计算机辅助设计与图形学学报最新文献_第2页

Survey on Visualization of Biomacromolecule 生物大分子可视化研究综述

计算机辅助设计与图形学学报 Pub Date : 2021-12-01 DOI: 10.3724/sp.j.1089.2021.19265

Dongliang Guo, Yanfen Wang, Yu Li, Ya. Guo, Ximing Xu, Junlan Nie

引用次数: 0

t-SNE for Complex Multi-Manifold High-Dimensional Data 复杂多流形高维数据的t-SNE

计算机辅助设计与图形学学报 Pub Date : 2021-11-01 DOI: 10.3724/sp.j.1089.2021.18806

Rongzhen Bian, Jian Zhang, Liang Zhou, Peng Jiang, Baoquan Chen, Yunhai Wang

引用次数: 0

Multi-Focus Image Fusion Based on Generative Adversarial Network 基于生成对抗网络的多焦点图像融合

计算机辅助设计与图形学学报 Pub Date : 2021-11-01 DOI: 10.3724/sp.j.1089.2021.18770

Liubing Jiang, Dian Zhang, Bo Pan, Peng Zheng, L. Che

引用次数: 1

Human-in-the-Loop Based Online Handwriting Mathematical Expressions Recognition 基于人在环的在线手写数学表达式识别

计算机辅助设计与图形学学报 Pub Date : 2021-11-01 DOI: 10.3724/sp.j.1089.2021.18796

Wenhui Kang, Jin Huang, Feng Tian, Xiangmin Fan, Jie Liu, G. Dai

引用次数: 0

RGB-D Image Saliency Detection Based on Cross-Model Feature Fusion 基于跨模型特征融合的RGB-D图像显著性检测

计算机辅助设计与图形学学报 Pub Date : 2021-11-01 DOI: 10.3724/sp.j.1089.2021.18710

Zheng Chen, Xiaoli Zhao, Jiaying Zhang, Mingchen Yin, Hanchen Ye, Haobin Zhou

引用次数: 0

Freehand-Sketched Part Recognition Using VGG-CapsNet 基于VGG CapsNet的手绘零件识别

计算机辅助设计与图形学学报 Pub Date : 2021-11-01 DOI: 10.3724/sp.j.1089.2021.18774

Zhongliang Yang, Ruihong Huang, Yumiao Chen, Song Zhang, Xinhua Mao

引用次数: 0

Automatic Measurement of Elongation at Break of Cable Sheath Based on Binocular Vision 基于双目视觉的电缆护套断裂伸长率自动测量

计算机辅助设计与图形学学报 Pub Date : 2021-11-01 DOI: 10.3724/sp.j.1089.2021.18779

G. Zhang, Jun Gong, Junsong Chen, Zhidong Zhang, Ce Zhu, Kai Liu

引用次数: 0

Ship Target Recognition Under Different Sunlight Intensity 不同日照强度下的船舶目标识别

计算机辅助设计与图形学学报 Pub Date : 2021-11-01 DOI: 10.3724/sp.j.1089.2021.18777

Kun Liu, L. Mi

{"title":"Ship Target Recognition Under Different Sunlight Intensity","authors":"Kun Liu, L. Mi","doi":"10.3724/sp.j.1089.2021.18777","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18777","url":null,"abstract":": In the case of surface target monitoring, the clarity of the ship target often varies with the reflec-tion intensity of the sea surface under different sunlight intensity, which will lead to the unstable recognition rate of the ship target and increase the false alarm rate. For this reason, the ship target recognition algorithm based on ResNet-50 is proposed. Firstly, it uses ResNet-50 network to extract image feature information and applies sunlight robust loss constraint to the features before and after sunlight intensity change to reduce the feature difference. Then, it uses gray-scale histogram to calculate the statistical matrices of features to obtain six features: light contrast, brightness, smoothness, information, third-order matrices and entropy, and gen-erates new feature vector to apply sunlight robust loss constraint to the features before and after sunlight intensity change again. Finally, the two constraints are combined to form a loss function and trained to opti-mize the optimal weights using Bayesian adaptive hyperparameters. The experimental results show that the average recognition rate of the database for ship sunlight variation reaches 90.47%, which is about 4.00% the and the recognition rate of ship images with sunlight variation of and increases by 3.14%, 6.07% and 16.41%, shows that the algorithm has a good constraint effect on sunlight variation and the recognition rate is significantly improved.","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43438275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Implicit Progressive-Iterative Algorithm of Curves and Surfaces with Compactly Supported Radial Basis Functions 紧支持径向基函数曲线曲面的隐式渐进迭代算法

计算机辅助设计与图形学学报 Pub Date : 2021-11-01 DOI: 10.3724/sp.j.1089.2021.18807

Haibo Wang, Tao Liu, Shengjun Liu, Wenyan Wei, Xinru Liu, Pingbo Liu, Yanyu Bai, Yue Chen

引用次数: 2

Hyperspectral Image Classification Based on SE-Res2Net and Multi-Scale Spatial Spectral Fusion Attention Mechanism 基于SE-Res2Net和多尺度空间光谱融合注意机制的高光谱图像分类

计算机辅助设计与图形学学报 Pub Date : 2021-11-01 DOI: 10.3724/sp.j.1089.2021.18778

Qin Xu, Yulian Liang, Dongyue Wang, B. Luo

{"title":"Hyperspectral Image Classification Based on SE-Res2Net and Multi-Scale Spatial Spectral Fusion Attention Mechanism","authors":"Qin Xu, Yulian Liang, Dongyue Wang, B. Luo","doi":"10.3724/sp.j.1089.2021.18778","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18778","url":null,"abstract":"In order to extract more discriminative features for hyperspectral image and prevent the network from degrading caused by deepening, a novel multi-scale feature extraction module SE-Res2Net based on the new dimensional residual network (Res2Net) and squeeze and exception network (SENet), and a multi-scale spectral-spatial fusion attention module is developed for hyperspectral image classification. In order to overcome the degradation problem caused by network deepening, the SE-Res2Net module uses channel grouping to extract fine-grained multi-scale features of hyperspectral images, and gets multiple receptive fields of different granularity. Then, the channel optimization module is employed to quantify the importance of the feature maps at the channel level. In order to optimize the features from spatial and spectral dimensions simultaneously, a multi-scale spectral-spatial fusion attention module is designed to mine the relationship between different spatial positions and different spectral dimensions at different scales using 第 11 期徐沁, 等: 基于 SE-Res2Net 与多尺度空谱融合注意力机制的高光谱图像分类 1727 asymmetric convolution, which can not only reduce the computation, but also effectively extract the discriminative spectral-spatial fusion features, and further improve the accuracy of hyperspectral image classification. Comparison experiments on three public datasets, Indian Pines, University of Pavia and Grss_dfc_2013 show that the proposed method has higher overall accuracy (OA), average accuracy (AA) and Kappa coefficient compared to other state-of-the-art deep networks.","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45625351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6