Interactive audio-visual applications such as free viewpoint video (FVV) endeavour to provide unrestricted spatiotemporal navigation within a multiple camera environment. Current novel view creation approaches for scene navigation within FVV applications are both purely image-based, implying large information redundancy and dense sampling of the scene; or involve reconstructing complex 3-D models of the scene. In this paper we present a new multiple image view synthesis algorithm for novel view creation that requires only implicit scene geometry information. The multi-view synthesis approach can be used in any multiple camera environments and is scalable, as virtual views can be created given 1 to N of the available video inputs, providing a means to gracefully handle scenarios where camera inputs decrease or increase over time. The algorithm identifies and selects only the best quality surface areas from available reference images, thereby reducing perceptual errors in virtual view reconstruction. Experimental results are provided and verified using both objective (PSNR) and subjective comparisons and also the improvements over the traditional multiple image view synthesis approach of view-oriented weighting are presented.
{"title":"Notice of Violation of IEEE Publication PrinciplesA Novel View Multi-view Synthesis Approach for Free Viewpoint Video","authors":"Yuhua Zhu","doi":"10.1109/JCAI.2009.163","DOIUrl":"https://doi.org/10.1109/JCAI.2009.163","url":null,"abstract":"Interactive audio-visual applications such as free viewpoint video (FVV) endeavour to provide unrestricted spatiotemporal navigation within a multiple camera environment. Current novel view creation approaches for scene navigation within FVV applications are both purely image-based, implying large information redundancy and dense sampling of the scene; or involve reconstructing complex 3-D models of the scene. In this paper we present a new multiple image view synthesis algorithm for novel view creation that requires only implicit scene geometry information. The multi-view synthesis approach can be used in any multiple camera environments and is scalable, as virtual views can be created given 1 to N of the available video inputs, providing a means to gracefully handle scenarios where camera inputs decrease or increase over time. The algorithm identifies and selects only the best quality surface areas from available reference images, thereby reducing perceptual errors in virtual view reconstruction. Experimental results are provided and verified using both objective (PSNR) and subjective comparisons and also the improvements over the traditional multiple image view synthesis approach of view-oriented weighting are presented.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134502153","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}
The optimization of supply chain distribution network need to consider many factors, especially useful information derived from distributors. In this paper, We consider a supply chain consisting of two layers, they are one manufacture and many distributors. Each distributor has full knowledge about his own value-added cost structure. The problem is to design the optimal distribution network for the manufacture. The approach of Network DEA is used to evaluate distributors’ relative validity and finish the filtration of distributors, and through these results the process of distributor selection is completed. At the end of this paper, a numerical example is given.
{"title":"Optimization of Supply Chain Design Based on Knowledge Discovery of Distribution Network","authors":"Zhong Ling, Min Zhang","doi":"10.1109/JCAI.2009.170","DOIUrl":"https://doi.org/10.1109/JCAI.2009.170","url":null,"abstract":"The optimization of supply chain distribution network need to consider many factors, especially useful information derived from distributors. In this paper, We consider a supply chain consisting of two layers, they are one manufacture and many distributors. Each distributor has full knowledge about his own value-added cost structure. The problem is to design the optimal distribution network for the manufacture. The approach of Network DEA is used to evaluate distributors’ relative validity and finish the filtration of distributors, and through these results the process of distributor selection is completed. At the end of this paper, a numerical example is given.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134522210","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}
With an ordinary style of twelve men's seamless underwear as the target of study, of which made the same style, material and the different cylinder diameters, organization structures and knitting methods. The pressure and pressure sense of different positions in the upper body of seamless underwear were tested by young men of M body sizes under static and action state. The methods of objective combined with subjective evaluation, grey correlation and multiple linear regression were used to analyzing pressure values and comfortable sense values. The key positions which can weigh total pressure comfort of men's seamless underwear are obtained, they are elbow, shoulder and chest. Models between pressure and comfort sense under different state are also obtained. By confirming, mathematical models have good accuracy and can give a useful guidance to enterprise for predicting whether the pressure of seamless underwear is comfort or not before mass production.
{"title":"Study on the model of men's upper body pressure and comfort sense based on the seamless underwear's upper parts","authors":"Zimin Jin, Xiaoju Luo, Jiajia Shen, Yuxiu Yan, Minzhi Chen","doi":"10.1109/JCAI.2009.87","DOIUrl":"https://doi.org/10.1109/JCAI.2009.87","url":null,"abstract":"With an ordinary style of twelve men's seamless underwear as the target of study, of which made the same style, material and the different cylinder diameters, organization structures and knitting methods. The pressure and pressure sense of different positions in the upper body of seamless underwear were tested by young men of M body sizes under static and action state. The methods of objective combined with subjective evaluation, grey correlation and multiple linear regression were used to analyzing pressure values and comfortable sense values. The key positions which can weigh total pressure comfort of men's seamless underwear are obtained, they are elbow, shoulder and chest. Models between pressure and comfort sense under different state are also obtained. By confirming, mathematical models have good accuracy and can give a useful guidance to enterprise for predicting whether the pressure of seamless underwear is comfort or not before mass production.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"43 19","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113974511","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}
Active Appearance Models are widely used to match statistical models of shape and appearance to new imagesrapidly. They work by finding model parameters whichminimise the sum of squares of residual differences between model and target image. A limitation of AAMs is that they are not robust to a large set of gross outliers. Using a robust kernel can help, but there are potential problems in determining the correct kernel scaling parameters. We describe a method of learning two sets of scaling parameters during AAM training: a coarse and a fine scale set. Our algorithm initially applies the coarse scale and then uses a form of deterministic annealing to reduce to the fine outlier rejection scaling as the AAM converges. The algorithm was assessed on two large datasets consisting of a set of faces, and a medical dataset of images of the spine. A significant improvement in accuracy and robustness was observed in cases which were difficult for a standard AAM.
{"title":"Using a Robust Active Appearance Model for Face Processing","authors":"Shaojun Zhu, Jieyu Zhao","doi":"10.1109/JCAI.2009.177","DOIUrl":"https://doi.org/10.1109/JCAI.2009.177","url":null,"abstract":"Active Appearance Models are widely used to match statistical models of shape and appearance to new imagesrapidly. They work by finding model parameters whichminimise the sum of squares of residual differences between model and target image. A limitation of AAMs is that they are not robust to a large set of gross outliers. Using a robust kernel can help, but there are potential problems in determining the correct kernel scaling parameters. We describe a method of learning two sets of scaling parameters during AAM training: a coarse and a fine scale set. Our algorithm initially applies the coarse scale and then uses a form of deterministic annealing to reduce to the fine outlier rejection scaling as the AAM converges. The algorithm was assessed on two large datasets consisting of a set of faces, and a medical dataset of images of the spine. A significant improvement in accuracy and robustness was observed in cases which were difficult for a standard AAM.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"28 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123998202","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}
Along with the development of internet, a lot of new data appears in the web every day. To construct a retrieval model to adapt the new data quickly and to retrieval the new documents accurately is becoming an important research topic. In this paper, we put forward a new retrieval model by incorporating the theory of transfer learning with Markov Network. Firstly, compare term spaces network of old dataset and new (target) dataset, and the distance between data sets is measured using the Kullback-Leibler divergence. Moreover, KL-divergence is used to decide the trade-off parameter in retrieval formula. Then we transfer the useful prior knowledge of old dataset to the new (target) dataset, and finally implement the retrieval process on the target dataset. Experiments on multiple datasets indicate that our new approach outperforms other methods. Furthermore, we perform several T-tests to demonstrate the improvements are statistically significant.
{"title":"Transferring Markov Network for Information Retrieval","authors":"Meihua Yu, Mingwen Wang, Jiali Zuo, Xiaofang Zou","doi":"10.1109/JCAI.2009.92","DOIUrl":"https://doi.org/10.1109/JCAI.2009.92","url":null,"abstract":"Along with the development of internet, a lot of new data appears in the web every day. To construct a retrieval model to adapt the new data quickly and to retrieval the new documents accurately is becoming an important research topic. In this paper, we put forward a new retrieval model by incorporating the theory of transfer learning with Markov Network. Firstly, compare term spaces network of old dataset and new (target) dataset, and the distance between data sets is measured using the Kullback-Leibler divergence. Moreover, KL-divergence is used to decide the trade-off parameter in retrieval formula. Then we transfer the useful prior knowledge of old dataset to the new (target) dataset, and finally implement the retrieval process on the target dataset. Experiments on multiple datasets indicate that our new approach outperforms other methods. Furthermore, we perform several T-tests to demonstrate the improvements are statistically significant.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127807354","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}
The traditional three-dimensional object recognition method based on hypothesise and test need to solve the coordinate transformation matrix from scene to model through a group of non-linear equations. Therefore, it has a very high complexity. This paper presents a man-made object recognition method based on the geometry feature of line segments characteristics, and disperses the overall coordinate transformation calculation in every local plane homography calculation, reduces the complexity of the solution. First we prematch the feature points using geometric invariants, then assume and solve the plane homography matrix between scenes to model. After that we match the line segments on the homography plane, and by this we verify the assumption. Experiments proved that this method can rapidly and accurately identify man-made objects which contain coplanar line segment features.
{"title":"Line Segment Based Man-Made Object Recognition Using Invariance","authors":"Z. Qiu, Hui Wei","doi":"10.1109/JCAI.2009.149","DOIUrl":"https://doi.org/10.1109/JCAI.2009.149","url":null,"abstract":"The traditional three-dimensional object recognition method based on hypothesise and test need to solve the coordinate transformation matrix from scene to model through a group of non-linear equations. Therefore, it has a very high complexity. This paper presents a man-made object recognition method based on the geometry feature of line segments characteristics, and disperses the overall coordinate transformation calculation in every local plane homography calculation, reduces the complexity of the solution. First we prematch the feature points using geometric invariants, then assume and solve the plane homography matrix between scenes to model. After that we match the line segments on the homography plane, and by this we verify the assumption. Experiments proved that this method can rapidly and accurately identify man-made objects which contain coplanar line segment features.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129208658","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}
On the basis of vibration signal of rolling bearing, anew method of fault diagnosis based on K-L transformation and Lagrange support vector regression is presented.Multidimensional correlated variable is transformed into low dimensional independent eigenvector by the means of K-L Transformation. The pattern recognition and nonlinear regression are achieved by the method of Lagrange support vector regression. Lagrange support vector regression can be used to recognize the fault after be trained by the example data. Theory and experiment shows that the recognition of fault diagnosis of rolling bearing based on K-L transformation and Lagrange support vector regression theory is available to recognize the fault pattern accurately and provides a new approach to intelligent fault diagnosis.
{"title":"Study on Fault Diagnosis of Rolling Bearing Based on K-L Transformation and Lagrange Support Vector Regression","authors":"Yang Xu","doi":"10.1109/JCAI.2009.60","DOIUrl":"https://doi.org/10.1109/JCAI.2009.60","url":null,"abstract":"On the basis of vibration signal of rolling bearing, anew method of fault diagnosis based on K-L transformation and Lagrange support vector regression is presented.Multidimensional correlated variable is transformed into low dimensional independent eigenvector by the means of K-L Transformation. The pattern recognition and nonlinear regression are achieved by the method of Lagrange support vector regression. Lagrange support vector regression can be used to recognize the fault after be trained by the example data. Theory and experiment shows that the recognition of fault diagnosis of rolling bearing based on K-L transformation and Lagrange support vector regression theory is available to recognize the fault pattern accurately and provides a new approach to intelligent fault diagnosis.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"33 1-2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116731071","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}
aiming at the low 1eve1 of automation of case retrieva1 in case— based design the retrieva1 model design used in case— based fixture design was studied in detail. On the analysis of the functional surfaces of work piece, the design requirement is extracted whereby the functional mode of work piece is presented, and the prototype of fixture assembling based on the theory of General—location is constructed. Aim at increasing the accurate rate of retrieval in case-based reasoning, the fixture assembling information of three layers structure is realized. The theory and methodology is lastly exemplified¿ where a new approach of fixture design automation is explored.
{"title":"Research on Fixture Design Automation Based on the Prototype of General–Assembling","authors":"Pei-gang Li, Shu-chun Zhao, Xian-ying Feng, Ke-zheng Huang","doi":"10.1109/JCAI.2009.175","DOIUrl":"https://doi.org/10.1109/JCAI.2009.175","url":null,"abstract":"aiming at the low 1eve1 of automation of case retrieva1 in case— based design the retrieva1 model design used in case— based fixture design was studied in detail. On the analysis of the functional surfaces of work piece, the design requirement is extracted whereby the functional mode of work piece is presented, and the prototype of fixture assembling based on the theory of General—location is constructed. Aim at increasing the accurate rate of retrieval in case-based reasoning, the fixture assembling information of three layers structure is realized. The theory and methodology is lastly exemplified¿ where a new approach of fixture design automation is explored.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116199930","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}
his paper endogenizes the numbers of informed and uninformed customers in Varian’s Model of Sales. Following [2], this paper establishes a simultaneous move pricing game, in which all consumers are assumed to be ex ant uninformed. Post ant informed and uninformed customers are the result of strategic interactions between sellers and buyers. This paper derives all possible symmetric equilibria of the pricing game. A representative firm makes negative, zero or positive expected profit depending on the realized consumer decision rules.
{"title":"How Do Informed and Uninformed Customers Come into Being in Varian's Model of Sales?","authors":"Q. Chen, Min Fan, Guoliang Kuang","doi":"10.1109/JCAI.2009.216","DOIUrl":"https://doi.org/10.1109/JCAI.2009.216","url":null,"abstract":"his paper endogenizes the numbers of informed and uninformed customers in Varian’s Model of Sales. Following [2], this paper establishes a simultaneous move pricing game, in which all consumers are assumed to be ex ant uninformed. Post ant informed and uninformed customers are the result of strategic interactions between sellers and buyers. This paper derives all possible symmetric equilibria of the pricing game. A representative firm makes negative, zero or positive expected profit depending on the realized consumer decision rules.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125634016","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 semantic web, ontology mapping is the basis of the interoperation of heterogeneous ontologies. Ontologies are usually distributed and heterogeneous and thus it is necessary to find the mapping between them before processing across them. The current ontology mapping methods merely use massive web pages in the internet and they are unpractical to subsequent interoperation and integration of heterogeneous data sources. This paper proposes a method based on internet search engine and realizes it to a component of the framework for knowledge management system. Ontologies to be mapped and mapping results are all stored in the database. Finally we evaluate our approach with experiments which demonstrate that our solution yields a better performance.
{"title":"An Applicable Approach to Ontology Mapping Based on Knowledge Base","authors":"L. Zhang, Song Ding, Shengqun Tang","doi":"10.1109/JCAI.2009.29","DOIUrl":"https://doi.org/10.1109/JCAI.2009.29","url":null,"abstract":"In semantic web, ontology mapping is the basis of the interoperation of heterogeneous ontologies. Ontologies are usually distributed and heterogeneous and thus it is necessary to find the mapping between them before processing across them. The current ontology mapping methods merely use massive web pages in the internet and they are unpractical to subsequent interoperation and integration of heterogeneous data sources. This paper proposes a method based on internet search engine and realizes it to a component of the framework for knowledge management system. Ontologies to be mapped and mapping results are all stored in the database. Finally we evaluate our approach with experiments which demonstrate that our solution yields a better performance.","PeriodicalId":154425,"journal":{"name":"2009 International Joint Conference on Artificial Intelligence","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127829933","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：