Pub Date : 2017-10-01DOI: 10.1109/ICVRV.2017.00034
Xiang Nan, Zhang Mingmin, Long Jianwu
Multi-events driven emotion generation was an important research point in the affective computing field. However, as the events have different types and occurred in variable times, then computing the emotion state intensity became a challenge. The existed solutions for this problem did not take time influences of different event types into consideration. In order to solve this problem, we provided a Hawkes process based multi-events driven emotion generation method. Firstly we appraised every event and generate the related emotional reaction; secondly, we treated the emotion generation process with a certain period as a point process and trained the parameters of Hawkes process by maximum likelihood estimation with real individual emotional reactions; thirdly, we used Hawkes process to simulate the accumulated emotion reactions. The experimental results showed that our method can generate a multi-events driven emotion more accurately and efficiently.
{"title":"Multi-events Driven Emotion Dynamic Generation Using Hawkes Process","authors":"Xiang Nan, Zhang Mingmin, Long Jianwu","doi":"10.1109/ICVRV.2017.00034","DOIUrl":"https://doi.org/10.1109/ICVRV.2017.00034","url":null,"abstract":"Multi-events driven emotion generation was an important research point in the affective computing field. However, as the events have different types and occurred in variable times, then computing the emotion state intensity became a challenge. The existed solutions for this problem did not take time influences of different event types into consideration. In order to solve this problem, we provided a Hawkes process based multi-events driven emotion generation method. Firstly we appraised every event and generate the related emotional reaction; secondly, we treated the emotion generation process with a certain period as a point process and trained the parameters of Hawkes process by maximum likelihood estimation with real individual emotional reactions; thirdly, we used Hawkes process to simulate the accumulated emotion reactions. The experimental results showed that our method can generate a multi-events driven emotion more accurately and efficiently.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133883198","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 : 2017-10-01DOI: 10.1109/ICVRV.2017.00063
Hao Jiang, Chang Gao, Tianlu Mao, Hui Li, Zhaoqi Wang
In recent years there has been an increasing interest in human-computer interaction research in large display systems. We contribute with a design of efficient group interaction technique and application to a large display by using optical technology to track the markers on users' hands. Participants were asked to execute predefined interaction actions based on the contents of the application screen. With the help of well-designed interaction processes and algorithms, our system can receive response signals of multiple users and then trigger corresponding actions in real-time. Moreover, we designed a performance experiment to evaluate the recognition and response results from practical application. The experiment results demonstrate that, although integrating group interaction into large display system, this framework can effectively support user's participation in large display.
{"title":"Efficiency Group Interaction Between Participants and Large Display","authors":"Hao Jiang, Chang Gao, Tianlu Mao, Hui Li, Zhaoqi Wang","doi":"10.1109/ICVRV.2017.00063","DOIUrl":"https://doi.org/10.1109/ICVRV.2017.00063","url":null,"abstract":"In recent years there has been an increasing interest in human-computer interaction research in large display systems. We contribute with a design of efficient group interaction technique and application to a large display by using optical technology to track the markers on users' hands. Participants were asked to execute predefined interaction actions based on the contents of the application screen. With the help of well-designed interaction processes and algorithms, our system can receive response signals of multiple users and then trigger corresponding actions in real-time. Moreover, we designed a performance experiment to evaluate the recognition and response results from practical application. The experiment results demonstrate that, although integrating group interaction into large display system, this framework can effectively support user's participation in large display.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132974810","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 : 2017-10-01DOI: 10.1109/ICVRV.2017.00117
Jiaqi Wang, Yongting Wang, Feng Yang
In order to assist the military operator to make accurate analysis of the situation in the modern war, which has the characteristics of large amount of information. Based on ArcGIS Engine, in this paper, a modular two-dimensional battlefield situation display system is designed and implemented. The function of each module in the system is discussed and analyzed, then some key technologies of the system are introduced. The demonstration results show the validation of the situation display system.
{"title":"Development of Battlefield Situation Display System Based on ArcGIS Engine Software","authors":"Jiaqi Wang, Yongting Wang, Feng Yang","doi":"10.1109/ICVRV.2017.00117","DOIUrl":"https://doi.org/10.1109/ICVRV.2017.00117","url":null,"abstract":"In order to assist the military operator to make accurate analysis of the situation in the modern war, which has the characteristics of large amount of information. Based on ArcGIS Engine, in this paper, a modular two-dimensional battlefield situation display system is designed and implemented. The function of each module in the system is discussed and analyzed, then some key technologies of the system are introduced. The demonstration results show the validation of the situation display system.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114668487","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}
Real-world face detection and alignment demand an advanced discriminative model to address challenges by pose, lighting and expression. Recent studies have utilized the relation between face detection and alignment to make models computationally efficiency, but they ignore the connection between each cascade CNNs. In this paper, we combine detection, calibration and alignment in each cascade structure and propose an End-to-End cascade Online Hard Example Mining (OHEM) for training, which expert in accelerating convergence. Experiments on FDDB and AFLW demonstrate considerable improvement on accuracy and speed.
{"title":"End-to-End Cascade CNN for Simultaneously Face Detection and Alignment","authors":"Sanyuan Zhao, Hongmei Song, Weilin Cong, Q. Qi, Hui Tian","doi":"10.1109/ICVRV.2017.00016","DOIUrl":"https://doi.org/10.1109/ICVRV.2017.00016","url":null,"abstract":"Real-world face detection and alignment demand an advanced discriminative model to address challenges by pose, lighting and expression. Recent studies have utilized the relation between face detection and alignment to make models computationally efficiency, but they ignore the connection between each cascade CNNs. In this paper, we combine detection, calibration and alignment in each cascade structure and propose an End-to-End cascade Online Hard Example Mining (OHEM) for training, which expert in accelerating convergence. Experiments on FDDB and AFLW demonstrate considerable improvement on accuracy and speed.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133472190","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 : 2017-10-01DOI: 10.1109/ICVRV.2017.00121
Zhixin Ma, Chong Cao, Xukun Shen
With the rapid growth of virtual reality industry, fast and accurate algorithms for scene reconstruction and understanding became the research focus in related fields. Traditional methods always consider the 3D model and scene understanding as two problems and work them out separately. In this paper, we propose a new method to reconstruct semantic 3D models from multi-view images. This method not only contains information of points in 3D space, but also builds up their relationship with pixels from images. We commit experiments on four real challenging datasets to test the effectiveness of our proposed method. The reconstruction can be directly applied to virtual reality applications, such as roaming in 3D scenes.
{"title":"Semantic Scene Reconstruction Using the DenseCRF Model","authors":"Zhixin Ma, Chong Cao, Xukun Shen","doi":"10.1109/ICVRV.2017.00121","DOIUrl":"https://doi.org/10.1109/ICVRV.2017.00121","url":null,"abstract":"With the rapid growth of virtual reality industry, fast and accurate algorithms for scene reconstruction and understanding became the research focus in related fields. Traditional methods always consider the 3D model and scene understanding as two problems and work them out separately. In this paper, we propose a new method to reconstruct semantic 3D models from multi-view images. This method not only contains information of points in 3D space, but also builds up their relationship with pixels from images. We commit experiments on four real challenging datasets to test the effectiveness of our proposed method. The reconstruction can be directly applied to virtual reality applications, such as roaming in 3D scenes.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133124990","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 : 2017-10-01DOI: 10.23940/IJPE.18.01.P9.7788
Yang Wenzhen, Luo Jiali, Li Xin, Wu Xinli, Jiang Zhaona, Pan Zhigeng
Image tactile interaction is a new interaction between human and digital images, allowing users to know digital images by touch. In order to improve the authenticity of image tactile perception, this paper proposes a tactile perception model based on image region features. Aiming at the phenomenon of over-partitioning and computational complexity of JSEG algorithm, we propose an improved JSEG algorithm, which can effectively reduce the computational complexity and divide the image areas which are more in line with the subjective visual judgment, and can be used for region-based image tactile generation. The experimental results show that the proposed algorithm can correctly distinguish the image area and improve the accuracy of image tactile perception.
{"title":"Image Tactile Perception with an Improved JSEG Algorithm","authors":"Yang Wenzhen, Luo Jiali, Li Xin, Wu Xinli, Jiang Zhaona, Pan Zhigeng","doi":"10.23940/IJPE.18.01.P9.7788","DOIUrl":"https://doi.org/10.23940/IJPE.18.01.P9.7788","url":null,"abstract":"Image tactile interaction is a new interaction between human and digital images, allowing users to know digital images by touch. In order to improve the authenticity of image tactile perception, this paper proposes a tactile perception model based on image region features. Aiming at the phenomenon of over-partitioning and computational complexity of JSEG algorithm, we propose an improved JSEG algorithm, which can effectively reduce the computational complexity and divide the image areas which are more in line with the subjective visual judgment, and can be used for region-based image tactile generation. The experimental results show that the proposed algorithm can correctly distinguish the image area and improve the accuracy of image tactile perception.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116609105","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}
In this work, a novel three-dimensional (3D) mesh sequence compression framework suitable for progressive streaming is described. The proposed approach first implements a temporal frame-clustering algorithm based on the curvature of pivot vertex trajectory. Then, a decorrelation method is used to remove the redundancy of data in x, y, and z coordinates. Next, to reduce the amount of mesh sequence data, the vertex motion trajectory data in each cluster is compressed using principal component analysis (PCA). Further, the coefficients of x, y and z coordinates obtained from different principal components are considered as mesh signals, which are processed by a spectral graph wavelet transform(SGWT). Finally, the obtained wavelet coefficients are encoded using CSPECK. By transmitting data on different bit-planes from encoder, a 3D mesh sequence is encoded into a multi-resolution sequence. Experimental results show that the proposed method can realize progressive streaming of mesh sequence. Furthermore, the results also show that the proposed approach outperforms state-of-the-art methods in terms of storage space requirement and minimizing the reconstruction error
{"title":"A Novel Dynamic Mesh Sequence Compression Framework for Progressive Streaming","authors":"Bailin Yang, Zhaoyi Jiang, Yan Tian, Jiantao Shangguan, Chao Song, Yibo Guo, Mingliang Xu","doi":"10.1109/ICVRV.2017.00019","DOIUrl":"https://doi.org/10.1109/ICVRV.2017.00019","url":null,"abstract":"In this work, a novel three-dimensional (3D) mesh sequence compression framework suitable for progressive streaming is described. The proposed approach first implements a temporal frame-clustering algorithm based on the curvature of pivot vertex trajectory. Then, a decorrelation method is used to remove the redundancy of data in x, y, and z coordinates. Next, to reduce the amount of mesh sequence data, the vertex motion trajectory data in each cluster is compressed using principal component analysis (PCA). Further, the coefficients of x, y and z coordinates obtained from different principal components are considered as mesh signals, which are processed by a spectral graph wavelet transform(SGWT). Finally, the obtained wavelet coefficients are encoded using CSPECK. By transmitting data on different bit-planes from encoder, a 3D mesh sequence is encoded into a multi-resolution sequence. Experimental results show that the proposed method can realize progressive streaming of mesh sequence. Furthermore, the results also show that the proposed approach outperforms state-of-the-art methods in terms of storage space requirement and minimizing the reconstruction error","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121935287","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 : 2017-10-01DOI: 10.1109/ICVRV.2017.00033
Sheng Wu, Teng Miao, Boxiang Xiao, Xinyu Guo
This paper presents a generally 3D approach for simulating the decay process in fruits to provide a visual model for the digital design of fruit. A global decay parameter and a decay resistance parameter are used to control the dynamic simulation process of decay for users. The decay resistance parameters are set for every point on the 3D fruit model by an interactive designing method which is similar to traditional drawing tools. The resistance parameters finally form a texture of decay region on the fruit surface. With the resistance parameters, the degree of decay which is used to control the shape and appearance of fruit decay surface, can be compute by tuning the global decay parameters. For the shape of decay region, the exponential function is given for calculating the depression displacement cased by decay. In order to render the wrinkle on the decay region, a noise normal map is used to disturb the normal vector of fruit model. We verified our method by simulating the rotten apple, the result shows that a dynamic and real-time realistic simulation can be obtained using our method which is flexible, fast and general. We believe this approach is suitable for fruit digital design as a visualization model.
{"title":"A Realistic Modeling and Real Time Rendering Method of Fruit Decay Based on Interactive Design","authors":"Sheng Wu, Teng Miao, Boxiang Xiao, Xinyu Guo","doi":"10.1109/ICVRV.2017.00033","DOIUrl":"https://doi.org/10.1109/ICVRV.2017.00033","url":null,"abstract":"This paper presents a generally 3D approach for simulating the decay process in fruits to provide a visual model for the digital design of fruit. A global decay parameter and a decay resistance parameter are used to control the dynamic simulation process of decay for users. The decay resistance parameters are set for every point on the 3D fruit model by an interactive designing method which is similar to traditional drawing tools. The resistance parameters finally form a texture of decay region on the fruit surface. With the resistance parameters, the degree of decay which is used to control the shape and appearance of fruit decay surface, can be compute by tuning the global decay parameters. For the shape of decay region, the exponential function is given for calculating the depression displacement cased by decay. In order to render the wrinkle on the decay region, a noise normal map is used to disturb the normal vector of fruit model. We verified our method by simulating the rotten apple, the result shows that a dynamic and real-time realistic simulation can be obtained using our method which is flexible, fast and general. We believe this approach is suitable for fruit digital design as a visualization model.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124950666","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 : 2017-10-01DOI: 10.1109/icvrv.2017.00108
Benyue Su, Wei Han, Yusheng Peng, Min Sheng
This paper proposes a coarse registration method based on RGB-D data. The feature points are obtained from the mixed feature. The corresponding points of the feature points are searched in target point cloud according to the feature descriptor. The feature points are divided into several partitions and the rigid transformation is calculated between the corresponding point pairs in each partition. The optimal rigid transformation is chosen from the rigid transformation of each partition. The mixed feature is constructed by geometric information and color information of the neighborhood points. The feature descriptor is built with the mixed feature and normalized RGB value. The experimental results demonstrated that the method is effective for RGB-D data.
{"title":"Color-Guided Coarse Registration Method Based on RGB-D Data","authors":"Benyue Su, Wei Han, Yusheng Peng, Min Sheng","doi":"10.1109/icvrv.2017.00108","DOIUrl":"https://doi.org/10.1109/icvrv.2017.00108","url":null,"abstract":"This paper proposes a coarse registration method based on RGB-D data. The feature points are obtained from the mixed feature. The corresponding points of the feature points are searched in target point cloud according to the feature descriptor. The feature points are divided into several partitions and the rigid transformation is calculated between the corresponding point pairs in each partition. The optimal rigid transformation is chosen from the rigid transformation of each partition. The mixed feature is constructed by geometric information and color information of the neighborhood points. The feature descriptor is built with the mixed feature and normalized RGB value. The experimental results demonstrated that the method is effective for RGB-D data.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127423575","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 : 2017-10-01DOI: 10.1109/ICVRV.2017.00118
Peipei Yang, Haoxiang Wang, Yuchen Liu
This paper proposes an optimized method of collision detection in web virtual reality (VR) environment. The proposed solution consists of two layers. Experimental results demonstrate the effectivity of the method and its significant improvement in efficiency (measured by average frame number per second) with proper accuracy of collision detection guaranteed.
{"title":"Web Virtual Reality Oriented Collision Detection","authors":"Peipei Yang, Haoxiang Wang, Yuchen Liu","doi":"10.1109/ICVRV.2017.00118","DOIUrl":"https://doi.org/10.1109/ICVRV.2017.00118","url":null,"abstract":"This paper proposes an optimized method of collision detection in web virtual reality (VR) environment. The proposed solution consists of two layers. Experimental results demonstrate the effectivity of the method and its significant improvement in efficiency (measured by average frame number per second) with proper accuracy of collision detection guaranteed.","PeriodicalId":187934,"journal":{"name":"2017 International Conference on Virtual Reality and Visualization (ICVRV)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128029006","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：