检索结果-南通市图书馆

ED-Ged:Nighttime Image Semantic Segmentation Based on Enhanced Detail and Bidirectional Guidance

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第8期80卷 2443-2462页

作者： Xiaoli Yuan jianxun zhang Xuejie Wang Zhuhong Chu College of Computer Science and Engineering Chongqing University of TechnologyChongqing400054China

Semantic segmentation of driving scene images is crucial for autonomous *** deep learning technology has significantly improved daytime image semantic segmentation,nighttime images pose challenges due to factors like poor lighting and overexposure,making it difficult to recognize small *** address this,we propose an Image Adaptive Enhancement(IAEN)module comprising a parameter predictor(Edip),multiple image processing filters(Mdif),and a Detail Processing Module(DPM).Edip combines image processing filters to predict parameters like exposure and hue,optimizing image *** adopt a novel image encoder to enhance parameter prediction accuracy by enabling Edip to handle features at different *** strengthens overlooked image details,extending the IAEN module’s *** the segmentation network,we integrate a Depth Guided Filter(DGF)to refine segmentation *** entire network is trained end-to-end,with segmentation results guiding parameter prediction optimization,promoting self-learning and network *** lightweight and efficient network architecture is particularly suitable for addressing challenges in nighttime image *** experiments validate significant performance improvements of our approach on the ACDC-night and Nightcity datasets.

关键词： Night driving semantic segmentation nighttime image processing adverse illumination differentiable filters

YOLO-O2E:A Variant YOLO Model for Anomalous Rail Fastening Detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第7期80卷 1143-1161页

作者： Zhuhong Chu jianxun zhang Chengdong Wang Changhui Yang Department of Computer Science and Engineering Chongqing University of TechnologyChongqing400054China Institute of Flexible Electronics(Future Technologies) Xiamen UniversityXiamen361000China College of Mechanical Engineering Chongqing University of TechnologyChongqing400054China

Rail fasteners are a crucial component of the railway transportation safety *** fasteners,distinguished by their high length-to-width ratio,frequently encounter elevated failure rates,necessitating manual inspection and *** inspection not only consumes time but also poses the risk of potential *** the advancement of deep learning technology in rail fasteners,challenges such as the complex background of rail fasteners and the similarity in their states are *** have proposed an efficient and high-precision rail fastener detection algorithm,named YOLO-O2E(you only look once-O2E).Firstly,we propose the EFOV(Enhanced Field of View)structure,aiming to adjust the effective receptive field size of convolutional kernels to enhance insensitivity to small spatial ***,The OD_MP(ODConv and MP_2)and EMA(EfficientMulti-Scale Attention)modules mentioned in the algorithm can acquire a wider spectrum of contextual information,enhancing the model’s ability to recognize and locate ***,we collected and prepared the GKA dataset,sourced from real train *** testing on the GKA dataset and the publicly available NUE-DET dataset,our method outperforms general-purpose object detection *** the GKA dataset,our model achieved a mAP 0.5 value of 97.6%and a mAP 0.5:0.95 value of 83.9%,demonstrating excellent inference ***-O2E is an algorithm for detecting anomalies in railway fasteners that is applicable in practical industrial settings,addressing the industry gap in rail fastener detection.

关键词： Rail fastening detection deep learning anomalous rail fastening variant YOLO feature reinforcement

CVTD: A Robust Car-Mounted Video Text Detector

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第2期78卷 1821-1842页

作者： Di Zhou jianxun zhang Chao Li Yifan Guo Bowen Li Department of Computer Science and Engineering Chongqing University of TechnologyChongqingChina College of Information and Engineering Jingdezhen Ceramic UniversityJingdezhenChina

Text perception is crucial for understanding the semantics of outdoor scenes,making it a key requirement for building intelligent systems for driver assistance or autonomous *** information in car-mounted videos can assist drivers in making ***,Car-mounted video text images pose challenges such as complex backgrounds,small fonts,and the need for real-time *** proposed a robust Car-mounted Video Text Detector(CVTD).It is a lightweight text detection model based on ResNet18 for feature extraction,capable of detecting text in arbitrary *** model efficiently extracted global text positions through the Coordinate Attention Threshold Activation(CATA)and enhanced the representation capability through stacking two Feature Pyramid Enhancement Fusion Modules(FPEFM),strengthening feature representation,and integrating text local features and global position information,reinforcing the representation capability of the CVTD *** enhanced feature maps,when acted upon by Text Activation Maps(TAM),effectively distinguished text foreground from non-text ***,we collected and annotated a dataset containing 2200 images of Car-mounted Video Text(CVT)under various road conditions for training and evaluating our model’s *** further tested our model on four other challenging public natural scene text detection benchmark datasets,demonstrating its strong generalization ability and real-time detection *** model holds potential for practical applications in real-world scenarios.

关键词： Deep learning text detection Car-mounted video text detector intelligent driving assistance arbitrary shape text detector

BDPartNet: Feature Decoupling and Reconstruction Fusion Network for Infrared and Visible Image

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第6期79卷 4621-4639页

作者： Xuejie Wang jianxun zhang Ye Tao Xiaoli Yuan Yifan Guo Department of Computer Science and Engineering Chongqing University of TechnologyChongqing400054China Liangjiang Institute of Artificial Intelligence Chongqing University of TechnologyChongqing400054China

While single-modal visible light images or infrared images provide limited information,infrared light captures significant thermal radiation data,whereas visible light excels in presenting detailed texture ***-bining images obtained from both modalities allows for leveraging their respective strengths and mitigating individual limitations,resulting in high-quality images with enhanced contrast and rich texture *** capabilities hold promising applications in advanced visual tasks including target detection,instance segmentation,military surveillance,pedestrian detection,among *** paper introduces a novel approach,a dual-branch decomposition fusion network based on AutoEncoder(AE),which decomposes multi-modal features into intensity and texture information for enhanced *** contrast enhancement module(CEM)and texture detail enhancement module(DEM)are devised to process the decomposed images,followed by image fusion through the *** proposed loss function ensures effective retention of key information from the source images of both *** comparisons and generalization experiments demonstrate the superior performance of our network in preserving pixel intensity distribution and retaining texture *** the qualitative results,we can see the advantages of fusion details and local *** the quantitative experiments,entropy(EN),mutual information(MI),structural similarity(SSIM)and other results have improved and exceeded the SOTA(State of the Art)model as a whole.

关键词： Deep learning feature enhancement computer vision

激光选区熔化成形GH3536高温合金缺陷及质量控制

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

激光与光电子学进展 2024年第5期61卷 341-348页

作者：华文娟张建勋西安增材制造国家研究院有限公司陕西西安710065

为了研究激光选区熔化GH3536高温合金成形工艺对成形件内部缺陷类型、尺寸、数量的影响,采用激光选区熔化设备进行样件制备,对其进行抛光态观察和致密度、缺陷数量测试,并分析了合金的缺陷类型、尺寸分布及数量。研究表明:随着工艺参数... 详细信息

为了研究激光选区熔化GH3536高温合金成形工艺对成形件内部缺陷类型、尺寸、数量的影响,采用激光选区熔化设备进行样件制备,对其进行抛光态观察和致密度、缺陷数量测试,并分析了合金的缺陷类型、尺寸分布及数量。研究表明:随着工艺参数的改变,能量密度逐渐增加,成形件致密度逐渐增加,并趋于稳定。在79.17~92.59 J/mm^(3)的能量密度范围内,样件内部均匀致密,无缺陷;随着能量密度逐渐增大或者降低,样件内部主要为气孔型缺陷,气孔尺寸<0.1 mm。能量密度≤48.87 J/mm^(3)时,样件内部缺陷主要为未熔合及微裂纹。

关键词：激光选区熔化 GH3536高温合金工艺参数缺陷

基于蒙特卡洛法的Euler-Bernoulli梁基频和振型求解方法

在线全文

学校读者我要写书评

暂无评论

Journal of Southeast University(English Edition) 2024年第2期40卷 203-209页

作者：祝磊张建勋孙海林北京建筑大学北京未来城市设计高精尖创新中心北京100044 北京建筑大学土木与交通工程学院北京100044 中国建筑设计研究院有限公司北京100044

将Rayleigh法和蒙特卡洛法相结合,在Euler-Bernoulli梁理论假设下求解了均匀梁、变截面梁和附带集中质量的变截面梁自由振动问题.对原本连续的梁结构模型进行离散化处理,利用蒙特卡洛法给出梁结构的假设振型.将假设得到的梁结构振型函... 详细信息

将Rayleigh法和蒙特卡洛法相结合,在Euler-Bernoulli梁理论假设下求解了均匀梁、变截面梁和附带集中质量的变截面梁自由振动问题.对原本连续的梁结构模型进行离散化处理,利用蒙特卡洛法给出梁结构的假设振型.将假设得到的梁结构振型函数代入Rayleigh法,多次计算过程中,将历次基频所得值与计算所得最小值进行比较,根据其相对误差判断是否满足收敛条件,进而求得基频及对应的振型.结果表明,不同计算模型中基频最大误差不超过10%,能够满足工程需求,且精度和时间的控制参数调整灵活,使用者可根据自身需要自行调节.该方法理论简明,适用范围广泛,能够快速准确地求解诸多类型的梁结构基频和振型.

关键词： Euler-Bernoulli梁基频蒙特卡洛法数值解

在线全文

学校读者我要写书评

暂无评论

多智能体深度强化学习的图像特征分类方法

计算机工程与应用 2024年第7期60卷 222-228页

作者：张泽崴张建勋邹航李林南海重庆理工大学计算机科学与工程学院重庆400054

为解决在图像特征识别分类等机器学习任务中,存在输入图像数据复杂度过高且与部分数据与特征无关的问题,提出了一种多智能体深度强化学习的图像特征分类方法。将图像特征分类任务转化为一个部分可观测的马尔可夫决策过程。通过使用多个... 详细信息

为解决在图像特征识别分类等机器学习任务中,存在输入图像数据复杂度过高且与部分数据与特征无关的问题,提出了一种多智能体深度强化学习的图像特征分类方法。将图像特征分类任务转化为一个部分可观测的马尔可夫决策过程。通过使用多个移动的同构智能体去收集部分图像信息,并研究智能体如何形成对图像的局部理解并采取行动,以及如何从局部观察的图像中提取相关特征并分类,以此降低数据复杂性和过滤掉不相关数据。通过改进的值函数分解方法训练智能体策略网络,对环境的全局回报按照每个智能体的贡献进行拆分,解决智能体的信度分配问题。该方法在MNIST手写数字数据集和NWPU-RESISC45遥感图像数据集上进行了验证,相比基线算法能够学习到更加有效的联合策略,分类过程拥有更好的稳定性,同时精确率也有提升。

关键词：多智能体图像特征分类深度强化学习值函数分解

韧性大学校园的概念内涵、机制框架与规划实践路径

在线全文

学校读者我要写书评

暂无评论

灾害学 2024年第3期39卷 116-124页

作者：高昊冯刚张建勋张小寒天津大学建筑学院天津300072

厘清韧性大学校园的概念内涵、机制框架,并构建其规划实践路径,是深化韧性大学校园概念和推动韧性大学校园规划的重要抓手。通过综述当前韧性大学校园研究进展并引介韧性研究领域相关理论,探讨了复杂适应系统视角下的韧性大学校园概念内... 详细信息

厘清韧性大学校园的概念内涵、机制框架,并构建其规划实践路径,是深化韧性大学校园概念和推动韧性大学校园规划的重要抓手。通过综述当前韧性大学校园研究进展并引介韧性研究领域相关理论,探讨了复杂适应系统视角下的韧性大学校园概念内涵,构建了复合“压力-状态-响应”模型的韧性大学校园运行机制,并将大学校园韧性在制度、文化、生态、基础设施和空间五个维度进行解释。此外,基于迈向大学校园规划建设的思维转变,在韧性评价体系构建、韧性规划策略制定和现行相关规范完善等方面,提出了韧性大学校园规划的实践路径,以期解决当前大学校园语境下韧性理论与规划操作关联性不足的问题,并为相关研究提供参考和借鉴。

关键词：韧性韧性大学校园校园灾害 “压力-状态-响应”模型规划实践

在线全文

学校读者我要写书评

暂无评论

冻融循环作用下路基结构水热汽迁移规律研究

冰川冻土 2024年第1期46卷 170-184页

作者：张建勋毛雪松吴谦长安大学公路学院陕西西安710064

在冻融循环环境下,路基结构内水分迁移是导致道路冻胀、融沉变形的主要原因。为了探究冻融循环条件下路基结构的水热汽迁移规律,模拟了实际工程的路基结构,基于半透膜材料开展了冻融循环条件下的水、汽分离的水分迁移试验,通过监测试样... 详细信息

在冻融循环环境下,路基结构内水分迁移是导致道路冻胀、融沉变形的主要原因。为了探究冻融循环条件下路基结构的水热汽迁移规律,模拟了实际工程的路基结构,基于半透膜材料开展了冻融循环条件下的水、汽分离的水分迁移试验,通过监测试样的水热变化、荧光素上升图像、补水量和集水量变化曲线,得到了水分迁移规律,进而分析了土的孔隙结构、升降温速率和温度梯度等因素对水汽迁移和液态水流出特征的影响。试验结果表明,在土水势作用下,马氏瓶的水分首先以水-汽混合的形式在土柱中向上迁移,达到一定高度后,转变为以水汽的形式向上迁移。非饱和土柱的水汽会透过半透膜向碎石层和控温板底迁移,在整个冻融循环过程中,水汽向碎石层和控温板底的迁移量呈现线性增加的趋势,表明水汽迁移在水分聚集过程中的作用不可忽视。碎石层和控温板底液态水的流出主要集中在每个冻融周期的两个阶段,第一阶段为降温阶段,以冷凝水为主;第二阶段为融化阶段,以融化水为主,融化水占一个冻融周期液态水流出量的70%以上。粉质黏土孔隙较小导致水汽迁移主要受体积含气率的影响,随着粉质黏土土柱含水率的增加,水汽迁移量呈减小趋势。而砂土的孔隙较大,水汽迁移主要受水汽扩散增强因子的影响,随砂土土柱含水率的增加,水汽迁移量呈增大趋势。降温速率减小使冻结锋面有一个缓慢下移的过程,减小土体冻结对水汽迁移通道的封闭影响。升降温速率的减小导致碎石层和控温板底的水分聚集量增大。较大的温度梯度导致水汽扩散系数和水汽密度梯度的增加,从而引起碎石层和控温板底的水汽迁移量增大。

关键词：冻融循环路基结构半透膜水汽迁移孔隙结构升降温速率融化水