期刊文献+
共找到821篇文章
< 1 2 42 >
每页显示 20 50 100
A Survey of Crime Scene Investigation Image Retrieval Using Deep Learning
1
作者 Ying Liu Aodong Zhou +1 位作者 Jize Xue Zhijie Xu 《Journal of Beijing Institute of Technology》 EI CAS 2024年第4期271-286,共16页
Crime scene investigation(CSI)image is key evidence carrier during criminal investiga-tion,in which CSI image retrieval can assist the public police to obtain criminal clues.Moreover,with the rapid development of deep... Crime scene investigation(CSI)image is key evidence carrier during criminal investiga-tion,in which CSI image retrieval can assist the public police to obtain criminal clues.Moreover,with the rapid development of deep learning,data-driven paradigm has become the mainstreammethod of CSI image feature extraction and representation,and in this process,datasets provideeffective support for CSI retrieval performance.However,there is a lack of systematic research onCSI image retrieval methods and datasets.Therefore,we present an overview of the existing worksabout one-class and multi-class CSI image retrieval based on deep learning.According to theresearch,based on their technical functionalities and implementation methods,CSI image retrievalis roughly classified into five categories:feature representation,metric learning,generative adversar-ial networks,autoencoder networks and attention networks.Furthermore,We analyzed the remain-ing challenges and discussed future work directions in this field. 展开更多
关键词 crime scene investigation(CSI)image image retrieval deep learning
下载PDF
Preservation of the Crime Scene
2
作者 Besim Arifi 《Sociology Study》 2015年第8期628-632,共5页
Crime scene is any given place where it committed a criminal offense, in which the investigation should be done to find the causes and mechanisms of occurrence and on these to be investigated, for tracking and apprehe... Crime scene is any given place where it committed a criminal offense, in which the investigation should be done to find the causes and mechanisms of occurrence and on these to be investigated, for tracking and apprehension of perpetrators. Preservation of the scene is a very important action regarding the investigation and prosecution of the event that has happened, where law enforcement agencies or units that conduct surveillance of the scene make it. To preserve a scene means: to preserve the land in that state who has left the presidency. Preservation of the scene of that condition that has left the perpetrator is of particular importance to the inspection teams for tracks and material evidence found there are untouched and proceeding or their expertise will help prosecute perpetrators respectively capture of that work. Tracks and material evidence found in the scene should be retained together with all the space where the event happened because a possible carelessness during the examination as well as during the process of storage and security will bring us to a situation in which we will have our doubts concerning the tracks and material evidence found in that place. Also, preservation of the crime scene needs to be done because of the all action who have to take the searching unit, they need to be sure and security from everything that comes from outside. 展开更多
关键词 crime scene PRESERVaTION tracks and material evidence
下载PDF
Predicting the Type of Crime: Intelligence Gathering and Crime Analysis 被引量:3
3
作者 Saleh Albahli Anadil Alsaqabi +3 位作者 Fatimah Aldhubayi Hafiz Tayyab Rauf Muhammad Arif Mazin Abed Mohammed 《Computers, Materials & Continua》 SCIE EI 2021年第3期2317-2341,共25页
Crimes are expected to rise with an increase in population and the rising gap between society’s income levels.Crimes contribute to a significant portion of the socioeconomic loss to any society,not only through its i... Crimes are expected to rise with an increase in population and the rising gap between society’s income levels.Crimes contribute to a significant portion of the socioeconomic loss to any society,not only through its indirect damage to the social fabric and peace but also the more direct negative impacts on the economy,social parameters,and reputation of a nation.Policing and other preventive resources are limited and have to be utilized.The conventional methods are being superseded by more modern approaches of machine learning algorithms capable of making predictions where the relationships between the features and the outcomes are complex.Making it possible for such algorithms to provide indicators of specific areas that may become criminal hot-spots.These predictions can be used by policymakers and police personals alike to make effective and informed strategies that can curtail criminal activities and contribute to the nation’s development.This paper aims to predict factors that most affected crimes in Saudi Arabia by developing a machine learning model to predict an acceptable output value.Our results show that FAMD as features selection methods showed more accuracy on machine learning classifiers than the PCA method.The naïve Bayes classifier performs better than other classifiers on both features selections methods with an accuracy of 97.53%for FAMD,and PCA equals to 97.10%. 展开更多
关键词 PREDICTION machine learning crime prevention naïve bayes crime prediction classification algorithms
下载PDF
Learning Multi-Modality Features for Scene Classification of High-Resolution Remote Sensing Images 被引量:1
4
作者 Feng’an Zhao Xiongmei Zhang +2 位作者 Xiaodong Mu Zhaoxiang Yi Zhou Yang 《Journal of Computer and Communications》 2018年第11期185-193,共9页
Scene classification of high-resolution remote sensing (HRRS) image is an important research topic and has been applied broadly in many fields. Deep learning method has shown its high potential to in this domain, owin... Scene classification of high-resolution remote sensing (HRRS) image is an important research topic and has been applied broadly in many fields. Deep learning method has shown its high potential to in this domain, owing to its powerful learning ability of characterizing complex patterns. However the deep learning methods omit some global and local information of the HRRS image. To this end, in this article we show efforts to adopt explicit global and local information to provide complementary information to deep models. Specifically, we use a patch based MS-CLBP method to acquire global and local representations, and then we consider a pretrained CNN model as a feature extractor and extract deep hierarchical features from full-connection layers. After fisher vector (FV) encoding, we obtain the holistic visual representation of the scene image. We view the scene classification as a reconstruction procedure and train several class-specific stack denoising autoencoders (SDAEs) of corresponding class, i.e., one SDAE per class, and classify the test image according to the reconstruction error. Experimental results show that our combination method outperforms the state-of-the-art deep learning classification methods without employing fine-tuning. 展开更多
关键词 FEaTURE Fusion Multiple FEaTURES scene classification STaCK DENOISING autoencoder
下载PDF
Analysis of the Resolution of Crime Using Predictive Modeling 被引量:1
5
作者 Keshab R. Dahal Jiba N. Dahal +1 位作者 Kenneth R. Goward Oluremi Abayami 《Open Journal of Statistics》 2020年第3期600-610,共11页
There has been evidence of crime in the US since colonization. In this article, we analyze the crime statistics of San Francisco and its resolution of crime recorded from January to September of the year 2018. We defi... There has been evidence of crime in the US since colonization. In this article, we analyze the crime statistics of San Francisco and its resolution of crime recorded from January to September of the year 2018. We define resolution of crime as a target variable and study its relationship with other variables. We make several classification models to predict resolution of crime using several data mining techniques and suggest the best model for predicting resolution. 展开更多
关键词 Machine Learning classification Model Comparison Predictive Modeling Resolution of crime
下载PDF
TP-MobNet: A Two-pass Mobile Network for Low-complexity Classification of Acoustic Scene
6
作者 Soonshin Seo Junseok Oh +3 位作者 Eunsoo Cho Hosung Park Gyujin Kim Ji-Hwan Kim 《Computers, Materials & Continua》 SCIE EI 2022年第11期3291-3303,共13页
Acoustic scene classification(ASC)is a method of recognizing and classifying environments that employ acoustic signals.Various ASC approaches based on deep learning have been developed,with convolutional neural networ... Acoustic scene classification(ASC)is a method of recognizing and classifying environments that employ acoustic signals.Various ASC approaches based on deep learning have been developed,with convolutional neural networks(CNNs)proving to be the most reliable and commonly utilized in ASC systems due to their suitability for constructing lightweight models.When using ASC systems in the real world,model complexity and device robustness are essential considerations.In this paper,we propose a two-pass mobile network for low-complexity classification of the acoustic scene,named TP-MobNet.With inverse residuals and linear bottlenecks,TPMobNet is based on MobileNetV2,and following mobile blocks,coordinate attention and two-pass fusion approaches are utilized.The log-range dependencies and precise position information in feature maps can be trained via coordinate attention.By capturing more diverse feature resolutions at the network’s end sides,two-pass fusions can also train generalization.Also,the model size is reduced by applying weight quantization to the trained model.By adding weight quantization to the trained model,the model size is also lowered.The TAU Urban Acoustic Scenes 2020 Mobile development set was used for all of the experiments.It has been confirmed that the proposed model,with a model size of 219.6 kB,achieves an accuracy of 73.94%. 展开更多
关键词 acoustic scene classification LOW-COMPLEXITY device robustness two-pass mobile network coordinate attention weight quantization
下载PDF
面向遥感图像场景分类的LAG-MANet模型
7
作者 王威 郑薇 王新 《测绘学报》 EI CSCD 北大核心 2024年第7期1371-1383,共13页
遥感图像分类过程中,局部信息与全局信息至关重要。目前,遥感图像分类的方法主要包括卷积神经网络(CNN)及Transformer。CNN在局部信息提取方面具有优势,但在全局信息提取方面有一定的局限性。相比之下,Transformer在全局信息提取方面表... 遥感图像分类过程中,局部信息与全局信息至关重要。目前,遥感图像分类的方法主要包括卷积神经网络(CNN)及Transformer。CNN在局部信息提取方面具有优势,但在全局信息提取方面有一定的局限性。相比之下,Transformer在全局信息提取方面表现出色,但计算复杂度高。为提高遥感图像场景分类性能,降低复杂度,设计了LAG-MANet纯卷积网络。该网络既关注局部特征,又关注全局特征,并且考虑了多尺度特征。输入图像被预处理后,首先采用多分支扩张卷积模块(MBDConv)提取多尺度特征;然后依次进入网络的4个阶段,在每个阶段采用并行双域特征融合模块(P2DF)分支路提取局部、全局特征并进行融合;最后先经过全局平均池化、再经过全连接层输出分类标签。LAG-MANet在WHU-RS19数据集、SIRI-WHU数据集及RSSCN7数据集上的分类准确率分别为97.76%、97.04%、97.18%。试验结果表明,在3个具有挑战性的公开遥感数据集上,LAG-MANet更具有优越性。 展开更多
关键词 遥感图像 场景分类 CNN LaG-MaNet
下载PDF
基于双层DCT-Mask特征融合算法的堆叠垃圾实例分割
8
作者 李利 梁晶 +1 位作者 陈旭东 潘红光 《科学技术与工程》 北大核心 2024年第26期11341-11348,共8页
复杂堆叠场景下的垃圾实例分割受到严重遮挡和高密集性特点的影响,具有更大的检测难度。针对该问题,提出了一种结合DCT-Mask和双层特征融合网络思想的实例分割方法,用于高度堆叠场景下的垃圾实例分割。在网络结构层面,首先在数据预处理... 复杂堆叠场景下的垃圾实例分割受到严重遮挡和高密集性特点的影响,具有更大的检测难度。针对该问题,提出了一种结合DCT-Mask和双层特征融合网络思想的实例分割方法,用于高度堆叠场景下的垃圾实例分割。在网络结构层面,首先在数据预处理环节对特征数据进行解耦,并通过双分支特征融合降低堆叠对遮挡物体特征的影响,从而解决复杂堆叠遮挡下的实例分割问题。针对该场景下的密集混淆问题,在候选框分类回归部分融入了级联分类器,并优化了分割网络分支的损失函数。实验采用堆叠垃圾分类实例分割数据集进行实验验证,实验结果表明,该方法的AP_(50)、平均准确率mAP等指标有较大提升,且具有较好的分割效果和一定的可解释性。 展开更多
关键词 复杂堆叠遮挡场景 垃圾分类 双层特征融合网络 多级联检测器 损失函数优化
下载PDF
Deep Scalogram Representations for Acoustic Scene Classification 被引量:5
9
作者 Zhao Ren Kun Qian +3 位作者 Zixing Zhang Vedhas Pandit Alice Baird Bjorn Schuller 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2018年第3期662-669,共8页
Spectrogram representations of acoustic scenes have achieved competitive performance for acoustic scene classification. Yet, the spectrogram alone does not take into account a substantial amount of time-frequency info... Spectrogram representations of acoustic scenes have achieved competitive performance for acoustic scene classification. Yet, the spectrogram alone does not take into account a substantial amount of time-frequency information. In this study, we present an approach for exploring the benefits of deep scalogram representations, extracted in segments from an audio stream. The approach presented firstly transforms the segmented acoustic scenes into bump and morse scalograms, as well as spectrograms; secondly, the spectrograms or scalograms are sent into pre-trained convolutional neural networks; thirdly,the features extracted from a subsequent fully connected layer are fed into(bidirectional) gated recurrent neural networks, which are followed by a single highway layer and a softmax layer;finally, predictions from these three systems are fused by a margin sampling value strategy. We then evaluate the proposed approach using the acoustic scene classification data set of 2017 IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events(DCASE). On the evaluation set, an accuracy of 64.0 % from bidirectional gated recurrent neural networks is obtained when fusing the spectrogram and the bump scalogram, which is an improvement on the 61.0 % baseline result provided by the DCASE 2017 organisers. This result shows that extracted bump scalograms are capable of improving the classification accuracy,when fusing with a spectrogram-based system. 展开更多
关键词 acoustic scene classification(aSC) (bidirectional) gated recurrent neural networks((B) GRNNs) convolutional neural networks(CNNs) deep scalogram representation spectrogram representation
下载PDF
A More Efficient Approach for Remote Sensing Image Classification
10
作者 Huaxiang Song 《Computers, Materials & Continua》 SCIE EI 2023年第3期5741-5756,共16页
Over the past decade,the significant growth of the convolutional neural network(CNN)based on deep learning(DL)approaches has greatly improved the machine learning(ML)algorithm’s performance on the semantic scene clas... Over the past decade,the significant growth of the convolutional neural network(CNN)based on deep learning(DL)approaches has greatly improved the machine learning(ML)algorithm’s performance on the semantic scene classification(SSC)of remote sensing images(RSI).However,the unbalanced attention to classification accuracy and efficiency has made the superiority of DL-based algorithms,e.g.,automation and simplicity,partially lost.Traditional ML strategies(e.g.,the handcrafted features or indicators)and accuracy-aimed strategies with a high trade-off(e.g.,the multi-stage CNNs and ensemble of multi-CNNs)are widely used without any training efficiency optimization involved,which may result in suboptimal performance.To address this problem,we propose a fast and simple training CNN framework(named FST-EfficientNet)for RSI-SSC based on an EfficientNetversion2 small(EfficientNetV2-S)CNN model.The whole algorithm flow is completely one-stage and end-to-end without any handcrafted features or discriminators introduced.In the implementation of training efficiency optimization,only several routine data augmentation tricks coupled with a fixed ratio of resolution or a gradually increasing resolution strategy are employed,so that the algorithm’s trade-off is very cheap.The performance evaluation shows that our FST-EfficientNet achieves new state-of-the-art(SOTA)records in the overall accuracy(OA)with about 0.8%to 2.7%ahead of all earlier methods on the Aerial Image Dataset(AID)and Northwestern Poly-technical University Remote Sensing Image Scene Classification 45 Dataset(NWPU-RESISC45D).Meanwhile,the results also demonstrate the importance and indispensability of training efficiency optimization strategies for RSI-SSC by DL.In fact,it is not necessary to gain better classification accuracy by completely relying on an excessive trade-off without efficiency.Ultimately,these findings are expected to contribute to the development of more efficient CNN-based approaches in RSI-SSC. 展开更多
关键词 FST-EfficientNet efficient approach scene classification remote sensing deep learning
下载PDF
基于TomBERT的local-global社交平台多模态情感分类
11
作者 戴可玉 严华 《现代计算机》 2024年第11期50-54,共5页
随着自媒体时代的兴起,社交媒体上用户表达的情感和态度成为反映社会公众情感的重要信息源。然而,现有多模态情感分类方法在处理文字和图片融合时往往忽略了目标外的场景因素,影响了情感分类的准确性。针对此问题,提出基于TomBERT的loca... 随着自媒体时代的兴起,社交媒体上用户表达的情感和态度成为反映社会公众情感的重要信息源。然而,现有多模态情感分类方法在处理文字和图片融合时往往忽略了目标外的场景因素,影响了情感分类的准确性。针对此问题,提出基于TomBERT的local-global社交平台多模态情感分类模型,该模型以TomBERT模型为基础架构,将输入信息分为主体(local)和场景(global)两部分,分别进行图文匹配,通过多模态编码器获得最终的多模态隐藏表示后进行分类,充分考虑了主体信息与场景信息的关联,使用场景因素对主体进行特征增强,辅助情感分类。实验证明,基于TomBERT的local-global社交平台多模态情感分类模型较于传统方法,在捕捉模态间关系的同时,更全面地考虑了主体与场景的影响,提高了情感分类的准确性。 展开更多
关键词 情感分类 多模态 主体信息 场景信息 BERT
下载PDF
Natural Scene Classification Inspired by Visual Perception and Cognition Mechanisms
12
作者 ZHANG Rui 《重庆理工大学学报(自然科学)》 CAS 2011年第7期24-43,共20页
The process of human natural scene categorization consists of two correlated stages: visual perception and visual cognition of natural scenes.Inspired by this fact,we propose a biologically plausible approach for natu... The process of human natural scene categorization consists of two correlated stages: visual perception and visual cognition of natural scenes.Inspired by this fact,we propose a biologically plausible approach for natural scene image classification.This approach consists of one visual perception model and two visual cognition models.The visual perception model,composed of two steps,is used to extract discriminative features from natural scene images.In the first step,we mimic the oriented and bandpass properties of human primary visual cortex by a special complex wavelets transform,which can decompose a natural scene image into a series of 2D spatial structure signals.In the second step,a hybrid statistical feature extraction method is used to generate gist features from those 2D spatial structure signals.Then we design a cognitive feedback model to realize adaptive optimization for the visual perception model.At last,we build a multiple semantics based cognition model to imitate human cognitive mode in rapid natural scene categorization.Experiments on natural scene datasets show that the proposed method achieves high efficiency and accuracy for natural scene classification. 展开更多
关键词 natural scene classification visual perception model visual cognition model
下载PDF
Intelligent Deep Data Analytics Based Remote Sensing Scene Classification Model
13
作者 Ahmed Althobaiti Abdullah Alhumaidi Alotaibi +2 位作者 Sayed Abdel-Khalek Suliman A.Alsuhibany Romany F.Mansour 《Computers, Materials & Continua》 SCIE EI 2022年第7期1921-1938,共18页
Latest advancements in the integration of camera sensors paves a way for newUnmannedAerialVehicles(UAVs)applications such as analyzing geographical(spatial)variations of earth science in mitigating harmful environment... Latest advancements in the integration of camera sensors paves a way for newUnmannedAerialVehicles(UAVs)applications such as analyzing geographical(spatial)variations of earth science in mitigating harmful environmental impacts and climate change.UAVs have achieved significant attention as a remote sensing environment,which captures high-resolution images from different scenes such as land,forest fire,flooding threats,road collision,landslides,and so on to enhance data analysis and decision making.Dynamic scene classification has attracted much attention in the examination of earth data captured by UAVs.This paper proposes a new multi-modal fusion based earth data classification(MMF-EDC)model.The MMF-EDC technique aims to identify the patterns that exist in the earth data and classifies them into appropriate class labels.The MMF-EDC technique involves a fusion of histogram of gradients(HOG),local binary patterns(LBP),and residual network(ResNet)models.This fusion process integrates many feature vectors and an entropy based fusion process is carried out to enhance the classification performance.In addition,the quantum artificial flora optimization(QAFO)algorithm is applied as a hyperparameter optimization technique.The AFO algorithm is inspired by the reproduction and the migration of flora helps to decide the optimal parameters of the ResNet model namely learning rate,number of hidden layers,and their number of neurons.Besides,Variational Autoencoder(VAE)based classification model is applied to assign appropriate class labels for a useful set of feature vectors.The proposedMMF-EDCmodel has been tested using UCM and WHU-RS datasets.The proposed MMFEDC model attains exhibits promising classification results on the applied remote sensing images with the accuracy of 0.989 and 0.994 on the test UCM and WHU-RS dataset respectively. 展开更多
关键词 Remote sensing unmanned aerial vehicles deep learning artificial intelligence scene classification
下载PDF
Adaptive Binary Coding for Scene Classification Based on Convolutional Networks
14
作者 Shuai Wang Xianyi Chen 《Computers, Materials & Continua》 SCIE EI 2020年第12期2065-2077,共13页
With the rapid development of computer technology,millions of images are produced everyday by different sources.How to efficiently process these images and accurately discern the scene in them becomes an important but... With the rapid development of computer technology,millions of images are produced everyday by different sources.How to efficiently process these images and accurately discern the scene in them becomes an important but tough task.In this paper,we propose a novel supervised learning framework based on proposed adaptive binary coding for scene classification.Specifically,we first extract some high-level features of images under consideration based on available models trained on public datasets.Then,we further design a binary encoding method called one-hot encoding to make the feature representation more efficient.Benefiting from the proposed adaptive binary coding,our method is free of time to train or fine-tune the deep network and can effectively handle different applications.Experimental results on three public datasets,i.e.,UIUC sports event dataset,MIT Indoor dataset,and UC Merced dataset in terms of three different classifiers,demonstrate that our method is superior to the state-of-the-art methods with large margins. 展开更多
关键词 scene classification convolutional neural network one-hot encoding supervised feature training
下载PDF
遥感场景理解中视觉Transformer的参数高效微调
15
作者 尹文昕 于海琛 +2 位作者 刁文辉 孙显 付琨 《电子与信息学报》 EI CAS CSCD 北大核心 2024年第9期3731-3738,共8页
随着深度学习和计算机视觉技术的飞速发展,遥感场景分类任务对预训练模型的微调通常需要大量的计算资源。为了减少内存需求和训练成本,该文提出一种名为“多尺度融合适配器微调(MuFA)”的方法,用于遥感模型的微调。MuFA引入了一个多尺... 随着深度学习和计算机视觉技术的飞速发展,遥感场景分类任务对预训练模型的微调通常需要大量的计算资源。为了减少内存需求和训练成本,该文提出一种名为“多尺度融合适配器微调(MuFA)”的方法,用于遥感模型的微调。MuFA引入了一个多尺度融合模块,将不同下采样倍率的瓶颈模块相融合,并与原始视觉Transformer模型并联。在训练过程中,原始视觉Transformer模型的参数被冻结,只有MuFA模块和分类头会进行微调。实验结果表明,MuFA在UCM和NWPU-RESISC45两个遥感场景分类数据集上取得了优异的性能,超越了其他参数高效微调方法。因此,MuFA不仅保持了模型性能,还降低了资源开销,具有广泛的遥感应用前景。 展开更多
关键词 遥感图像 场景分类 参数高效 深度学习
下载PDF
双分支注意力与FasterNet相融合的航拍场景分类
16
作者 杨本臣 曲业田 金海波 《计算机系统应用》 2024年第5期15-27,共13页
航拍高分辨率图像的场景类别多且类间相似度高,经典的基于深度学习的分类方法,由于在提取特征过程中会产生冗余浮点运算,运行效率较低,FasterNet通过部分卷积提高了运行效率但会降低模型的特征提取能力,从而降低模型的分类精度.针对上... 航拍高分辨率图像的场景类别多且类间相似度高,经典的基于深度学习的分类方法,由于在提取特征过程中会产生冗余浮点运算,运行效率较低,FasterNet通过部分卷积提高了运行效率但会降低模型的特征提取能力,从而降低模型的分类精度.针对上述问题,提出了一种融合FasterNet和注意力机制的混合结构分类方法.首先采用“十字型卷积模块”对场景特征进行部分提取,以提高模型运行效率.然后采用坐标注意力与通道注意力相融合的双分支注意力机制,以增强模型对于特征的提取能力.最后将“十字型卷积模块”与双分支注意力模块之间进行残差连接,使网络能训练到更多与任务相关的特征,从而在提高分类精度的同时,减小运行代价,提高运行效率.实验结果表明,与现有基于深度学习的分类模型相比,所提出的方法,推理时间短而且准确率高,参数量为19M,平均一张图像的推理时间为7.1 ms,在公开的数据集NWPU-RESISC45、EuroSAT、VArcGIS (10%)和VArcGIS (20%)的分类精度分别为96.12%、98.64%、95.42%和97.87%,与FasterNet相比分别提升了2.06%、0.77%、1.34%和0.65%. 展开更多
关键词 遥感场景 图像分类 注意力机制 残差连接 FasterNet
下载PDF
基于CNN-Transformer半监督交叉学习的遥感图像场景分类方法
17
作者 单飞龙 吕鹏远 李梦晨 《宁夏大学学报(自然科学版)》 CAS 2024年第3期325-332,共8页
随着深度学习技术的发展,基于卷积神经网络(CNN)和Transformer的深度学习方法在全监督遥感图像场景分类任务中得到了广泛的关注与研究.然而,如何在标注样本有限的情况下实现良好的分类性能仍然具有挑战.考虑到CNN和Transformer在深度特... 随着深度学习技术的发展,基于卷积神经网络(CNN)和Transformer的深度学习方法在全监督遥感图像场景分类任务中得到了广泛的关注与研究.然而,如何在标注样本有限的情况下实现良好的分类性能仍然具有挑战.考虑到CNN和Transformer在深度特征提取方式上的差异,提出一种CNN和Transformer半监督交叉学习的遥感图像场景分类方法(SCL-CTNet),通过构建CNN和Transformer输出的一致性约束,更好地提取未标记数据中的信息,指导模型训练.半监督交叉学习方法将弱增强图像在一个网络上的输出作为伪标签用于监督强增强图像在另一个网络的预测结果,充分利用未标记样本的局部-全局信息,鼓励两个网络对相同输入图像预测间的一致性,提高模型泛化性.使用自适应阈值筛选伪标签,提高伪标签可靠性.在AID和NWPU-RESISC45数据集上的实验结果证明了所提出方法的有效性. 展开更多
关键词 高分辨率遥感图像 场景分类 卷积神经网络 TRaNSFORMER 半监督学习
下载PDF
Semi-supervised remote sensing image scene classification with prototype-based consistency
18
作者 Yang LI Zhang LI +2 位作者 Zi WANG Kun WANG Qifeng YU 《Chinese Journal of Aeronautics》 SCIE EI CAS CSCD 2024年第2期459-470,共12页
Deep learning significantly improves the accuracy of remote sensing image scene classification,benefiting from the large-scale datasets.However,annotating the remote sensing images is time-consuming and even tough for... Deep learning significantly improves the accuracy of remote sensing image scene classification,benefiting from the large-scale datasets.However,annotating the remote sensing images is time-consuming and even tough for experts.Deep neural networks trained using a few labeled samples usually generalize less to new unseen images.In this paper,we propose a semi-supervised approach for remote sensing image scene classification based on the prototype-based consistency,by exploring massive unlabeled images.To this end,we,first,propose a feature enhancement module to extract discriminative features.This is achieved by focusing the model on the foreground areas.Then,the prototype-based classifier is introduced to the framework,which is used to acquire consistent feature representations.We conduct a series of experiments on NWPU-RESISC45 and Aerial Image Dataset(AID).Our method improves the State-Of-The-Art(SOTA)method on NWPU-RESISC45 from 92.03%to 93.08%and on AID from 94.25%to 95.24%in terms of accuracy. 展开更多
关键词 Semi-supervised learning Remote sensing scene classification Prototype network Deep learning
原文传递
基于模糊共生网络的SAR遥感场景分类
19
作者 周易 卢延荣 《遥感信息》 CSCD 北大核心 2023年第6期103-109,共7页
合成孔径雷达(synthetic aperture radar,SAR)图像的场景分类被广泛运用于军事和民用领域,而合成孔径雷达图像存在场景复杂、图像分辨率低等特点,使其准确分类成为挑战。由此,文章提出基于模糊共生网络的合成孔径雷达图像场景分类方法... 合成孔径雷达(synthetic aperture radar,SAR)图像的场景分类被广泛运用于军事和民用领域,而合成孔径雷达图像存在场景复杂、图像分辨率低等特点,使其准确分类成为挑战。由此,文章提出基于模糊共生网络的合成孔径雷达图像场景分类方法。该方法的ML-Net(multi layer convolutional network)模块可提取合成孔径雷达图像的低分辨特征,模糊灰度共生矩阵模块则能多角度融合4组二阶统计量提取合成孔径雷达图像的纹理特征,并输入至多类支持向量机完成场景分类。选用Terra SAR-X和GS-SAR6数据集完成该方法与全频通道注意力网络和多特征融合全局-局部卷积网络的实验。对比结果可知,该方法的准确率与Kappa值较高,可获得更小的初始损失值、更高的训练准确率和更快的收敛速度。 展开更多
关键词 SaR图像 场景 分类 GLCM SVM 准确率
下载PDF
基于RetinaNet的红枣果实分类检测研究
20
作者 郭新东 邓玄龄 孙瑜 《安徽农业科学》 CAS 2023年第16期226-229,264,共5页
为解决不同成熟度红枣图像中多尺度红枣目标检测问题,以自然场景下获取的红枣图像为研究对象,首先建立包含不同成熟度红枣图像数据集;然后以骨干网络ResNet50和特征金字塔网络作为特征提取器,连接2个相似结构的分类子网和回归子网,以Foc... 为解决不同成熟度红枣图像中多尺度红枣目标检测问题,以自然场景下获取的红枣图像为研究对象,首先建立包含不同成熟度红枣图像数据集;然后以骨干网络ResNet50和特征金字塔网络作为特征提取器,连接2个相似结构的分类子网和回归子网,以Focal Loss为损失函数,建立基于RetinaNet的红枣成熟度分类检测模型。结果表明,基于RetinaNet红枣成熟度检测模型对红枣4种成熟度分类检测平均精度均值为74.235%,满足农业生产基本要求,该研究为智能检测红枣果实及自动化采摘可行性提供了技术参考。 展开更多
关键词 深度学习 RetinaNet 红枣 成熟度检测 自然场景
下载PDF
上一页 1 2 42 下一页 到第
使用帮助 返回顶部