Pub Date : 2021-05-01DOI: 10.3724/sp.j.1089.2021.18581
Shuo Zhang, Q. Ye, Jing Shi, Hang Liu
{"title":"A Semantic Segmentation Method of In-Vehicle Small Targets Point CloudBased on Improved RangeNet++ Loss Function","authors":"Shuo Zhang, Q. Ye, Jing Shi, Hang Liu","doi":"10.3724/sp.j.1089.2021.18581","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18581","url":null,"abstract":"","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41245708","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}
Pub Date : 2021-05-01DOI: 10.3724/sp.j.1089.2021.18556
Zhigeng Pan, Jiali Gao, Ruonan Wang, Qingshu Yuan, Ran Fan, Ling She
: In spatial augmented reality (SAR) systems supporting tangible interaction, user interactions can cause rapid changes in orientation and position of interaction objects. To ensure the efficiency and accuracy of registration during objects movements, a digital twin registration technique for SAR is proposed. Models are made in the digital space and their geometric parameters are entirely consistent with the objects in the physical space. The orientation and position parameters of the physical objects are tracked in real-time during user interaction. Then the digital objects are adjusted according the parameters. Moreover, intrinsic and extrinsic parameters of the pro-jector, which are calibrated in advance, are used to set the virtual camera in the digital space. The projection pat-terns are rendered in that virtual camera and then projected onto the interaction objects. The efficiency and accuracy are evaluated in the middle school physical experiment learning magnetic induction line based on the projection interaction tabletop, which meet the requirements of tangible interaction in SAR systems.
{"title":"Digital Twin Registration Technique of Spatial Augmented Reality for Tangible Interaction","authors":"Zhigeng Pan, Jiali Gao, Ruonan Wang, Qingshu Yuan, Ran Fan, Ling She","doi":"10.3724/sp.j.1089.2021.18556","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18556","url":null,"abstract":": In spatial augmented reality (SAR) systems supporting tangible interaction, user interactions can cause rapid changes in orientation and position of interaction objects. To ensure the efficiency and accuracy of registration during objects movements, a digital twin registration technique for SAR is proposed. Models are made in the digital space and their geometric parameters are entirely consistent with the objects in the physical space. The orientation and position parameters of the physical objects are tracked in real-time during user interaction. Then the digital objects are adjusted according the parameters. Moreover, intrinsic and extrinsic parameters of the pro-jector, which are calibrated in advance, are used to set the virtual camera in the digital space. The projection pat-terns are rendered in that virtual camera and then projected onto the interaction objects. The efficiency and accuracy are evaluated in the middle school physical experiment learning magnetic induction line based on the projection interaction tabletop, which meet the requirements of tangible interaction in SAR systems.","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42999616","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}
Pub Date : 2021-05-01DOI: 10.3724/sp.j.1089.2021.18514
Hao Yang, Yingzhen Yu
Existing deep-learning-based inpainting methods may have some shortcomings in perceiving and presenting image information at multi-scales. For this problem, we proposed an image inpainting model based on multi-scale channel attention and a hierarchical residual backbone network. Firstly, we adopted a U-Net architecture as the generator backbone of our inpainting model to encode and decode the damaged image. Secondly, we built multi-scale hierarchical residual structures in the encoder and decoder respectively, which can improve the ability of the model to extract and express occluded image features. Finally, we designed a dilated multi-scale channel-attention block and inserted it into the skip-connection of the generator. This block can improve the utilization efficiency of low-level features in the encoder. Experimental results show that our model outperforms other classical inpainting approaches in the face, street-view inpainting tasks, both qualitatively and quantitatively.
{"title":"Image Inpainting Using Channel Attention and Hierarchical Residual Networks","authors":"Hao Yang, Yingzhen Yu","doi":"10.3724/sp.j.1089.2021.18514","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18514","url":null,"abstract":"Existing deep-learning-based inpainting methods may have some shortcomings in perceiving and presenting image information at multi-scales. For this problem, we proposed an image inpainting model based on multi-scale channel attention and a hierarchical residual backbone network. Firstly, we adopted a U-Net architecture as the generator backbone of our inpainting model to encode and decode the damaged image. Secondly, we built multi-scale hierarchical residual structures in the encoder and decoder respectively, which can improve the ability of the model to extract and express occluded image features. Finally, we designed a dilated multi-scale channel-attention block and inserted it into the skip-connection of the generator. This block can improve the utilization efficiency of low-level features in the encoder. Experimental results show that our model outperforms other classical inpainting approaches in the face, street-view inpainting tasks, both qualitatively and quantitatively.","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44793879","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}
Pub Date : 2021-05-01DOI: 10.3724/sp.j.1089.2021.18636
Zhenzhong Kuang, Jie Yang, Jun Yu
{"title":"Unsupervised 3D Object Retrieval in Loop View","authors":"Zhenzhong Kuang, Jie Yang, Jun Yu","doi":"10.3724/sp.j.1089.2021.18636","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18636","url":null,"abstract":"","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46435264","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}
Pub Date : 2021-04-01DOI: 10.3724/sp.j.1089.2021.18810
Danny Cheng, Yunhai Wang
: A visual analysis system called STVAS is presented to help users explore and analyze data collected from search engines, which includes data collection and preprocessing, calculation of streamgraph, generation of streamlines and text placement, along with interactive analysis. It presents a visualization method that combines streamgraph and text to reveal search trends and hotspots. To guide the text placement within streamgraph, this system uses a novel layout algorithm with streamlines generated from the vector field inside the streamgraph. In addition, a set of interactions is offered to help user explore and analyze data on different levels. Quantitative evaluation of the visualization method is made on five blog datasets, and case studies on two real search datasets. The results demonstrate that this system can help users understand the evolving pattern of search engine data, discover the implicit search trends, and quickly grasp public opinions from the Internet.
{"title":"Visual Analysis System for Search Trend Data","authors":"Danny Cheng, Yunhai Wang","doi":"10.3724/sp.j.1089.2021.18810","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18810","url":null,"abstract":": A visual analysis system called STVAS is presented to help users explore and analyze data collected from search engines, which includes data collection and preprocessing, calculation of streamgraph, generation of streamlines and text placement, along with interactive analysis. It presents a visualization method that combines streamgraph and text to reveal search trends and hotspots. To guide the text placement within streamgraph, this system uses a novel layout algorithm with streamlines generated from the vector field inside the streamgraph. In addition, a set of interactions is offered to help user explore and analyze data on different levels. Quantitative evaluation of the visualization method is made on five blog datasets, and case studies on two real search datasets. The results demonstrate that this system can help users understand the evolving pattern of search engine data, discover the implicit search trends, and quickly grasp public opinions from the Internet.","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49405355","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}
Pub Date : 2021-04-01DOI: 10.3724/sp.j.1089.2021.18525
Shangluan Xie, Yinshui Xia, Xiaojing Zha
Aiming at the power consumption increase problem from the defects of CMOS/nanowire/ molecular hybrid (CMOL) circuits, a defect-tolerant mapping method based on cell limitation is proposed. First, the power consumption model of defect pairs is established and the effect of different mapping patterns of the defect pairs on power consumption is analyzed. Then, the use of power hungry cells is restricted and the power consumption constraint is set to reduce the power consumption overhead caused by the high cost mapping patterns. Finally, the modified genetic algorithm is chosen to implement the defect-tolerant mapping of CMOL circuits. The ISCAS benchmarks are tested for verification. The experimental results demonstrated that the proposed method effectively reduces the power consumption and area of CMOL circuits on the basis of successful defect-tolerance, with better optimization of solution speed.
{"title":"Power Oriented Optimization for the Defect-Tolerant Mapping of CMOL Circuits","authors":"Shangluan Xie, Yinshui Xia, Xiaojing Zha","doi":"10.3724/sp.j.1089.2021.18525","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18525","url":null,"abstract":"Aiming at the power consumption increase problem from the defects of CMOS/nanowire/ molecular hybrid (CMOL) circuits, a defect-tolerant mapping method based on cell limitation is proposed. First, the power consumption model of defect pairs is established and the effect of different mapping patterns of the defect pairs on power consumption is analyzed. Then, the use of power hungry cells is restricted and the power consumption constraint is set to reduce the power consumption overhead caused by the high cost mapping patterns. Finally, the modified genetic algorithm is chosen to implement the defect-tolerant mapping of CMOL circuits. The ISCAS benchmarks are tested for verification. The experimental results demonstrated that the proposed method effectively reduces the power consumption and area of CMOL circuits on the basis of successful defect-tolerance, with better optimization of solution speed.","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44425110","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}
Pub Date : 2021-04-01DOI: 10.3724/sp.j.1089.2021.18542
Hailong Hu, Zhong Li, S. Qin, Li-zhuang Ma
Local self-similarity of 3D model is a fundamental problem in the shape analysis. The construction of a local shape descriptor is very important to the final result of self-similarity analysis. To solve this problem, a self-similarity analysis method based on the tensor fusion feature descriptor is proposed. Firstly, the shape diameter function (SDF) of a point cloud model is approximately calculated by using relevant facets and antipodal points. Then, spectral clustering is used to segment the model into sub-blocks, and the three-dimensional feature tensor is constructed from the SDF, shape index (SI) and Gauss curvature (GS) matrix of KNN neighborhood points. Finally, the shape descriptor is obtained by constructing the mapping with the tensor norm, and then the similarity measure is defined and the self-similarity between the sub-blocks of the model is analyzed. Several state-of-the-art methods (including partial matching and saliency detection) are 第 4 期 胡海龙, 等: 三维点云模型特征张量描述符的构造及自相似性分析 591 tested. In terms of not only the visual effect, but also the similarity measure and the relative errors, the results show that this method can effectively describe the shape and improves the recognition accuracy of similar sub-blocks of a point cloud model.
{"title":"Construction of Feature Tensor Descriptor and Self-Similarity Analysis for 3D Point Cloud Models","authors":"Hailong Hu, Zhong Li, S. Qin, Li-zhuang Ma","doi":"10.3724/sp.j.1089.2021.18542","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18542","url":null,"abstract":"Local self-similarity of 3D model is a fundamental problem in the shape analysis. The construction of a local shape descriptor is very important to the final result of self-similarity analysis. To solve this problem, a self-similarity analysis method based on the tensor fusion feature descriptor is proposed. Firstly, the shape diameter function (SDF) of a point cloud model is approximately calculated by using relevant facets and antipodal points. Then, spectral clustering is used to segment the model into sub-blocks, and the three-dimensional feature tensor is constructed from the SDF, shape index (SI) and Gauss curvature (GS) matrix of KNN neighborhood points. Finally, the shape descriptor is obtained by constructing the mapping with the tensor norm, and then the similarity measure is defined and the self-similarity between the sub-blocks of the model is analyzed. Several state-of-the-art methods (including partial matching and saliency detection) are 第 4 期 胡海龙, 等: 三维点云模型特征张量描述符的构造及自相似性分析 591 tested. In terms of not only the visual effect, but also the similarity measure and the relative errors, the results show that this method can effectively describe the shape and improves the recognition accuracy of similar sub-blocks of a point cloud model.","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48482414","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}
Pub Date : 2021-04-01DOI: 10.3724/SP.J.1089.2021.18663
Jianfei Cao, Jincheng Yu, S. Pan, Feng Gao, Chao Yu, Zhilin Xu, Zhengfeng Huang, Yu Wang
, Abstract: Backend trajectory optimization is an important part of the visual simultaneous localization and mapping system, which can significantly improve localization accuracy. However, the existing optimization methods based on the bundle adjustment have a large amount of calculation in large scenes and cannot be applied to end-to-end visual odometries. To solve this problem, a universal backend pose graph optimization algorithm with two visual odometries at the front end is proposed, which can be applied to end-to-end visual odometries. This method uses a high-speed but low-precision end-to-end visual odometry to run at high frequency, while a low-speed but high-precision visual odometry runs at a low frequency. Local optimization uses Gauss-Newton method iterative optimization through the constraints provided by two odometries. Global optimization is per-formed simultaneously which based on key frames scene matching. Experiments show that the simultaneous localization and mapping system which apply this optimization method can run in real-time on the KITTI dataset. Compared with the two visual odometries, the accuracy has been greatly improved. And compared with several well-known open source simultaneous localization and mapping methods that apply backend trajectory optimization, low errors have been achieved in trajectory error, absolute translational error, rotation error and rela-tive pose error, taking into account the advantages of the accuracy of traditional methods and the advantages of high speed end-to-end methods. In addition, the optimization framework can also be applied to other more visual odometries.
{"title":"A SLAM Pose Graph Optimization Method Using Dual Visual Odometry","authors":"Jianfei Cao, Jincheng Yu, S. Pan, Feng Gao, Chao Yu, Zhilin Xu, Zhengfeng Huang, Yu Wang","doi":"10.3724/SP.J.1089.2021.18663","DOIUrl":"https://doi.org/10.3724/SP.J.1089.2021.18663","url":null,"abstract":", Abstract: Backend trajectory optimization is an important part of the visual simultaneous localization and mapping system, which can significantly improve localization accuracy. However, the existing optimization methods based on the bundle adjustment have a large amount of calculation in large scenes and cannot be applied to end-to-end visual odometries. To solve this problem, a universal backend pose graph optimization algorithm with two visual odometries at the front end is proposed, which can be applied to end-to-end visual odometries. This method uses a high-speed but low-precision end-to-end visual odometry to run at high frequency, while a low-speed but high-precision visual odometry runs at a low frequency. Local optimization uses Gauss-Newton method iterative optimization through the constraints provided by two odometries. Global optimization is per-formed simultaneously which based on key frames scene matching. Experiments show that the simultaneous localization and mapping system which apply this optimization method can run in real-time on the KITTI dataset. Compared with the two visual odometries, the accuracy has been greatly improved. And compared with several well-known open source simultaneous localization and mapping methods that apply backend trajectory optimization, low errors have been achieved in trajectory error, absolute translational error, rotation error and rela-tive pose error, taking into account the advantages of the accuracy of traditional methods and the advantages of high speed end-to-end methods. In addition, the optimization framework can also be applied to other more visual odometries.","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42660500","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}
Pub Date : 2021-04-01DOI: 10.3724/sp.j.1089.2021.18811
Chen Bao, Yunhai Wang
: Word cloud is a popular text visualization technique that extracts keywords from text and displays them on the 2D space aesthetically. Word cloud is often used to display contents, aid text analysis and attract readers. In this work, the design space of word cloud is introduced from three aspects: visual encoding, layout and interaction. Then current word cloud design researches are summarized by four categories: semantic word clouds, shape-constrained word clouds, interactive word clouds and multi-document word clouds. Several works related to word cloud evaluation are also concluded. Finally, research challenges in semantic word clouds, shape-con-strained word clouds, multi-document word clouds and Chinese word clouds, and suggest future work of word cloud visualization are discussed.
{"title":"A Survey of Word Cloud Visualization","authors":"Chen Bao, Yunhai Wang","doi":"10.3724/sp.j.1089.2021.18811","DOIUrl":"https://doi.org/10.3724/sp.j.1089.2021.18811","url":null,"abstract":": Word cloud is a popular text visualization technique that extracts keywords from text and displays them on the 2D space aesthetically. Word cloud is often used to display contents, aid text analysis and attract readers. In this work, the design space of word cloud is introduced from three aspects: visual encoding, layout and interaction. Then current word cloud design researches are summarized by four categories: semantic word clouds, shape-constrained word clouds, interactive word clouds and multi-document word clouds. Several works related to word cloud evaluation are also concluded. Finally, research challenges in semantic word clouds, shape-con-strained word clouds, multi-document word clouds and Chinese word clouds, and suggest future work of word cloud visualization are discussed.","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47223244","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：