检索结果-内蒙古大学图书馆

Leveraging high-resolution remote sensing images for vehicle type detection using sparrow search optimization with deep learning

引用

MULTIMEDIA TOOLS AND applications 2024年第32期83卷 77549-77564页

作者： Umamaheswari, Ramisetti Avanija, J. Mohan Babu Univ Sch Comp Tirupati AP India

High-resolution remote sensing images (RSI) refer to images captured from a distance, usually from an aircraft or satellite that provide details about the Earth's surface. It can be used in several application areas like environmental monitoring, urban planning, agriculture, and disaster response. In urban planning, high-resolution imagery is used to monitor the growth of urban areas or to recognize the area that requires infrastructure improvement. Vehicle detection is a significant way of understanding high-resolution RSIs. Vehicle detection and classification on high-resolution RSI is a difficult task that needs a group of computer vision (CV), image processing, and machine learning (ML) algorithms. Deep convolutional neural network (DCNN) based techniques have attained recent outcomes in many object detection datasets and have enriched several CV tasks. This article designed and developed a sparrow search optimization algorithm with deep learning for vehicle type detection and classification (SSOADL-VTDC) technique on high-resolution remote sensing images. The presented SSOADL-VTDC technique examines the high-quality RSIs for the accurate detection and classification of vehicles. To accomplish this, the SSOADL-VTDC technique employs a YOLOv5 object detector with a Residual Network as a backbone approach. In addition, the SSOADL-VTDC technique uses SSOA based hyperparameter optimizer designed for the parameter tuning of the YOLOv5 model. For the vehicle classification process, the SSOADL-VTDC technique exploits the softmax classifier. The simulation validation of the SSOADL-VTDC approach was validated on a high-resolution RSI dataset and the outcomes demonstrated the greater of the SSOADL-VTDC methodology in terms of different measures.

关键词： Remote sensing images Vehicle classification Deep learning Sparrow search optimizer Computer vision

来源：评论

学校读者我要写书评

暂无评论

A Survey on Adversarial Text Attacks on Deep Learning Models in Natural Language processing 5th

A Survey on Adversarial Text Attacks on Deep Learning Models...

引用

5th International Conference on Data Science, machine Learning and applications

作者： Deepan, S. Torres-Cruz, Fred Placido-Lerma, Ruben L. Udhayakumar, R. Anuradha, S. Kapila, Dhiraj SR Univ Sch Comp Sci & Artificial Intelligence Warangal Telangana India Univ Nacl Altiplanode Puno Unit Stat & Comp Engn Puno Peru Univ Andina Nestor Caceres Velasquez Syst Engn Juliaca Peru VelTech Rangarajan Dr Sagunthala R&D Inst Sci & T Chennai Tamil Nadu India Sri Sairam Engn Coll Dept English Chennai Tamil Nadu India Lovely Profess Univ Dept Comp Sci & Engn Phagwara Punjab India

ISBN: (纸本)9789819780334;9789819780310;9789819780303

Deep neural networks have recently seen a significant surge in adoption for different Artificial Intelligence technologies due to the development of powerful computer systems. However, because of the growing security concerns, they are susceptible to dangerous risks. Adversarial instances were initially discovered in the field of computer vision (CV), where systems were deceived by altering their initial inputs. In the field of natural language processing (NLP), additionally they occur. Several approaches are put up to address this gap and handle an extensive variety of NLP applications. We give an organized survey of these works in this *** text is distinct and meaningful in nature, in contrast to the image, which makes the creation of hostile assaults much more challenging. In this study, we present a thorough analysis of adversarial attacks and counterattacks in the textual domain. In order to make the essay self-contained, we examine related important works in computer vision and cover the fundamentals of NLP. We explore unresolved concerns to close the gap between current advancements and increasingly powerful adversarial assaults on NLP DNNs in our survey's conclusion.

关键词： NLP DNN adversarial text attacks adversarial defense textual data

来源：评论

学校读者我要写书评

暂无评论

A Survey on Few-Shot Techniques in the Context of Computer vision applications Based on Deep Learning 21st

A Survey on Few-Shot Techniques in the Context of Computer V...

引用

21st International Conference on image Analysis and processing (ICIAP)

作者： San-Emeterio, Miguel G. Atos Res & Innovat Madrid 28037 Spain

ISBN: (纸本)9783031133244;9783031133237

This review article about Few-Shot Learning techniques is focused on Computer vision applications based on Deep Convolutional Neural Networks. A general discussion about Few-Shot Learning is given, featuring a context-constrained description, a short list of applications, a description of a couple of commonly used techniques and a discussion of the most used benchmarks for FSL computer vision applications. In addition, the paper features a few examples of recent publications in which FSL techniques are used for training models in the context of Human Behaviour Analysis and Smart City Environment Safety. These examples give some insight about the performance of state-of-the-art FSL algorithms, what metrics do they achieve, and how many samples are needed for accomplishing that.

关键词： Few-Shot Learning Deep Learning Computer vision Human Behaviour Analysis Smart City Environment Safety

来源：评论

学校读者我要写书评

暂无评论

A MULTIMODAL OPTICAL SENSING SYSTEM FOR AUTOMATED AND INTELLIGENT FOOD SAFETY INSPECTION

JOURNAL OF THE ASABE

引用

JOURNAL OF THE ASABE 2023年第4期66卷 839-849页

作者： Qin, Jianwei Hong, Jeehwa Cho, Hyunjeong Van Kessel, Jo Ann S. Baek, Insuck Chao, Kuanglin Kim, Moon S. USDA ARS Beltsville Agr Res Ctr Environm Microbial & Food Safety Lab Beltsville MD 20705 USA Natl Agr Prod Qual Management Serv Expt Res Inst Gimcheon Si Gyeongbuk Do South Korea

A novel multimodal optical sensing system was developed for automated and intelligent food safety inspection. The system uses two pairs of compact point lasers and dispersive spectrometers at 785 and 1064 nm to realize dual-band Raman spectroscopy and imaging, which is suitable to measure samples generating low- and high-fluorescence interference signals, respectively. Automated spectral acquisition can be performed using a direct-drive XY moving stage for solid, powder, and liquid samples placed in customized well plates or randomly scattered in standard Petri dishes (e.g., bacterial colonies). Three LED lights (white backlight, UV ring light, and white ring light) and two miniature color cameras are used for machine vision measurements of samples in the Petri dishes using different combinations of illuminations and imaging modalities (e.g., transmission, fluorescence, and color). Real-time image processing and motion control techniques are used to implement automated sample counting, positioning, sampling, and synchronization functions. System software was developed using LabVIEW with integrated artificial intelligence functions able to identify and label interesting targets instantly. The system capability was demonstrated by an example application for rapid identification of five common foodborne bacteria, including Bacillus cereus, E. coli, Listeria monocytogenes, Staphylococcus aureus, and Salmonella spp.. Using a machine learning model based on a linear support vector machine, a classification accuracy of 98.6% was achieved using Raman spectra automatically collected from 222 bacterial colonies of the five species grown on nutrient nonselective agar in 90 mm Petri dishes. The entire system was built on a 30x45 cm(2) breadboard, enabling it compact and portable and its use for field and on-site biological and chemical food safety inspection in regulatory and industrial applications.

关键词： Artificial intelligence Automated sampling Bacteria Food safety machine learning machine vision Raman Sensing

来源：评论

学校读者我要写书评

暂无评论

Lightweight deep learning model for automatic landslide prediction and localization

引用

MULTIMEDIA TOOLS AND applications 2023年第21期82卷 33245-33266页

作者： Varangaonkar, Payal Rode, S. V. Sipna Coll Engn & Technol Amravati India Sipna Coll Engn & Technol Elect & Telecommun Dept Amravati India

There has been a lot of interest in utilizing remote sensing images to anticipate landslides. We propose a novel framework for automatic landslide detection and landslide region localization from the input remote sensing image. The framework consists of pre-processing, dynamic segmentation, automatic feature extraction, classification, and localization. The pre-processing is the integrated step that performs atmospheric corrections, geometric corrections, and unnecessary region removal with denoising using 2D median filtering. The pre-processed image is then segmented using the dynamic segmentation approach to extract the Region of Interest (ROI). We propose lightweight Convolutional Neural Network (CNN) layers for automatic feature extraction and scaling using the ResNet50 model. The CNN layers are designed systematically for automatic feature extraction to improve accuracy and reduce computational requirements. The Long-Term Short Memory (LSTM), Artificial Neural Network (ANN), and Support Vector machine (SVM) classifiers are designed to perform the landslide prediction. If landslides are forecast, the post-processing stages are intended to identify potential landslide locations. The experimental results show that the proposed CNN-LSTM model outperformed the existing solutions in terms of accuracy, F1 score, precision, and recall rates. The experimental outcomes reveal that the proposed model improves the overall prediction accuracy by 2% and reduces the computational complexity by 35% compared to state-of-the-art methods.

关键词： Computer vision methods Convolutional neural network Deep learning LSTM Landslide detection Landslide localization Segmentation

来源：评论

学校读者我要写书评

暂无评论

A review of ground camera-based computer vision techniques for flood management

引用

COMPUTERS AND CONCRETE 2024年第4期33卷 425-443页

作者： Jun, Sanghoon Jang, Hyewoon Kim, Seungjun Lee, Jong-Sub Jung, Donghwi Korea Univ Hyper Converged Forens Res Ctr Infrastruct Seoul 02841 South Korea Korea Univ Dept Civil Environm & Architectural Engn Seoul 02841 South Korea Korea Univ Sch Civil Environm & Architectural Engn Seoul 02841 South Korea

Floods are among the most common natural hazards in urban areas. To mitigate the problems caused by flooding, unstructured data such as images and videos collected from closed circuit televisions (CCTVs) or unmanned aerial vehicles (UAVs) have been examined for flood management (FM). Many computer vision (CV) techniques have been widely adopted to analyze imagery data. Although some papers have reviewed recent CV approaches that utilize UAV images or remote sensing data, less effort has been devoted to studies that have focused on CCTV data. In addition, few studies have distinguished between the main research objectives of CV techniques (e.g., flood depth and flooded area) for a comprehensive understanding of the current status and trends of CV applications for each FM research topic. Thus, this paper provides a comprehensive review of the literature that proposes CV techniques for aspects of FM using ground camera (e.g., CCTV) data. Research topics are classified into four categories: flood depth, flood detection, flooded area, and surface water velocity. These application areas are subdivided into three types: urban, river and stream, and experimental. The adopted CV techniques are summarized for each research topic and application area. The primary goal of this review is to provide guidance for researchers who plan to design a CV model for specific purposes such as flood-depth estimation. Researchers should be able to draw on this review to construct an appropriate CV model for any FM purpose.

关键词： CCTV computer vision flooding image processing machine learning segmentation

来源：评论

学校读者我要写书评

暂无评论

Organ Localization and Detection in Sow’s Using machine Learning and Deep Learning in Computer vision

Organ Localization and Detection in Sow’s Using Machine Lea...

引用

作者： Almadani, Iyad Mohd Eid H. The University of Memphis

学位级别：M.S., Master of Science/Master of Surgery

The objective of computer vision research is to endow computers with human-like perception to enable the capability to detect their surroundings, interpret the data they sense, take appropriate actions, and learn from their experiences to improve future performance. The area has progressed from using traditional pattern recognition and image processing technologies to advanced techniques in image understanding such as model-based and knowledge-based vision. In the past few years, there has been a surge of interest in machine learning algorithms for computer vision-based applications. machine learning technology has the potential to significantly contribute to the development of flexible and robust vision algorithms that will improve the performance of practical vision systems with a higher level of competence and greater generality. Additionally, the development of machine learning-based architectures has the potential to reduce system development time while simultaneously achieving the above-stated performance improvements. This work proposes utilizing a computer vision-based approach that leverages machine and deep learning systems to aid the detection and identification of sow reproduction cycles by segmentation and object detection techniques. A lightweight machine learning system is proposed for object detection to address dataset collection issues in one of the most crucial and potentially lucrative farming applications. This technique was designed to detect the vulvae region in pre-estrous sows using a single thermal image. In the first experiment, the support vector machine (SVM) classifier was used after extracting features determined by 12 Gabor filters. The features are then concatenated with the features obtained from the Histogram of oriented gradients (HOG) to produce the results of the first experiment. In the second experiment, the number of distinct Gabor filters used was increased from 12 to 96. The system is trained on cropped image windows and us

关键词： Computer vision Gabor filter machine learning Object localization Support vector machine

来源：评论

学校读者我要写书评

暂无评论

Fourier-Based and Rational Graph Filters for Spectral processing

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND machine INTELLIGENCE 2023年第6期45卷 7063-7074页

作者： Patane, Giuseppe CNR CNR IMATI Ist Matemat Applicata & Tecnol Informat Genova I-16149 Genoa Italy

Data are represented as graphs in a wide range of applications, such as Computer vision (e.g., images) and Graphics (e.g., 3D meshes), network analysis (e.g., social networks), and bio-informatics (e.g., molecules). In this context, our overall goal is the definition of novel Fourier-based and graph filters induced by rational polynomials for graph processing, which generalise polynomial filters and the Fourier transform to non-euclidean domains. For the efficient evaluation of discrete spectral Fourier-based and wavelet operators, we introduce a spectrum-free approach, which requires the solution of a small set of sparse, symmetric, well-conditioned linear systems and is oblivious of the evaluation of the Laplacian or kernel spectrum. Approximating arbitrary graph filters with rational polynomials provides a more accurate and numerically stable alternative with respect to polynomials. To achieve these goals, we also study the link between spectral operators, wavelets, and filtered convolution with integral operators induced by spectral kernels. According to our tests, main advantages of the proposed approach are (i) its generality with respect to the input data (e.g., graphs, 3D shapes), applications (e.g., signal reconstruction and smoothing, shape correspondence), and filters (e.g., polynomial, rational polynomial), and (ii) a spectrum-free computation with a generally low computational cost and storage overhead.

关键词： Convolution Laplace equations Kernel Fourier transforms Chebyshev approximation Eigenvalues and eigenfunctions Three-dimensional displays Chebyshev rational polynomials frequency filtering graph Fourier transform graphs heat kernel kernels Laplacian spectrum spectral graph processing

来源：评论

学校读者我要写书评

暂无评论

Raw Camera Data Object Detectors: An Optimisation for Automotive Video processing and Transmission

引用

IEEE ACCESS 2025年 13卷 21695-21706页

作者： Chan, Pak Hung Wei, Chuheng Huggett, Anthony Donzella, Valentina Univ Warwick WMG Coventry CV4 7AL England Onsemi Greenwood House Bracknell RG12 2AA England

Whilst Deep Neural Networks (DNNs) have been developing swiftly, most of the research has been focused on videos based on RGB frames. RGB data has been traditionally optimised for human vision and is a highly re-elaborated and interpolated version of the collected raw data. In fact, the sensor collects the light intensity value per pixel, but an RGB frame contains 3 values, for red, green, and blue colour channels. This conversion to RGB requires computational resource, time, power, and increases by a factor of three the amount of output data. This work investigates DNN based detection using (for training and evaluation) Bayer frames, generated from a benchmarking automotive dataset (i.e. KITTI dataset). A Deep Neural Network (DNN) is deployed in an unmodified form, and also modified to accept only single channel frames, such as Bayer frames. Eleven different re-trained versions of the DNN are produced, and cross-evaluated across different data formats. The results demonstrate that the selected DNN has the same accuracy when evaluating RGB or Bayer data, without significant degradation in the perception (the variation of the Average Precision is <1%). Moreover, the colour filter array position and the colour correction matrix do not seem to contribute significantly to the DNN performance. This work demonstrates that Bayer data can be used for object detection in automotive without significant perception performance loss, allowing for more efficient sensing-perception systems.

关键词： image color analysis Artificial neural networks Accuracy Pedestrians Cameras Automotive engineering machine learning Pipelines Feature extraction Europe Bayer data object detection perception sensors assisted and automated driving intelligent vehicles

来源：评论

学校读者我要写书评

暂无评论

Segmenting Sonar images with an Enhanced OTSU Algorithm 2

Segmenting Sonar Images with an Enhanced OTSU Algorithm

引用

2nd International Conference on image processing, Computer vision and machine Learning, ICICML 2023

作者： Yang, Fan University of Jinan School of Electrical Engineering Jinan250022 China

ISBN: (纸本)9798350331417

Sonar image segmentation technique is crucial for underwater target tracking, among other things. Due to the undersea environment's influence, noise is easily absorbed, which leads to a poor tracking performance. In order to address the issues with the traditional one-dimensional and two-dimensional OTSU algorithms, which have a slow computation time and poor anti-noise performance, this paper proposes a fast OTSU segmentation algorithm based on wavelet boosting and analyses the algorithmic principles and implementation steps of one-dimensional OTSU algorithm, two-dimensional OTSU algorithm and its fast algorithm, fast algorithm with the variance as the eigenvalue, and maximum entropy algorithm. On the basis of this, the aforementioned algorithms are used to perform image segmentation on four photos. The segmentation findings demonstrate the method's quick processing speed and strong noise resistance, which have significant implications for sonar image segmentation applications. © 2023 IEEE.

关键词： image segmentation OTSU second generation wavelet transform sonar images

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：