检索结果-内蒙古大学图书馆

Data Science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： v. Arthi R. Murugeswari Nagaraj P Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Krishnankoil Virudhunagar India

ISBN: (纸本)9798350333855

The computer vision systems that are responsible for driving Autonomous vehicles (Av) are evaluated based on their capacity to recognize obstacles and objects located close to the vehicle in a variety of settings. An essential obstacle when it is related to computer vision is finding a way to improve the capacity of an Av to differentiate between the components of its surroundings, even when operating in challenging conditions. For instance, unfavorable weather conditions such as fog and rain can cause image corruption, which in turn can result in a significant reduction in the performance of Object Detection (OD). The primary navigation of Avs is dependent on the efficacy of the image processing algorithms that are used for the data collected from the many different visual sensors. This information is gathered by the vehicle itself. Therefore, it is of the utmost importance to cultivate the capacity to recognize items such as road lanes, automobiles, and pedestrians under adverse conditions such as bad weather. The main purpose of this article is to examine the related works concerning weather detection and OD. Significant objects such as road lanes, vehicles, and pedestrians are considered for review.

关键词： Computer vision visualization Rain Navigation Roads vehicle detection Object detection

来源：评论

学校读者我要写书评

暂无评论

The Tangential velocity MTI algorithms in Space-borne systems for Remote Sensing of the Earth

The Tangential Velocity MTI Algorithms in Space-borne System...

引用

2020 Russian Open Scientific Conference on Modern Problems of Remote Sensing, Radar, Wave Propagation and Diffraction, MPRSRWPD 2020

作者： Kostrov, v.v. Tolstov, E.F. Khramov, K.K. Murom Institute of Vladimir State University Murom Russia Head of Department Aerocon Company Zhukovsky Russia

In this paper, the problem of moving target indication (MTI) using synthetic aperture radar (SAR) is considered. The focus of the article is the tangential component of velocity. Two tangential velocity MTI algorithms are considered. The first algorithm uses two apertures with various synthetic time of the radar image (AvST algorithm), and the second uses two apertures displaced along trajectory (ADAT algorithm). The structure of the MTI system based on the analysis of phase and amplitude radar images is considered. For S band and X band SAR, the phase change in the trajectory signal of a moving target, the effects of shift and bifurcation of target responses on the radar image are analyzed in detail. It was found that the AvST algorithm has a small working range of unambiguous velocity estimate (up to ±10 m/s). It is shown that the ADAT algorithm has a higher quality of work in a wide velocity range and can effectively suppress the signals of stationary objects by 20...30 dB. The obtained characteristics allow us to make demands on the parameters of space-borne systems for remote sensing of the Earth and processing systems. © Published under licence by IOP Publishing Ltd.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Augmented visualization by computer vision and chromatographic fingerprinting on comprehensive two-dimensional gas chromatographic patterns: Unraveling diagnostic signatures in food volatilome

引用

JOURNAL OF CHROMATOGRAPHY A 2023年第1期1699卷 464010页

作者： Caratti, Andrea Squara, Simone Bicchi, Carlo Tao, Qingping Geschwender, Daniel Reichenbach, Stephen E. Ferrero, Francesco Borreani, Giorgio Cordero, Chiara Univ Torino Dipartimento Sci & Tecnol Farmaco Via Pietro Giuria 9 I-10125 Turin Italy GC Image LLC Lincoln NE USA Univ Nebraska Lincoln Comp Sci & Engn Dept Lincoln NE USA Univ Torino Dept Agr Forestry & Food Sci Grugliasco Italy

Computer vision is an approach of Artificial Intelligence (AI) that conceptually enables "computers and systems to derive useful information from digital images " giving access to higher-level information and "take actions or make recommendations based on that information ". Comprehensive two-dimensional chro-matography gives access to highly detailed, accurate, yet unstructured information on the sample's chem-ical composition, and makes it possible to exploit the AI concepts at the data processing level (e.g., by Computer vision) to rationalize raw data explorations. The goal is the understanding of the biolog-ical phenomena interrelated to a specific/diagnostic chemical signature. This study introduces a novel workflow for Computer vision based on pattern recognition algorithms (i.e., combined untargeted and targeted UT fingerprinting) which includes the generation of composite Class images for representa-tive samples' classes, their effective re-alignment and registration against a comprehensive feature tem-plate followed by Augmented visualization by comparative visual analysis. As an illustrative applica-tion, a sample set originated from a Research Project on artisanal butter (from raw sweet cream to ripened butter) is explored, capturing the evolution of volatile components along the production chain and the impact of different microbial cultures on the finished product volatilome. The workflow has significant advantages compared to the classical one-step pairwise comparison process given the abil-ity to realign and pairwise compare both targeted and untargeted chromatographic features belong-ing to Class images resembling chemical patterns from many different samples with intrinsic biological variability. (c) 2023 Elsevier B.v. All rights reserved.

关键词： Comprehensive two-dimensional gas chromatography Augmented visualization Ut fingerprinting Butter volatilome analysis Chromatograms registration and alignment

来源：评论

学校读者我要写书评

暂无评论

Classification of Landsat 8 imagery Using Kohonen’s Self Organizing Maps and Learning vector Quantization

Classification of Landsat 8 Imagery Using Kohonen’s Self Or...

引用

International Conference on vLSI, Signal processing, Power systems, Illumination and Lighting Control, Communication and Embedded systems, vSPICE 2019

作者： Shivakumar, B.R. Rajashekararadhya, S.v. Department of E&C Engineering N.M.A.M. Institute of Technology Nitte Karkala India Department of E&C Engineering Kalpataru Institute of Technology Tiptur India

ISBN: (纸本)9789811506253

image classification is the most commonly employed technique for extricating land cover report from remotely sensed images. In the last two decades, advanced image classifiers have been extensively applied in remotely sensed (RS) image classification studies. Kohonen’s Self Organizing Maps (SOM) and its supervised version Learning vector Quantization (LvQ) algorithms have been applied in a variety of machine learning and pattern recognition studies as they are derived from neural networks. In this paper, the classification ability of SOM, LvQ-1 and LvQ-2 techniques are investigated using medium resolution Landsat 8 OLI/TIRS RS imagery. The study presents a detailed analysis of SOM and LvQ algorithms in RS data classification based on the LULC separability. The study uses Divergence (Div) and Transformed Divergence (TD) as metrics for measuring LULC separability. Results of SOM and LvQs were compared with conventional maximum likelihood and minimum-distance- to-means classifiers. Supervised Kohonen’s LvQ algorithms produced better accuracies than conventional classifiers. Also, LvQ algorithms showed great efficiency in avoiding overfitting of the dominant classes and separating spectrally overlapping classes. The study is indication of the applicability of Kohonen’s algorithms for RS data classification. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Self organizing maps

来源：评论

学校读者我要写书评

暂无评论

Unmanned Aerial vehicle (Uav) Imaging and Machine Learning Applications for Plant Phenotyping

SSRN

引用

SSRN 2023年

作者： Teshome, Fitsum Tilahun Bayabil, Haimanote Kebede Hoogenboom, Gerrit Schaffer, Bruce Singh, Aditya Ampatzidis, Yiannis Department of Agricultural and Biological Engineering Tropical Research and Education Center IFAS University of Florida HomesteadFL United States Department of Agricultural and Biological Engineering Institute for Sustainable Food Systems University of Florida GainesvilleFL United States Horticultural Sciences Department Tropical Research and Education Center University of Florida 18905 SW 280th Street HomesteadFL33031-3314 United States Agricultural and Biological Engineering Department Southwest Florida Research and Education Center University of Florida IFAS 2685 SR 29 North ImmokaleeFL34142 United States

The availability of timely and accurate information about plant conditions is critical for making informed decisions for maintaining or improving agricultural productivity. However, field data collection is often laborious and time-consuming. The objective of this study was to evaluate the effectiveness of combining unmanned aerial vehicle (UAv)-based imaging and machine learning (ML) techniques for monitoring sweet corn (Zea mays var. saccharata) height, biomass, and yield, with the aim of providing a more accurate and efficient means of monitoring crop growth and development. The study was conducted at the Tropical Research and Education Center (TREC) during the winter (dry) seasons of 2020-21 using 16 experimental plots planted with sweet corn. The treatments were set up with a completely randomized block design (RCBD) with 4 irrigation treatments of 25, 50, 75, and 100% maximum allowable depletion (MAD) with 4 replications each. Field data collection included plant height, fresh and dry biomass, and yield. In addition, UAv images were collected using the DJI Matrice 210 v2 UAv (SZ DJI Technology Co., Ltd., Shenzhen, China) equipped with a MicaSense RedEdge-MX multispectral sensor (MicaSense, Seattle, WA, US). image processing was done with Pix4Dmapper 4.7.5 (Pix4D S.A., Prilly, Switzerland). A crop surface model, which represents estimated plant height (UAvH), was calculated based on pixel-to-pixel differences between digital surface and terrain models. A simple linear regression model was used to estimate sweet corn biomass and yield from UAv images estimated plant height (UAvH). In addition, two linear algorithms known as a linear model (LM) and lasso and elastic-net regularized generalized linear model (GLMNET) and three non-linear ML algorithms including random forest (RF), support vector machine (SvM), and k-nearest neighbor (kNN) were used to predict plant height and biomass. These algorithms have been chosen due to their reliable performance and ability t

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Fast algorithm of image enhancement based on multi-scale retinex

Fast algorithm of image enhancement based on multi-scale ret...

引用

作者： Zotin, Alexander G. Department of Informatics and Computer Techniques Reshetnev Siberian State University of Science and Technology Krasnoyarsky Rabochy Av. 31 Krasnoyarsk660037 Russia

In this paper, a fast image enhancement algorithm based on multi-scale retinex in HSv colour model is presented. The proposed algorithm produces the result similar to the one which uses a nonlinear processing in the HSv colour model, but with less computational cost. It uses linear dependencies of RGB colours from the v-component of HSv model. Additionally, to speed up the images processing and enhance the local contrast is suggested to perform multi-scale retinex (MSR) computation only in the low-frequency area obtained by the wavelet transform. Experimental research was performed on more than 100 colour images having non-uniform brightness. Different algorithms based on retinex technology were implemented and their performance was compared. The proposed way of output image colour formation allows reducing processing time by 30%-75%, depending on the image size. The experimental data show that the usage of the wavelet transform in proposed MSR algorithm additionally leads to 2-2.8 times increase in processing speed. Copyright © 2020 Inderscience Enterprises Ltd.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Artificial Object images Synthesis in Underwater Robot vision System

Artificial Object Images Synthesis in Underwater Robot Visio...

引用

International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM)

作者： Sai, Sergey, v Sai, Ilya S. Pacific Natl Univ Dept Comp Engn Khabarovsk Russia

ISBN: (纸本)9781728145907

the article discusses the features of the synthesis of images of artificial objects with the aim of their search and recognition in the vision system of an underwater robot. The results of research and development to given: a database - a classifier of features that allows you to store information about the reference underwater objects;software module for generating images of reference objects and their insertion in a sonar image file. In the modeling program for the synthesis of underwater objects in the HBO image, the algorithms for introducing objects used by taking into account the peculiarities of the formation of HBO images by sonar. The program allows implementing several objects of spherical, cylindrical and cubic shapes with specified parameters, which allows simulating the situation of search for an artificial object according to given geometric features against the background of other objects. The developed software allows simulating underwater objects according to the characteristics close to real objects with the help of their preliminary processing and subsequent implementation in real HBO images

关键词： vision systems image synthesis sonar image

来源：评论

学校读者我要写书评

暂无评论

RESCOvIDTCNnet: A residual neural network-based framework for COvID-19 detection using TCN and EWT with chest X-ray images

引用

EXPERT systems WITH APPLICATIONS 2022年第0期204卷 117410页

作者： El-Dahshan, El-Sayed. A. Bassiouni, Mahmoud. M. Hagag, Ahmed Chakrabortty, Ripon K. Loh, Huiwen Acharya, U. Rajendra Ain Shams Univ Fac Sci Dept Phys Cairo 11566 Egypt Egyptian Elearning Univ EELU 33 El-messah St Eldoki Giza 11261 Egypt Benha Univ Fac Comp & Artificial Intelligence Dept Sci Comp Banha 13518 Egypt UNSW Canberra ADFA Sch Engn Canberra ACT 2612 Australia UNSW Canberra ADFA IT Canberra ACT 2612 Australia SUSS Univ Sch Sci & Technol Dept Biomed Engn Singapore Singapore Ngee Ann Polytech Dept Elect & Comp Engn Singapore 599489 Singapore Asia Univ Dept Biomed Informat & Med Engn Taichung Taiwan

Since the advent of COvID-19, the number of deaths has increased exponentially, boosting the requirement for various research studies that may correctly diagnose the illness at an early stage. Using chest X-rays, this study presents deep learning-based algorithms for classifying patients with COvID illness, healthy controls, and pneumonia classes. Data gathering, pre-processing, feature extraction, and classification are the four primary aspects of the approach. The pictures of chest X-rays utilized in this investigation came from various publicly available databases. The pictures were filtered to increase image quality in the pre-processing stage, and the chest X-ray images were de-noised using the empirical wavelet transform (EWT). Following that, four deep learning models were used to extract features. The first two models, Inception-v3 and Resnet-50, are based on transfer learning models. The Resnet-50 is combined with a temporal convolutional neural network (TCN) to create the third model. The fourth model is our suggested RESCOvIDTCNNet model, which integrates EWT, Resnet-50, and TCN. Finally, an artificial neural network (ANN) and a support vector machine were used to classify the data (SvM). Using five-fold cross-validation for 3-class classification, our suggested RESCOvIDTCNNet achieved a 99.5 percent accuracy. Our prototype can be utilized in developing nations where radiologists are in low supply to acquire a diagnosis quickly.

关键词： COvID-19 diagnosis X-ray Lung images Pre-trained CNN methods: Inception-v3 & Resnet-50 TCN EWT

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning-Based Approach for Defect Detection and Removing on Archival Photos 18

A Deep Learning-Based Approach for Defect Detection and Remo...

引用

18th image processing: algorithms and systems Conference, IPAS 2020

作者： Sizyakin, R. voronin, v. Gapon, N. Zelensky, A. Pižurica, A. Department Telecommunications and Information Processing IPITELIN-imec Ghent University Ghent Belgium Moscow State University of Technology "STANKIN" Moscow Russia Lab. "Mathematical methods of image processing and intelligent computer vision systems" Don State Technical University Rostov-on-Don Russia

Many archival photos are unique, existed only in a single copy. Some of them are damaged due to improper archiving (e.g. affected by direct sunlight, humidity, insects, etc.) or have physical damage resulting in the appearance of cracks, scratches on photographs, non-necessary signs, spots, dust, and so on. This paper proposed a system for detection and removing image defects based on machine learning. The method for detecting damage to an image consists of two main steps: the first step is to use morphological filtering as a pre-processing, the second step is to use the machine learning method, which is necessary to classify pixels that have received a massive response in the preprocessing phase. The second part of the proposed method is based on the use of the adversarial convolutional neural network for the reconstruction of damages detected at the previous stage. The effectiveness of the proposed method in comparison with traditional methods of defects detection and removal was confirmed experimentally. © 2020, Society for Imaging Science and Technology

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Extremely Tiny Face Detector for Platforms with Limited Resources 11th

Extremely Tiny Face Detector for Platforms with Limited Reso...

引用

11th International Conference on image and Graphics, ICIG 2021

作者： Chen, Chen Zhang, Maojun Peng, Yang Tan, Hanlin Xiao, Huaxin College of Systems Engineering National University of Defense Technology Zunyi China

ISBN: (纸本)9783030873578

Face detection is a fundamental step for face analysis tasks. In recent years, deep learning-based algorithms in face detection have grown rapidly. Most neural networks are computationally expensive and rely on graphics processing units, falling to be applied in practical applications. This paper explores the principles of designing tiny models and proposes an extremely tiny face detector based on the tiny-YOLOv3 framework, introducing new network structures such as Cross-Stage-Partial-connections (CSP), depthwise convolution, and Spatial Pyramid Pooling (SPP). The number of parameters is less than 10k, and the storage is less than 50Kb by using half-precision float point (FP16) for each parameter. Furthermore, each layer’s peak memory usage is under 0.07MB, leading the model to be accessible to various platforms. The experiments on a subset of the WIDER FACE dataset and Open images Dataset v4 (OID) show that the proposed face detector can achieve comparable performance to the more massive face detectors heavier in model size and floating-point operations. © 2021, Springer Nature Switzerland AG.

关键词： Computational efficiency

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：