Remote Sensing Image Super-Resolution via Efficient Non-Loca...

引用

Proceedings of the 2023 6th International Conference on Artificial Intelligence and pattern recognition

作者： Jinpeng Shi Dong Liang Shizhuang Weng Anhui University School of Electronic and Information Engineering China

ISBN: (纸本)9798400707674

remote sensing (RS) images typically exhibit com plex spatial distributions, making non-local features critical for achieving high-quality super-resolution (SR). Most existing SR networks extract local and non-local features alternately, making the non-local feature to be explored at high spatial resolution. This leads to substantial computational costs and limits the performance of these networks. In this paper, we propose an efficient non-local feature extraction strategy to solve this problem. Specifically, we propose a dual branch super-resolution network (DBSRN) with different branches focusing on local and non-local feature extraction. For the local feature extraction branch (LFEBranch), we design an adaptive feature enhancement block (AFEB) to optimize its processing of local features. For the non-local feature extraction branch (NFEBranch), we propose a non-local feature aggregation block (NFAB) to extract non-local features more efficiently by continuously reducing the spatial resolution of the input. Extensive experiments have demonstrated that the proposed DBSRN can effectively leverage the non-local features of RS images, resulting in superior SR performance compared to state-of-the-art networks.

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：