检索结果-内蒙古大学图书馆

15th International Conference on Signal processing systems, ICSPS 2023

作者： Hua, Chunjian Li, xiuqin Zhang, Airong School of Mechanical Engineering Jiangnan University Jiangsu China Wuxi Pioneer Intelligent Equipment Company China

ISBN: (纸本)9781510675056

In order to solve the problem of difficulty in segmenting the foreground of lawn weed images due to the similarity between the foreground and background grayscale, this paper proposes a Retinex enhancement algorithm based on local density fusion. Firstly, image preprocessing is completed based on local variance to realize prominent image foreground and smooth cluttered background;Secondly, using multi threshold segmentation and operational differentiation, pixels are divided into three categories: foreground, background, and pixels to be subdivided. Local density is used to extract spatial information of pixels to be subdivided;Finally, the sigmoid function is used to optimize the reflection component grayscale transformation coefficient, achieving the fusion of local density information and obtaining the final image. The results show that the algorithm proposed in this paper expands the gray difference between weeds and lawn grass while suppressing background noise;Compared with other enhancement algorithms, the peak signal-to-noise ratio, average running time, and segmentation accuracy have all been improved greatly. At the same time, through image analysis, it has been found that the algorithm results in occasional problems of uneven brightness and over segmentation of fine leaf weeds in the image. In response to these two problems, this article finally proposes two corresponding optimization measures, namely global brightness adjustment based on a new adaptive gamma function and Retinex reflection component saturation adjustment based on AHE. © 2024 SPIE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

DeepSensitive: A Fuzzing Test for Deep Neural Networks with Sensitive Neurons 1st

DeepSensitive: A Fuzzing Test for Deep Neural Networks with ...

引用

1st International Conference on Applied Intelligence, ICAI 2023

作者： Yang, Zixuan Lin, Chenhao Hu, Pengwei Shen, Chao Xi’an Jiaotong University Shaanxi Xi’an China The Xinjiang Technical Institute of Physics and Chemistry Chinese Academy of Sciences Beijing China

ISBN: (纸本)9789819709021

Deep learning (DL) systems have exhibited remarkable capabilities in various domains, such as image classification, natural language processing, and recommender systems, thereby establishing themselves as significant contributors to the advancement of software intelligence. Nevertheless, in domains emphasizing security assurance, the reliability and stability of deep learning systems necessitate thorough testing prior to practical implementation. Given the increasing demand for high-quality assurance of DL systems, the field of DL testing has gained significant traction. Researchers have adapted testing techniques and criteria from traditional software testing to deep neural networks, yielding results that enhance the overall security of DL technology. To address the challenge of enriching test samples in DL testing systems and resolving the issue of unintelligibility in samples generated by multiple mutations, we propose an innovative solution called DeepSensitive. DeepSensitive functions as a fuzzy testing tool, leveraging DL interpretable algorithms to identify sensitive neurons within the input layer via the DeepLIFT algorithm. Employing a fuzzy approach, DeepSensitive perturbs these sensitive neurons to generate novel test samples. We conducted evaluations of DeepSensitive using various mainstream image processing datasets and deep learning models, thereby demonstrating its efficient and intuitive capacity for generating test samples. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Garbage image classification robotic arm based on deep learning

Garbage image classification robotic arm based on deep learn...

引用

2023 International Conference on Computer Graphics, Artificial Intelligence, and Data processing, ICCAID 2023

作者： Lyu, Shaofan School of Electronic Engineering Xidian University Shaanxi Xi'an China

ISBN: (纸本)9781510677685

This study aims to compare and evaluate the performance of four popular deep learning models (CNN, ResNet50, VGG16, and InceptionResNetV2) in the garbage classification task. Waste classification is essential for sustainable development, and automated waste classification systems have become the key to solving the increasing global waste problem. To achieve accurate waste classification, these systems utilize various machine learning algorithms. In recent years, deep learning models have achieved great success in image classification tasks, so they have attracted much attention in garbage classification. In this study, we comprehensively evaluate the performance of CNN, ResNet50, VGG16, and InceptionResNetV2 models in classifying garbage into 12 different categories by comparing metrics such as accuracy, precision, and confusion matrix. The experimental results show that the InceptionResNetV2 model outperforms other models in the garbage classification task, with high precision and recall. This means that using the InceptionResNetV2 model for garbage classification can identify and separate different types of garbage more accurately. Finally, the deep learning model is connected to the CoppeliaSim platform to control the movement of the robotic arm based on the predictive results of the deep learning model. © 2024 SPIE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

An Artificial Olfactory Chemical-Resistant Synapse for Training-Free Gas Recognition

引用

ADVANCED MATERIALS TECHNOLOGIES 2024年第7期9卷

作者： Hu, Fangzhen Cao, Chenkai Han, Sancan Wang, Ding Chen, xi Univ Shanghai Sci & Technol Inst Photon Chips Shanghai 200093 Peoples R China Univ Shanghai Sci & Technol Ctr Artificial Intelligence Nanophoton Sch Opt Elect & Comp Engn Shanghai 200093 Peoples R China Univ Shanghai Sci & Technol Sch Mat & Chem Shanghai 200093 Peoples R China

Transferring the concept of chemical-driven responses into artificial intelligence technology holds the key to mimicking olfactory for neuromorphic computing of chemical recognition. Currently, artificial olfactory systems are designed based on chemical sensor arrays. Time-dependent responses of the sensor arrays are processed by artificial neural networks for recognition. However, the sensors generate instantly volatile responses, and algorithms for the processing of the time-dependent responses have not been involved. The recognition accuracy and speed are severely impeded. A sensor array can only achieve an accuracy of 90% after at least 5 training epochs. Herein an artificial olfactory chemical-resistant synapse consisting of 3D hierarchical WO3@WO3 nanofibers are demonstrated. The nanofibers exhibit persistent resistance responses through chemical exposures due to the strong chemisorption of water molecules. Typical synaptic behaviors including paired-pulse facilitation, long-term -1 short-term memory, and learning experience have been achieved. Next, a recurrent neural network that is committed to processing the time-dependent data is used to identify gas-phase chemicals of 3-hydroxy-2-butanone, triethylamine, and trimethylamine. Training-free gas recognition has been realized by a WO3@WO3 nanofiber synapse only, in which the accuracy is above 90% at the first epoch. The results have great potential to satisfy stringent performance requirements on artificial perception systems. An artificial olfactory chemical-resistant synapse consisting of 3D hierarchical WO3@WO3 nanofibers is demonstrated. The nanofibers exhibit persistent resistance responses through chemical exposures due to the strong chemisorption of water molecules and result in training-free gas recognition. A recurrent neural network is employed to identify gas-phase chemicals, achieving an accuracy of over 90% at the first epoch. image

关键词： artificial olfactory synapse chemical recognition recurrent neural network tungsten oxide

来源：评论

学校读者我要写书评

暂无评论

Camera-Based Channel Modeling and Symbol Error Rate Analysis of CSK Modulation for Outdoor OCC systems

引用

IEEE ACCESS 2022年 10卷 50254-50264页

作者： Dong, Ke Ke, xizheng Li, Hui Xian Univ Technol Sch Automat & Informat Engn Xian 710048 Peoples R China

A camera with an image sensor is an important alternative device to a photodiode-based receiver of visible-light communication in outdoor scenarios. The intrinsic color separation capability of a camera qualifies color shift keying (CSK) modulation as an intuitive solution to enhance the achievable data rate. The symbol error rate (SER) of CSK modulation is considerably important to system design and performance evaluation, and has not been extensively investigated for outdoor optical camera communication systems from the viewpoint of camera-based channel and image processing-based demodulation. In this study, a two-level channel model is proposed to characterize CSK transmission in a single pixel and in the entire image. A general framework of SER analysis for arbitrary CSK constellations was proposed by directly calculating the upper bounds from the empirical distribution of the noise light in the CIE 1931 color space. Through numerical simulations, the influence of the image detector on CSK demodulation was evaluated. The results indicated that an accurate target region is important for maintaining the SER, and an enlarged target region is beneficial when the maximum ratio combination and selective combination algorithms are used in pixel combination.

关键词： image color analysis Modulation Cameras Colored noise Symbols Visible light communication Light sources Color shift keying image detector optical camera communication pixel combination symbol error rate visible light communication

来源：评论

学校读者我要写书评

暂无评论

A Hierarchical Optimizing Energy Management Strategy for Alleviating Degradation in Fuel Cell Hybrid System

引用

IEEE ACCESS 2024年 12卷 57117-57127页

作者： Fu, Jun xiang, Qian Zeng, Linghong Zu, Yanmin You, Hang Shan, xinkai xin, Jie Li, xi Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Processing & Intelligent Control Minist Educ Wuhan 430074 Peoples R China State Grid Corp China Beijing 102200 Peoples R China Hangzhou ArcSoft Software Co Ltd Hangzhou 310051 Peoples R China

This study designs an energy management strategy for fuel cell hybrid vehicles aimed to alleviating the performance degradation of Proton Exchange Membrane Fuel Cells (PEMFC), fuel consumption, and battery State of Charge (SOC) fluctuations during vehicle operation. The research focuses on the decrease in Electrochemical Surface Area (ECSA) due to Platinum (Pt) catalyst degradation, which is a key factor influencing PEMFC durability. An ECSA model based on the Pt dissolution mechanism is established, and a dynamic condition accelerated stress test (DC-AST) is designed to specifically investigate the impacts of key parameters, such as cycle period, amplitude, and duty cycle on the degradation of ECSA. This reveals the association between ECSA degradation and irregular potential fluctuations. A hierarchical power allocation strategy is then proposed, combining the global search capabilities of optimization algorithms with heuristic strategies in light of these features. The upper level employs Pontryagin's Minimum Principle (PMP) strategy for global power allocation optimization, while the lower level uses a satisfaction-based heuristic strategy that is tailored to the ECSA degradation characteristics, to dynamically adjust power output. Simulation results demonstrate that, compared to traditional rule-based strategies and classical PMP-based strategies, the proposed energy management strategy more effectively mitigates ECSA degradation of PEMFC under typical vehicle conditions.

关键词： Degradation Fuel cells Platinum Batteries Electric potential State of charge Resource management Hybrid power systems Energy management PEMFC hybrid power degradation ECSA energy management

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Cooperative Perception of Constrained Multi-UAV Platform 17th

Multi-modal Cooperative Perception of Constrained Multi-UAV ...

引用

17th International Conference on Intelligent Robotics and Applications

作者： Zhang, Yiheng Cui, Yuanzhe Su, Yongbo Li, Tong Wang, Bingzheng Tang, Qirong Tongji Univ Lab Robot & Multibody Syst Sch Mech Engn Shanghai Peoples R China

ISBN: (纸本)9789819607884;9789819607891

The constrained multi-UAV platform is composed of multiple unmanned aerial vehicles (UAVs) connected physically and mutually. When multiple UAVs operate collaboratively on an interconnected platform, challenges in external environment perception arise due to limited movement range and sensor disturbance among UAVs. Additionally, real-time perception is crucial for various UAV tasks, posing a significant challenge for conventional single-modal algorithms to balance speed and accuracy effectively. This paper proposes an innovative multi-modal collaborative sensing method for multi-UAV systems, integrating point cloud and image processing algorithms. A feature-level fusion is employed by our framework to accurately determine target positioning in real-time. The multi-UAV decision layer utilizes a Kalman Filter to extract data from multiple individual outputs, yielding stable and accurate positioning and classification information. Simulation experiments validate the robustness of this method, reducing disturbance from structural and mutual obstructions among UAVs, and providing accurate target positioning.

关键词： Multi-UAV Perception Sensor Fusion Target Detection

来源：评论

学校读者我要写书评

暂无评论

UAV image object detection based on improved Yolov8 4

UAV image object detection based on improved Yolov8

引用

4th International Conference on image processing and Intelligent Control, IPIC 2024

作者： Zhang, Wei Wang, Jiaxin Wang, Dan Kong, xiangwei Institute of Measurement and Testing Technology Chinese Flight Test Establishment Xi'an710089 China

ISBN: (纸本)9781510682313

In a variety of UAV application scenarios, such as agricultural monitoring, urban safety and traffic management, high-precision image object detection is crucial for real-time analysis and decision-making. Traditional object detection algorithms are often ineffective in dealing with small objects in complex environments. To this end, this paper proposes an improved YOLOv8 model that integrates a NAM (Normalization-based Attention Module) attention mechanism and a Bidirectional Feature Pyramid Network (BiFPN) specifically to optimize the object detection performance of UAV images. The NAM module enhances the model's spatial attention capability by utilizing a normalization process that This enables the model to adaptively emphasize important feature regions in the image, which significantly improves the recognition accuracy of small-scale objects without adding too much computational burden. BiFPN further optimizes the flow of information between different scales, which improves the efficiency of feature utilization and the overall performance of detection. Extensive experiments on the VisDrone2019 dataset show that the improved YOLOv8 model improves the mAP metrics by 11.3% compared to the original model, and performs especially well in scenes with complex backgrounds and the presence of multi-scale objects. This study not only validates the potential application of NAM in UAV vision tasks, but also provides a new technical path for the implementation of deep learning models in real monitoring systems. © 2024 SPIE.

关键词： image analysis

来源：评论

学校读者我要写书评

暂无评论

Research on Parallel Computation and Memory Optimization of Multi-Core Embedded DSP Technology in High Precision Missile Terminal Guidance image Tracking Algorithm 6

Research on Parallel Computation and Memory Optimization of ...

引用

6th IEEE International Conference on Power, Intelligent Computing and systems, ICPICS 2024

作者： xia, Fuming Jing, Bo Huo, Mingge Jiao, xiaoxuan Wang, Shenglong Pan, Jinxin School of Aeronautical Engineering Air Force Engineering University Xi'an710038 China Beijing Electro-Mechanical Engineering Institute Beijing100074 China

ISBN: (纸本)9798350374315

This paper mainly discusses how to effectively use multi-core embedded digital signal processor (DSP) technology to realize parallel computation of image tracking algorithm and memory optimization in high precision missile terminal guidance system. With the increasing requirement of missile strike accuracy in modern war, the vision-based terminal guidance technology has been widely concerned because of its strong autonomy and anti-jamming ability. However, such image processing algorithms are usually highly computation-intensive and data dependent, which requires high real-time and hardware resources. In this paper, the key steps of image tracking algorithm are analyzed and reconstructed deeply, and the architecture suitable for parallel processing of multi-core DSP is designed by modularization. The parallel computing advantages of multi-core DSP are given full play through task division and scheduling strategies to improve the execution efficiency and real-time performance of the algorithm. Secondly, the research also focuses on memory optimization, including the design of data cache strategy, reducing data redundancy, improving memory access locality, etc., and strives to maximize the data reading speed and reduce the memory bandwidth pressure under the condition of limited embedded system resources. To sum up, this research is committed to building an efficient and stable multi-core embedded DSP environment, parallel computing model and memory optimization scheme for high-precision missile terminal guidance image tracking algorithm, which has important theoretical value and practical significance for improving the intelligence level and combat efficiency of missile terminal guidance system. © 2024 IEEE.

关键词： Guided missiles

来源：评论

学校读者我要写书评

暂无评论

Research on Driving Behavior Recognition Algorithm and Implementation Based on Convolutional Neural Networks 24

Research on Driving Behavior Recognition Algorithm and Imple...

引用

4th International Conference on Artificial Intelligence, Automation and High Performance Computing, AIAHPC 2024

作者： Xu, Qiangqiang Guo, Junhua Chen, xi School of Transportation Engineering East China Jiaotong University China

ISBN: (纸本)9798400710049

The technology of driver behavior recognition holds significant importance in modern traffic management and autonomous driving systems. This paper revolves around Convolutional Neural Networks (CNNs) as the cornerstone, delving into the design and implementation of driver behavior recognition algorithms. Initially, image preprocessing using OpenCV lays the foundation for subsequent neural network processing. Subsequently, critical components within the neural network, such as activation functions and loss functions, are elaborated upon, alongside discussions on gradient-based optimization methods and backpropagation algorithms. Furthermore, this study provides an in-depth analysis of the roles of convolutional layers and pooling layers within CNNs, emphasizing their applications in driver behavior recognition. Lastly, by detailing specific algorithmic workflows and network architectures, the development of a driver behavior detection system is achieved. This research supports advancements in autonomous driving and traffic safety, demonstrating the vast potential of convolutional neural networks in practical applications. © 2024 Copyright held by the owner/author(s).

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：