Pub Date : 2016-09-01DOI: 10.1109/ICNIDC.2016.7974558
Seongsu Lee, Y. Won
Non-volatile memory is a promising material that covers both cache and secondary storage in a memory hierarchy. Many software platforms exploiting non-volatile have been developed and provide user-level programming interfaces. However, common programs cannot allocate non-volatile memory. In this paper, we introduce a code generation method for HEAPO that is one of non-volatile memory software platforms. With the method, a program designed for a legacy operating system using DRAM as main memory is converted to a program running on the non-volatile memory platform without code modification manually.
{"title":"Program code regeneration method for non-volatile memory platform","authors":"Seongsu Lee, Y. Won","doi":"10.1109/ICNIDC.2016.7974558","DOIUrl":"https://doi.org/10.1109/ICNIDC.2016.7974558","url":null,"abstract":"Non-volatile memory is a promising material that covers both cache and secondary storage in a memory hierarchy. Many software platforms exploiting non-volatile have been developed and provide user-level programming interfaces. However, common programs cannot allocate non-volatile memory. In this paper, we introduce a code generation method for HEAPO that is one of non-volatile memory software platforms. With the method, a program designed for a legacy operating system using DRAM as main memory is converted to a program running on the non-volatile memory platform without code modification manually.","PeriodicalId":439987,"journal":{"name":"2016 IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123278289","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 : 2016-09-01DOI: 10.1109/ICNIDC.2016.7974549
Yunong Yang, Zhenyu Wu, Xinning Zhu
Integrating semantic technology to the Web of Things (WoT) facilitates the creation of a networked knowledge infrastructure with more interoperable data from both physical and cyber world. However, most of current solutions relies on manual methods based on domain-specific ontology, which is only suitable for domain expert and developers but not compatible with large-scale knowledge construction. This paper proposes a semi-automatic annotation framework for the metadata representation of WoT resource. This framework is based on a probabilistic graphical model to collectively infer entities, classes and relations from schematic WoT resources mapping to domain independent knowledge base. A proof-of-concept implementation and performance evaluation are illustrated to show a feasibility of our method.
{"title":"Semi-automatic metadata annotation of Web of Things with knowledge base","authors":"Yunong Yang, Zhenyu Wu, Xinning Zhu","doi":"10.1109/ICNIDC.2016.7974549","DOIUrl":"https://doi.org/10.1109/ICNIDC.2016.7974549","url":null,"abstract":"Integrating semantic technology to the Web of Things (WoT) facilitates the creation of a networked knowledge infrastructure with more interoperable data from both physical and cyber world. However, most of current solutions relies on manual methods based on domain-specific ontology, which is only suitable for domain expert and developers but not compatible with large-scale knowledge construction. This paper proposes a semi-automatic annotation framework for the metadata representation of WoT resource. This framework is based on a probabilistic graphical model to collectively infer entities, classes and relations from schematic WoT resources mapping to domain independent knowledge base. A proof-of-concept implementation and performance evaluation are illustrated to show a feasibility of our method.","PeriodicalId":439987,"journal":{"name":"2016 IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132551485","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 : 2016-09-01DOI: 10.1109/ICNIDC.2016.7974610
Hua-xin Zhou, Ni Zhang, Di Huang, Zhanyu Ma, Weisong Hu, Jun Guo
Atmospheric pollution is getting more and more attention because of the serious status. Finding the pollutant source is one of the key steps to solve this problem. This paper introduces a new method to trace the pollution diffusion path according to the relevance of different areas where they were polluted (the relatively small areas regard as points or lattices in this paper). We present the single point tracing to show the specific traceability and the area tracing to show the pollution spread trend.
{"title":"Activation force-based air pollution tracing","authors":"Hua-xin Zhou, Ni Zhang, Di Huang, Zhanyu Ma, Weisong Hu, Jun Guo","doi":"10.1109/ICNIDC.2016.7974610","DOIUrl":"https://doi.org/10.1109/ICNIDC.2016.7974610","url":null,"abstract":"Atmospheric pollution is getting more and more attention because of the serious status. Finding the pollutant source is one of the key steps to solve this problem. This paper introduces a new method to trace the pollution diffusion path according to the relevance of different areas where they were polluted (the relatively small areas regard as points or lattices in this paper). We present the single point tracing to show the specific traceability and the area tracing to show the pollution spread trend.","PeriodicalId":439987,"journal":{"name":"2016 IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121918931","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 : 2016-09-01DOI: 10.1109/ICNIDC.2016.7974560
Han Deng, Yonggang Qi, Jun Liu, Jie Yang
As the increasing number of intelligent mobile phones that are available for people which lead to tones of network flow data are produced. Hence, how to dig the user's behavior pattern by using the data collected form mobile phones is a significant problem. While some achievements have been made in this area, it is still too complicated to be put into practice due to various conditions needed by traditional research method. Meanwhile, users' data of mobile communication network gradually improved, so that it only requires part of information to reach the ideal status. Hence, we propose a Non-negative Matrix Factorization based method to analyze the mobility patterns of mobile phone users, i.e., find the groups of people with the similar mobility patterns. The experimental results on the real data obtained from the capital of a south province validate our proposed method.
{"title":"Analysis of mobile subscribers' behavior pattern based on non-negative matrix factorization","authors":"Han Deng, Yonggang Qi, Jun Liu, Jie Yang","doi":"10.1109/ICNIDC.2016.7974560","DOIUrl":"https://doi.org/10.1109/ICNIDC.2016.7974560","url":null,"abstract":"As the increasing number of intelligent mobile phones that are available for people which lead to tones of network flow data are produced. Hence, how to dig the user's behavior pattern by using the data collected form mobile phones is a significant problem. While some achievements have been made in this area, it is still too complicated to be put into practice due to various conditions needed by traditional research method. Meanwhile, users' data of mobile communication network gradually improved, so that it only requires part of information to reach the ideal status. Hence, we propose a Non-negative Matrix Factorization based method to analyze the mobility patterns of mobile phone users, i.e., find the groups of people with the similar mobility patterns. The experimental results on the real data obtained from the capital of a south province validate our proposed method.","PeriodicalId":439987,"journal":{"name":"2016 IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122662304","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 : 2016-09-01DOI: 10.1109/ICNIDC.2016.7974613
Yi Zheng, Yumei Wang, Yu Liu
Nowadays, Dynamic Adaptive Streaming over HTTP (DASH) emerges as an increasingly popular video streaming technology on the Internet. And many rate adaptation algorithms have been proposed to decide the best bitrate for DASH video players. In different real applications, not all the video segments are of same importance for users. However, none of these existing rate adaptation algorithms takes segment importance into consideration. In this paper, we propose a segment importance based rate adaptation (SIA) algorithm for DASH, which not only considers the network bandwidth and the client video buffer but also takes segment importance into account. To evaluate the performance of SIA under different bandwidth conditions, experiments are conducted under both different values of fixed bandwidth and available bandwidth variations. And results show that SIA achieves a considerable gain for the average bitrate for important segments (ABIS) under low fixed bandwidth and available bandwidth variations while keeping comparable performance of other objective QoE metrics compared to the buffer-based rate adaptation (BBA) [6] and the segment-aware rate adaptation (SARA) algorithm [11]. We also validate that in a certain range, the increment of the percentage of important segments in SIA will lead to the decrement of ABIS and the increment of the duration of video rebuffering.
当前，基于HTTP的动态自适应流媒体技术(Dynamic Adaptive Streaming over HTTP, DASH)作为一种日益流行的视频流技术出现在互联网上。为了确定适合DASH视频播放器的最佳比特率，已经提出了多种速率自适应算法。在不同的实际应用中，并非所有的视频片段对用户的重要性都是一样的。然而，这些现有的速率自适应算法都没有考虑片段的重要性。本文提出了一种基于段重要性的DASH速率自适应(SIA)算法，该算法不仅考虑了网络带宽和客户端视频缓冲，而且考虑了段重要性。为了评估SIA在不同带宽条件下的性能，分别在不同的固定带宽和可用带宽变化值下进行了实验。结果表明，与基于缓冲的速率自适应(BBA)[6]和段感知速率自适应(SARA)算法[11]相比，SIA在低固定带宽和可用带宽变化下，在保持其他客观QoE指标性能的同时，取得了重要段(ABIS)平均比特率的可观增益。我们还验证了在一定范围内，SIA中重要段百分比的增加会导致ABIS的减少和视频再缓冲时间的增加。
{"title":"SIA: Segment importance based rate adaptation for Dynamic Adaptive Streaming over HTTP","authors":"Yi Zheng, Yumei Wang, Yu Liu","doi":"10.1109/ICNIDC.2016.7974613","DOIUrl":"https://doi.org/10.1109/ICNIDC.2016.7974613","url":null,"abstract":"Nowadays, Dynamic Adaptive Streaming over HTTP (DASH) emerges as an increasingly popular video streaming technology on the Internet. And many rate adaptation algorithms have been proposed to decide the best bitrate for DASH video players. In different real applications, not all the video segments are of same importance for users. However, none of these existing rate adaptation algorithms takes segment importance into consideration. In this paper, we propose a segment importance based rate adaptation (SIA) algorithm for DASH, which not only considers the network bandwidth and the client video buffer but also takes segment importance into account. To evaluate the performance of SIA under different bandwidth conditions, experiments are conducted under both different values of fixed bandwidth and available bandwidth variations. And results show that SIA achieves a considerable gain for the average bitrate for important segments (ABIS) under low fixed bandwidth and available bandwidth variations while keeping comparable performance of other objective QoE metrics compared to the buffer-based rate adaptation (BBA) [6] and the segment-aware rate adaptation (SARA) algorithm [11]. We also validate that in a certain range, the increment of the percentage of important segments in SIA will lead to the decrement of ABIS and the increment of the duration of video rebuffering.","PeriodicalId":439987,"journal":{"name":"2016 IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129668771","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 : 2016-09-01DOI: 10.1109/ICNIDC.2016.7974606
Chunli Ye, Yaxin Wang, Xin Zhang, Dacheng Yang
In face of the rapid growth of data traffic in cellular networks, Cloud Radio Access Network (C-RAN) architecture has been proposed as a solution to obtain better performance in terms of efficiency, expansibility, elasticity, stability and expenditure such as Capital Expenditure (CAPEX) and Operational Expenditure (OPEX). However, C-RAN demands a comprehensive evaluation model and accurate qualitative metrics for designing Base Band Unit (BBU) and Remote Radio Head (RRH) switching mechanism. Many literatures have studied an energy consumption model which discusses the optimized resource utilization and power saving compared with typical RAN architecture, but it seems that they did not consider how to guarantee the quality of service (QoS) that may require more limitation. This paper is the first to study the C-RAN to achieve the reasonable BBU-RRH switching with good QoS by considering two new factors, resource waste (ReW) and traffic backlog (TB), which directly affect system performance. New BBU-RRH switching model for C-RAN is proposed for finding out the loss indicated by ReW and TB. An algorithm that optimizes the QoS, resource utilization and power saving of system is derived and it contains two parameters called higher threshold (HT) and lower threshold (LT) that represent upper limit and lower limit of one BBU's resource utilization, respectively. And we provide a parameter Pu as the evaluation criteria for HT and LT. Numerical results validated theoretical analyses and revealed HT set to 0.85 and LT set to 0.35 as optimal configuration under the assumptions in this paper. Compared with existing literatures, this paper solves the calibration of HT and LT for C-RAN BBU-RRH switching schemes.
{"title":"Calibration algorithm for C-RAN BBU-RRH switching schemes","authors":"Chunli Ye, Yaxin Wang, Xin Zhang, Dacheng Yang","doi":"10.1109/ICNIDC.2016.7974606","DOIUrl":"https://doi.org/10.1109/ICNIDC.2016.7974606","url":null,"abstract":"In face of the rapid growth of data traffic in cellular networks, Cloud Radio Access Network (C-RAN) architecture has been proposed as a solution to obtain better performance in terms of efficiency, expansibility, elasticity, stability and expenditure such as Capital Expenditure (CAPEX) and Operational Expenditure (OPEX). However, C-RAN demands a comprehensive evaluation model and accurate qualitative metrics for designing Base Band Unit (BBU) and Remote Radio Head (RRH) switching mechanism. Many literatures have studied an energy consumption model which discusses the optimized resource utilization and power saving compared with typical RAN architecture, but it seems that they did not consider how to guarantee the quality of service (QoS) that may require more limitation. This paper is the first to study the C-RAN to achieve the reasonable BBU-RRH switching with good QoS by considering two new factors, resource waste (ReW) and traffic backlog (TB), which directly affect system performance. New BBU-RRH switching model for C-RAN is proposed for finding out the loss indicated by ReW and TB. An algorithm that optimizes the QoS, resource utilization and power saving of system is derived and it contains two parameters called higher threshold (HT) and lower threshold (LT) that represent upper limit and lower limit of one BBU's resource utilization, respectively. And we provide a parameter Pu as the evaluation criteria for HT and LT. Numerical results validated theoretical analyses and revealed HT set to 0.85 and LT set to 0.35 as optimal configuration under the assumptions in this paper. Compared with existing literatures, this paper solves the calibration of HT and LT for C-RAN BBU-RRH switching schemes.","PeriodicalId":439987,"journal":{"name":"2016 IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121313671","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 : 2016-09-01DOI: 10.1109/ICNIDC.2016.7974561
Chengyang Wang, Sangdo Lee, Choonhwa Lee
Service composition is recognized as a key enabler to deliver the vision of service-oriented computing. Although OSGi specification provides some level of support for service discovery, tracking, and composition, more should be done to be able to adequately address the need for more diverse service interactions. This paper proposes a novel service composition scheme to allow for a directed-acyclic-graph style composition of OSGi services. The proposal can model and instantiate a realistic topology of component service interactions beyond linear interactions as supported by the status quo. The design and implementation details of our proposed approach are discussed in the paper.
{"title":"Enabling declarative service composition for cloud applications","authors":"Chengyang Wang, Sangdo Lee, Choonhwa Lee","doi":"10.1109/ICNIDC.2016.7974561","DOIUrl":"https://doi.org/10.1109/ICNIDC.2016.7974561","url":null,"abstract":"Service composition is recognized as a key enabler to deliver the vision of service-oriented computing. Although OSGi specification provides some level of support for service discovery, tracking, and composition, more should be done to be able to adequately address the need for more diverse service interactions. This paper proposes a novel service composition scheme to allow for a directed-acyclic-graph style composition of OSGi services. The proposal can model and instantiate a realistic topology of component service interactions beyond linear interactions as supported by the status quo. The design and implementation details of our proposed approach are discussed in the paper.","PeriodicalId":439987,"journal":{"name":"2016 IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129284670","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 : 2016-09-01DOI: 10.1109/ICNIDC.2016.7974533
Honggang Guo, Ke Wang, Hong Ji, Victor C. M. Leung
Cloud radio access network (C-RAN) is a novel mobile network architecture which can reduce energy consumption compare to the traditional RAN. There are lots of baseband units (BBU) in C-RAN. All BBUs are in active mode even when traffic load is light, this brings the problem of high energy consumption in BBU Pool. BBU switching scheme can switch off part of BBUs to save energy. It needs to consider BBUs' resource utilization rate but estimating BBUs' resource utilization rate is a challenging issue and lacks researches. In this paper, firstly we propose a novel scheme to estimate BBUs' resource utilization rate with the consideration of rate requirement of mobile user equipment (MUE), number of MUEs, bandwidth of Remote Radio Head (RRH) and the transmission power between RRH and MUE. Secondly, we provide a combine and remove (CnR) algorithm to decide BBU when to be switched off or to be switched on. It can remove overloaded BBU and underloaded BBU while combine them together and transfer them to normal BBU or sleeping BBU. The algorithm aims to maximize the number of sleeping BBUs without losing of Quality of Service (QoS). Numerical results indicate that the number of sleeping BBUs reaches maximum, BBUs' resource utilization rate keep in normal state and the energy consumption in the BBU Pool varies with the fluctuation of traffic load. In addition, our proposed scheme outperform the primary static scheme and schemes in relevant papers in terms of energy saving in the BBU Pool. The overall system using our scheme also consume less energy compare to the traditional RAN according to the provided energy consumption models.
{"title":"Energy saving in C-RAN based on BBU switching scheme","authors":"Honggang Guo, Ke Wang, Hong Ji, Victor C. M. Leung","doi":"10.1109/ICNIDC.2016.7974533","DOIUrl":"https://doi.org/10.1109/ICNIDC.2016.7974533","url":null,"abstract":"Cloud radio access network (C-RAN) is a novel mobile network architecture which can reduce energy consumption compare to the traditional RAN. There are lots of baseband units (BBU) in C-RAN. All BBUs are in active mode even when traffic load is light, this brings the problem of high energy consumption in BBU Pool. BBU switching scheme can switch off part of BBUs to save energy. It needs to consider BBUs' resource utilization rate but estimating BBUs' resource utilization rate is a challenging issue and lacks researches. In this paper, firstly we propose a novel scheme to estimate BBUs' resource utilization rate with the consideration of rate requirement of mobile user equipment (MUE), number of MUEs, bandwidth of Remote Radio Head (RRH) and the transmission power between RRH and MUE. Secondly, we provide a combine and remove (CnR) algorithm to decide BBU when to be switched off or to be switched on. It can remove overloaded BBU and underloaded BBU while combine them together and transfer them to normal BBU or sleeping BBU. The algorithm aims to maximize the number of sleeping BBUs without losing of Quality of Service (QoS). Numerical results indicate that the number of sleeping BBUs reaches maximum, BBUs' resource utilization rate keep in normal state and the energy consumption in the BBU Pool varies with the fluctuation of traffic load. In addition, our proposed scheme outperform the primary static scheme and schemes in relevant papers in terms of energy saving in the BBU Pool. The overall system using our scheme also consume less energy compare to the traditional RAN according to the provided energy consumption models.","PeriodicalId":439987,"journal":{"name":"2016 IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130747955","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 : 2016-09-01DOI: 10.1109/ICNIDC.2016.7974541
Yanhui Guo, Yuhao Gao, Bo Wu, Miao Zhang
With the development of mobile application reinforcement technology, traditional detecting and reverse analysis technology has been unable to cope with the reinforced mobile application using new reinforcement technology. In this paper, we analyze the mechanism of new reinforcement technology such as process state detection and memory protection, and proposed a novel shelling method using Hook and bytecode restore techniques. Experiment results show that the proposed method can be effectively applied to the reverse analysis of reinforced applications.
{"title":"Research on the technology of shelling of android reinforced application","authors":"Yanhui Guo, Yuhao Gao, Bo Wu, Miao Zhang","doi":"10.1109/ICNIDC.2016.7974541","DOIUrl":"https://doi.org/10.1109/ICNIDC.2016.7974541","url":null,"abstract":"With the development of mobile application reinforcement technology, traditional detecting and reverse analysis technology has been unable to cope with the reinforced mobile application using new reinforcement technology. In this paper, we analyze the mechanism of new reinforcement technology such as process state detection and memory protection, and proposed a novel shelling method using Hook and bytecode restore techniques. Experiment results show that the proposed method can be effectively applied to the reverse analysis of reinforced applications.","PeriodicalId":439987,"journal":{"name":"2016 IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"191 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115727191","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 : 2016-09-01DOI: 10.1109/ICNIDC.2016.7974623
Yingnan Geng, Xiuyan Wang
Stereo matching is one of the most active research areas in computer vision. Many algorithms including local algorithms and global algorithms have been proposed. As a global algorithm, belief propagation (BP) is one of the best algorithms for stereo matching. But BP algorithm is still a difficult problem because of ambiguous matching of the edge points. In this work, the priori on both matching image pairs appearances is considered during the matching process. And the distinctiveness of points, which is the difference between points in the reference image and target image, is introduced to reflect the prior of edge points appearances. Experimental results show that the proposed method performs better than the conventional BP algorithm.
{"title":"Improved belief propagation with istinctiveness measure for stereo matching","authors":"Yingnan Geng, Xiuyan Wang","doi":"10.1109/ICNIDC.2016.7974623","DOIUrl":"https://doi.org/10.1109/ICNIDC.2016.7974623","url":null,"abstract":"Stereo matching is one of the most active research areas in computer vision. Many algorithms including local algorithms and global algorithms have been proposed. As a global algorithm, belief propagation (BP) is one of the best algorithms for stereo matching. But BP algorithm is still a difficult problem because of ambiguous matching of the edge points. In this work, the priori on both matching image pairs appearances is considered during the matching process. And the distinctiveness of points, which is the difference between points in the reference image and target image, is introduced to reflect the prior of edge points appearances. Experimental results show that the proposed method performs better than the conventional BP algorithm.","PeriodicalId":439987,"journal":{"name":"2016 IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115122127","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：