检索结果-内蒙古大学图书馆

Machine learning-Based Denoising Techniques for Monte Carlo Rendering: A Literature Review

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2025年第2期16卷 581-588页

作者： Yen, Liew Wen Thinakaran, Rajermani Somasekar, J. INTI Int Univ Fac Data Sci & Informat Technol Negeri Sembilan Malaysia Jain Dept Comp Sci & Engn Bangalore Karnataka India

Monte Carlo (MC) rendering is a powerful technique for achieving photorealistic images by simulating complex light interactions. However, the inherent noise introduced by MC rendering necessitates effective denoising techniques to enhance image quality. This paper presents a comprehensive review and comparative analysis of various machine learning (ML) methods for denoising MC renderings, focusing on four main categories: radiance prediction using convolutional neural networks (CNNs), kernel prediction networks, temporal rendering with recurrent architectures, and adaptive sampling approaches. Through systematic analysis of 7 peer-reviewed studies from 2019-2024, the author's findings reveal that deep learning models, particularly generative adversarial networks (GANs), achieve superior denoising performance. The study identifies key challenges including computational demands, with some methods requiring significant GPU resources, and generalization across diverse scenes. Additionally, we observe a trade-off between denoising quality and processing speed, particularly crucial for real-time applications. The study concludes with recommendations for future research, emphasizing the need for hybrid approaches combining physics- based models with ML techniques to improve robustness and efficiency in production environments.

关键词： -Convolutional neural network Monte Carlo rendering generative adversarial network deep learning machine learning denoising techniques

来源：评论

学校读者我要写书评

暂无评论

Advanced fine-tuning procedures to enhance DNN robustness in visual coding for machines

引用

EURASIP JOURNAL ON image AND VIDEO processing 2024年第1期2024卷 31页

作者： Marie, Alban Desnos, Karol Mercat, Alexandre Morin, Luce Vanne, Jarno Zhang, Lu Tampere Univ Ultra Video Grp Tampere Finland Univ Rennes INSA Rennes CNRS IETRUMR 6164 Rennes France

Video Coding for Machines (VCM) is gaining momentum in applications like autonomous driving, industry manufacturing, and surveillance, where the robustness of machine learning algorithms against coding artifacts is one of the key success factors. This work complements the MPEG/JVET standardization efforts in improving the resilience of deep neural network (DNN)-based machine models against such coding artifacts by proposing the following three advanced fine-tuning procedures for their training: (1) the progressive increase of the distortion strength as the training proceeds;(2) the incorporation of a regularization term in the original loss function to minimize the distance between predictions on compressed and original content;and (3) a joint training procedure that combines the proposed two approaches. These proposals were evaluated against a conventional fine-tuning anchor on two different machine tasks and datasets: image classification on imageNet and semantic segmentation on Cityscapes. Our joint training procedure is shown to reduce the training time in both cases and still obtain a 2.4% coding gain in image classification and 7.4% in semantic segmentation, whereas a slight increase in training time can bring up to 9.4% better coding efficiency for the segmentation. All these coding gains are obtained without any additional inference or encoding time. As these advanced fine-tuning procedures are standard-compliant, they offer the potential to have a significant impact on visual coding for machine applications.

关键词： Video Coding for Machines (VCM) Coding artifacts image and video coding deep neural network (DNN) deep learning Fine-tuning

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised generative adversarial learning for denoising adaptive optics retinal images

引用

BIOMEDICAL OPTICS EXPRESS 2024年第3期15卷 1437-1452页

作者： Wang, Shidan Li, Kaiwen Yin, Qi Ren, Ji Zhang, Jie Robotrak Technol Adv Ophthalmol Lab AOL Nanjing 210000 Peoples R China

This study presents denoiseGAN, a novel semi-supervised generative adversarial network, for denoising adaptive optics (AO) retinal images. By leveraging both synthetic and real -world data, denoiseGAN effectively addresses various noise sources, including blur, motion artifacts, and electronic noise, commonly found in AO retinal imaging. Experimental results demonstrate that denoiseGAN outperforms traditional image denoising methods and the state -of -the -art conditional GAN model, preserving retinal cell structures and enhancing image contrast. Moreover, denoiseGAN aids downstream analysis, improving cell segmentation accuracy. Its 30% faster computational efficiency makes it a potential choice for real -time AO image processing in ophthalmology research and clinical practice.

关键词： Adaptive optics Imaging techniques Optical coherence tomography real time imaging Spatial resolution Three dimensional reconstruction

来源：评论

学校读者我要写书评

暂无评论

A deep-Reinforcement-learning-Based Beam Prediction Scheme for Vision-Aided mmWave Wireless Communications

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第11期12卷 17869-17879页

作者： Wang, Heng Yang, Dihan Xie, Xin Chongqing Univ Posts & Telecommun Key Lab Ind Internet Things & Networked Control Chongqing 400065 Peoples R China

Millimeter wave (mmWave) wireless communications are significant technologies that support Internet of Things (IoT) systems to achieve fast and stable data transmission, and the guarantee of its communication quality usually depends on accurate beam prediction. Due to the advantage of not relying on channel state information, beam prediction schemes using visual data and artificial intelligence become popular. Most of the current vision-aided beam prediction schemes directly predict the index of the optimal beam in the codebook. However, these methods are only applicable to certain codebooks and have limited generalization and scalability. To address the issues, we propose a vision-aided beam prediction scheme based on deep reinforcement learning (DRL). The scheme takes the original image as input and extracts the position and velocity of the user through the object detection algorithm. Subsequently, combined with the current state of the base station, it outputs a continuous angle value and finally matches it with the beam index in the codebook. Furthermore, we integrate the attention mechanism into the actor network of the deep deterministic policy gradient (DDPG) and propose a scheme of DDPG with attention mechanism (DDPG-A), which can perform differential processing on features, thereby enhancing algorithmic performance. The simulation test utilizing real datasets demonstrates that the proposed scheme has good generalization and scalability while considerably reducing the beam training overheads.

关键词： Wireless sensor networks Wireless communication Training Millimeter wave communication Internet of Things Data mining YOLO Prediction algorithms Cameras Accuracy Beam prediction deep reinforcement learning (DRL) millimeter wave (mmWave) communications vision-aided

来源：评论

学校读者我要写书评

暂无评论

Comparison of image processing techniques for defect detection 1

Comparison of image processing techniques for defect detecti...

引用

1st International Workshop of Young Scientists on Artificial Intelligence for Sustainable Development, AISD 2024

作者： Kovalskyi, Semen Koval, Vasyl West Ukrainian National University 11 Lvivska Str. Ternopil46009 Ukraine

Defect detection is a crucial quality control process in the manufacturing industry, aimed at identifying and classifying imperfections or anomalies in products before they reach customers. Traditional manual inspection methods are time-consuming, labor-intensive, and prone to human error. This paper provides a comprehensive overview of image-based defect detection algorithms, including traditional image processing techniques, machine learning algorithms, and deep learning models. The study analyzes the strengths, limitations, and performance of each approach across various applications and datasets. The results demonstrate that while traditional methods and machine learning algorithms offer reliable defect detection, deep learning models, particularly convolutional neural networks (CNNs), achieve exceptional accuracy and robustness. However, deep learning models require significant computational resources and large amounts of labeled data for training. The paper highlights the importance of selecting the most appropriate approach based on specific application requirements, data characteristics, and computational constraints. Furthermore, it discusses future research opportunities, such as developing more robust and generalized algorithms, leveraging multi-modal data, improving model interpretability, and enabling real-time and edge computing solutions. © 2024 Copyright for this paper by its authors.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

A lightweight convolutional neural network for multipoint displacement measurements on bridge structures

引用

NONLINEAR DYNAMICS 2024年第14期112卷 11745-11763页

作者： Wang, Sen Lin, Sen Yang, Rongliang Kunming Univ Sci & Technol Fac Mech & Elect Engn Kunming Peoples R China

Emerging computer vision measurement methods overcome the limitations of traditional sensors. However, conventional digital image processing algorithms encounter issues of low precision and timeliness when performing vibration displacement measurements in complex operating conditions. Therefore, this paper builds a deep learning detection algorithm based on a lightweight convolutional neural network to measure the vibration displacement of the structure. In the feature extraction part, the ghost module and depthwise separable convolution are used to condense effective information. In the feature fusion part, it is combined based on the underlying feature similarity principle. The attention mechanism obtains the fine features, edge information and sensitive position information of the target. In the target regression part, preset anchor frames of different sizes are used to return the vibrating targets in the image to obtain precise position information. First, a cable-stayed bridge model is selected for experiments in a laboratory environment, and compared with the measurement results of seven visual algorithms. Furthermore, experiments are conducted outdoors on real bridges to verify the effectiveness of the proposed method. Qualitative and quantitative analysis of the experimental results show that the proposed algorithm can effectively return the small offset of the vibration target, efficiently and precisely measure the vibration displacement signal of the structure in real time, providing an efficient solution for structural damage and health monitoring.

关键词： Bridge structure Visual measurement deep convolutional neural network Lightweight Small offset

来源：评论

学校读者我要写书评

暂无评论

deep learning Approach for Hand Gesture Recognition:Applications in Deaf Communication and Healthcare

引用

Computers, Materials & Continua 2024年第1期78卷 127-144页

作者： Khursheed Aurangzeb Khalid Javeed Musaed Alhussein Imad Rida Syed Irtaza Haider Anubha Parashar Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityP.O.Box 51178Riyadh11543Kingdom of Saudi Arabia Department of Computer Engineering College of Computing and InformaticsUniversity of SharjahSharjah27272United Arab Emirates Laboratory Biomechanics and Bioengineering University of Technology of CompiegneCompiegne60200France Department of Computer Science and Engineering Manipal University JaipurJaipur303007India

Hand gestures have been used as a significant mode of communication since the advent of human *** facilitating human-computer interaction(HCI),hand gesture recognition(HGRoc)technology is crucial for seamless and error-free *** technology is pivotal in healthcare and communication for the deaf *** significant advancements in computer vision-based gesture recognition for language understanding,two considerable challenges persist in this field:(a)limited and common gestures are considered,(b)processing multiple channels of information across a network takes huge computational time during discriminative feature ***,a novel hand vision-based convolutional neural network(CNN)model named(HVCNNM)offers several benefits,notably enhanced accuracy,robustness to variations,real-time performance,reduced channels,and ***,these models can be optimized for real-time performance,learn from large amounts of data,and are scalable to handle complex recognition tasks for efficient human-computer *** proposed model was evaluated on two challenging datasets,namely the Massey University Dataset(MUD)and the American Sign Language(ASL)Alphabet Dataset(ASLAD).On the MUD and ASLAD datasets,HVCNNM achieved a score of 99.23% and 99.00%,*** results demonstrate the effectiveness of CNN as a promising HGRoc *** findings suggest that the proposed model have potential roles in applications such as sign language recognition,human-computer interaction,and robotics.

关键词： Computer vision deep learning gait recognition sign language recognition machine learning

来源：评论

学校读者我要写书评

暂无评论

real-time 3D Visual Perception by Cross-Dimensional Refined learning

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第10期34卷 10326-10338页

作者： Hong, Ziyang Yue, C. Patrick Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Hong Kong Peoples R China

We introduce a novel learning method that can effectively perceive both the geometry structure and semantic labels of a 3D scene in real time. Existing real-time 3D scene reconstruction approaches often rely on volumetric schemes to regress a Truncated Signed Distance Function (TSDF) as the 3D representation. However, these volumetric approaches primarily focus on ensuring global coherence in the reconstructed scene, which often results in a lack of local geometric detail. To address this limitation, we propose a solution that leverages the latent geometric knowledge present in 2D image features by explicit depth prediction thereby creating anchored features, which are used to refine the learning of occupancy in the TSDF volume. Furthermore, we discover that this cross-dimensional feature refinement methodology can also be applied to the task of semantic segmentation by utilizing semantic priors. As a result, we propose an end-to-end cross-dimensional refinement neural network (CDRNet) that can extract both the 3D mesh and 3D semantic labeling of a scene in real time. Through experimental evaluation on multiple datasets, we demonstrate that our method achieves state-of-the-art 3D perception capability by boosting over 40% and 18% in 3D semantic segmentation and geometric reconstruction respectively over the prior art. These promising results indicate the significant potential of our approach for various industrial applications. Demo video and code can be found on the project page, https://***/cdrnet/.

关键词： Three-dimensional displays Semantics real-time systems Feature extraction Sensors image reconstruction Semantic segmentation Monocular vision 3D perception 3D reconstruction 3D semantic segmentation deep learning

来源：评论

学校读者我要写书评

暂无评论

NeuroIGN: Explainable Multimodal image-Guided System for Precise Brain Tumor Surgery

引用

JOURNAL OF MEDICAL SYSTEMS 2024年第1期48卷 25-25页

作者： Zeineldin, Ramy A. Karar, Mohamed E. Burgert, Oliver Mathis-Ullrich, Franziska Friedrich Alexander Univ Erlangen Nurnberg Dept Artificial Intelligence Biomed Engn D-91052 Erlangen Germany Reutlingen Univ Res Grp Comp Assisted Med CaMed Reutlingen 72762 Germany Menoufia Univ Fac Elect Engn Fee Minuf 32952 Egypt

Precise neurosurgical guidance is critical for successful brain surgeries and plays a vital role in all phases of image-guided neurosurgery (IGN). Neuronavigation software enables real-time tracking of surgical tools, ensuring their presentation with high precision in relation to a virtual patient model. Therefore, this work focuses on the development of a novel multimodal IGN system, leveraging deep learning and explainable AI to enhance brain tumor surgery outcomes. The study establishes the clinical and technical requirements of the system for brain tumor surgeries. NeuroIGN adopts a modular architecture, including brain tumor segmentation, patient registration, and explainable output prediction, and integrates open-source packages into an interactive neuronavigational display. The NeuroIGN system components underwent validation and evaluation in both laboratory and simulated operating room (OR) settings. Experimental results demonstrated its accuracy in tumor segmentation and the success of ExplainAI in increasing the trust of medical professionals in deep learning. The proposed system was successfully assembled and set up within 11 min in a pre-clinical OR setting with a tracking accuracy of 0.5 (+/- 0.1) mm. NeuroIGN was also evaluated as highly useful, with a high frame rate (19 FPS) and real-time ultrasound imaging capabilities. In conclusion, this paper describes not only the development of an open-source multimodal IGN system but also demonstrates the innovative application of deep learning and explainable AI algorithms in enhancing neuronavigation for brain tumor surgeries. By seamlessly integrating pre- and intra-operative patient image data with cutting-edge interventional devices, our experiments underscore the potential for deep learning models to improve the surgical treatment of brain tumors and long-term post-operative outcomes.

关键词： Neuronavigation deep learning IGN Explainability MRI iUS

来源：评论

学校读者我要写书评

暂无评论

GSBF-YOLO: a lightweight model for tomato ripeness detection in natural environments

引用

JOURNAL OF real-time image processing 2025年第1期22卷 1-14页

作者： Hao, Fengqi Zhang, Zuyao Ma, Dexin Kong, Hoiio Qilu Univ Technol Key Lab Comp Power Network & Informat Secur Minist EducShandong Comp Sci Ctr Natl Supercomp Ctr JinanShandong Acad Sci Jinan 250014 Shandong Peoples R China City Univ Macau Fac Data Sci Macau 999078 Peoples R China Shandong Fundamental Res Ctr Comp Sci Shandong Prov Key Lab Ind Network & Informat Syst Jinan 250014 Peoples R China Qingdao Agr Univ Commun Coll Qingdao 266109 Peoples R China

Accurate tomato ripeness detection is essential for optimizing harvest timing and maximizing yield. deep learning-based object detection has proven effective in this task. However, many existing algorithms have numerous parameters and substantial computational demands, making them unsuitable for agricultural environments with limited computational resources. Additionally, accurate detection becomes challenging with overlapping fruits, leaf occlusion, or complex backgrounds. To address these issues, this paper proposes a lightweight detection model, GSBF-YOLO. This model designs the GSim module to reduce parameters while maintaining detection accuracy. The C3Ghost module further reduces parameter count by replacing the traditional C3 module. The PANet multi-scale feature fusion network in the neck is replaced with the Bi-directional Feature Pyramid Network (BiFPN), which adjusts weights based on the importance of input features. Lastly, the fine-tuned FocalEIOU Loss function is used to calculate the bounding box regression loss, enhancing the model's ability to adjust the weights of high-quality anchor boxes for better detection of targets in occlusion scenarios. Experimental results show that GSBF-YOLO reduces parameters and computational load by 42% and 45%, respectively, while mean Average Precision (mAP) increases by 1.9% and 1.6% on two datasets. The model achieves 110 Frames Per Second (FPS), meeting real-time detection requirements, and has fewer parameters and higher accuracy compared to models like YOLOv8. The research indicates that the proposed lightweight model can effectively detect tomato ripeness in natural environments.

关键词： Lightweight deep learning Tomato ripeness Object detection real-time detection

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：