检索结果-南通市图书馆

Criss-Cross Attentional Siamese Networks for Object Tracking

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 2022年第11期73卷 2931-2946页

作者： Zhangdong Wang Jiaohua Qin xuyu xiang Yun Tan Neal N.Xiong College of Computer Science and Information Technology Central South University of Forestry&TechnologyChangsha410004China Department of Mathematics and Computer Science Northeastern State UniversityTahlequah74464OKUSA

Visual object tracking is a hot topic in recent years.In the meanwhile,Siamese networks have attracted extensive attention in this field because of its balanced precision and speed.However,most of the Siamese network methods can only distinguish foreground from the non-semantic background.The fine-tuning and retraining of fully-convolutional Siamese networks for object tracking(SiamFC)can achieve higher precision under interferences,but the tracking accuracy is still not ideal,especially in the environment with more target interferences,dim light,and shadows.In this paper,we propose crisscross attentional Siamese networks for object tracking(SiamCC).To solve the imbalance between foreground and non-semantic background,we use the feature enhancement module of criss-cross attention to greatly improve the accuracy of video object tracking in dim light and shadow environments.Experimental results show that the maximum running speed of SiamCC in the object tracking benchmark dataset is 90 frames/second.In terms of detection accuracy,the accuracy of shadow sequences is greatly improved,especially the accuracy score of sequence HUMAN8 is improved from 0.09 to 0.89 compared with the original SiamFC,and the success rate score is improved from 0.07 to 0.55.

关键词： Criss-cross attention object-tracking siamese-network

Aortic Dissection Diagnosis Based on Sequence Information and Deep Learning

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 2022年第11期73卷 2757-2771页

作者： Haikuo Peng Yun Tan Hao Tang Ling Tan xuyu xiang Yongjun Wang Neal N.Xiong Central South University of Forestry and Technology Changsha410004China The Second xiangya Hospital of Central South University Changsha410011China Department of Mathematics and Computer Science Northeastern State UniversityTahlequah74464USA

Aortic dissection(AD)is one of the most serious diseases with high mortality,and its diagnosis mainly depends on computed tomography(CT)results.Most existing automatic diagnosis methods of AD are only suitable for AD recognition,which usually require preselection of CT images and cannot be further classified to different types.In this work,we constructed a dataset of 105 cases with a total of 49021 slices,including 31043 slices expertlevel annotation and proposed a two-stage AD diagnosis structure based on sequence information and deep learning.The proposed region of interest(RoI)extraction algorithm based on sequence information(RESI)can realize high-precision for RoI identification in the first stage.Then DenseNet-121 is applied for further diagnosis.Specially,the proposed method can judge the type of AD without preselection of CT images.The experimental results show that the accuracy of Stanford typing classification of AD is 89.19%,and the accuracy at the slice-level reaches 97.41%,which outperform the state-ofart methods.It can provide important decision-making information for the determination of further surgical treatment plan for patients.

关键词： Aortic dissection deep learning sequence information RoI

基于Transformer双线性网络的细粒度图像分类方法

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

华中科技大学学报（自然科学版） 2024年第2期52卷 84-89页

作者：向旭宇刘亚捷曾彬谭云中南林业科技大学计算机与信息工程学院湖南长沙410000 长沙学院计算机科学与工程学院湖南长沙410000

为了改进在细粒度图像分类过程中类别差异难以提取的问题,提出了一种基于Transformer双线性网络的细粒度网络分类优化方法(BT-Net).首先,将输入图像通过不同卷积处理成不同长度的二维向量;然后,构建重复次数不同的编码器;最后,双网络分... 详细信息

为了改进在细粒度图像分类过程中类别差异难以提取的问题,提出了一种基于Transformer双线性网络的细粒度网络分类优化方法(BT-Net).首先,将输入图像通过不同卷积处理成不同长度的二维向量;然后,构建重复次数不同的编码器;最后,双网络分支将图像表示为来自两个Transformer的特征集合,得到更加丰富的互补特征信息,从而提高细粒度分类的精度.实验结果表明:在CUB-200-2011,Cars196和Stanford Dogs数据集中,BT-Net分类准确率分别为89.4%,92.5%,94.8%,优于已有的双线性卷积神经网络.

关键词：细粒度特征融合图像分类双线性 Transformer

An Encrypted Image Retrieval Method Based on SimHash in Cloud Computing

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2020年第4期63卷 389-399页

作者： Jiaohua Qin Yusi Cao xuyu xiang Yun Tan Lingyun xiang Jianjun Zhang College of Computer Science and Information Technology Central South University of Forestry&TechnologyChangsha410004China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China College of Engineering and Design Hunan Normal UniversityChangsha410012China

With the massive growth of images data and the rise of cloud computing that can provide cheap storage space and convenient access,more and more users store data in cloud server.However,how to quickly query the expected data with privacy-preserving is still a challenging in the encryption image data retrieval.Towards this goal,this paper proposes a ciphertext image retrieval method based on SimHash in cloud computing.Firstly,we extract local feature of images,and then cluster the features by K-means.Based on it,the visual word codebook is introduced to represent feature information of images,which hashes the codebook to the corresponding fingerprint.Finally,the image feature vector is generated by SimHash searchable encryption feature algorithm for similarity retrieval.Extensive experiments on two public datasets validate the effectiveness of our method.Besides,the proposed method outperforms one popular searchable encryption,and the results are competitive to the state-of-the-art.

关键词： Cloud computing SimHash encryption image retrieval K-means

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

基于语义分割的三维模型版权保护算法

华中科技大学学报（自然科学版） 2024年第2期52卷 49-54页

作者：秦姣华段振雄向旭宇谭云中南林业科技大学计算机与信息工程学院湖南长沙410004

为解决传统数字水印技术导致模型精度下降的问题,并保护局部版权,提出了一种基于语义分割的三维模型版权保护算法.首先,使用PointNet对三维模型进行语义分割,并根据分割结果将模型划分为子块,以子块为单位计算版权信息,保护局部版权;然... 详细信息

为解决传统数字水印技术导致模型精度下降的问题,并保护局部版权,提出了一种基于语义分割的三维模型版权保护算法.首先,使用PointNet对三维模型进行语义分割,并根据分割结果将模型划分为子块,以子块为单位计算版权信息,保护局部版权;然后,提出了一种基于顶点范数与表面曲率的版权信息生成算法.由于版权信息是使用无载体隐写方式生成的,因此该算法可以在不修改模型本身的情况下对模型整体及各子部件进行版权保护.实验证明:该算法在完全抵抗相似变换攻击的情况下,对其他种类攻击同样具有较好的鲁棒性.

关键词：三维模型点云模型版权保护无载体隐写 PointNet

An Adaptive Image Calibration Algorithm for Steganalysis

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2020年第2期62卷 963-976页

作者： xuyu xiang Jiaohua Qin Junshan Tan Neal N.Xiong 无 College of Computer Science and Information Technology Central South University of Forestry&TechnologyChangsha410114China Department of Mathematics and Computer Science Northeastern State UniversityOK74464USA

In this paper,a new adaptive calibration algorithm for image steganalysis is proposed.Steganography disturbs the dependence between neighboring pixels and decreases the neighborhood node degree.Firstly,we analyzed the effect of steganography on the neighborhood node degree of cover images.Then,the calibratable pixels are marked by the analysis of neighborhood node degree.Finally,the strong correlation calibration image is constructed by revising the calibratable pixels.Experimental results reveal that compared with secondary steganography the image calibration method significantly increased the detection accuracy for LSB matching steganography on low embedding ratio.The proposed method also has a better performance against spatial steganography.

关键词： Calibration algorithm neighborhood node degree ordinary pixel sensitive pixel steganalysis

Algorithm of Helmet Wearing Detection Based on AT-YOLO Deep Mode

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 2021年第10期69卷 159-174页

作者： Qingyang Zhou Jiaohua Qin xuyu xiang Yun Tan Neal NXiong College of Computer Science and Information Technology Central South University of Forestry&TechnologyChangsha410004China Department of Mathematics and Computer Science Northeastern State UniversityTahlequah74464OKUSA

The existing safety helmet detection methods are mainly based on one-stage object detection algorithms with high detection speed to reach the real-time detection requirements,but they can’t accurately detect small objects and objects with obstructions.Therefore,we propose a helmet detection algorithm based on the attention mechanism(AT-YOLO).First of all,a channel attention module is added to the YOLOv3 backbone network,which can adaptively calibrate the channel features of the direction to improve the feature utilization,and a spatial attention module is added to the neck of the YOLOv3 network to capture the correlation between any positions in the feature map so that to increase the receptive field of the network.Secondly,we use DIoU(Distance Intersection over Union)bounding box regression loss function,it not only improving the measurement of bounding box regression loss but also increases the normalized distance loss between the prediction boxes and the target boxes,which makes the network more accurate in detecting small objects and faster in convergence.Finally,we explore the training strategy of the network model,which improves network performance without increasing the inference cost.Experiments show that the mAP of the proposed method reaches 96.5%,and the detection speed can reach 27 fps.Compared with other existing methods,it has better performance in detection accuracy and speed.

关键词： Safety helmet detection attention mechanism convolutional neural network training strategies

Image Augmentation-Based Food Recognition with Convolutional Neural Networks

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 2019年第4期59卷 297-313页

作者： Lili Pan Jiaohua Qin Hao Chen xuyu xiang Cong Li Ran Chen College of Computer Science and Information Technology Central South University of Forestry and TechnologyChangsha410004China College of Computer Science and Electronic Engineering Hunan UniversityChangsha410082China

Image retrieval for food ingredients is important work,tremendously tiring,uninteresting,and expensive.Computer vision systems have extraordinary advancements in image retrieval with CNNs skills.But it is not feasible for small-size food datasets using convolutional neural networks directly.In this study,a novel image retrieval approach is presented for small and medium-scale food datasets,which both augments images utilizing image transformation techniques to enlarge the size of datasets,and promotes the average accuracy of food recognition with state-of-the-art deep learning technologies.First,typical image transformation techniques are used to augment food images.Then transfer learning technology based on deep learning is applied to extract image features.Finally,a food recognition algorithm is leveraged on extracted deepfeature vectors.The presented image-retrieval architecture is analyzed based on a smallscale food dataset which is composed of forty-one categories of food ingredients and one hundred pictures for each category.Extensive experimental results demonstrate the advantages of image-augmentation architecture for small and medium datasets using deep learning.The novel approach combines image augmentation,ResNet feature vectors,and SMO classification,and shows its superiority for food detection of small/medium-scale datasets with comprehensive experiments.

关键词： Image augmentation small-scale dataset deep feature deep learning convolutional neural network

Coverless Image Steganography Based on Image Segmentation

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 2020年第8期64卷 1281-1295页

作者： Yuanjing Luo Jiaohua Qin xuyu xiang Yun Tan Zhibin He Neal NXiong College of Computer Science and Information Technology Central South University of Forestry&TechnologyChangsha410114China Department of Mathematics and Computer Science Northeastern State UniversityTahlequah74464USA

To resist the risk of the stego-image being maliciously altered during transmission,we propose a coverless image steganography method based on image segmentation.Most existing coverless steganography methods are based on whole feature mapping,which has poor robustness when facing geometric attacks,because the contents in the image are easy to lost.To solve this problem,we use ResNet to extract semantic features,and segment the object areas from the image through Mask RCNN for information hiding.These selected object areas have ethical structural integrity and are not located in the visual center of the image,reducing the information loss of malicious attacks.Then,these object areas will be binarized to generate hash sequences for information mapping.In transmission,only a set of stego-images unrelated to the secret information are transmitted,so it can fundamentally resist steganalysis.At the same time,since both Mask RCNN and ResNet have excellent robustness,pre-training the model through supervised learning can achieve good performance.The robust hash algorithm can also resist attacks during transmission.Although image segmentation will reduce the capacity,multiple object areas can be extracted from an image to ensure the capacity to a certain extent.Experimental results show that compared with other coverless image steganography methods,our method is more robust when facing geometric attacks.

关键词： Coverless steganography semantic feature image segmentation Mask RCNN ResNet