检索结果-内蒙古大学图书馆

5th International conference on Artificial Intelligence and pattern recognition, AIPR 2022

作者： Tang, Haoyang Shi, Jiakun Miao, Xin Wu, Ruichen Yang, Dongfang School of Automation Xi'an University of Posts and Telecommunications Xi'an710121 China School of Computer Science Xi'an University of Posts and Telecommunications Xi'an710121 China The Rocket Force University of Engineering Graduate School Xi'an710025 China

ISBN: (纸本)9781450396899

At present, the positioning function of intelligent UAVs mainly uses GPS technology, and GPS signals are susceptible to environmental and electromagnetic interference factors. In this paper, we combine remote sensing image processing with image matching algorithms to propose a GPS-independent visual localization technique for UAVs. First, the VGG16 network is used as the feature extraction backbone network, and the backbone network is designed and optimized for the characteristics of heterogenous remote sensing images. Secondly, a feature point screening and matching strategy is constructed, by which common feature points between heterogeneous remote sensing images can be screened and used for feature matching. Finally, the remote sensing image containing geographic location information and the UAV aerial image are fed into the network for feature extraction and matching, and the transformation matrix between the aligned images is calculated by the successfully matched feature points, and the transformation matrix is used to complete the mapping from the aerial image to the satellite image, and finally the geographic location information of each pixel can be read from the mapped image to complete the localization. © 2022 ACM.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

CNNX: A Low Cost, CNN Accelerator for Embedded System in Vision at Edge

引用

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2023年第2期48卷 1537-1545页

作者： Farahani, Ali Beithollahi, Hakem Fathi, Mahmood Barangi, Reza Iran Univ Sci & Technol Sch Comp Engn Tehran Iran

Convolutional neural networks (CNNs) have been widely deployed in artificial intelligence, including computer vision and pattern recognition. In these applications, CNN is the most computationally intensive part. Recently, many researchers have used depthwise convolution to decrease the computational load in the execution of CNNs;on the other hand, today, CNNs have become larger and larger. Consequently, they need more computational budget for their executions. The problem is more serious when this application is run in an embedded system, especially in the edge devices, as the embedded processor can hardly handle these heavy computational loads. This paper proposes a lightweight, low-power, and efficient CNN hardware accelerator for edge computing devices. This accelerator is explicitly designed for depthwise CNN. The proposed accelerator can be configured and programmed to run any lightweight CNN of a wide range of AI networks such as MobileNet, Xception, and shuffleNet. Our experimental results show that our accelerator can run MobileNet 70 times per second in a remote sensing AI application with a 224 x 224 pixel image from the imageNet dataset.

关键词： Convolutional neural networks (CNNs) Hardware accelerator Low power AI at edge Vision at edge Edge processing

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 6

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

引用

6th International conference on Artificial Intelligence and pattern recognition, AIPR 2023

作者： Shi, Jinpeng Liang, Dong Weng, Shizhuang School of Electronic and Information Engineering Anhui University 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. © 2023 ACM.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Study on the Spatial pattern of Small Towns Based on Computer image processing and image recognition - Taking Guanhaiwei Town of Cixi as an Example

Study on the Spatial Pattern of Small Towns Based on Compute...

引用

2023 International conference on remote sensing, Mapping, and Geographic Systems, RSMG 2023

作者： Yu, Qiqi School of Tourism and Urban-Rural Planning Zhejiang Gongshang University Hangzhou310018 China

ISBN: (纸本)9781510668898

This paper uses GIS and Fragstats4.2 software to quantitatively analyze the landscape space of Guanhaiwei Town, and visualize the data combined with image processing technology to enhance its spatial expression, analyze the hydrological characteristics of river corridors in Guanhaiwei Town, and the accessibility of traffic corridors, etc., and summarize the current problems. It is found that the construction land patches are concentrated on the traffic arteries and there are construction land disturbances within the woodland patches;the construction land is widely distributed, with scattered scattered points and irregular shapes. The woodland is mainly distributed in the south of the town, and the green patches in the town are less and the layout of green space is not reasonable enough, and the articulation with the surrounding landscape is weak. In the traffic land, the patches are highly fragmented and the landscape area is small. The patches of agricultural land are the landscape matrix, but their edges are highly fragmented, with small patches distributed sporadically and irregular in shape. The water patches were highly fragmented and no isolation zone was established. The study used GIS for image processing and spatial analysis, which fully reflects the importance and application of computer technology in geographic research. © 2023 SPIE.

关键词： Geographic information systems

来源：评论

学校读者我要写书评

暂无评论

OB-ConvLSTM: A sequential remote sensing crop classification model with OBIA and ConvLSTM models 11

OB-ConvLSTM: A sequential remote sensing crop classification...

引用

11th International conference on Agro-Geoinformatics, Agro-Geoinformatics 2023

作者： Luo, Chen Li, Haiyang Zhang, Jie Wang, Yaojun China Agricultural University College of Information and Electrical Engineering Beijing China

ISBN: (纸本)9798350303513

remote sensing technology has become increasingly important in recent years due to its ability to collect high-resolution images of agricultural fields. One of the most popular methods for crop classification in agricultural fields is object-based image analysis (OBIA). At the same time, the convolutional long short-term memory (ConvLSTM) network has shown great potential in processing spatiotemporal *** this study, we proposed a new model called OB-ConvLSTM (Object-based ConvLSTM) that combines OBIA and ConvLSTM for spatiotemporal crop classification tasks. This model extracts crop spectral information from the spatial dimension of remote sensing images, extracts crop growth information from multiple remote sensing images in the temporal dimension, and synthesizes the spatial and temporal dimension information to improve crop classification accuracy. Compared with traditional crop classification models based on single temporal remote sensing, the model proposed in this study is superior to existing models in classification accuracy and model robustness. The proposed OB-ConvLSTM model has been applied to crop classification tasks in major crop-producing regions, achieving over 93% of the crop species recognition accuracy, with mIoU reaching 83%.The main contribution of this study is to design a temporal remote sensing image semantic segmentation model structure suitable for field crop classification, combining the OBIA method with ConvLSTM and improving the model's performance by optimizing model components such as activation functions and optimizers. Specifically, there are several innovations in the following aspects: First, to facilitate model input, this study uses the SLIC algorithm to segment remote sensing images into uniformly sized superpixel objects and aligns the superpixel objects in the temporal dimension;Subsequently, we used the ConvLSTM model totrain and classify superpixel objects with temporal information, and adopted the Mish activation functi

关键词： remote sensing

来源：评论

学校读者我要写书评

暂无评论

LiDAR-Based Point Cloud Data processing Application Research 5

LiDAR-Based Point Cloud Data Processing Application Research

引用

5th International conference on Geoscience and remote sensing Mapping, GRSM 2023

作者： Zheng, Zichuan Zhang, Xiaoting Zhou, Wanxin School of Information Engineering Northwest Agriculture and Forestry University Shaanxi Yangling China

ISBN: (纸本)9798350329551

LiDAR technology is widely used for point cloud data acquisition in geographic mapping, ecological surveying, etc., which facilitates the research. The PointNet model is a pioneering representative of deep learning technology and semantic segmentation of 3D point cloud, which improves the network generalization ability through a large number of trainings, but at the same time there are problems such as loss of detail data, complex scene recognition accuracy lower, and incomplete local feature extraction. Attention mechanism is a technique in deep learning that enables the network to focus on valid data and discard invalid data in the process of image processing. The attention mechanism can make the local features of point cloud data under deep learning more distinctive, so that the local features can be extracted more completely and accurately. In this paper, we propose to use PointN et network, combined with our own collected dataset for semantic segmentation experiments. And the attention mechanism is introduced to improve the recognition ability of Point Net network as well as the accuracy of segmentation. © 2023 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

image enhancement model for ultrasonic nondestructive testing based on deep learning super-resolution 12

Image enhancement model for ultrasonic nondestructive testin...

引用

SPIE 12th International Symposium on Multispectral image processing and pattern recognition, MIPPR 2023

作者： Zhu, Jinxuan Zhang, Xinfang He, Ruixian Kang, Luo Wang, Guoyou Huang, Yan School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Institute of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (数字)9781510675001

ISBN: (纸本)9781510674998

Ultrasonic nondestructive testing has been widely used in industry due to its various advantages. However. with the increasing demand for non-destructive testing accuracy, low-resolution ultrasonic images can easily lead to misidentification of defects. How to improve the resolution of ultrasonic images has become a key issue restricting development of the non-destructive testing industry. Therefore. this paper proposes a super-resolution model for ultrasonic NDT images consisting of up and down sampling layers and deep residual networks. The model learns the degraded features of the image through the up and down sampling layers, and learns the intrinsic features of the image through the deep residual network, so as to learn the feature information of the image more completely to complete the super-resolution task of the image. Experimental results on ultrasound image datasets also validate the effectiveness of the model, outperforming other models in peak signa-to-noise ratio (PSNR) and structural similarity (SSIM) metrics. © 2024 SPIE.

关键词： Nondestructive examination

来源：评论

学校读者我要写书评

暂无评论

Estimation of Varietal Classification and Quality Analysis in Rice Seeds Using Digital image processing - A Survey

Estimation of Varietal Classification and Quality Analysis i...

引用

2023 IEEE International conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： Sandhiya, M. Christy, S. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

ISBN: (纸本)9798350305708

Agriculture plays a major role in today's world. 70% of rice production is cultivated in south India. Thailand, the US, India, Vietnam, etc., are exporting rice all over the world. But they are facing one of the most difficult tasks: assuring the rice seed quality. Good seeds can increase production, so selecting seeds is very important. A maximum of the work was done physically or by using huge, expensive machines. For choosing good seeds, agronomists be conscious of two factors, such as the variety which is determined by some quality criteria, and next by the skilled one who is going to analyze the rice seed physically. Both tasks take a long time and the result of accuracy is also not as expected. Nowadays computer vision technology with Digital image processing plays a major role in many fields, namely agronomy, healthcare, machine vision, pattern recognition, remote sensing, Video processing, etc. Our research work mainly focuses on the agricultural arena, going to provide good quality seeds and identify dissimilar varieties of rice seeds by digital image processing techniques such as image capturing, segmenting the rice seeds, extracting the features from the rice seeds and finally feeding into the machine learning algorithm to find out the accuracy too. © 2023 IEEE.

关键词： Classification of rice seeds Machine learning algorithm Machine vision Quality analysis of rice seed Rice seed varietal purity

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal Evolution of Total Nitrogen in Xixi River Based on Sentinel-2 remote sensing images

Spatio-temporal Evolution of Total Nitrogen in Xixi River Ba...

引用

2024 International conference on remote sensing and Global Positioning Algorithm, RSGPA 2024

作者： Wei, Chenyan Fu, Haiyan Zheng, Yuanmao Fujian Engineering Research Center of Rural Sewage Treatment and Water Safety Xiamen University of Technology Xiamen361024 China

remote sensing technology holds significant advantages in the analysis of aquatic ecological environments, including rapid processing speed, abundant information, extensive spatial coverage, and high reliability. Total nitrogen, as a key indicator for assessing the eutrophication state of water bodies, has important application value in evaluating aquatic ecological environments and water quality monitoring. By analyzing the spatiotemporal changes in the concentration of total nitrogen, the dynamic changes in water quality can be effectively reflected. This study selected the Xixi River in Tong’an District, Xiamen City, as the research subject, using six Sentinel-2 satellite remote sensing image data from 2018 to 2023 to construct an empirical regression model for remote sensing inversion of the total nitrogen concentration in the study area. The spatiotemporal evolution of the research results was analyzed, to achieve real-time monitoring and assessment of water quality. The study results indicate that from 2018 to 2023, the total nitrogen concentration in the Xixi River showed a cyclical fluctuation pattern of first increasing, then decreasing and increasing again. The concentration reached its lowest in 2021, at 2.415 mg/L, and the research findings can provide important support for the sustainable development of the river. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Eutrophication

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Review on Lossy and Lossless Compression Techniques

引用

Journal of The Institution of Engineers (India): Series B 2022年第3期103卷 1003-1012页

作者： Elakkiya, S. Thivya, K.S. Department of Electronics and Communication Engineering Dr.M.G.R. Educational and Research Institute Tamil Nadu Chennai India

images are now employed as data in a variety of applications, including medical imaging, remote sensing, pattern recognition, and video processing. image compression is the process of minimizing the size of images by removing or grouping certain parts of an image file without affecting the quality, thereby saving storage space and bandwidth. image compression plays a vital role where there is a need for images to be stored, transmitted, or viewed quickly and efficiently. There are different techniques through which images can be compressed. This paper mainly focuses on the survey of basic compression techniques available and the performance metrics that are used to evaluate them. In addition to this, it also provides a review of important pieces of the literature relating to advancements in the fundamental lossy and lossless compression algorithms. © 2021, The Institution of Engineers (India).

关键词： image compression

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：