期刊文献+
共找到3,274篇文章
< 1 2 164 >
每页显示 20 50 100
A Simple and Effective Surface Defect Detection Method of Power Line Insulators for Difficult Small Objects
1
作者 Xiao Lu Chengling Jiang +2 位作者 Zhoujun Ma Haitao Li Yuexin Liu 《Computers, Materials & Continua》 SCIE EI 2024年第4期373-390,共18页
Insulator defect detection plays a vital role in maintaining the secure operation of power systems.To address the issues of the difficulty of detecting small objects and missing objects due to the small scale,variable... Insulator defect detection plays a vital role in maintaining the secure operation of power systems.To address the issues of the difficulty of detecting small objects and missing objects due to the small scale,variable scale,and fuzzy edge morphology of insulator defects,we construct an insulator dataset with 1600 samples containing flashovers and breakages.Then a simple and effective surface defect detection method of power line insulators for difficult small objects is proposed.Firstly,a high-resolution featuremap is introduced and a small object prediction layer is added so that the model can detect tiny objects.Secondly,a simplified adaptive spatial feature fusion(SASFF)module is introduced to perform cross-scale spatial fusion to improve adaptability to variable multi-scale features.Finally,we propose an enhanced deformable attention mechanism(EDAM)module.By integrating a gating activation function,the model is further inspired to learn a small number of critical sampling points near reference points.And the module can improve the perception of object morphology.The experimental results indicate that concerning the dataset of flashover and breakage defects,this method improves the performance of YOLOv5,YOLOv7,and YOLOv8.In practical application,it can simply and effectively improve the precision of power line insulator defect detection and reduce missing detection for difficult small objects. 展开更多
关键词 Insulator defect detection small object power line deformable attention mechanism
下载PDF
Effect of low-degree astigmatism on the objective visual quality
2
作者 Ling-Ying Ye Shu-Feng Li +2 位作者 Jing-Jing Zuo Jin Li Hui-Xiang Ma 《International Journal of Ophthalmology(English edition)》 SCIE CAS 2024年第6期1086-1093,共8页
AIM:To evaluate the effect of low-degree astigmatism on objective visual quality through the Optical Quality Analysis System(OQAS).METHODS:This study enrolled 46 participants(aged 23 to 30y,90 eyes)with normal or corr... AIM:To evaluate the effect of low-degree astigmatism on objective visual quality through the Optical Quality Analysis System(OQAS).METHODS:This study enrolled 46 participants(aged 23 to 30y,90 eyes)with normal or corrected-to-normal vision.The cylindrical lenses(0,0.5,0.75,1.0,and 1.25 D)were placed at the axial direction(180°,45°,90°,and 135°)in front of the eyes with the best correction to form 16 types of regular low-degree astigmatism.OQAS was used to detect the objective visual quality,recorded as the objective scattering index(OSI),OQAS values at contrasts of 100%,20%,and 9%predictive visual acuity(OV100%,OV20%,and OV9%),modulation transfer function cut-off(MTFcut-off)and Strehl ratio(SR).The mixed effect linear model was used to compare objective visual quality differences between groups and examine associations between astigmatic magnitude and objective visual quality parameters.RESULTS:Apparent negative relationships between the magnitude of low astigmatism and objective visual quality were observed.The increase of OSI per degree of astigmatism at 180°,45°,90°,and 135°axis were 0.38(95%CI:0.35,0.42),0.50(95%CI:0.46,0.53),0.49(95%CI:0.45,0.54)and 0.37(95%CI:0.34,0.41),respectively.The decrease of MTFcut-off per degree of astigmatism at 180°,45°,90°,and 135°axis were-10.30(95%CI:-11.43,-9.16),-12.73(95%CI:-13.62,-11.86),-12.75(95%CI:-13.79,-11.70),and-9.97(95%CI:-10.92,-9.03),respectively.At the same astigmatism degree,OSI at 45°and 90°axis were higher than that at 0°and 135°axis,while MTFcut-off were lower.CONCLUSION:Low astigmatism of only 0.50 D can significantly reduce the objective visual quality. 展开更多
关键词 low-degree astigmatism objective visual quality Optical Quality Analysis System
下载PDF
Promotion of structural plasticity in area V2 of visual cortex prevents against object recognition memory deficits in aging and Alzheimer's disease rodents
3
作者 Irene Navarro-Lobato Mariam Masmudi-Martín +8 位作者 Manuel F.López-Aranda Juan F.López-Téllez Gloria Delgado Pablo Granados-Durán Celia Gaona-Romero Marta Carretero-Rey Sinforiano Posadas María E.Quiros-Ortega Zafar U.Khan 《Neural Regeneration Research》 SCIE CAS CSCD 2024年第8期1835-1841,共7页
Memory deficit,which is often associated with aging and many psychiatric,neurological,and neurodegenerative diseases,has been a challenging issue for treatment.Up till now,all potential drug candidates have failed to ... Memory deficit,which is often associated with aging and many psychiatric,neurological,and neurodegenerative diseases,has been a challenging issue for treatment.Up till now,all potential drug candidates have failed to produce satisfa ctory effects.Therefore,in the search for a solution,we found that a treatment with the gene corresponding to the RGS14414protein in visual area V2,a brain area connected with brain circuits of the ventral stream and the medial temporal lobe,which is crucial for object recognition memory(ORM),can induce enhancement of ORM.In this study,we demonstrated that the same treatment with RGS14414in visual area V2,which is relatively unaffected in neurodegenerative diseases such as Alzheimer s disease,produced longlasting enhancement of ORM in young animals and prevent ORM deficits in rodent models of aging and Alzheimer’s disease.Furthermore,we found that the prevention of memory deficits was mediated through the upregulation of neuronal arbo rization and spine density,as well as an increase in brain-derived neurotrophic factor(BDNF).A knockdown of BDNF gene in RGS14414-treated aging rats and Alzheimer s disease model mice caused complete loss in the upregulation of neuronal structural plasticity and in the prevention of ORM deficits.These findings suggest that BDNF-mediated neuronal structural plasticity in area V2 is crucial in the prevention of memory deficits in RGS14414-treated rodent models of aging and Alzheimer’s disease.Therefore,our findings of RGS14414gene-mediated activation of neuronal circuits in visual area V2 have therapeutic relevance in the treatment of memory deficits. 展开更多
关键词 behavioral performance brain-derived neurotrophic factor cognitive dysfunction episodic memory memory circuit activation memory deficits memory enhancement object recognition memory prevention of memory loss regulator of G protein signaling
下载PDF
Development and optimization of object detection technology in pavement engineering: A literature review
4
作者 Hui Yao Yaning Fan +7 位作者 Yanhao Liu Dandan Cao Ning Chen Tiancheng Luo Jingyu Yang Xueyi Hu Jie Ji Zhanping You 《Journal of Road Engineering》 2024年第2期163-188,共26页
Due to the rapid advancement of the transportation industry and the continual increase in pavement infrastructure,it is difficult to keep up with the huge road maintenance task by relying only on the traditional manua... Due to the rapid advancement of the transportation industry and the continual increase in pavement infrastructure,it is difficult to keep up with the huge road maintenance task by relying only on the traditional manual detection method.Intelligent pavement detection technology with deep learning techniques is available for the research and industry areas by the gradual development of computer vision technology.Due to the different characteristics of pavement distress and the uncertainty of the external environment,this kind of object detection technology for distress classification and location still faces great challenges.This paper discusses the development of object detection technology and analyzes classical convolutional neural network(CNN)architecture.In addition to the one-stage and two-stage object detection frameworks,object detection without anchor frames is introduced,which is divided according to whether the anchor box is used or not.This paper also introduces attention mechanisms based on convolutional neural networks and emphasizes the performance of these mechanisms to further enhance the accuracy of object recognition.Lightweight network architecture is introduced for mobile and industrial deployment.Since stereo cameras and sensors are rapidly developed,a detailed summary of three-dimensional object detection algorithms is also provided.While reviewing the history of the development of object detection,the scope of this review is not only limited to the area of pavement crack detection but also guidance for researchers in related fields is shared. 展开更多
关键词 Pavement engineering object detection Lightweight network Attention mechanism Convolutional neural network
下载PDF
Management of Penetrating Cranioencephalic Trauma Caused by Sharp Metal Objects—Therapeutic and Evolutionary Aspects: 12 Cases at the Renaissance University Hospital in N’Djamena
5
作者 Goumantar Félicien Toudjingar Li-Iyane Olivier Ouambi +3 位作者 Yannick Canton Kessely Donal Djasdé Mahouli Fata Vounki Momar Codé Ba 《Open Journal of Modern Neurosurgery》 2024年第2期170-178,共9页
Introduction: Cranioencephalic trauma caused by bladed weapons is rare, and that caused by sharp objects is exceptional. The aim of our study was to describe the clinical, therapeutic and evolutionary aspects. Materia... Introduction: Cranioencephalic trauma caused by bladed weapons is rare, and that caused by sharp objects is exceptional. The aim of our study was to describe the clinical, therapeutic and evolutionary aspects. Materials and method: This was a descriptive and analytical study over a 48-month period at CHU la Renaissance from January 1, 2018 to December 31, 2021, concerning patients admitted for penetrating cranioencephalic trauma by pointed object. Results: Twelve cases, all male, of penetrating cranioencephalic sharp-force trauma were identified. The mean age was 34 ± 7 years, with extremes of 11 and 60 years. Farmers and herders accounted for 31% and 25% of cases respectively. The average admission time was 47 hours. Brawls were the circumstances of occurrence in 81.2% of cases. Knives (33%), arrows (25%) and iron bars (16.6%) were the objects used. Altered consciousness was present in 43.8% of cases, and focal deficit in 50%. Scannographic lesions were fracture and/or embarrhment (12 cases), intra-parenchymal haematomas (6 cases) and presence of object in place (4 cases). Surgery was performed in 11 patients. Postoperative outcome was favorable in 9 patients. After 12 months, 2 patients were declared unfit. Conclusion: Penetrating head injuries caused by sharp objects are common in Chad. Urgent surgery can prevent disabling after-effects. 展开更多
关键词 Penetrating Trauma SKULL Encephalon Sharp object Surgery Patient Outcome
下载PDF
The Fusion of Temporal Sequence with Scene Priori Information in Deep Learning Object Recognition
6
作者 Yongkang Cao Fengjun Liu +2 位作者 Xian Wang Wenyun Wang Zhaoxin Peng 《Open Journal of Applied Sciences》 2024年第9期2610-2627,共18页
For some important object recognition applications such as intelligent robots and unmanned driving, images are collected on a consecutive basis and associated among themselves, besides, the scenes have steady prior fe... For some important object recognition applications such as intelligent robots and unmanned driving, images are collected on a consecutive basis and associated among themselves, besides, the scenes have steady prior features. Yet existing technologies do not take full advantage of this information. In order to take object recognition further than existing algorithms in the above application, an object recognition method that fuses temporal sequence with scene priori information is proposed. This method first employs YOLOv3 as the basic algorithm to recognize objects in single-frame images, then the DeepSort algorithm to establish association among potential objects recognized in images of different moments, and finally the confidence fusion method and temporal boundary processing method designed herein to fuse, at the decision level, temporal sequence information with scene priori information. Experiments using public datasets and self-built industrial scene datasets show that due to the expansion of information sources, the quality of single-frame images has less impact on the recognition results, whereby the object recognition is greatly improved. It is presented herein as a widely applicable framework for the fusion of information under multiple classes. All the object recognition algorithms that output object class, location information and recognition confidence at the same time can be integrated into this information fusion framework to improve performance. 展开更多
关键词 Computer Vison object Recognition Deep Learning Consecutive Scene Information Fusion
下载PDF
Patterns of Interactions of the Complex City System:Emotional Urban Objects as Triggering Agents-A Secondary Publication
7
作者 O.A.Gonzalez Liliana Beatriz Sosa Compeán 《Journal of World Architecture》 2024年第1期45-53,共9页
This article presents an analysis of the patterns of interactions resulting from the positive and negative emotional events that occur in cities,considering them as complex systems.It explores,from the imaginaries,how... This article presents an analysis of the patterns of interactions resulting from the positive and negative emotional events that occur in cities,considering them as complex systems.It explores,from the imaginaries,how certain urban objects can act as emotional agents and how these events affect the urban system as a whole.An adaptive complex systems perspective is used to analyze these patterns.The results show patterns in the processes and dynamics that occur in cities based on the objects that affect the emotions of the people who live there.These patterns depend on the characteristics of the emotional charge of urban objects,but they can be generalized in the following process:(1)immediate reaction by some individuals;(2)emotions are generated at the individual level which begins to generalize,permuting to a collective emotion;(3)a process of reflection is detonated in some individuals from the reading of collective emotions;(4)integration/significance in the community both at the individual and collective level,on the concepts,roles and/or functions that give rise to the process in the system.Therefore,it is clear that emotions play a significant role in the development of cities and these aspects should be considered in the design strategies of all kinds of projects for the city.Future extensions of this work could include a deeper analysis of specific emotional events in urban environments,as well as possible implications for urban policy and decision making. 展开更多
关键词 Emotional events Urban objects Complex adaptive systems Adaptive complex systems City
下载PDF
Advancing Crowd Object Detection: A Review of YOLO, CNN and ViTs Hybrid Approach*
8
作者 Mahmoud Atta Mohammed Ali Tarek Aly +2 位作者 Atef Tayh Raslan Mervat Gheith Essam A. Amin 《Journal of Intelligent Learning Systems and Applications》 2024年第3期175-221,共47页
One of the most basic and difficult areas of computer vision and image understanding applications is still object detection. Deep neural network models and enhanced object representation have led to significant progre... One of the most basic and difficult areas of computer vision and image understanding applications is still object detection. Deep neural network models and enhanced object representation have led to significant progress in object detection. This research investigates in greater detail how object detection has changed in the recent years in the deep learning age. We provide an overview of the literature on a range of cutting-edge object identification algorithms and the theoretical underpinnings of these techniques. Deep learning technologies are contributing to substantial innovations in the field of object detection. While Convolutional Neural Networks (CNN) have laid a solid foundation, new models such as You Only Look Once (YOLO) and Vision Transformers (ViTs) have expanded the possibilities even further by providing high accuracy and fast detection in a variety of settings. Even with these developments, integrating CNN, YOLO and ViTs, into a coherent framework still poses challenges with juggling computing demand, speed, and accuracy especially in dynamic contexts. Real-time processing in applications like surveillance and autonomous driving necessitates improvements that take use of each model type’s advantages. The goal of this work is to provide an object detection system that maximizes detection speed and accuracy while decreasing processing requirements by integrating YOLO, CNN, and ViTs. Improving real-time detection performance in changing weather and light exposure circumstances, as well as detecting small or partially obscured objects in crowded cities, are among the goals. We provide a hybrid architecture which leverages CNN for robust feature extraction, YOLO for rapid detection, and ViTs for remarkable global context capture via self-attention techniques. Using an innovative training regimen that prioritizes flexible learning rates and data augmentation procedures, the model is trained on an extensive dataset of urban settings. Compared to solo YOLO, CNN, or ViTs models, the suggested model exhibits an increase in detection accuracy. This improvement is especially noticeable in difficult situations such settings with high occlusion and low light. In addition, it attains a decrease in inference time in comparison to baseline models, allowing real-time object detection without performance loss. This work introduces a novel method of object identification that integrates CNN, YOLO and ViTs, in a synergistic way. The resultant framework extends the use of integrated deep learning models in practical applications while also setting a new standard for detection performance under a variety of conditions. Our research advances computer vision by providing a scalable and effective approach to object identification problems. Its possible uses include autonomous navigation, security, and other areas. 展开更多
关键词 object Detection Deep Learning Computer Vision YOLO Convolutional Neural Networks (CNN) Vision Transformers Neural Networks Transfer Learning Autonomous Driving Self-Drive Vehicles
下载PDF
Research on the Relationship between the School-Running Characteristics of Private Colleges and Universities and the Development Objectives of the Government
9
作者 Lishuxian Zhao Xiaoxia Wu Zhuolin Zhu 《Journal of Contemporary Educational Research》 2024年第9期296-302,共7页
The development objectives of the Chinese government have a guiding effect on the school-running characteristics of private colleges and universities.This paper explores the relationship between the characteristics of... The development objectives of the Chinese government have a guiding effect on the school-running characteristics of private colleges and universities.This paper explores the relationship between the characteristics of private colleges and universities and the development objectives of the provincial government,using Jiangsu Province as a case study.All the schools have the consciousness of fully considering the development objectives of Jiangsu Province when formulating the school-running characteristics.Their characteristics all contain some training methods,training courses,or institutional construction aiming at the development objectives.Most universities can support the government’s objectives on employment and innovation.Only a third of the schools provide government support for science research.Private colleges and universities should make full use of the free and flexible advantages of private education,combine them with the continuous changes of policies and markets,and create clear,scientific,and dynamic school-running characteristics,in order to achieve long-term development. 展开更多
关键词 Development objectives of the government School-running characteristics Chinese Private colleges and universities
下载PDF
Objective Identification and Climatic Characteristics of Heavy-Precipitation Northeastern China Cold Vortexes 被引量:2
10
作者 Xu CHEN Xiaoyong ZHUGE +2 位作者 Xidi ZHANG Yuan WANG Daokai XUE 《Advances in Atmospheric Sciences》 SCIE CAS CSCD 2023年第2期305-316,I0009,I0010,共14页
The northeastern China cold vortex(NCCV)plays an important role in regional rainstorms over East Asia.Using the National Centers for Environmental Prediction Final reanalysis dataset and the Global Precipitation Measu... The northeastern China cold vortex(NCCV)plays an important role in regional rainstorms over East Asia.Using the National Centers for Environmental Prediction Final reanalysis dataset and the Global Precipitation Measurement product,an objective algorithm for identifying heavy-precipitation NCCV(HPCV)events was designed,and the climatological features of 164 HPCV events from 2001 to 2019 were investigated.The number of HPCV events showed an upward linear trend,with the highest frequency of occurrence in summer.The most active region of HPCV samples was the Northeast China Plain between 40°–55°N.Most HPCV events lasted 3–5 days and had radii ranging from 250 to 1000 km.The duration of HPCV events with larger sizes was longer.About half of the HPCV events moved into(moved out of)the definition region(35°–60°N,115°–145°E),and half initiated(dissipated)within the region.The initial position was close to the western boundary of the definition region,and the final position was mainly near the eastern boundary.The locations associated with the precipitation were mostly concentrated within 2000 km southeast of the HPCV systems,and they were farther from the center in the cold season than in the warm season. 展开更多
关键词 northeastern China cold vortex heavy precipitation objective identification climatological features
下载PDF
Smart object recommendation based on topic learning and joint features in the social internet of things 被引量:1
11
作者 Hongfei Zhang Li Zhu +4 位作者 Tao Dai Liwen Zhang Xi Feng Li Zhang Kaiqi Zhang 《Digital Communications and Networks》 SCIE CSCD 2023年第1期22-32,共11页
With the extensive integration of the Internet,social networks and the internet of things,the social internet of things has increasingly become a significant research issue.In the social internet of things application... With the extensive integration of the Internet,social networks and the internet of things,the social internet of things has increasingly become a significant research issue.In the social internet of things application scenario,one of the greatest challenges is how to accurately recommend or match smart objects for users with massive resources.Although a variety of recommendation algorithms have been employed in this field,they ignore the massive text resources in the social internet of things,which can effectively improve the effect of recommendation.In this paper,a smart object recommendation approach named object recommendation based on topic learning and joint features is proposed.The proposed approach extracts and calculates topics and service relevant features of texts related to smart objects and introduces the“thing-thing”relationship information in the internet of things to improve the effect of recommendation.Experiments show that the proposed approach enables higher accuracy compared to the existing recommendation methods. 展开更多
关键词 Social internet of things Smart object recommendation Topics Features Thing-thing relationship
下载PDF
Multi‐objective particle swarm optimisation of complex product change plan considering service performance 被引量:1
12
作者 Ruizhao Zheng Yong Zhang +4 位作者 Xiaoyan Sun Faguang Wang Lei Yang Chen Peng Yulong Wang 《CAAI Transactions on Intelligence Technology》 SCIE EI 2023年第3期1058-1076,共19页
Design change is an inevitable part of the product development process.This study proposes an improved binary multi‐objective PSO algorithm guided by problem char-acteristics(P‐BMOPSO)to solve the optimisation probl... Design change is an inevitable part of the product development process.This study proposes an improved binary multi‐objective PSO algorithm guided by problem char-acteristics(P‐BMOPSO)to solve the optimisation problem of complex product change plan considering service performance.Firstly,a complex product multi‐layer network with service performance is established for the first time to reveal the impact of change effect propagation on the product service performance.Secondly,the concept of service performance impact(SPI)is defined by decoupling the impact of strongly associated nodes on the service performance in the process of change affect propagation.Then,a triple‐objective selection model of change nodes is established,which includes the three indicators:SPI degree,change cost,and change time.Furthermore,an integer multi‐objective particle swarm optimisation algorithm guided by problem characteristics is developed to solve the model above.Experimental results on the design change problem of a certain type of Skyworth TV verify the effectiveness of the established optimisation model and the proposed P‐BMOPSO algorithm. 展开更多
关键词 multi‐objective particle swarm optimization product change service performance
下载PDF
Multiple Data Augmentation Strategy for Enhancing the Performance of YOLOv7 Object Detection Algorithm 被引量:2
13
作者 Abdulghani M.Abdulghani Mokhles M.Abdulghani +1 位作者 Wilbur L.Walters Khalid H.Abed 《Journal on Artificial Intelligence》 2023年第1期15-30,共16页
The object detection technique depends on various methods for duplicating the dataset without adding more images.Data augmentation is a popularmethod that assists deep neural networks in achieving better generalizatio... The object detection technique depends on various methods for duplicating the dataset without adding more images.Data augmentation is a popularmethod that assists deep neural networks in achieving better generalization performance and can be seen as a type of implicit regularization.Thismethod is recommended in the casewhere the amount of high-quality data is limited,and gaining new examples is costly and time-consuming.In this paper,we trained YOLOv7 with a dataset that is part of the Open Images dataset that has 8,600 images with four classes(Car,Bus,Motorcycle,and Person).We used five different data augmentations techniques for duplicates and improvement of our dataset.The performance of the object detection algorithm was compared when using the proposed augmented dataset with a combination of two and three types of data augmentation with the result of the original data.The evaluation result for the augmented data gives a promising result for every object,and every kind of data augmentation gives a different improvement.The mAP@.5 of all classes was 76%,and F1-score was 74%.The proposed method increased the mAP@.5 value by+13%and F1-score by+10%for all objects. 展开更多
关键词 Artificial intelligence object detection YOLOv7 data augmentation data brightness data darkness data blur data noise convolutional neural network
下载PDF
Improvement of High-Speed Detection Algorithm for Nonwoven Material Defects Based on Machine Vision 被引量:2
14
作者 LI Chengzu WEI Kehan +4 位作者 ZHAO Yingbo TIAN Xuehui QIAN Yang ZHANG Lu WANG Rongwu 《Journal of Donghua University(English Edition)》 CAS 2024年第4期416-427,共12页
Defect detection is vital in the nonwoven material industry,ensuring surface quality before producing finished products.Recently,deep learning and computer vision advancements have revolutionized defect detection,maki... Defect detection is vital in the nonwoven material industry,ensuring surface quality before producing finished products.Recently,deep learning and computer vision advancements have revolutionized defect detection,making it a widely adopted approach in various industrial fields.This paper mainly studied the defect detection method for nonwoven materials based on the improved Nano Det-Plus model.Using the constructed samples of defects in nonwoven materials as the research objects,transfer learning experiments were conducted based on the Nano DetPlus object detection framework.Within this framework,the Backbone,path aggregation feature pyramid network(PAFPN)and Head network models were compared and trained through a process of freezing,with the ultimate aim of bolstering the model's feature extraction abilities and elevating detection accuracy.The half-precision quantization method was used to optimize the model after transfer learning experiments,reducing model weights and computational complexity to improve the detection speed.Performance comparisons were conducted between the improved model and the original Nano Det-Plus model,YOLO,SSD and other common industrial defect detection algorithms,validating that the improved methods based on transfer learning and semi-precision quantization enabled the model to meet the practical requirements of industrial production. 展开更多
关键词 defect detection nonwoven materials deep learning object detection algorithm transfer learning halfprecision quantization
下载PDF
Automatic detection of small bowel lesions with different bleeding risks based on deep learning models 被引量:1
15
作者 Rui-Ya Zhang Peng-Peng Qiang +5 位作者 Ling-Jun Cai Tao Li Yan Qin Yu Zhang Yi-Qing Zhao Jun-Ping Wang 《World Journal of Gastroenterology》 SCIE CAS 2024年第2期170-183,共14页
BACKGROUND Deep learning provides an efficient automatic image recognition method for small bowel(SB)capsule endoscopy(CE)that can assist physicians in diagnosis.However,the existing deep learning models present some ... BACKGROUND Deep learning provides an efficient automatic image recognition method for small bowel(SB)capsule endoscopy(CE)that can assist physicians in diagnosis.However,the existing deep learning models present some unresolved challenges.AIM To propose a novel and effective classification and detection model to automatically identify various SB lesions and their bleeding risks,and label the lesions accurately so as to enhance the diagnostic efficiency of physicians and the ability to identify high-risk bleeding groups.METHODS The proposed model represents a two-stage method that combined image classification with object detection.First,we utilized the improved ResNet-50 classification model to classify endoscopic images into SB lesion images,normal SB mucosa images,and invalid images.Then,the improved YOLO-V5 detection model was utilized to detect the type of lesion and its risk of bleeding,and the location of the lesion was marked.We constructed training and testing sets and compared model-assisted reading with physician reading.RESULTS The accuracy of the model constructed in this study reached 98.96%,which was higher than the accuracy of other systems using only a single module.The sensitivity,specificity,and accuracy of the model-assisted reading detection of all images were 99.17%,99.92%,and 99.86%,which were significantly higher than those of the endoscopists’diagnoses.The image processing time of the model was 48 ms/image,and the image processing time of the physicians was 0.40±0.24 s/image(P<0.001).CONCLUSION The deep learning model of image classification combined with object detection exhibits a satisfactory diagnostic effect on a variety of SB lesions and their bleeding risks in CE images,which enhances the diagnostic efficiency of physicians and improves the ability of physicians to identify high-risk bleeding groups. 展开更多
关键词 Artificial intelligence Deep learning Capsule endoscopy Image classification object detection Bleeding risk
下载PDF
Masked Autoencoders as Single Object Tracking Learners 被引量:1
16
作者 Chunjuan Bo XinChen Junxing Zhang 《Computers, Materials & Continua》 SCIE EI 2024年第7期1105-1122,共18页
Significant advancements have beenwitnessed in visual tracking applications leveragingViT in recent years,mainly due to the formidablemodeling capabilities of Vision Transformer(ViT).However,the strong performance of ... Significant advancements have beenwitnessed in visual tracking applications leveragingViT in recent years,mainly due to the formidablemodeling capabilities of Vision Transformer(ViT).However,the strong performance of such trackers heavily relies on ViT models pretrained for long periods,limitingmore flexible model designs for tracking tasks.To address this issue,we propose an efficient unsupervised ViT pretraining method for the tracking task based on masked autoencoders,called TrackMAE.During pretraining,we employ two shared-parameter ViTs,serving as the appearance encoder and motion encoder,respectively.The appearance encoder encodes randomly masked image data,while the motion encoder encodes randomly masked pairs of video frames.Subsequently,an appearance decoder and a motion decoder separately reconstruct the original image data and video frame data at the pixel level.In this way,ViT learns to understand both the appearance of images and the motion between video frames simultaneously.Experimental results demonstrate that ViT-Base and ViT-Large models,pretrained with TrackMAE and combined with a simple tracking head,achieve state-of-the-art(SOTA)performance without additional design.Moreover,compared to the currently popular MAE pretraining methods,TrackMAE consumes only 1/5 of the training time,which will facilitate the customization of diverse models for tracking.For instance,we additionally customize a lightweight ViT-XS,which achieves SOTA efficient tracking performance. 展开更多
关键词 Visual object tracking vision transformer masked autoencoder visual representation learning
下载PDF
Enhancing Dense Small Object Detection in UAV Images Based on Hybrid Transformer 被引量:1
17
作者 Changfeng Feng Chunping Wang +2 位作者 Dongdong Zhang Renke Kou Qiang Fu 《Computers, Materials & Continua》 SCIE EI 2024年第3期3993-4013,共21页
Transformer-based models have facilitated significant advances in object detection.However,their extensive computational consumption and suboptimal detection of dense small objects curtail their applicability in unman... Transformer-based models have facilitated significant advances in object detection.However,their extensive computational consumption and suboptimal detection of dense small objects curtail their applicability in unmanned aerial vehicle(UAV)imagery.Addressing these limitations,we propose a hybrid transformer-based detector,H-DETR,and enhance it for dense small objects,leading to an accurate and efficient model.Firstly,we introduce a hybrid transformer encoder,which integrates a convolutional neural network-based cross-scale fusion module with the original encoder to handle multi-scale feature sequences more efficiently.Furthermore,we propose two novel strategies to enhance detection performance without incurring additional inference computation.Query filter is designed to cope with the dense clustering inherent in drone-captured images by counteracting similar queries with a training-aware non-maximum suppression.Adversarial denoising learning is a novel enhancement method inspired by adversarial learning,which improves the detection of numerous small targets by counteracting the effects of artificial spatial and semantic noise.Extensive experiments on the VisDrone and UAVDT datasets substantiate the effectiveness of our approach,achieving a significant improvement in accuracy with a reduction in computational complexity.Our method achieves 31.9%and 21.1%AP on the VisDrone and UAVDT datasets,respectively,and has a faster inference speed,making it a competitive model in UAV image object detection. 展开更多
关键词 UAV images TRANSFORMER dense small object detection
下载PDF
Application of 3D Scanned Big Data of Large-scale Cultural Heritage Objects Based on Noise-robust Transparent Visualization
18
作者 Tanaka Satoshi 《系统仿真学报》 CAS CSCD 北大核心 2023年第8期1635-1650,共16页
Three-dimensional(3D) scanning technology has undergone remarkable developments in recent years.Data acquired by 3D scanning have the form of 3D point clouds.The 3D scanned point clouds have data sizes that can be con... Three-dimensional(3D) scanning technology has undergone remarkable developments in recent years.Data acquired by 3D scanning have the form of 3D point clouds.The 3D scanned point clouds have data sizes that can be considered big data.They also contain measurement noise inherent in measurement data.These properties of 3D scanned point clouds make many traditional CG/visualization techniques difficult.This paper reviewed our recent achievements in developing varieties of high-quality visualizations suitable for the visual analysis of 3D scanned point clouds.We demonstrated the effectiveness of the method by applying the visualizations to various cultural heritage objects.The main visualization targets used in this paper are the floats in the Gion Festival in Kyoto(the float parade is on the UNESCO Intangible Cultural Heritage List) and Borobudur Temple in Indonesia(a UNESCO World Heritage Site). 展开更多
关键词 3D scanning point cloud transparent visualization noise transparentization cultural heritage object
下载PDF
Role of Cannabinoid CB1 Receptor in Object Recognition Memory Impairment in Chronically Rapid Eye Movement Sleep-deprived Rats
19
作者 Kaveh Shahveisi Seyedeh Marziyeh Hadi +1 位作者 Hamed Ghazvini Mehdi Khodamoradi 《Chinese Medical Sciences Journal》 CAS CSCD 2023年第1期29-37,共9页
Objective We aimed to investigate whether antagonism of the cannabinoid CB1 receptor(CB1R)could affect novel object recognition(NOR)memory in chronically rapid eye movement sleep-deprived(RSD)rats.Methods The animals ... Objective We aimed to investigate whether antagonism of the cannabinoid CB1 receptor(CB1R)could affect novel object recognition(NOR)memory in chronically rapid eye movement sleep-deprived(RSD)rats.Methods The animals were examined for recognition memory following a 7-day chronic partial RSD paradigm using the multiple platform technique.The CB1R antagonist rimonabant(1 or 3 mg/kg,i.p.)was administered either at one hour prior to the sample phase for acquisition,or immediately after the sample phase for consolidation,or at one hour before the test phase for retrieval of NOR memory.For the reconsolidation task,rimonabant was administered immediately after the second sample phase.Results The RSD episode impaired acquisition,consolidation,and retrieval,but it did not affect the reconsolidation of NOR memory.Rimonabant administration did not affect acquisition,consolidation,and reconsolidation;however,it attenuated impairment of the retrieval of NOR memory induced by chronic RSD.Conclusions These findings,along with our previous report,would seem to suggest that RSD may affect different phases of recognition memory based on its duration.Importantly,it seems that the CB1R may,at least in part,be involved in the adverse effects of chronic RSD on the retrieval,but not in the acquisition,consolidation,and reconsolidation,of NOR memory. 展开更多
关键词 REM sleep deprivation novel object recognition memory cannabinoid CB1 receptor RIMONABANT
下载PDF
Automatic Examination of Condition of Used Books with YOLO-Based Object Detection Framework
20
作者 Sumin Hong Jin-Woo Jeong 《Computer Systems Science & Engineering》 SCIE EI 2023年第11期1611-1632,共22页
As the demand for used books has grown in recent years,various online/offline market platforms have emerged to support the trade in used books.The price of used books can depend on various factors,such as the state of... As the demand for used books has grown in recent years,various online/offline market platforms have emerged to support the trade in used books.The price of used books can depend on various factors,such as the state of preservation(i.e.,condition),the value of possession,and so on.Therefore,some online platforms provide a reference document to evaluate the condition of used books,but it is still not trivial for individual sellers to determine the price.The lack of a standard quantitative method to assess the condition of the used book would confuse both sellers and consumers,thereby decreasing the user experience of the online secondhand marketplace.Therefore,this paper discusses the automatic examination of the condition of used books based on deep learning approaches.In this work,we present a book damage detection system based on various You Only Look Once(YOLO)object detection models.Using YOLOv5,YOLOR,and YOLOX,we also introduce various training configurations that can be applied to improve performance.Specifically,a combination of different augmentation strategies including flip,rotation,crop,mosaic,and mixup was used for comparison.To train and validate our system,a book damage dataset composed of a total of 620 book images with 3,989 annotations,containing six types of damages(i.e.,Wear,Spot,Notch,Barcode,Tag,and Ripped),collected from the library books is presented.We evaluated each model trained with different configurations to figure out their detection accuracy as well as training efficiency.The experimental results showed that YOLOX trained with its best training configuration yielded the best performance in terms of detection accuracy,by achieving 60.0%(mAP@.5:.95)and 72.9%(mAP@.5)for book damage detection.However,YOLOX performed worst in terms of training efficiency,indicating that there is a trade-off between accuracy and efficiency.Based on the findings from the study,we discuss the feasibility and limitations of our system and future research directions. 展开更多
关键词 Deep learning object detection damage detection book damage
下载PDF
上一页 1 2 164 下一页 到第
使用帮助 返回顶部