检索结果-内蒙古大学图书馆

17th Asian Conference on Computer vision, ACCV 2024

作者： Islam, Md Tanvir Alam, Inzamamul Woo, Simon S. Anwar, Saeed Lee, Ik Hyun Muhammad, Khan Department of Software Sungkyunkwan University Suwon Korea Republic of The Australian National University Canberra Australia Department of Mechatronics Engineering Tech University of Korea Siheung Korea Republic of Department of Human-AI Interaction Sungkyunkwan University Seoul Korea Republic of

ISBN: (纸本)9789819609161

Low-light image enhancement (LLIE) is essential for numerous computer vision tasks, including object detection, tracking, segmentation, and scene understanding. Despite substantial research on improving low-quality images captured in underexposed conditions, clear vision remains critical for autonomous vehicles, which often struggle with low-light scenarios, signifying the need for continuous research. However, paired datasets for LLIE are scarce, particularly for street scenes, limiting the development of robust LLIE methods. Despite using advanced transformers and/or diffusion-based models, current LLIE methods struggle in real-world low-light conditions and lack training on street-scene datasets, limiting their effectiveness for autonomous vehicles. To bridge these gaps, we introduce a new dataset "LoLI-Street" (Low-Light images of Streets) with 33k paired low-light and well-exposed images from street scenes in developed cities, covering 19k object classes for object detection. LoLI-Street dataset also features 1,000 real low-light test images for testing LLIE models under real-life conditions. Furthermore, we propose a transformer and diffusion-based LLIE model named "TriFuse". Leveraging the LoLI-Street dataset, we train and evaluate our TriFuse and SOTA models to benchmark on our dataset. Comparing various models, our dataset’s generalization feasibility is evident in testing across different mainstream datasets by significantly enhancing images and object detection for practical applications in autonomous driving and surveillance systems. Complete code and dataset is available on https://***/tanvirnwu/TriFuse. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Development of Enhance-Net Deep Learning Approach for Performance Boosting on Medical images 5th

Development of Enhance-Net Deep Learning Approach for Perfor...

引用

5th International Conference on Data Science, machine Learning and applications

作者： Manoharan, Geetha Solanke, D. R. Acharjee, Purnendu Bikash Nayak, Chinmaya Kumar Sharma, Mukesh Kumar Sahu, Dillip Narayan SR Univ Sch Business Warangal Telangana India SGB Amravati Univ Dept Appl Elect Amravati 444602 Maharashtra India CHRIST Univ Pune Maharashtra India Sri Sri Univ Fac Emerging Technol Cuttack Odisha India Rungta Coll Pharmaceut Sci & Res Bhilai 490024 Chhattisgarh India Gangadhar Meher Univ Dept MCA Sambalpur Odisha India

ISBN: (纸本)9789819780334;9789819780310;9789819780303

Only a few clinical procedures include the use of clinical methods for the early detection, observing, evaluation, and treatment evaluation of a range of medical illnesses. Knowing the analysis of medical images in computer vision necessitates being acquainted with the core concepts and uses of deep learning and artificial neural networks. The A rapidly expanding area of study is the Deep Learning Approach (DLA) in medical image processing. DLA is often used in medical imaging to determine if an ailment is present or not. By producing speedier, more accurate results in real time, deep learning algorithms may make the jobs of radiologists and orthopaedic surgeons easier. But the standard deep learning approach has reached its efficiencies. While offering an ideal solution known as boost-Net, we study numerous optimization strategies to increase the effectiveness of deep neural networks in this research. From a selection of well-known deep learning models, Champion-Net was selected as the deep learning model. The musculoskeletal radiograph-bone classification (MURA-BC) dataset is used in this investigation. Utilizing the train and test datasets, Enhance-Net's classification precision was evaluated.

关键词： Deep learning Medical image Enhance- net Dataset

来源：评论

学校读者我要写书评

暂无评论

Drone-Assisted Infrared Thermography and machine Learning for Enhanced Photovoltaic Defect Detection: A Comparative Study of vision Transformers and YOLOv8 44th

Drone-Assisted Infrared Thermography and Machine Learning f...

引用

44th SGAI International Conference on Innovative Techniques and applications of Artificial Intelligence, SGAI 2024

作者： Memari, Ammar Debich, Tarek Jade University of Applied Sciences Friedrich-Paffrath-Straße 101 Wilhelmshaven26389 Germany

ISBN: (纸本)9783031779176

This paper presents a comparative study on the application of drone-assisted infrared thermography coupled with state-of-the-art machine learning models, including vision Transformers (ViTs) and YOLOv8, for efficient and accurate defect detection in Photovoltaic (PV) systems. The research outlines the methodology for on-site inspections and details the integration of drones to capture high-resolution thermal imagery, identifying minute anomalies indicative of potential system failures. By employing advanced image processing techniques and training AI models, the study compares the performance of these models in accurately identifying and classifying PV defects. A segmentation model based on TensorFlow was trained and used to detect the location of PV panels in the camera imagery, followed by the separate application of YOLOv8 and ViTs to classify defects in the detected PV panels. The dataset used to train the models was carefully curated and prepared specifically for this study, representing another contribution of this paper. This approach not only enhances detection capabilities but also streamlines the processes of data collection, analysis, and reporting, ultimately leading to improved decision-making for system operators and stakeholders. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Thermography (imaging)

来源：评论

学校读者我要写书评

暂无评论

Heart Signal processing Using Wavelet Analysis and Deep Learning Algorithms Based on Artificial Intelligence

Heart Signal Processing Using Wavelet Analysis and Deep Lear...

引用

International Conference on applications in Electronics Pervading Industry, Environment and Society, APPLEPIES 2024

作者： Zilaie, Morteza Mohammadkhani, Zohreh Asrari, Keyvan Azimi Talebiyan, Seyed Reza Islamic Azad University Science and Research Branch Khorasan Razavi Mashhad Iran The University of Pavia Pavia Italy Imam Reza International University Khorasan Razavi Mashhad Iran

ISBN: (纸本)9783031840999

The electrocardiogram signal of the heart is used to monitor the health status and function of the human heart and to a doctor in diagnosing the type of disease. For this purpose, first, the scalogram of the different heart failures produces different types of this signal. In this research, the cardiac signals of the patients are analyzed by an artificial intelligence neural network, and the type of the person’s disease is diagnosed. The artificial intelligence in question can be learned and can be used as an assistant ECG signal is calculated using continuous wavelet transform and then it is subjected to learning and evaluation using a deep convolutional neural network. In the architecture of artificial intelligence, two well-known neural networks GoogLeNet and SqueezeNet are used, which have been sufficiently trained in similar applications such as image processing and machine vision. In the end, the type of heart failure is diagnosed and classified. The cardiac signals of the patients used in the simulation were extracted from the PhysioNet medical engineering standard dataset of MIT University. In the end, the simulation results of the research are given. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

LoG-VMamba: Local-Global vision Mamba for Medical image Segmentation 17th

LoG-VMamba: Local-Global Vision Mamba for Medical Image Seg...

引用

17th Asian Conference on Computer vision, ACCV 2024

作者： Dang, Trung DQ. Nguyen, Huy Hoang Tiulpin, Aleksei University of Oulu Oulu Finland

ISBN: (纸本)9789819609000

Mamba, a State Space Model (SSM), has recently shown competitive performance to Convolutional Neural Networks (CNNs) and Transformers in Natural Language processing and general sequence modeling. Various attempts have been made to adapt Mamba to Computer vision tasks, including medical image segmentation (MIS). vision Mamba (VM)-based networks are particularly attractive due to their ability to achieve global receptive fields, similar to vision Transformers, while also maintaining linear complexity in the number of tokens. However, the existing VM models still struggle to maintain both spatially local and global dependencies of tokens in high dimensional arrays due to their sequential nature. Employing multiple and/or complicated scanning strategies is computationally costly, which hinders applications of SSMs to high-dimensional 2D and 3D images that are common in MIS problems. In this work, we propose Local-Global vision Mamba, LoG-VMamba, that explicitly enforces spatially adjacent tokens to remain nearby on the channel axis, and retains the global context in a compressed form. Our method allows the SSMs to access the local and global contexts even before reaching the last token while requiring only a simple scanning strategy. Our segmentation models are computationally efficient and substantially outperform both CNN and Transformers-based baselines on a diverse set of 2D and 3D MIS tasks. The implementation of LoG-VMamba is available at https://***/Oulu-IMEDS/LoG-VMamba. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

FPGA-based image signal processing CEPST module design 2

FPGA-based image signal processing CEPST module design

引用

2nd International Conference on Frontiers of Applied Optics and Computer Engineering, AOCE 2025

作者： Tsai, Lifen Chen, Chinta Yang, Chihchung Tang, Lijie Wang, Xiahui Xue, Wuyang Ma, Huan Zhaoqing University Guangdong China Zhaoqing University Guangdong China

ISBN: (纸本)9781510689404

CEPST algorithm is an important step in image processing, which is widely used in computer vision, pattern recognition, and machine learning. In order to improve the efficiency and performance of CEPST algorithm, more and more studies have implemented the task of CEPST algorithm on FPGA boards in recent years. FPGA boards offer parallel computing capabilities, low power consumption, and low latency, making them suitable for high-performance computing and real-time applications. In this paper, the Vivado tool is used to implement the method of CEPST algorithm. Vivado has a complete toolchain and debugging environment, supports a variety of hardware description languages, and provides a rich set of IP cores and acceleration libraries to facilitate FPGA design and development. This paper details the steps of CEPST algorithm using Vivado, from algorithm design to simulation. The CEPST algorithm was designed to improve the accuracy and speed, and further improve the performance of the overall system. © The Authors.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Robust automatic crater detection at all latitudes on Mars with deep-learning

引用

PLANETARY AND SPACE SCIENCE 2025年 260卷

作者： Martinez, L. Andrieu, F. Schmidt, F. Talbot, H. Bentley, M. S. Univ Paris Saclay CNRS GEOPS F-91405 Orsay France Inst Univ France IUF Paris France CentraleSupelec Paris Saclay Univ Inria Gif Sur Yvette France European Space Astron Ctr Camino Bajo CastilloUrb Villafranca CastilloVill Madrid 28692 Spain

Understanding the distribution and characteristics of impact craters on planetary surfaces is essential for unraveling geological processes and the evolution of celestial bodies. Several machine learning and AI-based approaches have been proposed to detect craters on planetary surface images automatically. However, designing a robust tool for an entire complex planet such as Mars, is still an open problem. This article presents a novel approach using the Faster Region-based Convolutional Neural Network (Faster R-CNN) for such a detection. The proposed method involves the pre-processing, training and crater detection steps, which are especially designed for robustness regarding latitude and complex geomorphological features. The objectives of this studies are to (i) be robust at all latitudes and (ii) for >= 1 km diameter crater sizes. (iii) To propose an open-source and re-usable algorithm that (iv) only needs an image to run. Extensive experiments on high-resolution planetary imagery demonstrate excellent performances with an average precision AP(50)>0.82 with an intersection over union criterion IoU >= 0.5, irrespective of crater scale. For mid and high latitudes (higher than 48 degrees north and south), performance decreases down to AP(50)similar to 0.7, which is still better than the current state of the art. Loss of performance is mostly due to strong shadowing effects. Our results also highlight the versatility and potential of our robust model for automating the analysis of craters across different celestial bodies. The automated crater detection tool presented in this article is publicly available as open-source and holds great promise for future scientific research of space exploration missions.

关键词： Detection algorithm Impact craters Computer vision Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

S²NeRF: Neural Radiance Fields Training with Sparse Points and Sparse Views 17th

S<SUP>2</SUP>NeRF: Neural Radiance Fields Training with Spar...

引用

17th International Conference on Intelligent Robotics and applications

作者： Zhang, Zhihong Wang, Wenjun Qi, Dexin Mei, Xuesong Xi An Jiao Tong Univ Sch Mech Engn Xian 710049 Shaanxi Peoples R China State Key Lab Mfg Syst Engn Xian 710049 Shaanxi Peoples R China Shaanxi Key Lab Intelligent Robots Xian 710049 Shaanxi Peoples R China

ISBN: (纸本)9789819607730;9789819607747

Neural volume rendering methods, especially NeRF, have demonstrated remarkable performance in novel view synthesis. However, NeRF relies solely on image data and lacks explicit geometric information, necessitating a large number of posed images and a computationally intensive ray sampling strategy to learn accurate scene representations. This poses challenges and may result in incomplete or locally optimal scene geometry when views are sparse or incomplete, as the limited views may not provide sufficient constraints to determine a unique geometry solution for complex scenes. Meanwhile, sparse point clouds provide an attractive source of scene information, especially for geometry, to complement images in neural scene representations, particularly when input views are sparse. To overcome these limitations, we propose (SNeRF)-Ne-2, a novel Neural Radiance Field that simultaneously incorporates features from both point clouds and images for volume rendering. Specifically, (SNeRF)-Ne-2 extracts patch-wise point features from point clouds and raywise image features from adjacent views. Then the scene feature volume is constructed by implicitly fusing these point and image features through self-attention. Finally, the volume feature is utilized to render novel views of the scene. Experimental results on the challenging TartanAir dataset demonstrate that, thanks to the integration of feature volume from point clouds and images, (SNeRF)-Ne-2 achieves state-of-the-art performance in novel view synthesis.

关键词： machine Learning Computer vision Volume Rendering

来源：评论

学校读者我要写书评

暂无评论

Class preserving projections and data augmentation for appearance-based face recognition

引用

PATTERN ANALYSIS AND applications 2025年第1期28卷 1-12页

作者： Soldera, John Scharcanski, Jacob Inst Fed Farroupilha Estr RS-218 BR-98806700 St Angelo Rio Grande do S Brazil Univ Fed Rio Grande do Sul Inst Informat Ave Bento Goncalves 9500 BR-91501970 Porto Alegre Rio Grande do S Brazil

Computer vision and Biometrics benefit from the recent advances in Pattern Recognition and Artificial Intelligence, which tends to make model-based face recognition more efficient. Also, deep learning combined with data augmentation tends to enrich the training sets used for learning tasks. Nevertheless, face recognition still is challenging, especially because of imaging issues that occur in practice, such as changes in lighting, appearance, head posture and facial expression. In order to increase the reliability of face recognition, we propose a novel supervised appearance-based face recognition method which creates a low-dimensional orthogonal subspace that enforces the face class separability. The proposed approach uses data augmentation to mitigate the problem of training sample scarcity. Unlike most face recognition approaches, the proposed approach is capable of handling efficiently grayscale and color face images, as well as low and high-resolution face images. Moreover, proposed supervised method presents better class structure preservation than typical unsupervised approaches, and also provides better data preservation than typical supervised approaches as it obtains an orthogonal discriminating subspace that is not affected by the singularity problem that is common in such cases. Furthermore, a soft margins Support Vector machine classifier is learnt in the low-dimensional subspace and tends to be robust to noise and outliers commonly found in practical face recognition. To validate the proposed method, an extensive set of face identification experiments was conducted on three challenging public face databases, comparing the proposed method with methods representative of the state-of-the-art. The proposed method tends to present higher recognition rates in all databases. In addition, the experiments suggest that data augmentation also plays an essential role in the appearance-based face recognition, and that the CIELAB color space (L*a*b) is generally mor

关键词： Pattern recognition image processing Appearance-based face recognition Supervised methods Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Visual Feedback System Supporting Robotic Manipulation of Hemp Plants

引用

JOURNAL OF NATURAL FIBERS 2025年第1期22卷

作者： Kraft, Marek Ptak, Bartosz Piechocki, Mateusz Pieczynski, Dominik Mlodzikowski, Kamil Kulecki, Bartlomiej Belter, Dominik Poznan Univ Tech Inst Robot & Machine Intelligence Piotrowo 3A PL-60965 Poznan Poland

This paper presents an agricultural robotics system designed to automate the detection and manipulation of male hemp plants, addressing the challenge of manually removing these to enhance crop quality. The solution uses an industry-standard, inexpensive RGB-D camera as the input data source to derive control signals controlling the robotic arm and end effector. Input image data processing is performed by a dedicated neural network model trained using a dataset created specifically for the described task to achieve detection by stalk segmentation and postprocessing. The research involved assessing various neural network models, including UNet, DeepLabV3+, and YOLOv8 in various variants, for their capability to detect stalks accurately and swiftly. Fast operation is necessary for effective real-time feedback in robotic grasping tasks. Among tested architectures, the integration of UNet with ResNet50 was found to provide a good trade-off between detection precision and operational speed on edge AI devices. The resulting solution offers good accuracy and significantly outperforms existing methods in terms of processing speed, promising substantial improvements in agricultural robotics by enabling on-line adaptive grasping using low-cost components. The applications can be extended beyond hemp tending to include various other crops, eliminating tedious manual labor. (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic), (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic), (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic). (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic),(sic)(sic)(sic)RGB-D(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic), (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic). (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic), (sic)(sic)(sic)(sic)(sic)(sic)(sic)(si

关键词： Hemp computer vision deep learning robotics manipulation (sic)(sic) (sic)(sic)(sic)(sic)(sic) (sic)(sic)(sic)(sic) (sic)(sic)(sic) (sic)(sic)

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：