检索结果-内蒙古大学图书馆

8th International conference on Data Science and machine Learning applications, CDMA 2025

作者： Alsharaa, Mohammad Alfawzan, Layla Fati, Suliman Qureshi, Basit Akour, Mohammad Alzamil, Mohammad College of Computer and Information Sciences Prince Sultan University Riyadh Saudi Arabia

Welcome to the eighth edition of the biennial International conference on Data Science and machine Learning applications (CDMA2025). This edition honors the 2030 Saudi vision by exploring its ambitious goals and trans... 详细信息

ISBN: (纸本)9798331539696

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

vision-based power line cables and pylons detection for low flying aircraft

引用

machine vision AND applications 2025年第2期36卷 1-21页

作者： Gwizdala, Jakub Oner, Doruk Roy, Soumava Kumar Shah, Mian Akbar Eberhard, Ad Egorov, Ivan Krusi, Philipp Yakushev, Grigory Fua, Pascal Ecole Polytech Fed Lausanne Comp Vis Lab Lausanne Switzerland Bilkent Univ Dept Comp Engn NeuraVis Res Lab Ankara Turkiye Daedalean AG Zurich Switzerland

Power lines are dangerous for low-flying aircraft, especially in low-visibility conditions. Thus, a vision-based system able to analyze the aircraft's surroundings and to provide the pilots with a "second pair of eyes" can contribute to enhancing their safety. To this end, we develop a deep learning approach to jointly detect power line cables and pylons from images captured at distances of several hundred meters by aircraft-mounted cameras. In doing so, we combine a modern convolutional architecture with transfer learning and a loss function adapted to curvilinear structure delineation. We use a single network for both detection tasks and demonstrate its performance on two benchmarking datasets. We have also integrated it within an onboard system and run it inflight. We show with our experiments that it outperforms the prior distant cable detection method by Stambler et al. (in: International conference on Robotics and Automation, 2019) on both datasets, while also successfully detecting pylons, given their annotations are available for the data.

关键词： Power lines detection Transmission towers detection Poles detection Delineation Deep learning

来源：评论

学校读者我要写书评

暂无评论

Annotation Tools for Computer vision Tasks 17

Annotation Tools for Computer Vision Tasks

引用

17th International conference on machine vision, ICMV 2024

作者： Moschidis, Christos Vrochidou, Eleni Papakostas, George A. Department of Informatics Democritus University of Thrace Kavala65404 Greece

ISBN: (纸本)9781510688278

Common computer vision (CV) tasks include image classification, object detection, segmentation, and recognition. To handle such tasks, machine learning (ML) models for image processing require a great amount of annotated training data. While datasets are expanding in size and variety, annotation becomes demanding, since its quality can severely affect the models' performance. Thus, several annotation tools have been developed and designated for specific applications and model requirements. This work aims to provide an overview of the most up-to-date annotation tools for computer vision tasks, including 2D and 3D image data and video, comparatively highlighting their advantages and limitations. The appropriateness of each tool for specific tasks is emphasized, providing a reference map for researchers towards determining the annotation tool best tailored to their needs. Future trends in image annotation are also discussed. © 2025 SPIE.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

machine vision-Enabled Automated System for Precise Dimension Measurement 1

Machine Vision-Enabled Automated System for Precise Dimensio...

引用

1st International conference on AIML-applications for Engineering and Technology, ICAET 2025

作者： Bhawar, Harshada Darshane, Rucha Kadam, Anushka Jambhale, Samruddhi Patil, Harishchandra. T. Daimiwal, Nivedita Shriram, Revati MKSSS's Cummins College Instrumentation & Control Pune India

ISBN: (纸本)9798350355611

The dimension measurement system is implemented using Raspberry Pi 4 and its camera module. The algorithm development is done using Python programming, majorly Open Source Computer vision (OpenCV) and other allied libraries. Real-time accurate measurement of dimensions plays a critical role in various industrial and manufacturing processes, ensuring product quality, compliance with standards, and overall efficiency. machine vision technology has emerged as a powerful tool for achieving precise dimension measurement, offering numerous advantages over traditional methods. The paper highlights the capabilities of machine vision in the accurate measurement of various objects with high repeatability and speed. This is a framework where accuracy about the dimension of real-time objects in 3 different classes like small, medium, and large-sized objects is estimated. In the proposed approach, the object is detected by using an edge detection technique, continuous contour measurement and computing Euclidean distance. Under uniform environmental conditions, the proposed system gives accurate results for diverse object sizes ranging in height from 2 to 30 cm. The accuracy of the results is reliably within a defined range, which corresponds to the distance of the camera from the object. The span for small-sized objects is 6 to 35 cm, for medium-sized sized it is 17.5 to 72.5 cm and for large-sized sized it is 37 to 85 cm. © 2025 IEEE.

关键词： machine vision

来源：评论

学校读者我要写书评

暂无评论

Utilizing Pretrained vision Transformers and Large Language Models for Epileptic Seizure Prediction 8

Utilizing Pretrained Vision Transformers and Large Language ...

引用

8th International conference on Data Science and machine Learning applications, CDMA 2025

作者： Parani, Paras Mohammad, Umair Saeed, Fahad Knight Foundation School of Computing and Information Sciences Florida International University MiamiFL United States

ISBN: (纸本)9798331539696

Repeated unprovoked seizures are a major source of concern for people with epilepsy. Predicting seizures before they occur is of interest to both machine-learning scientists as well as clinicians, and is an active area of research. The variability of EEG sensors, type of seizures, and specialized knowledge required for annotating the data complicates the large-scale annotation process essential for supervised predictive models. To address these challenges, we propose the use of vision Transformers (Vits) and Large Language Models (LLMs) that were originally trained on publicly available image or text data. Our work leverages these pre-trained models by refining the input, embedding, and classification layers in a minimalistic fashion to predict seizures. Our results demonstrate that LLMs outperforms the Vits in patient-independent seizure prediction achieving a sensitivity of 79.02% which is 8% higher compared to Vits and about 12% higher compared to a custom-designed ResNet-based model. Our work demonstrates the successful feasibility of pre-trained models for seizure prediction with its potential for improving the quality of life of people with epilepsy. Our code and related materials are available open-source at: https://***/pcdslab/UtilLLM_EPS/. © 2025 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

vision-Based Autonomous Car Brake and Steering Assistance Using Deep Learning 1

Vision-Based Autonomous Car Brake and Steering Assistance Us...

引用

1st International conference on AIML-applications for Engineering and Technology, ICAET 2025

作者： Anees, H. Agrawal, Pooja School of Robotics Defence Institute of advanced technology Pune India

ISBN: (纸本)9798350355611

This paper presents a novel approach for enhancing vehicle safety and navigation through an integrated system for lane detection, vehicle alignment, and automatic braking using visual feedback. Our proposed system employs advanced deep learning and computer vision techniques with real-time processing to detect the exact boundaries of lane and ensures precise vehicle movement within the lane. The system continuously analyses lane markings and modifies the vehicle's position to ensure optimal lane adherence by utilizing a combination of machine learning algorithms and camera-based image processing. Additionally, the system incorporates an adaptive braking mechanism that identifies vehicles ahead using visual inputs. Furthermore, the jerks experienced during steering alignment can be greatly reduced by the suggested steering control system. The system's efficiency in various driving conditions is evidenced by its experimental simulation results, which also show improvements in collision avoidance and lane-keeping accuracy. This approach contributes to improved driving convenience and road safety by marking a substantial advancement in autonomous driving technologies. © 2025 IEEE.

关键词： Steering

来源：评论

学校读者我要写书评

暂无评论

Authentication and Verification in Human-Robot Cooperative Robotic Cells using Stereo vision and Gesture Control 6

Authentication and Verification in Human-Robot Cooperative R...

引用

6th IEEE International conference on Image Processing, applications and Systems, IPAS 2025

作者： Kovacs, Gabor Sziranyi, Tamas HUN-REN Institute for Computer Science and Control Machine Perception Research Laboratory Budapest Hungary

ISBN: (纸本)9798331506520

The integration of human-robot interaction (HRI) technologies with industrial automation has become increasingly essential for enhancing productivity and safety in manufacturing environments. In this paper, we propose a novel approach to address these challenges by using stereo vision and gesture control in cooperative robotic cells. Our system enables seamless authentication of operators and real-time verification of task execution, ensuring compliance with established protocols and safety *** features of our system include its gesture-based operation with gesture recognition algorithms, allowing operators to interact with robotic systems intuitively and efficiently. By leveraging stereo vision, our system accurately tracks the operators' movement within the workspace, facilitating precise task execution and object *** present a detailed description of our system architecture, experimental configuration, and real-world performance assessment. Our results demonstrate the effectiveness and feasibility of our approach in enhancing operational efficiency, ensuring quality, and improving the overall user experience in industrial automation. © 2025 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Retaining and Enhancing Pre-trained Knowledge in vision-Language Models with Prompt Ensembling

Retaining and Enhancing Pre-trained Knowledge in Vision-Lang...

引用

2025 IEEE/CVF Winter conference on applications of Computer vision, WACV 2025

作者： Kim, Donggeun Jo, Yujin Lee, Myungjoo Kim, Taesup Graduate School of Data Science Seoul National University Korea Republic of Nota Inc.

ISBN: (纸本)9798331510831

The advancement of vision-language models, particularly the Contrastive Language-Image Pre-training (CLIP) model, has revolutionized the field of machine learning by enabling robust zero-shot learning capabilities. These capabilities allow models to understand and respond to previously unseen data without task-specific training. However, adapting CLIP to integrate specialized knowledge from various domains while retaining its zero-shot capabilities remains a significant challenge. To address this, we introduce a novel prompt ensemble learning approach called Group-wise Prompt Ensemble (GPE). This method aims to enhance CLIP's zero-shot capabilities by incorporating new domain knowledge while improving its adaptability and robustness against data distribution shifts. Our approach hinges on three main strategies: prompt grouping with masked attention to optimize CLIP's adaptability while safeguarding its zero-shot capabilities;the incorporation of auxiliary prompts for the seamless integration of new domain insights without disrupting the original model's representation;and an ensemble learning strategy that effectively merges original and new knowledge. Through rigorous experimentation, including more challenging cross-dataset transfer evaluations, our GPE method redefines the benchmarks for the adaptability and efficiency of vision-language models, surpassing existing models across various scenarios. © 2025 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

GroundingMate: Aiding Object Grounding for Goal-Oriented vision-and-Language Navigation

GroundingMate: Aiding Object Grounding for Goal-Oriented Vis...

引用

2025 IEEE/CVF Winter conference on applications of Computer vision, WACV 2025

作者： Liu, Qianyi Zhang, Siqi Qiao, Yanyuan Zhu, Junyou Li, Xiang Guo, Longteng Wang, Qunbo He, Xingjian Wu, Qi Liu, Jing Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Tongji University Department of Computer Science and Technology China Australian Institute for Machine Learning The University of Adelaide Australia

ISBN: (纸本)9798331510831

Goal-Oriented vision-and-Language Navigation (VLN) aims to enable agents to navigate to specified locations and identify designated target objects following natural language instruction. This approach has gained popularity due to its close alignment with real-world scenarios. However, existing studies have predominantly focused on enhancing navigation performance, neglecting the ability to locate objects at the navigation endpoint. This oversight has resulted in a significant discrepancy between the success rates of navigation and object grounding. The challenge is compounded by the complex reasoning required by the instructions and the necessity to synthesize multiperspective images of objects, which overwhelms traditional object grounding methods. We leverage the Multi-Modal Large Language Model (MLLM) to bridge this gap, allowing agents to seek assistance from these models when struggling to locate the target object. The agent conducts a multi-stage evaluation to discern the cause of its confusion and promptly extracts and updates the most relevant information for MLLM to assess. Our method is plug-and-play and model-agnostic, facilitating integration with numerous existing VLN strategies without the need for retraining. Implementing our approach across four distinct methods has improved performance on the REVERIE and SOON datasets, demonstrating the effectiveness and generalizability of our technique. © 2025 IEEE.

关键词： Electric grounding

来源：评论

学校读者我要写书评

暂无评论

vision-based in-situ process monitoring for increased productivity in abrasive waterjet trepanning 6

Vision-based in-situ process monitoring for increased produc...

引用

6th International conference on Industry 4.0 and Smart Manufacturing, ISM 2024

作者： Datta, Chinmoyee Ravi, Rajesh Ranjan Srinivasu, D.S. Indian Institute of Technology Madras Chennai600036 India

Hole-making stands as a fundamental process in various high-value industries for various applications (aircraft structures, automobile parts, defence, and biomedical components). Well-established conventional trepanning/drilling can achieve the desired tolerances, yet they come with drawbacks, such as the need for tool adjustments, heat-affected zones (HAZ), and residual stress. In contrast, abrasive waterjet (AWJ) trepanning emerged as a promising alternative due to its potential benefits - the absence of HAZ, minimal residual stress, and flexibility with material type. its capacity to generate a variety of hole geometries with near-net shapes through jet manipulation makes AWJ trepanning suitable for assembly-line production. However, due to the aggressive and stochastic behaviour of the jet, extensive experimental trials and regular in-process measurements are required to optimize trepanning parameters. Conventional measurement approaches demand trepanned holes moving from the machining zone to the measurement zone, leading to increased downtime and cost-ineffectiveness. Therefore, there is a need to develop an in-situ non-contact approach. In this work, a machine vision-based measurement approach is proposed to measure the geometrical features, such as taper angle (α), diameter (D), and burr length (bl). Al 6061 alloy is considered a target material by considering the difficulties in trepanning deeper holes. The proposed machine vision-based measurements are validated against measurements from one contact mode instrument (i.e., coordinate measuring machine) and one non-contact measurement instrument (i.e., 3D laser confocal microscope) to assess the potential of the proposed approach. Results indicate that the machine vision method yields results within a 5% error margin for taper angle and diameter and 11% for burr length. Furthermore, a qualitative approach is proposed and demonstrated for the operators to select optimal trepanning parameters for achieving mul

关键词： Aircraft manufacture

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：