检索结果-内蒙古大学图书馆

5th IEEE International image processing, Applications and Systems Conference, IPAS 2022

ISBN: (纸本)9781665462198

The proceedings contain 59 papers. The topics discussed include: comparative studies on similarity distances for remote sensing image classification;combination of object tracking and object detection for animal recognition;a combined acute and chronic risk assessment rolling window for type 1 diabetes;evaluating attention in convolutional neural networks for blended images;computer vision-based Bengali sign language to text generation;experimental validation of photogrammetry based 3D reconstruction software;vehicle color identification framework using pixel-level color estimation from segmentation masks of car parts;image processing and control of tracking intelligent vehicle based on grayscale camera;a light weight approach for real-time background subtraction in camera surveillance systems;real-time powered wheelchair assistive navigation system based on intelligent semantic segmentation for visually impaired users;innovative tools for investigation on flame dynamics by means of fast imaging;and improving 3D point cloud reconstruction with dynamic tree-structured capsules.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Amalgamation of Dynamic DNA and Two Novel Chaotic Maps for Satellite image Encryption

引用

Journal of the Indian Society of remote sensing 2025年 1-22页

作者： Dua, Mohit Jadon, Suraj Singh Raghuvanshi, Anant Vishwakarma, Deepanshu Dua, Shelza Dhingra, Deepti Department of Computer Engineering NIT Kurukshetra India Department of Electronics and Communication Engineering NIT Kurukshetra India Department of Computer Science and Engineering PIET Samalkha India

image encryption has gained significant attention these days due to the increasing need for secured transmission and storage of digital images. The traditional encryption algorithms that are based on mathematical operations, and symmetric key ciphers have shown vulnerabilities to attacks and are not well-suited for effectively securing images. The work in this paper proposes two novel chaotic maps Chaotic-Harmonics (CH) chaotic map, and Sine–cosine-Hybrid (SCH) chaotic map. The unpredictability, complexity, randomness and initial condition sensitivity of these maps have also been evaluated in this work. The work further proposes a novel image encryption scheme using the proposed CH and SCH chaotic maps in combination with dynamic Deoxyribonucleic Acid (DNA) encoding to encrypt satellite images. Unlike static DNA encoding, where a fixed rule is applied throughout the encryption process, our scheme dynamically generates a sequence of encoding rules called as Dynamic DNA Rule Sequence (DDRS) using the CH and SCH chaotic maps. DDRS changes the encoding rules for each pixel, which adds complexity to the encryption scheme and makes it much harder for attackers to employ brute force or pattern recognition attacks to break the encryption. In the first phase of the proposed image cryptosystem, the colored input image is converted into an array, and DDRS is generated to encode each element of the image array. The second phase generates a Confusion Rule Sequence (CRS) using CH and SCH chaotic maps, and uses it with an encoded image array of the first phase to perform pixel permutation. The final phase generates a Diffusion Control Sequence (DCS) to using both novel proposed chaotic maps, and uses it with an output of the second phase to perform diffusion. The scheme undergoes rigorous security analysis to demonstrate its performance against various types of attack.

关键词： Chaos map Chaotic-harmonics DCS DDRS DNA encoding Sine–cosine-Hybrid

来源：评论

学校读者我要写书评

暂无评论

High-resolution sliding-spotlight spaceborne SAR imaging algorithm for Ka-band

High-resolution sliding-spotlight spaceborne SAR imaging alg...

引用

IET International Radar Conference (IRC 2023)

作者： Feng Xiao Maoqiang Jing Dehua He Guo Zhang JiaGuo Zu SongBai Yu HanWei Sun XinMin Wang Beijing Institute of Radio Measurement Beijing People's Republic of China State Key Laboratory of information Engineering in Surveying Mapping and Remote Sensing of Wuhan University Wuhan People's Republic of China Institute of Remote Sensing Satellites (IRSS) of the China Academy of Space Technology (CAST) Beijing People's Republic of China

ISBN: (数字)9781837240982

High-band spaceborne SAR offers image-like optics and broadens the application range of microwave remote sensing on space-based platforms. The sliding-spotlight mode fulfils the high-resolution detection requirements for target recognition in remote sensing and has gained significant attention and application in the industry. Given the differences between high-band spaceborne SAR data processing and traditional low-band spaceborne SAR data processing in terms of orbital accuracy analysis, key parameter calculation of imaging, algorithm acceleration, and parallelization, this study conducts an analysis of data accuracy, imaging, and image quality using real data from Luojia-2. The results demonstrate that the proposed imaging process method achieves high-precision imaging of the sliding-spotlight SAR real data from Luojia-2.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Use of Sentinel-1 Dual Polarization Multi-Temporal Data with Gray Level Co-Occurrence Matrix Textural Parameters for Building Damage Assessment

引用

pattern recognition AND image ANALYSIS 2021年第2期31卷 240-250页

作者： Akhmadiya, Asset Nabiyev, Nabi Moldamurat, Khuralay Dyussekeyev, Kanagat Atanov, Sabyrzhan S Seifullin Kazakh Agro Tech Univ Dept Radio Engn Elect & Telecommun Nur Sultan 010011 Kazakhstan Eurasian Natl Univ Dept Comp & Software Engn Nur Sultan 010011 Kazakhstan

In this research paper, change detection based methods were considered to find collapsed and intact buildings using radar remote sensing data or radar imageries. The main task of this research paper is the collection of most relevant scientific research in the field of building damage assessment using radar remote sensing data. Several methods are selected and presented as best methods in the present time, there are methods with using interferometric coherence, backscattering coefficients in different spatial resolution. In conclusion, methods are given in the end, which show, which methods and radar remote sensing data give more accuracy and more available for building damage assessment. Low-resolution Sentinel-1A/B radar remote sensing data are recommended as free available for monitoring of destruction on a degree microregion level. Change detection and texture-based methods are used together to increase overall accuracy. Homogeneity and Dissimilarity GLCM texture parameters found better for the separation of collapsed and intact buildings. Dual polarization (VV, VH) backscattering coefficients and coherence coefficients (before the earthquake and coseismic) were fully utilized for this study. There were defined the better multi variable for supervised classification of none building, damaged and intact buildings features in urban areas. In this work, we were achieved overall accuracy 0.77, producer's accuracy for none building is 0.84, for damaged building case 0.85, for intact building 0.64. Amatrice town was chosen as most damaged from the 2016 Central Italy Earthquake.

关键词： radar remote sensing building damage assessment change detection method Gray Level Co-occurrence Matrix

来源：评论

学校读者我要写书评

暂无评论

Vision Transformer is Required for Hyperspectral Semantic Segmentation 5

Vision Transformer is Required for Hyperspectral Semantic Se...

引用

5th International Conference on pattern recognition and Artificial Intelligence, PRAI 2022

作者： Chen, Yuhan Yan, Qingyun Nanjing University of Information Science and Technology School of Remote Sensing and Geomatics Engineering Nanjing China

ISBN: (数字)9781665499163

ISBN: (纸本)9781665499163

Convolutional Neural Networks (CNNs) are widely used in hyperspectral image classification with great success. However, CNNs have inductive biases in the architecture, local correlation and weight sharing, which in turn can be minimized by the Vision Transformer. Therefore, we try to apply the Vision Transformer to the hyperspectral classification task. But when training on the hyperspectral dataset, the original Vision Transformer is difficult to learn effective features, and it cannot make good use of the global spatial context information for pixel-level classification. In this paper, the vision transformer is lightweight with an improved lightweight attention mechanism being added to the encoder-decoder architecture. Therefore, Vision Transformer is successfully applied to hyperspectral semantic segmentation tasks. Our method is evaluated on three public datasets. Only 15% of the labeled data is used for training in IP, 3% in PU, and 1% in SA. The overall accuracy of our proposed VHSS is 99.85%, 99.88%, 99.83%. The results show that our method can effectively solve the problem of hyperspectral image classification. © 2022 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Advances in optoelectronic artificial synapses

引用

CELL REPORTS PHYSICAL SCIENCE 2022年第9期3卷

作者： Li, Ying Shen, Guozhen Chinese Acad Sci Inst Semicond State Key Lab Superlatt & Microstruct Beijing 100083 Peoples R China Beijing Inst Technol Sch Integrated Circuits & Elect Beijing 100081 Peoples R China

The biological neuromorphic system exhibits a high degree of con-nectivity to process information. Inspired by function, optoelec-tronic synapses are expected to pave a way to overcome the von Neumann bottleneck for nonconventional computing, which inte-grates synaptic and optical-sensing functions for visual information processing and complex learning and memory in an energy-efficient way. Herein, this review summarizes the working mechanisms of light-stimulated artificial synapses, including ionization and dissoci-ation of oxygen vacancies, capture and release of carriers through barriers formed by heterojunctions, capture and release of carriers at the semiconductor and dielectric interface, and phase transition. Then, we present a comprehensive overview of the advanced prog-ress in different material systems, including two-dimensional mate-rials, organic material, metal halide, and metal oxide. The existing application scenarios of various synaptic devices are outlined. Finally, the current challenges and perspective toward the develop-ment of optoelectronic artificial synapses are briefly discussed for future applications.

关键词： optoelectronic synapses ionization and dissociation of oxygen vacancies charge-trapping effect phase transition logic function image memory Pavlov’s dog pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Robust line segment matching across views via ranking the line-point graph

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND remote sensing 2021年 171卷 49-62页

作者： Wei, Dong Zhang, Yongjun Liu, Xinyi Li, Chang Li, Zhuofan Wuhan Univ Sch Remote Sensing & Informat Engn Wuhan 430079 Peoples R China Cent China Normal Univ Key Lab Geog Proc Anal & Simulat Wuhan 430079 Peoples R China

Line segment matching in two or multiple views is helpful to 3D reconstruction and pattern recognition. To fully utilize the geometry constraint of different features for line segment matching, a novel graph-based algorithm denoted as GLSM (Graph-based Line Segment Matching) is proposed in this paper, which includes: (1) the employment of three geometry types, i.e., homography, epipolar, and trifocal tensor, to constrain line and point candidates across views;(2) the method of unifying different geometry constraints into a line-point association graph for two or multiple views;and (3) a set of procedures for ranking, assigning, and clustering with the linepoint association graph. The experimental results indicate that GLSM can obtain sufficient matches with a satisfactory accuracy in both two and multiple views. Moreover, GLSM can be employed with large image datasets. The implementation of GLSM will be available soon at https://***/research/.

关键词： Line segment matching Graph rank Scene plane theory 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Multi-task Learning Based Single Temporal remote sensing image Change Detection 23

Multi-task Learning Based Single Temporal Remote Sensing Ima...

引用

Proceedings of the 2023 12th International Conference on Computing and pattern recognition

作者： Peixuan Yang Yichao Cao Xiaobo Lu Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University China

ISBN: (纸本)9798400707988

Change Detection is a classic and fundamental task in remote sensing(RS), and has accomplish remarkable achievement on bitemporal image based methods. However, bitemporal images are very expensive and needs professional researchers to align and label the paired images. Furthermore, most bitemporal image based methods are only semantic-aware not instance-aware, which indicates these methods only use paired images’ semantic information. Thus, we propose a method that only needs unpaired RS images with semantic labels. In this paper, we introduce multi-task learning into change detection progress, which comprises four major parts: Boundary-Aware Module, Contextual-Aware Module, Segmentation Module, Change Detection Module. At first, we construct Boundary-Aware Module and Contextual-Aware Module to extract sharp boundary and dense contextual features. Then we feed the feature maps to Change Detection Module and Segmentation Module to accomplish the subtasks. The comprehensive experiments on a single temporal image dataset demonstrate the efficiency of our approach over other bitemporal image based methods, and the experimental results shows our approach is competitive with other methods while all methods was trained on bitemporal image dataset.

关键词： Change Detection Multi-task Learning Single Temporal image

来源：评论

学校读者我要写书评

暂无评论

Algorithm Design of Infrared image Three-Dimensional Non-Stationary Noise Based on Time Series Statistics

Algorithm Design of Infrared Image Three-Dimensional Non-Sta...

引用

image processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Xianghao Kong Hezhi Sun Peng Bi Fengjie Zheng Xingfeng Chen Guotao Qin Yuan Sun China Academy of Space Technology Beijing China School of Space Information Space Engineering University Beijing China Chinese Academy of Sciences Aerospace Information Research Institute Beijing China School of Software Engineering Jiangxi University of Science and Technology Nanchang China

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

With the development of high orbit area array starting infrared imaging technology in China, the quality of its image directly affects the user’s use. Therefore, noise detection and supplementation of area array staring infrared images are becoming increasingly important. This paper presented a detection method of the infrared image of three-dimensional non-stationary noise based on Time Series Statistics to solve the effect of the three-dimensional non-stationary noise, which formed because many factors influenced the infrared image of staring Plane Array such as orbit time, the inherent flaw of detectors, and imaging conditions. Meanwhile, this paper also located and analyzed the non-stationary noise, and suggested a method of Local filtering by using the trend extrapolation theory. Based on the evaluation of the test result, the non-stationary noise recognition accuracy of this method could be up to 85% and the non-stationary noise image correlation coefficient before and after removal could be up to 95%, which could provide the satellite with real-time processing and improve the quality of the infrared image. This method can effectively improve the data quality and information product quality of high orbit array infrared remote sensing images, promote application level, and enhance application efficiency.

关键词： Accuracy Statistical analysis Noise Time series analysis Infrared imaging Orbits Spatiotemporal phenomena Arrays Noise measurement remote sensing

来源：评论

学校读者我要写书评

暂无评论

HyLiOSR: Staged Progressive Learning for Joint Open-Set recognition of Hyperspectral and LiDAR Data

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2025年 63卷

作者： Xi, Bobo Cai, Mingshuo Li, Jiaojiao Wang, Zhengjue Feng, Shou Li, Yunsong Chanussot, Jocelyn Xidian Univ Sch Telecommun Engn State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Xidian Univ Guangzhou Inst Technol Guangzhou 510000 Guangdong Peoples R China Chinese Acad Sci Natl Space Sci Ctr Beijing 100190 Peoples R China Xidian Univ Sch Artificial Intelligence State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Harbin Engn Univ Sch Informat & Commun Engn Harbin Peoples R China Univ Grenoble Alpes Inria CNRS Grenoble INPLJK F-38000 Grenoble France

The joint classification of hyperspectral images (HSIs) and light detection and ranging (LiDAR) data have seen significant advancements in recent research. However, it would be more practical if we could simultaneously detect the unknown classes in a more realistic open-set scenario. In this article, we introduce a novel open-set recognition (OSR) method for HSI and LiDAR data, termed HyLiOSR, which devises a staged progressive learning strategy to effectively bridge the gap between closed-set and open-set feature distributions within an autoencoder framework. Specifically, for the first stage, the reconstruction-based network is dedicated to accurately modeling each known category by learning multiple Gaussian prototypes, which facilitates OSR by disentangling the distribution of known classes. In the second stage, we actively synthesize samples of unknown classes during the feature extraction phase and create a virtual unknown classifier, enabling the network to effectively differentiate between known and unknown class samples. This approach establishes a distinct separation between known and unknown classes in the latent feature space, thereby enhancing the capability of the frameworks to distinguish between them. Comprehensive experiments conducted on three benchmark datasets demonstrate that the proposed HyLiOSR outperforms existing state-of-the-art methods. The source code will be accessible at https://***/B-Xi/TGRS_2025_HyLiOSR.

关键词： image reconstruction Prototypes Laser radar Feature extraction Autoencoders Training Electronic mail Vectors Transformers image recognition Autoencoder Gaussian prototypes hyperspectral image (HSI) light detection and ranging (LiDAR) open-set recognition (OSR)

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：