检索结果-内蒙古大学图书馆

IEEE 11th Annual Computing and Communication Workshop and Conference (CCWC)

作者： Manore, Curtis Manjunath, Pratheek Larkin, Dominic US Mil Acad West Point NY 10996 USA

ISBN: (纸本)9781665414906

With the increasing complexity of machine vision algorithms and growing applications of image processing, how do computers without a dedicated graphics processor perform? This research discusses the computational abilities of two low-cost single board computers (SBCs) by subjecting them to various Visual Inertial Odometry (VIO) algorithms. The end goal of this research is to identify a SBC which meets the requirements of being employed on an Unmanned Aerial System for autonomous navigation.

关键词： Single Board Computer Odroid Computer vision VIO

来源：评论

学校读者我要写书评

暂无评论

Research on 3D model reconstruction based on a sequence of cross-sectional images

引用

machine vision AND applications 2021年第4期32卷 1-16页

作者： Dong, Zhiguo Wu, Xiaobo Ma, Zhipeng Taiyuan Univ Technol Coll Mech & Vehicle Engn Taiyuan Peoples R China Shanxi Key Lab Precis Machining Taiyuan Peoples R China

It is often difficult to obtain the high-precision inner cavity contour size and 3D model of parts and components in reverse engineering. This paper proposes a method that uses a sequence of section images of a part to reconstruct their 3D models. This method cuts the part layer by layer to obtain the sectional images and extracts the 3D information of the sectional image contours to generate point clouds. These point clouds are then used to reconstruct a 3D model of the part. High contrast material is used to embed the target part for pre-processing. A machining centre was used to mill the part layer by layer vertically to acquire high precision section profile images. The improved Canny edge detection operator was combined with the spatial moment sub-pixel subdivision algorithm to improve the edge detection accuracy. The camera imaging model algorithm transforms the coordinates of the image edge position to obtain a high-precision 3D point cloud of the part. The 3D solid model of the target part was obtained using NURBS surface reconstruction. The results show that the 3D model reconstruction method using the profile sequence of the cross-sectional images is independent of the complexity of the part's structure and the complete internal structure of the part can be obtained. The proposed edge detection algorithm significantly refines the edge position of the contours in the cross-sectional image and the measurement accuracy was improved. This method improves the minimum deviation to 50 mu m. The shape accuracy of roundness, cylindricity and perpendicularity of the structure is high. The proposed method can meet the reverse precision requirements in general precision machining.

关键词： 3D reconstruction of reverse engineering Slice image image contour sequence Sub-pixel subdivision edge detection NURBS surface reconstruction

来源：评论

学校读者我要写书评

暂无评论

A machine vision-Based Measurement Method for the Concentricity of Automotive Brake Piston Components

Research Square

引用

Research Square 2024年

作者： Weinan, Ge Qinghua, Li Wanting, Zhao Tiantian, Xu Shihong, Zhang School of Mechanical Engineering Changchun Guanghua University Changchun130033 China School of Mechanical and Vehicle Engineering Changchun University Changchun130022 China

The stability and reliability of the brake system are critically affected by the concentricity error of automotive brake piston components. Traditional contact-based concentricity measurement methods are inefficient. To address the issue of low detection efficiency, a non-contact concentricity measurement method based on the combination of machine vision and image processing technology is proposed in this paper. In this method, an industrial camera is utilized to capture images of the measured part's end face from the top of the spring. Edge contours are extracted through image preprocessing algorithms, the outer circle center is calculated, and the inner circle center is fitted. Finally, the concentricity error is calculated using the coordinates of the two circle centers. Experimental results show that, compared to a coordinate measuring machine(CMM), this method has a maximum error of only 0.0393mm and an average measurement time of just 3.9s. It significantly improves measurement efficiency and meets the industry's demand for automated inspection. The experiments verified the feasibility and effectiveness of this method in practical engineering applications, providing reliable technical support for the online inspection of automotive brake piston components. Additionally, this method can be applied to the concentricity measurement of other complex stepped shaft parts. © 2024, CC BY.

关键词： Pistons

来源：评论

学校读者我要写书评

暂无评论

Classification of Alzheimer’s Disease Using Improved MeshCNN based on Residuals Connection

Classification of Alzheimer’s Disease Using Improved MeshCN...

引用

machine vision, image processing and Imaging Technology (MVIPIT), International Conference on

作者： Yuankun Liu Duanyang Feng Lumin Xing Wenjian Liu Faculty of Data Science City University of Macau Macau S.A.R China Shandong Provincial Qianfoshan Hospital The First Affiliated Hospital of Shandong First Medical University Jinan China

ISBN: (数字)9798350306545

ISBN: (纸本)9798350306552

It’s great to see the potential of deep learning being applied to medical imaging for the diagnosis of Alzheimer’s disease. The challenges of small data size and overfitting are common issues in many deep learning applications, and it’s encouraging to see that the ADNI dataset was utilized to address these challenges. The use of MeshCNN network with residual connections borrowed from ResNet is a clever approach to improve the classification accuracy. The Mesh data representation of brain surfaces as triangular meshes is an interesting and innovative technique to incorporate into the classification model. The improvements in accuracy of 0.01 for AD / MCI / NC and 0.02 for AD / NC may seem small, but in the context of Alzheimer’s disease diagnosis, even small improvements in accuracy can have significant implications for early intervention and treatment. Overall, this study demonstrates the potential of deep learning to advance research on Alzheimer’s disease diagnosis and underscores the importance of continued innovation in medical imaging techniques to improve the accuracy and effectiveness of diagnosis and treatment.

关键词： Deep learning Technological innovation Accuracy machine vision Magnetic resonance Brain modeling Data models

来源：评论

学校读者我要写书评

暂无评论

Early Defect Detection in Conveyor Belts using machine vision 16

Early Defect Detection in Conveyor Belts using Machine Visio...

引用

16th International Joint Conference on Computer vision, Imaging and Computer Graphics Theory and applications (VISIGRAPP) / 16th International Conference on Computer vision Theory and applications (VISAPP)

作者： Netto, Guilherme G. Coelho, Bruno N. Delabrida, Saul E. Sinatora, Amilton Azpurua, Hector Pessin, Gustavo Oliveira, Ricardo A. R. Bianchi, Andrea G. C. Fed Univ Ouro Preto UFOP Sch Mines Dept Engn Control & Automat 122 Diogo de Vasconcelos BR-35400000 Ouro Preto MG Brazil Fed Univ Ouro Preto UFOP Comp Dept 122 Diogo de Vasconcelos BR-35400000 Ouro Preto MG Brazil Vale Inst Technol ITV 31 Juscelino Kubitschek BR-35400000 Ouro Preto MG Brazil

ISBN: (纸本)9789897584886

Continuous belt monitoring is of utmost importance since wears on its surface can develop into tears and even rupture. It can causes the interruption of the conveyor, and consequently, loss of capital, or even worse, serious or fatal accidents. This paper proposes a laser-based machine vision method for detecting defects in conveyor belts to solve the monitoring problem. The approach transforms an image of a laser line into a one-dimensional signal, then analyzes it to detect defects, considering that variations in this signal are caused by defects/imperfections on the belt surface. Differently from previous works, the proposed method can identify a defect through a 2D reconstruction of it. The results reveal that the proposed method was capable to detect superficial imperfections in simulated conveyor belt experiments, achieving high values in metrics such as precision and recall.

关键词： image and Signal processing Curvature Outlier Defects Detection machine vision Inspection Maintenance

来源：评论

学校读者我要写书评

暂无评论

All-optical geometric image transformations enabled by ultrathin metasurfaces

引用

NATURE COMMUNICATIONS 2023年第1期14卷 1-8页

作者： Zhang, Xingwang Zhang, Xiaojie Duan, Yao Zhang, Lidan Ni, Xingjie Penn State Univ Dept Elect Engn University Pk PA 16802 USA

image processing plays a vital role in artificial visual systems, which have diverse applications in areas such as biomedical imaging and machine vision. In particular, optical analog image processing is of great interest because of its parallel processing capability and low power consumption. Here, we present ultra-compact metasurfaces performing all-optical geometric image transformations, which are essential for image processing to correct image distortions, create special image effects, and morph one image into another. We show that our metasurfaces can realize binary image transformations by modifying the spatial relationship between pixels and converting binary images from Cartesian to log-polar coordinates with unparalleled advantages for scale- and rotation-invariant image preprocessing. Furthermore, we extend our approach to grayscale image transformations and convert an image with Gaussian intensity profile into another image with flat-top intensity profile. Our technique will potentially unlock new opportunities for various applications such as target tracking and laser manufacturing. Metasurfaces enable all-optical geometric coordinate transformations, converting images with altered pixel spatial relations, which can facilitate fast, energy-efficient preprocessing for tasks like object tracking, or aid in laser manufacturing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Literature Review of machine Learning Techniques for Dance Recognition and Robotic vision

A Literature Review of Machine Learning Techniques for Dance...

引用

Robotics and Technologies for Industrial Automation (ROBOTHIA), IEEE International Conference on

作者： Lee Wei San Samuel-Soma M. Ajibade Muhammed Basheer Jasser Adefemi Ayodele Babatunde Adedotun Ajayi Mbiatke Anthony Bassey Department of Data Science and Artificial Intelligence Faculty of Engineering and Technology Sunway University Selangor Darul Ehsan Malaysia Research Centre for Nanomaterials and Energy Technology (RCNMET) Faculty of Engineering and Technology Sunway University Selangor Malaysia Research Centre for Human-Machine Collaboration (HUMAC) Faculty of Engineering and Technology Sunway University Petaling Jaya Selangor Malaysia University of East London London UK Department of Cyber security Faculty of Computing & Informatics Ladoke Akintola University of Technology Ogbomoso Nigeria Department of Business Administration Universiti Tun Hussein Onn Malaysia Batu Pahat Malaysia

ISBN: (数字)9798350356755

ISBN: (纸本)9798350356762

image recognition, powered by machine learning (ML), has significantly advanced applications in both dance movement recognition and robotic vision. This review examines key ML techniques, including Convolutional Neural Networks (CNNs), Deep Neural Networks (DNNs), Self-Organizing Maps (SOMs), and Long Short-Term Memory (LSTM) networks, alongside pose estimation methods like OpenPose and Part Affinity Fields (PAFs). These techniques enhance dance classification, real-time feedback, and motion analysis, with OpenPose + LSTMs and PAFs + LSTMs demonstrating the highest accuracy. Notwithstanding progress, obstacles such as high computational costs, data dependency, and real-time implementation challenges persist. Beyond dance, these methods are critical in robotic vision, intelligent automation, and industrial image processing, enabling autonomous robotic navigation, defect detection in manufacturing, and AI-driven motion tracking. By leveraging human movement analysis for robotics, ML improves human-robot interaction, robotic-assisted rehabilitation, and industrial automation. Despite progress, challenges such as high computational demands, data dependency, and real-time constraints remain. This review explores future directions, including multimodal data fusion, hybrid AI models, and real-time optimization, bridging the gap between AI-driven motion systems and intelligent automation to enhance adaptability and efficiency across domains.

关键词： Intelligent automation Humanities Solid modeling image recognition Accuracy Service robots Robot sensing systems Real-time systems Robots Long short term memory

来源：评论

学校读者我要写书评

暂无评论

TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR Semantic Segmentation

TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR ...

引用

IEEE Computer Society Conference on Computer vision and Pattern Recognition Workshops (CVPRW)

作者： Rong Li Shijie Li Xieyuanli Chen Teli Ma Juergen Gall Junwei Liang HKUST(GZ) China University of Bonn Germany Lamarr Institute for Machine Learning and Artificial Intelligence Germany HKUST China

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

LiDAR semantic segmentation plays a crucial role in enabling autonomous driving and robots to understand their surroundings accurately and robustly. A multitude of methods exist within this domain, including point-based, range-image-based, polar-coordinate-based, and hybrid strategies. Among these, range-image-based techniques have gained widespread adoption in practical applications due to their efficiency. However, they face a significant challenge known as the "many-to-one" problem caused by the range image ’s limited horizontal and vertical angular resolution. As a result, around 20% of the 3D points can be occluded. In this paper, we present TFNet, a range-image-based LiDAR semantic segmentation method that utilizes temporal information to address this issue. Specifically, we incorporate a temporal fusion layer to extract useful information from previous scans and integrate it with the current scan. We then design a max-voting-based post-processing technique to correct false predictions, particularly those caused by the "many-to-one" issue. We evaluated the approach on two benchmarks and demonstrated that the plugin post-processing technique is generic and can be applied to various networks.

关键词： Training Laser radar Three-dimensional displays image resolution Semantic segmentation Face recognition Neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning-driven lossy image compression: A comprehensive survey

引用

ENGINEERING applications OF ARTIFICIAL INTELLIGENCE 2023年第PartB期123卷

作者： Jamil, Sonain Piran, Md. Jalil Rahman, MuhibUr Kwon, Oh-Jin Sejong Univ Dept Elect Engn Seoul 05006 South Korea Sejong Univ Dept Comp Engn Seoul 05006 South Korea Polytech Montreal Dept Elect Engn Montreal PQ H3T 1J4 Canada

In the field of image processing and computer vision (CV), machine learning (ML) architectures are widely used. image compression problems can be solved using convolutional neural networks (CNNs). As a result of bandwidth and memory constraints, compression of images is a necessity. There are three types of information found in images: useful, redundant, and irrelevant. In this survey, we will discuss how ML is used to compress lossy images. Firstly, we describe the background of lossy image compression. Next, we classify ML-based image compression frameworks into subgroups based on their architectures. Auto-encoders (AEs), variational auto-encoders (VAEs), CNNs, recurrent neural networks (RNNs), long short-term memories (LSTMs), gated recurrent units (GRUs), generative adversarial networks (GANs), transformers, principal component analysis (PCA) and fuzzy means clustering are among these subgroups. By analyzing learning-driven image compression frameworks, we present pros and cons of each subgroup. Lastly, we outline several research gaps and future research directions in the field of ML-based image compression.

关键词： Learned image compression Deep learning JPEG End-to-end image compression machine learning JPEG AI vision transformers

来源：评论

学校读者我要写书评

暂无评论

Research on Korla Fragrant Pear Grading Method Based on Random Forest and MLP

Research on Korla Fragrant Pear Grading Method Based on Rand...

引用

image processing and Computer applications (ICIPCA), IEEE International Conference on

作者： Yingchao Wang Jiangyu Zhang Na Li De'an Huang Lihao Qin Shan Sun Xingxing Xie Xinjiang University of Science and Technology Xinjiang Korla China

ISBN: (数字)9798350360240

ISBN: (纸本)9798350384161

In response to the problems of uneven quality and unstable accuracy caused by manual grading in the grading process of Korla pear, a Korla pear grading method based on random forest and MLP is proposed, aiming to further optimize the above problems using machine vision methods. This paper collects left and right views and top views of pear images. Using a combination of K-means clustering and threshold segmentation to achieve background separation; This paper constructs the minimum bounding rectangle for the left and top views of Xiangli to obtain its longitudinal and transverse diameters; Based on the measurement difficulty of pear weight, a pear weight prediction model based on random forest model is constructed using pear diameter parameters; This paper constructs a pear grading model using MLP neural network. The experimental results show that the proposed Korla pear grading method based on random forest and MLP has an accuracy of 99.69% in the training set and 98.75 % in the test set, verifying the feasibility and accuracy of this method.

关键词： Weight measurement Training image segmentation Accuracy Computational modeling Neural networks Object segmentation Manuals Predictive models Random forests

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：