检索结果-内蒙古大学图书馆

Research on Obstacle Detection and Avoidance of Autonomous Underwater vehicle Based on Forward-Looking Sonar

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING systems 2023年第11期34卷 9198-9208页

作者： Cao, Xiang Ren, Lu Sun, Changyin Anhui Univ Sch Artificial Intelligence Hefei 230601 Peoples R China Southeast Univ Sch Automat Nanjing 210096 Peoples R China

Due to the complexity of the ocean environment, an autonomous underwater vehicle (AUv) is disturbed by obstacles when performing tasks. Therefore, the research on underwater obstacle detection and avoidance is particularly important. Based on the images collected by a forward-looking sonar on an AUv, this article proposes an obstacle detection and avoidance algorithm. First, a deep learning-based obstacle candidate area detection algorithm is developed. This algorithm uses the You Only Look Once (YOLO) v3 network to determine obstacle candidate areas in a sonar image. Then, in the determined obstacle candidate areas, the obstacle detection algorithm based on the improved threshold segmentation algorithm is used to detect obstacles accurately. Finally, using the obstacle detection results obtained from the sonar images, an obstacle avoidance algorithm based on deep reinforcement learning (DRL) is developed to plan a reasonable obstacle avoidance path of an AUv. Experimental results show that the proposed algorithms improve obstacle detection accuracy and processing speed of sonar images. At the same time, the proposed algorithms ensure AUv navigation safety in a complex obstacle environment.

关键词： Sonar Sonar detection Collision avoidance Sonar navigation Feature extraction image segmentation Detection algorithms Autonomous underwater vehicle (AUv) forward-looking sonar obstacle detection and avoidance path planning

来源：评论

学校读者我要写书评

暂无评论

Optic Flow Approximated by a Homogeneous, Three-Dimensional Point Renewal Process 6th

Optic Flow Approximated by a Homogeneous, Three-Dimensional ...

引用

6th International conference on Software Testing, Machine Learning and Complex Process Analysis, TMPA 2021

作者： Dubinin, D.v. Kochegurov, A.I. Kochegurova, E.A. Geringer, v.E. Tomsk State University of Control Systems and Radioelectronics Prospect Lenina 40 Tomsk634050 Russia National Research Tomsk Polytechnic University Lenin Avenue 30 Tomsk634050 Russia Ravensburg Fallenbrunnen 2 Friedrichshafen88045 Germany

ISBN: (纸本)9783031504228

The paper describes a mechanism for modeling an optical flow as a random vector field – closed areas on the image plane with certain brightness and dynamics of changes in the vector field. The optical flow is formed by a homogeneous, three-dimensional point renewal process. The characteristics of the vector field on the image plane of the resulting optical flow are interconnected by the Palm’s formulas. The type of the constituent elements of the vector field (the alphabet, which determines the morphology of the field on the image plane) is chosen randomly. The proposed approach will produce various types of interconnected digital sequences of images with horizontal, vertical and diagonal elements;create the prerequisites for efficient and flexible motion analysis on digital video sequences;make it possible to use the probabilistic factor in researching image processing algorithms and comparing the algorithms based on a detailed factor analysis. © 2024, Springer Nature Switzerland AG.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Advanced Pansharpening Techniques for Satellite image Fusion 4

Advanced Pansharpening Techniques for Satellite Image Fusion

引用

4th International Conference on Power, Energy, Control and Transmission systems, ICPECTS 2024

作者： Kamala, B. Ramana, v. Giridharan, S. Ranjani, J. Sri Sairam Engineering College Department of Information Technology Chennai India

ISBN: (数字)9798331508845

ISBN: (纸本)9798331508845

This research develops an algorithm for efficiently fusing multiple satellite images, addressing challenges like varying spatial resolutions, spectral bands, radiometric differences, and geometric distortions. Objectives include creating a robust preprocessing pipeline, evaluating fusion algorithms, using quality metrics to assess performance, exploring applications such that land cover classifier and change detection and benchmarking against existing methods. The aim is to enhance satellite image processing, aiding environmental monitoring and urban planning. The proliferation of satellite sensors, each with unique strengths and weaknesses, has increased the need for image fusion to derive comprehensive information from datasets. Fusion techniques leverage the strengths of individual sensors, providing detailed spatial information, spectral diversity, and temporal variations. This integration leads to improved image quality, enhanced feature extraction, and more accurate analysis. The demand for satellite imagery in agriculture, environmental monitoring, urban planning, and disaster management drives the development of advanced algorithms for producing more informative and actionable data. © 2024 IEEE.

关键词： Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review of Pomegranate Fruit Disease Detection and Classification Using Machine Learning and Deep Learning Techniques 1

引用

8th International Conference on Information and Communication Technology for Competitive Strategies, ICTCS 2023

作者： Pakruddin, B. Hemavathy, R. Department of Computer Science and Engineering R.V College of Engineering Visvesvaraya Technological University Belagavi590018 India Department of Computer Science and Engineering Presidency University Bengaluru560064 India

ISBN: (数字)9789819994861

ISBN: (纸本)9789819994854

In India Agriculture is the backbone of the economy and a source of employment. Agriculture contributes 20% to the GDP of India. There are many losses due to diseases that bring downcast efficiency and increase financial losses. Agricultural area needs to stand and progress from such problems to be highly gainful. This can be achieved by detecting diseases at appropriate stages of the fruit and plant lifespan. Suitable machine learning algorithms (linear and logistic regression, KNN, K-means, SvM, etc.) and deep learning algorithms (CNNs, LSTMs, RNNs, etc.) can be used with image processing techniques for identifying the various diseases in fruits and plants. Researchers developed various methods for the detection of diseases using the above techniques. This paper proposes to emphasize the review of research work in the agriculture field such as disease detection in pomegranate and checking algorithms, diseases, datasets, accuracy merits, demerits of each technique used. For other researchers working in the field of image processing for the detection and classification of leaf/fruit diseases, this review article will be crucial in understanding the state-of-the-art. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Algorithm for Changing the Size of a Multi-Element Aperture of a Two-dimensional Recursive-Separable Five-Stage Filter for Digital image processing 25

Algorithm for Changing the Size of a Multi-Element Aperture ...

引用

25th IEEE International Conference of Young Professionals in Electron Devices and Materials, EDM 2024

作者： Kamenskiy, Andrey v. Kupriyanova, Kristina S. Podnebesnyy, Andrey v. Kuryachiy, Mikhail I. Borodina, Natalya Tatyana, Akaeva M. Dept. of Television and Control Tomsk State University of Control Systems and Radioelectronics Tomsk Russia

ISBN: (纸本)9798350389234

The paper presents a description of the developed algorithm for changing the size of a multi-element aperture of a recursive-separable five-stage filter for processing digital images generated by specialized optical systems. The developed algorithm has two features: it has the ability to change the size of a multi-element aperture during use;it makes it possible to use the recursive and separable properties. These capabilities make it possible to reduce the processing time of incoming data, which has a positive effect on the efficiency of the optical-electronic imaging system used. The paper presents a block diagram of a two-dimensional recursive-separable five-stage filter, with the help of which an algorithm was developed for changing the size of a multi-element aperture, and a study of the influence of the aperture size on the performance of the developed filter was carried out. As part of the performance evaluation, the developed algorithm was compared with the classical two-dimensional convolution algorithm. Developed algorithm was tested on three test images of different sizes and formats: 1300x700 Bitmap Picture, 1200x1200 Tagged image File, 2900x1900 Joint Photographic Experts Group. During the processing of test images, the dimensions of the multi-element aperture of the developed filter changed. As the aperture size increases, the performance evaluation results also increase. This shows that speeding up the algorithm is an actual task. However, the developed algorithm takes less time than the classical two-dimensional convolution algorithm, from which it can be concluded that the developed solution is effective for both conventional images and images from optoelectronic systems. © 2024 IEEE.

关键词： digital filters digital image processing optical-electronic systems performance real time recursively separable algorithms

来源：评论

学校读者我要写书评

暂无评论

Deforestation Detection from Remote Sensing images using Machine Learning 15

Deforestation Detection from Remote Sensing Images using Mac...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Tharun, Devisetty Sai Srija, Panguluri Sai Krishna, Peeta vamsi Panchikkil, Shaiju Manikandan, v.M. Srm University-AP Andhra Pradesh India

ISBN: (纸本)9798350370249

The study focuses on the utilization of remote sensing data to analyze and detect deforestation patterns, with an emphasis on the extraction of key parameters such as vegetation cover change, forest loss, and land use dynamics. various image processing methods, encompassing supervised and unsupervised classification, object-based image analysis, and change detection algorithms, are discussed in the context of their applicability to deforestation monitoring. The benefits and limitations of each technique are identified, highlighting the significance of choosing the most appropriate method based on the specific needs of the study area and the required level of accuracy. The paper also explores the incorporation of remote sensing data with geographic information systems (GIS) and other ancillary data sources to enhance the analysis and interpretation of deforestation patterns. The findings from this work contribute to the advancement of remote sensing image processing methods for deforestation monitoring, offering valuable insights for researchers and practitioners in the field. © 2024 IEEE.

关键词： change detection classification deforestation GIS integration image processing monitoring remote sensing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Solar Energy Efficiency: A Deep Learning Approach for Dust Detection

Enhancing Solar Energy Efficiency: A Deep Learning Approach ...

引用

2024 International Conference on Smart Electronics and Communication systems, ISENSE 2024

作者： vigna Harish, R. Ramya, A. Siva, S. Santhi, S. Kalaiselvi, S. Anitha, v. National Engineering College Dept. of Information Technology Tuticorin India National Engineering College Dept. of Computer Science and Engineering Tuticorin India

ISBN: (数字)9798331528126

ISBN: (纸本)9798331528126

In recent decades, power generation from Pv systems has become increasingly popular. However, several environmental variables, such as dust deposition on Pv panels, have significantly reduced Pv energy production. Several approaches are under investigation to identify dust and decrease power loss. These include thermal imaging, image processing, sensors, and IoT devices, machine learning, and deep learning. The orientation of a solar panel and the angular inclination relative to the horizontal plane affect one of the environmental factors that impact its performance: since they have an impact on how much solar energy that enters into the photovoltaic panel's surface. Dust, for one, is another example of environmental factors: the quantity of energy output can be influenced by coming into contact with dust. Dust particles lying on the panel's surface have the potential to reduce light from reaching the solar modules, which would drastically reduces the energy output. Cleaning or reducing modules is critical, but these procedures must be continuously monitored and assessed for their effects. image processing algorithms can be used to detect dust to optimize solar panels. In this paper, a novel dataset from Kaggle comprising images of dusty and clean solar panels is presented, aiming to facilitate the research on automated dust detection algorithms. The dataset is utilized to evaluate the performance of existing state-of-the-art (SOTA) image classification methods. Subsequently, a new Convolutional Neural Network (CNN) architecture, ResNet-50 with an additional attention mechanism, is proposed, specifically designed for solar panel dust detection. The experimental results shows that the proposed method outperforms other SOTA algorithms, achieving an accuracy level of 96.2%. © 2024 IEEE.

关键词： Thermography (imaging)

来源：评论

学校读者我要写书评

暂无评论

Object Detection and Tracking Approach for Traffic Monitoring 1

引用

8th Smart Trends in Computing and Communications (SmartCom)

作者： Barekar, Praful, v Singh, Kavita R. Yeshwantrao Chavan Coll Engn Comp Technol Dept Nagpur Maharashtra India

ISBN: (数字)9789819713233

ISBN: (纸本)9789819713226;9789819713233

In present day, many object detection algorithms are available. These computer vision-based object detection algorithms help to detect, locate and trace an object from an image or a video. It requires high speed and accuracy along with efficiency when it is concerned with real-time systems. In machine learning and computer vision, object detection is considered to be an essential research area, also widely implemented in various sectors such as robotic navigation and intelligent video. The traditional approach to object identification consists of the steps as partitioning, clustering, feature extraction and classification. The solution is dependent of manual annotation, which leads to increase in the cost of the algorithm. Due to the diversity of objects, multiple models are needed for feature detection. As a result, classical object detection algorithms have poor generalizability, low detection accuracy, slow operating rate and low robustness. Object detection strategies are widly categorized as one-step and two-step object detection strategies. We are presenting a comparative analysis on object detection algorithms from two categories, i.e. single shot feed forward object detection algorithms and region proposal-based object detection algorithms. Under single shot feed forward, YOLOv7 is being is used along with pretrained weights trained on MS-COCO dataset from scratch. On the contrary, Mask R-CNN is being used to compare with, with its pretrained weights. This study presents a comparative analysis of YOLOv7 and Mask R-CNN in the context of accuracy, memory footprint and processing speed by retraining the models on the dataset of images and videos obtained through real-time systems in constrained.

关键词： Object detection Object tracking YOLOv7 Mask R-CNN

来源：评论

学校读者我要写书评

暂无评论

CAAM: Compressor-Based Adaptive Approximate Multiplier for Neural Network Applications

引用

IEEE EMBEDDED systems LETTERS 2023年第3期15卷 117-120页

作者： Kumar, U. Anil Bharadwaj, S. vignesh Pattaje, Avinash Bhat Nambi, Suresh Ahmed, Syed Ershad B V Raju Inst Technol ECE Dept Narsapur 502313 India Birla Inst Technol & Sci Pilani Dept Elect Engn Hyderabad 500078 India Birla Inst Technol & Sci Pilani Dept Elect Hyderabad 500078 India

Approximate computing is an evolving paradigm that aims to improve the power, speed, and area in neural network applications that can tolerate errors up to a specific limit. This letter proposes a new multiplier architecture based on the algorithm that adapts the approximate compressor from the existing and proposed compressors' set to reduce error in the respective partial product columns. Further, the error due to the approximation in the proposed multiplier is corrected using a simple error-correcting module. Results prove that the power and power-delay product (PDP) of an 8-bit multiplier is improved by up to 39.9% and 43.6% compared with the exact multiplier and 27.5% and 23.9% compared to similar previous designs. The proposed multiplier is validated using image processing and neural network applications to prove its efficacy.

关键词： Approximation algorithms image coding Neural networks Measurement Layout Computer architecture Adders Approximate computing Energy efficiency Embedded systems Approximate compressor approximate computing neural network application partial product reduction (PPR)

来源：评论

学校读者我要写书评

暂无评论

image to Text Conversion Using Deep Learning algorithms: Survey 10

Image to Text Conversion Using Deep Learning Algorithms: Sur...

引用

10th International Conference on Advanced Computing and Communication systems, ICACCS 2024

作者： Saranya, M. Anusuya, v. veera Santhiya, R. vazhan Arul Srimathi, R. National Engineering College Department of Computer Science and Engineering Kovilpatti India

ISBN: (纸本)9798350384369

image Captioning (ICs) seamlessly combines the realms of Computer vision (Cv) and Natural Language processing (NLP) task involved in producing textual sentences that summarise the image content in a way which is understandable to humans. The primary objective is to enable machines to convey the content of images in human-readable language. image understanding and text formation are typically the two primary processes in the image captioning process. A family of Convolutional Neural Network (CNN) is used to retrieve visual information from an input image during the image understanding process. This visual information includes the image's scenes, relationships, and objects. To translate these visual features into coherent and contextually appropriate captions, recurrent neural network, long short-term memory, transformer-based models, etc. are used in the text generation step. In this article, we propose a survey about the previous research paper and the fundamental steps involved in image captioning tasks. © 2024 IEEE.

关键词： Convolutional neural networks

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：