检索结果-内蒙古大学图书馆

Advancing 6-DoF Instrument Pose Estimation in Variable X-Ray Imaging Geometries

IEEE TRANSACTIONS ON image processing 2024年 33卷 2462-2476页

作者： Viviers, Christiaan G. A. Filatova, Lena Termeer, Maurice de With, Peter H. N. van der Sommen, Fons Tech Univ Eindhoven Dept Elect Engn NL-5612 AZ Eindhoven Netherlands Philips IGT NL-5684 PC Best Netherlands Tech Univ Eindhoven Elect Engn Dept NL-5612 AZ Eindhoven Netherlands

Accurate 6-DoF pose estimation of surgical instruments during minimally invasive surgeries can substantially improve treatment strategies and eventual surgical outcome. Existing deep learning methods have achieved accurate results, but they require custom approaches for each object and laborious setup and training environments often stretching to extensive simulations, whilst lacking real-time computation. We propose a general-purpose approach of data acquisition for 6-DoF pose estimation tasks in X-ray systems, a novel and general purpose YOLOv5-6D pose architecture for accurate and fast object pose estimation and a complete method for surgical screw pose estimation under acquisition geometry consideration from a monocular cone-beam X-ray image. The proposed YOLOv5-6D pose model achieves competitive results on public benchmarks whilst being considerably faster at 42 FPS on GPU. In addition, the method generalizes across varying X-ray acquisition geometry and semantic image complexity to enable accurate pose estimation over different domains. Finally, the proposed approach is tested for bone-screw pose estimation for computer-aided guidance during spine surgeries. The model achieves a 92.41% by the 0.1 center dot d ADD-S metric, demonstrating a promising approach for enhancing surgical precision and patient outcomes. The code for YOLOv5-6D is publicly available at https://***/cviviers/YOLOv5-6D-Pose.

关键词： X-ray instrument detection 6-DoF pose estimation surgical vision imaging geometry deep learning

来源：评论

学校读者我要写书评

暂无评论

deep learning in Ultrasound Localization Microscopy: Applications and Perspectives

引用

IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL 2024年第12期71卷 1765-1784页

作者： Rauby, Brice Xing, Paul Gasse, Maxime Provost, Jean Polytech Montreal Biomed Engn Montreal PQ Canada Mila Quebec Artificial Intelligence Inst Montreal PQ Canada Polytech Montreal Montreal PQ Canada Polytech Montreal Dept Engn Phys Montreal PQ Canada

Ultrasound localization microscopy (ULM) is a novel super-resolution imaging technique that can image the vasculature in vivo at depth with resolution far beyond the conventional limit of diffraction. By relying on the localization and tracking of clinically approved microbubbles injected in the blood stream, ULM can provide not only anatomical visualization but also hemodynamic quantification of the microvasculature. Several deep learning approaches have been proposed to address challenges in ULM including denoising, improving microbubble localization, estimating blood flow velocity, or performing aberration correction. Proposed deep learning methods often outperform their conventional counterparts by improving image quality and reducing processing time. In addition, their robustness to high concentrations of microbubbles can lead to reduced acquisition times in ULM, addressing a major hindrance to ULM clinical application. Herein, we propose a comprehensive review of the diversity of deep learning applications in ULM focusing on approaches assuming a sparse microbubble distribution. We first provide an overview of how existing studies vary in the constitution of their datasets or in the tasks targeted by the deep learning model. We also take a deeper look into the numerous approaches that have been proposed to improve the localization of microbubbles since they differ highly in their formulation of the optimization problem, their evaluation, or their network architectures. We finally discuss the current limitations and challenges of these methods, as well as the promises and potential of deep learning for ULM in the future.

关键词： deep learning Imaging Ultrasonic imaging Location awareness In vivo Reviews Data models neural network super-resolution ultrasound localization microscopy (ULM)

来源：评论

学校读者我要写书评

暂无评论

deep learning based real-time Noise Removal in Retinal Fundus images

Deep Learning based Real-Time Noise Removal in Retinal Fundu...

引用

2024 IEEE International Conference on Signal processing and Advance Research in Computing, SPARC 2024

作者： Sharma, Gaurav Soni, K.M. Kumar, Basant Singh, Maninder Amity University Amity Institute of Information Technology Noida India MNNIT Allahabad Electronics and Communication Engineering Department Prayagraj India

ISBN: (纸本)9798350385199

real-time noise removal in fundus images, which are images of the back of the eye (retina), is a critical task in various medical applications, particularly in ophthalmology. This study presents a deep learning approach for denoising retinal fundus images affected by gaussian and speckle noise. A diverse dataset comprising various retinal image acquisition conditions was utilized, with synthetic speckle and gaussian noise introduced at different levels to simulate in real-world scenarios. In the proposed approach, the noise is introduced by considering the variance of 0.5 and 1. Moreover, pre-processing steps were employed to mitigate noise impact, followed by feeding the images into a proposed CNN-based denoising architecture. The architecture's performance was rigorously evaluated using quantitative metrics and expert clinician assessments. Results include an average Peak Signal-to-Noise Ratio (PSNR) of 47.5 dB, an average Structural Similarity Index Measure (SSIM) of 0.90, and an average $R 2$ score of 71 ± 0.7 %. Additionally, the BRISQUE score averaged 59.41. These results demonstrate the efficacy of the approach in enhancing image quality and preserving essential features, highlighting its potential for clinical applications in retinal imaging. © 2024 IEEE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

End-to-end deep learning pipeline for on-board extraterrestrial rock segmentation

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年第PartB期127卷

作者： Marek, Daniel Nalepa, Jakub Silesian Tech Univ Dept Algorithm & Software Akad 16 PL-44100 Gliwice Poland KP Labs Bojkowska 37J PL-44100 Gliwice Poland

Bringing autonomy on board edge devices is inevitable to accelerate the process of space exploration. Although there are various tasks that can be executed autonomously by such vehicles, detecting and segmenting rocks in on-board images of extraterrestrial landscapes is a critical step in the processing chain, as it can allow to navigate safely while avoiding collisions. We tackle this issue and introduce an end-to-end pipeline for building and validating resource-frugal machine learning techniques for this task, offering a high level of flexibility. Deploying such models on board edge devices poses numerous practical challenges, spanning across ensuring their memory and computational efficiency, and understanding their robustness against varying quality of acquired images. These aspects are often overlooked while building deep learning-powered on-board systems-we show that they can (and ultimately should) be a part of the deployment chain. Our extensive experimental study performed over several benchmark data sets shed more light on functional and non-functional capabilities of the investigated models, both in full-precision and compressed by quantisation, the latter delivering statistically same segmentation accuracy while being approximately 11x smaller. Additionally, we show that synthesised images can be utilised to quantify the robustness of deep learning models against on-board acquisition conditions which directly affect the quality of captured images-such simulations mimicking real-world acquisition settings could have a negative impact on the capabilities of the models trained over clean and high-quality image data. To ensure full reproducibility of this study, we made our implementation publicly available at https://***/danielmarek22/onboard-rock-segmentation.

关键词： Rock detection Semantic segmentation deep learning On-board processing Space exploration Model compression Planetary rover

来源：评论

学校读者我要写书评

暂无评论

Toward User-Guided Seismic Facies Interpretation With a Pre-Trained Large Vision Model

引用

IEEE ACCESS 2025年 13卷 42965-42976页

作者： Atolagbe, Joshua Koeshidayatullah, Ardiansyah King Fahd Univ Petr & Minerals Dept Geosci Dhahran 31261 Saudi Arabia King Fahd Univ Petr & Minerals Ctr Integrat Petr Res Dhahran 31261 Saudi Arabia

Recent advancements in computer vision and deep learning have made a paradigm shift in seismic facies interpretation. Various supervised and unsupervised deep learning-based seismic facies research using Convolutional Neural Network (CNN) as the baseline architecture have been proposed and achieved promising results. However, these approaches are often limited by the lack of available high-quality labelled dataset and minimum explainability of the model. This is further compounded by the fact that these models do not allow user-guided interaction, which limits the ability of seismic interpreters to perform localized seismic facies segmentation through prompts. To optimize the already existing approach, we present a time-efficient and high precision alternative by reformulating seismic facies segmentation as a Segment All or Segment One (SASO) task. In this paper, we propose FaciesSAM, based on Fast Segment Anything Model, for seismic facies segmentation. For the first time, our paper highlights that FaciesSAM can help to decouple seismic facies identification into all-instance segmentation (segment all) and prompt-guided selection (segment one) for broad and localized facies interpretation, respectively. The effectiveness of our proposed method was evaluated on the benchmark F3 geological dataset. Experimental results shows that our method is effective, even when trained on fewer seismic images, achieving a mAP0.5 of 83.3% with 3.1% increase in pixel accuracy and 4.6% increase in mean class accuracy when compared to the CNN benchmark results. Furthermore, our method meets real-time processing speed of 1.14ms per seismic section. These results underscore the capacity of prompt-based CNN detectors to solving specific geological challenges such as seismic interpretation accuracy and processing speed.

关键词： image segmentation Convolutional neural networks Computational modeling Training Computer vision Transformers Petroleum Head Feature extraction Data models Facies segmentation prompt-based FaciesSAM deep learning model explainability

来源：评论

学校读者我要写书评

暂无评论

real-time detection and location of reserved anchor hole in coal mine roadway support steel belt

引用

JOURNAL OF real-time image processing 2023年第5期20卷 89页

作者： Wang, Hongwei Zhang, Fujing Wang, Haoran Li, Zhenglong Wang, Yuheng Taiyuan Univ Technol Coll Mech & Vehicle Engn Taiyuan 030024 Peoples R China Taiyuan Univ Technol Coll Safety & Emergency Management Engn Taiyuan 030024 Peoples R China Taiyuan Univ Technol Coll Min Engn Taiyuan 030024 Peoples R China Taiyuan Univ Technol Shanxi Engn Res Ctr Coal Mine Intelligent Equipmen Taiyuan 030024 Peoples R China Shanxi Coking Coal Grp Co Ltd Postdoctoral Workstat Taiyuan 030024 Peoples R China

Based on the current coal mine roadway using supporting steel belt steel belt auxiliary anchor support, the location of the supporting steel belt anchor holes is mainly done manually;if the location is not accurate, there will be large safety hazards and other problems. An intelligent real-time detection and location method of anchor holes in coal mine roadway support steel belt based on deep learning model and depth camera is proposed. First, to reduce the influence of water mist and dust on the camera and improve the image quality of the camera, the image is pre-processed using contrast limited adaptive histogram equalization. Second, the YOLOv5s model is improved by adding SPD-Conv and coordinate attention mechanisms to improve the detection capability of the model. Third, a real-time depth map restoration method that fully preserves object edge features is proposed to avoid errors caused by areas with depth values of 0 in the depth map when locating anchor holes in combination with a depth camera. Finally, the improved YOLOv5s model proposed in this paper combined with the repaired depth map was used to achieve the detection and location of anchor holes in a laboratory simulated tunnel with a location error of less than 5 mm and an average FPS of 28.9. In summary, the real-time target detection and location method based on a deep learning model and a depth camera is feasible in an unstructured environment in coal mines.

关键词： deep learning real-time detection Detection and location of anchor hole Improved YOLOv5 network Coordinate attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A deep learning approach for deriving wheat phenology from near-surface RGB image series using spatiotemporal fusion

引用

PLANT METHODS 2024年第1期20卷 153页

作者： Cai, Yucheng Li, Yan Qi, Xuerui Zhao, Jianqing Jiang, Li Tian, Yongchao Zhu, Yan Cao, Weixing Zhang, Xiaohu Nanjing Agr Univ Natl Engn & Technol Ctr Informat Agr Nanjing 210095 Peoples R China Minist Agr & Rural Affairs Key Lab Crop Syst Anal & Decis Making Nanjing 210095 Peoples R China Jiangsu Second Normal Univ Coll Geog Nanjing 211200 Peoples R China Jiangsu Univ Coll Agr Engn Zhenjiang 212013 Peoples R China Jiangsu Collaborat Innovat Ctr Modern Crop Prod Nanjing 210095 Peoples R China

Accurate monitoring of wheat phenological stages is essential for effective crop management and informed agricultural decision-making. Traditional methods often rely on labour-intensive field surveys, which are prone to subjective bias and limited temporal resolution. To address these challenges, this study explores the potential of near-surface cameras combined with an advanced deep-learning approach to derive wheat phenological stages from high-quality, real-time RGB image series. Three deep learning models based on three different spatiotemporal feature fusion methods, namely sequential fusion, synchronous fusion, and parallel fusion, were constructed and evaluated for deriving wheat phenological stages with these near-surface RGB image series. Moreover, the impact of different image resolutions, capture perspectives, and model training strategies on the performance of deep learning models was also investigated. The results indicate that the model using the sequential fusion method is optimal, with an overall accuracy (OA) of 0.935, a mean absolute error (MAE) of 0.069, F1-score (F1) of 0.936, and kappa coefficients (Kappa) of 0.924 in wheat phenological stages. Besides, the enhanced image resolution of 512 x 512 pixels and a suitable image capture perspective, specifically a sensor viewing angle of 40 degrees to 60 degrees vertically, introduce more effective features for phenological stage detection, thereby enhancing the model's accuracy. Furthermore, concerning the model training, applying a two-step fine-tuning strategy will also enhance the model's robustness to random variations in perspective. This research introduces an innovative approach for real-time phenological stage detection and provides a solid foundation for precision agriculture. By accurately deriving critical phenological stages, the methodology developed in this study supports the optimization of crop management practices, which may result in improved resource efficiency and sustainability a

关键词： Wheat Phenology monitoring RGB image series deep learning Spatiotemporal feature

来源：评论

学校读者我要写书评

暂无评论

Denoising Seismic Waveforms Using a Wavelet-Transform-Based Machine-learning Method

引用

BULLETIN OF THE SEISMOLOGICAL SOCIETY OF AMERICA 2024年第4期114卷 1777-1788页

作者： Quinones, Louis Tibi, Rigobert Sandia Natl Labs Albuquerque NM 87123 USA

Seismic waveform data recorded at stations can be thought of as a superposition of the signal from a source of interest and noise from other sources. Frequency-based filtering methods for waveform denoising do not result in desired outcomes when the targeted signal and noise occupy similar frequency bands. Recently, denoising techniques based on deep-learning convolutional neural networks (CNNs), in which a recorded waveform is decomposed into signal and noise components, have led to improved results. These CNN methods, which use short-time Fourier transform representations of the time series, provide signal and noise masks for the input waveform. These masks are used to create denoised signal and designaled noise waveforms, respectively. However, advancements in the field of image denoising have shown the benefits of incorporating discrete wavelet transforms (DWTs) into CNN architectures to create multilevel wavelet CNN (MWCNN) models. The MWCNN model preserves the details of the input due to the good time-frequency localization of the DWT. Here, we use a data set of over 382,000 constructed seismograms recorded by the University of Utah Seismograph Stations network to compare the performance of CNN and MWCNN-based denoising models. Evaluation of both models on constructed test data shows that the MWCNN model outperforms the CNN model in the ability to recover the ground-truth signal component in terms of both waveform similarity and preservation of amplitude information. Model evaluation of real-world data shows that both the CNN and MWCNN models outperform standard band-pass filtering (BPF;average improvement in signal-to-noise ratio of 9.6 and 19.7 dB, respectively, with respect to BPF). Evaluation of continuous data suggests the MWCNN denoiser can improve both signal detection capabilities and phase arrival time estimates.

关键词： algorithms arrival time convolutional neural networks data processing deep learning denoising discrete filters elastic waves Fourier analysis functions machine learning monitoring neural networks noise phase velocity seismograms transformations United States University of Utah Seismic Network Utah waveforms wavelets

来源：评论

学校读者我要写书评

暂无评论

An automatic garbage detection using optimized YOLO model

引用

SIGNAL image AND VIDEO processing 2024年第1期18卷 315-323页

作者： Zailan, Nur Athirah Mohd Khairuddin, Anis Salwa Hasikin, Khairunnisa Junos, Mohamad Haniff Khairuddin, Uswah Univ Malaya Fac Engn Dept Elect Engn Kuala Lumpur Malaysia Univ Sains Malaysia Sch Aerosp Engn Engn Campus Nibong Tebal 14300 Penang Malaysia Univ Teknol Malaysia Sch Malaysia Japan Int Inst Technol Kuala Lumpur Malaysia

Garbage pollution is an increasing global concern. Hence, the adoption of innovative solutions is important for controlling garbage pollution. In order to develop an efficient cleaner robot, it is very crucial to obtain visual information of floating garbage on the river. deep learning has been actively applied over the past few years to tackle various problems. High-level, semantic, and advanced features can be learnt by deep learning models based on visual information. This is extremely important to detect and classify different types of floating garbage. This paper proposed an optimized You Only Look Once v4 Tiny model to detect floating garbage, mainly by improving the spatial pyramid pooling with average pooling, mish activation function, concatenated densely connected neural network, and hyperparameters optimization. The proposed model shows improved results of 74.89% mean average precision with a size of 16.4 MB, which can be concluded as the best trade-off among other models. The proposed model has promising results in terms of model size, detection time and memory space, which is feasible to be embedded in low-cost devices.

关键词： Computer vision Debris deep learning image processing Object detection

来源：评论

学校读者我要写书评

暂无评论

Automated tree ring detection of common Indiana hardwood species through deep learning: Introducing a new dataset of annotated images

引用

INFORMATION processing IN AGRICULTURE 2024年第4期11卷 552-558页

作者： Wu, Fanyou Huang, Yunmei Benes, Bedrich Warner, Charles C. Gazo, Rado Purdue Univ Dept Forestry & Nat Resources W Lafayette IN 47906 USA Purdue Univ Dept Comp Sci W Lafayette IN 47906 USA

Tree-ring dating enables gathering necessary knowledge about trees, and it is essential in many areas, including forest management and the timber industry. Tree-ring dating can be conducted on either wood's clean crosssections or tree trunks' rough end cross-sections. However, the measurement process is still time-consuming and frequently requires experts who use special devices, such as stereoscopes. Modern approaches based on image processing using deep learning have been successfully applied in many areas, and they can succeed in recognizing tree rings. While supervised deep learning-based methods often produce excellent results, they also depend on extensive datasets of tediously annotated data. To our knowledge, there are only a few publicly available ring image datasets with annotations. We introduce a new carefully captured dataset of images of hardwood species automatically annotated for tree ring detection. We capture each wood cookie twice, once in the rough form, similar to industrial settings, and then after careful cleaning, that reveals all growth rings. We carefully overlap the images and use them for an automatic ring annotation in the rough data. We then use the Feature Pyramid Network with Resnet encoder that obtains an overall pixel-level area under the curve score of 85.72% and ring level F1 score of 0.7348. The data and code are available at https://***/wufanyou/growth-ring-detection.

关键词： Dendrochronology deep learning Semantic segmentation

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：