检索结果-内蒙古大学图书馆

2nd International Conference on image processing and Media Computing, ICIPMC 2023

作者： Zhao, Yan Zhang, Shaobo Zhao, Wanqing Wei, Ying Peng, Jinye Northwest University School of Information Science and Technology Xi'an China

ISBN: (纸本)9798350326611

Augmented Reality (AR) refers to the perfect integration of virtual information with the real environment through computer technology, enhancing people's understanding of the real environment. Due to its excellent interactivity and realistic visual effects, it has received extensive attention from various fields. The effectiveness of augmented reality largely depends on whether virtual information can be accurately rendered in the real scene, with the most critical aspect being the 6D pose estimation of the target object in the real scene. Deep learning-based pose estimation methods have become indispensable technology in AR systems due to their high accuracy and wide applicability. Among existing pose estimation algorithms, YOLO6D has the advantages of good stability and fast speed. However, for AR applications that require interaction with the human eye, due to its complex network structure and large computational complexity, it still faces challenges in real-time performance and deployment on mobile devices. Therefore, this paper aims to achieve a mobile AR system based on real-time pose estimation, using the YOLO-6D pose estimation network as the foundation, and conducting research from the aspects of model compression and system design. By using model compression algorithms include channel pruning and knowledge distillation (KD), the computational and parameter complexity of the pose estimation model is reduced, and the network inference speed is improved. At the same time, the AR tasks are decomposed in the system design to alleviate the performance pressure during deployment on mobile devices, thus building a high-quality, low-latency mobile AR system. © 2023 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Parallel Dual Broad Learning Surrogate Assisted Semi-supervised Kernel Multi-objective Evolutionary Rough Fuzzy Clustering Algorithm for image Segmentation

Parallel Dual Broad Learning Surrogate Assisted Semi-supervi...

引用

Natural Language processing (ICNLP), International Conference on

作者： Weilin Du Feng Zhao School of Communications and Information Engineering (School of Artificial Intelligence) Xi’an University of Posts and Telecommunications Xi’an China

ISBN: (数字)9798350349115

ISBN: (纸本)9798350349122

To improve the segmentation performance of multi-objective evolutionary clustering algorithms, this paper proposes a parallel dual broad learning surrogate assisted semi-supervised kernel multi-objective evolutionary rough fuzzy clustering algorithm (PDBLS-SKMRFC) for image segmentation. First, the algorithm constructs a parallel dual broad learning surrogate assisted multi-objective evolutionary framework. It uses two broad learning systems as classification and regression surrogate models to evaluate the population in parallel manner. In the framework, a multi-population division strategy guided by dual broad learning system, a dominant individual crossover strategy, a sub-population mutation strategy, and a hierarchical environment selection strategy are designed to obtain more excellent offspring populations. Then, a semi-supervised kernel rough fuzzy intra-class compactness function is constructed, which uses a few labels and pseudo-labels as supervision information to improve the image segmentation performance, and evaluates the clustering quality together with the kernel separability function. Finally, a semi-supervised kernel rough fuzzy clustering validity index is designed to select the optimal solution from the final non-dominated solution set for image segmentation. Experimental results on color images show the effectiveness of the proposed algorithm.

关键词： Learning systems image segmentation Clustering algorithms Color Linear programming Natural language processing Classification algorithms Indexes Kernel Standards

来源：评论

学校读者我要写书评

暂无评论

Video Smoke Detection Algorithm Based on a Spatial-Temporal Neural Network Model 9

Video Smoke Detection Algorithm Based on a Spatial-Temporal ...

引用

9th International Conference on Intelligent Computing and Signal processing, ICSP 2024

作者： Cao, Zhen Zhang, xi Shenyang Fire Science and Technology Research Institute Ministry of Emergency Management Shengyang China

ISBN: (纸本)9798350376548

a kind of spatial-temporal neural network video smoke detection algorithm is proposed in order to solve the problems associated with the incorrect classification of the static approximate smoke background in the face of the detection of smoke in video detection networks, and the problem of false alarms and of the original test model algorithms being different in different detection environments. Based on the original YOLO v4 neural network algorithm, this paper introduces a k-means + + algorithm and genetic algorithm, while using the algorithm's clustering function to classify the sample points of the real boxes of the image data set, which make it a more suitable anchor. At the same time, the genetic algorithm is used to adjust its anchor in order to allow the generated anchor to adapt to the needs related to smoke detection. In the original neural network model, the dual-stream network model algorithm is used to extract information from the first step of the YOLO algorithm in order to further filter the smoke's characteristics as well as filter out error information, all to improve the detection capabilities of the overall neural network for video smoke fog images. Compared with traditional YOLOv4 networks, the algorithm obtained by the model algorithm has been improved by 8.51°/0. In actual tests, the alarm time requirements of the smoke alarm test program for early fire monitoring and the alarm systems for visual images were improved, and the detection accuracy of the network was also improved based on the assurance of the detection speed, while the performance of the model algorithm was also improved for different scenes. © 2024 IEEE.

关键词： dual-stream Network K-means safety science smoke detection YOLOv4

来源：评论

学校读者我要写书评

暂无评论

Denoising algorithm of OCT images via sparse representation based on noise estimation and global dictionary

引用

OPTICS EXPRESS 2022年第4期30卷 5788-5802页

作者： Zhang, xi Li, Zhongliang Nan, Nan Wang, xiangzhao Chinese Acad Sci Shanghai Inst Opt & Fine Mech Lab Informat Opt & Optoelect Technol Shanghai 201800 Peoples R China Univ Chinese Acad Sci Ctr Mat Sci & Optoelect Engn Beijing 100049 Peoples R China

Optical coherence tomography (OCT) is a high-resolution and non-invasive optical imaging technology, which is widely used in many fields. Nevertheless, OCT images are disturbed by speckle noise due to the low-coherent interference properties of light, resulting in significant degradation of OCT image quality. Therefore, a denoising algorithm of OCT images via sparse representation based on noise estimation and global dictionary is proposed in this paper. To remove noise and improve image quality, the algorithm first constructs a global dictionary from high-quality OCT images as training samples and then estimates the noise intensity for each input image. Finally, the OCT images are sparsely decomposed and reconstructed according to the global dictionary and noise intensity. Experimental results indicate that the proposed algorithm efficiently removes speckle noise from OCT images and yield high-quality images. The denoising effect and execution efficiency are evaluated based on quantitative metrics and running time, respectively. Compared with the mainstream adaptive dictionary denoising algorithm in sparse representation and other denoising algorithms, the proposed algorithm exhibits satisfying results in terms of speckle-noise reduction as well as edge preservation, at a reduced computational cost. Moreover, the final denoising effect is significantly better for sets of images with significant variations in noise intensity. (C) 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： image processing image quality Imaging systems Light properties Optical computed tomography Optical imaging

来源：评论

学校读者我要写书评

暂无评论

A review of intelligent vehicle motion planning algorithms 3

A review of intelligent vehicle motion planning algorithms

引用

3rd International Conference on Advanced algorithms and Signal image processing, AASIP 2023

作者： Kong, Lingming Wang, Zhiyu xi, Ruixuan Shen, Liangyi Ji, Zhao Li, Kai Co. Ltd. Tianjin300300 China

ISBN: (纸本)9781510668522

With vehicles becoming a necessity for people's life and work, the vigorous development of intelligent vehicles is of great significance in today's society in order to reduce traffic accidents, lower operating costs and achieve environmentally friendly travel. Motion planning, as the functional core of intelligent driving systems, is crucial to the driving safety of intelligent vehicles. This paper introduces the development status of intelligent vehicles at home and abroad, studies the current research status of mainstream motion planning techniques, analyses the technical challenges encountered in motion planning for intelligent vehicles in urban roads, and illustrates the development goal of establishing efficient and reliable motion planning algorithms in complex scenarios. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Research on Early Warning and Monitoring systems for Contact Between Live Equipment and Foreign Objects

引用

IET image processing 2025年第1期19卷

作者： Yuan, Fang Chen, BoYuan Tan, YunFei Liao, KaiYang xia, WeiMin State Grid Shaanxi Electric Power Company Limited Xi'an Power Supply Company of State Grid Shaanxi Electric Power Co. Ltd. Xi'an China Xi'an University of Technology School of Printing Packaging and Digital Media Xi'an University of Technology Xi'an China

Addressing the safety hazards arising from inadequate clearance between tree growth and power facilities, this paper innovatively proposes an online monitoring and early warning system for distribution networks based on advanced image processing technology. The system integrates three core functions: automatic tree species identification, precise detection of safety distances between tree crowns and live equipment, and real-time foreign object contact warnings. By deploying maintenance-free online monitoring terminals, the system can monitor tree growth around the distribution network around the clock, continuously. It utilizes efficient backend algorithms to intelligently analyse the collected image data, promptly detecting and warning of potential tree-obstacle hazards. Compared to traditional manual inspections and UAV inspections, this system not only significantly improves monitoring accuracy and real-time performance but also overcomes the limitations of UAV inspections, such as high costs and poor real-time performance. The solution proposed in this paper is expected to fundamentally enhance the safe operation level of distribution networks and effectively reduce power accidents such as tripping and short circuits caused by tree obstacles. Future plans include further optimizing system functions to promote the wider application and promotion of the technology. © 2025 The Author(s). IET image processing published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.

关键词： Distance measurement

来源：评论

学校读者我要写书评

暂无评论

Automatic conversion system of digital music score image based on image recognition algorithm 3

Automatic conversion system of digital music score image bas...

引用

3rd International Conference on Computer Science and Communication Technology, ICCSCT 2022

作者： Yao, Yi Xi'an Conservatory of Music Shaanxi Xi'an710000 China

ISBN: (纸本)9781510661240

The development of target detection and recognition algorithms in the field of image processing has promoted the development of automatic image conversion systems for digital musical scores and related algorithms. This was crucial for the development of note-recognition coding and the conversion of musical scores into readable digital formats. The purpose of this paper is to study the automatic conversion system of digital music score image based on image recognition algorithm. The deep learning technology based on computer vision is used for musical score image recognition, and a digital musical score image automatic conversion system is designed and built. Harmonic peak method and confidence method are introduced, and their shortcomings are analyzed. Combined with the advantages of these two algorithms, an improved normal harmonic method is proposed, and the detailed ideas and steps of the algorithm are given. And the extracted fundamental frequency and time information are converted into pitch and time value combined with the basic knowledge of music theory. The recognition accuracy rate of the normal harmonic method proposed in this paper reaches more than 92%, which not only greatly improves the recognition accuracy, but also retains the strong anti-noise characteristics of the traditional harmonic peak method. © 2022 SPIE.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

image Encryption Algorithm Based on Combination Chaotic System and DNA Coding 4

Image Encryption Algorithm Based on Combination Chaotic Syst...

引用

4th International Conference on Natural Language processing, ICNLP 2022

作者： Mao, Panpan Zhang, Xuefeng Jiang, Wen Xi'an University of Posts and Telecommunications School of Cyberspace Security Xi'an710121 China National Internet Emergency Center Beijing100029 China

ISBN: (数字)9781665495448

ISBN: (纸本)9781665495448

In order to increase the chaotic parameter range, improve the initial sensitivity of the chaotic system and the security of the image encryption algorithm, This paper proposed a new image encryption based on combination chaotic system and DNA coding. Two one-dimensional chaotic maps are nested to obtain a combined chaotic system, and the chaotic sequences generated by the combined chaotic system is amplified and modulated to obtain the DNA coding rule sequences and the scrambling sequences, and the uniformity of the coding rules are improved through rule replacement operation. Using DNA encoding, DNA exclusive-or(XOR),and DNA decoding operations to achieve plain image diffusion, bit-level permutation is performed on the diffused image through the permutation sequences to obtain encrypted image. Theoretical and experimental simulation analysis shows that the chaotic interval of the combined chaotic system is increased and the initial value sensitivity is improved. The encryption algorithm based on the combined chaotic system and DNA coding can effectively resist statistical attacks, differential attacks and exhaustive attacks, the security of the encryption algorithm is also significantly improved compared to other algorithms. © 2022 IEEE.

关键词： Chaotic systems

来源：评论

学校读者我要写书评

暂无评论

A Fast image Matching Approach in Fatigue Testing of Wall Plate Structures

A Fast Image Matching Approach in Fatigue Testing of Wall Pl...

引用

IEEE International Conference on Information Communication and Signal processing (ICICSP)

作者： Zhang Wendong Shi Baoquan Chen xianmin Lv Yuanbo National Key Laboratory of Strength and Structural Integrity AVIC Aircraft Strength Research Institute Xi'an China School of Mechano-Electronic Engineering Xidian University Xi'an China

ISBN: (数字)9798350355895

ISBN: (纸本)9798350355901

To address the challenges in motion vector estimation due to local non-uniform deformation of specimens during fatigue tests, this paper proposes an image matching method that combines template sub-image techniques with a Kalman filter. This method employs a mesh motion estimation model, initially using the Kalman filter to predict the matching point positions of mesh nodes. Subsequently, template matching is utilized to achieve precise matching of these nodes. The algorithm is accelerated through GPU-CPU heterogeneous parallel computing technology. Test results indicate that the GPU-accelerated image matching method attains the accuracy of the CPU-based algorithm while significantly reducing processing time, thereby fully meeting the real-time requirements of online image feature matching applications.

关键词： Accuracy Deformation image matching Signal processing algorithms Fatigue Prediction algorithms Vectors Real-time systems Kalman filters Testing

来源：评论

学校读者我要写书评

暂无评论

Students' Course Results Prediction Based on Data processing and Machine Learning Methods

引用

JOURNAL OF SIGNAL processing systems FOR SIGNAL image AND VIDEO TECHNOLOGY 2022年第11期94卷 1199-1211页

作者： Liu, Jinyang Yin, Chuantao Wang, Kunyang Guan, Minghui Wang, xi Zhou, Hong Beihang Univ Sch Econ & Management Beijing 100191 Peoples R China Beihang Univ Sino French Engineer Sch Beijing 100191 Peoples R China

Smart learning has been concerned in the domain of education, and how to correctly predict students' performance is one of meaningful issues. Mature performance prediction methods are promising to be applied to education systems to make educators know more about students' learning states and provide students with academic help in time. Based on students' historical course results and courses' basic information, our work proposes a student's course results prediction model using reasonable data processing and machine learning methods, which can well achieve the goal of out-of-sample results prediction. Our model framework mainly has two parts: numeric and non-numeric features vector embedding algorithms;model optimization based on data augmentation and integration. Firstly, we generate respectively feature embedding vectors for non-numeric and numeric data;Secondly by applying relative statistical methods we combine the previous embedding vectors to form a synthetic feature matrix, then use the Gramian Angular Field and Markov Transition Field to augment the data information and extend the feature embedding by matrix integration. To verify the validity of our model in experiments, we implement multilayer perceptron as training model to realize prediction task. Our model has quite good interpretability so that it can well be understood what happens in the model framework and how the data is processed throughout the model pipeline. This can well help us make relative adjustments and tunes according to different problems and scenarios, thus get better prediction results.

关键词： Machine learning Data optimization and processing Vector embedding Data augmentation Feature integration

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：