In this paper we develop a methodology for measuring visitors who come from other country using social media check-in data. Based on a review of the literature on this topic we propose an urban tourism check algorithm which can find the people who are the tourists and find out where the people come from and the route of their visit. We get the data from the Sina Weibo, and the data is composed of the POI data, user check-in data, place check-in data and so on. We choose Shanghai as the research target and analyze the tourism palace Renmin Square, Yu Garden, the Bund and Chenhuang Temple in 2016. We get the number of POI data 518, the user number 213091, and the check-in number 291295. The experimental results show that the number of outside visit is 177718, the rate is 83.4% in all the user, and 151060 visits are real tourist. The accuracy rate is 85.1%. And the distribution of the tourist shows that the most of tourists come from Zhe Jiang, Jiang Su and Bei Jing.
{"title":"Urban tourism research based on the social media check-in data","authors":"Kai Yang, W. Wan, Tianyu Xia, Xuan He","doi":"10.1049/CP.2017.0124","DOIUrl":"https://doi.org/10.1049/CP.2017.0124","url":null,"abstract":"In this paper we develop a methodology for measuring visitors who come from other country using social media check-in data. Based on a review of the literature on this topic we propose an urban tourism check algorithm which can find the people who are the tourists and find out where the people come from and the route of their visit. We get the data from the Sina Weibo, and the data is composed of the POI data, user check-in data, place check-in data and so on. We choose Shanghai as the research target and analyze the tourism palace Renmin Square, Yu Garden, the Bund and Chenhuang Temple in 2016. We get the number of POI data 518, the user number 213091, and the check-in number 291295. The experimental results show that the number of outside visit is 177718, the rate is 83.4% in all the user, and 151060 visits are real tourist. The accuracy rate is 85.1%. And the distribution of the tourist shows that the most of tourists come from Zhe Jiang, Jiang Su and Bei Jing.","PeriodicalId":424212,"journal":{"name":"4th International Conference on Smart and Sustainable City (ICSSC 2017)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132986530","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 order to improve the license plate character recognition rate, a license plate character recognition method based on combination feature and BP neural network is proposed. Firstly, according to the license plate character texture features, the basic LBP operator is improved in our method. Secondly, the improved local binary model and horizontal vertical projection are combined to extract the characteristics of the license plate character image. Then the combined feature is used to train the classifier in BP neural network, and it is applied to identify license plate characters. The experimental results show that the recognition accuracy rate of the license plate reaches 94 .55% . The validity and robustness of the method are verified.
{"title":"License plate character recognition method based on combination feature and BP network","authors":"Li Mingdong, Zhang Juan, Fang Zhijun","doi":"10.1049/CP.2017.0105","DOIUrl":"https://doi.org/10.1049/CP.2017.0105","url":null,"abstract":"In order to improve the license plate character recognition rate, a license plate character recognition method based on combination feature and BP neural network is proposed. Firstly, according to the license plate character texture features, the basic LBP operator is improved in our method. Secondly, the improved local binary model and horizontal vertical projection are combined to extract the characteristics of the license plate character image. Then the combined feature is used to train the classifier in BP neural network, and it is applied to identify license plate characters. The experimental results show that the recognition accuracy rate of the license plate reaches 94 .55% . The validity and robustness of the method are verified.","PeriodicalId":424212,"journal":{"name":"4th International Conference on Smart and Sustainable City (ICSSC 2017)","volume":"2012 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127410289","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 order to cluster the moving targets of the video in dense crowded scene, according to the video regulation reticulation, it can acquire the spatio-temporal motion patterns of every grid by spatio-temporal gradient. Using the symmetric K-L(Kullback-Leibler) divergence as a distance measure, the clustering of the spatio-temporal motion patterns could be finished. The accuracy of the clustering plays an important role in the target detection, and the K-L threshold is the key for the accuracy of the clustering. Different K-L threshold will lead to different clustering effect. This paper proposes a method based on the dichotomy combining power of the motion pattern to determine the K-L threshold accurately and quickly.
{"title":"Kullback-Leibler threshold computing method based on clustering motion patterns","authors":"Li-na Pan, Zhang Jing, Wang Ping","doi":"10.1049/CP.2017.0108","DOIUrl":"https://doi.org/10.1049/CP.2017.0108","url":null,"abstract":"In order to cluster the moving targets of the video in dense crowded scene, according to the video regulation reticulation, it can acquire the spatio-temporal motion patterns of every grid by spatio-temporal gradient. Using the symmetric K-L(Kullback-Leibler) divergence as a distance measure, the clustering of the spatio-temporal motion patterns could be finished. The accuracy of the clustering plays an important role in the target detection, and the K-L threshold is the key for the accuracy of the clustering. Different K-L threshold will lead to different clustering effect. This paper proposes a method based on the dichotomy combining power of the motion pattern to determine the K-L threshold accurately and quickly.","PeriodicalId":424212,"journal":{"name":"4th International Conference on Smart and Sustainable City (ICSSC 2017)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127220201","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}
Qinghong Cui, H. Kan, Jinxian Zhao, Jianhong Shen, Kai Xue
As challenges of urban development are progressively prominent, smart city provides a new solution and brings important opportunities. In order to grasp main research hotspots and explore evolution process of the smart city in China, data sources of this paper are journal articles about smart city from China National Knowledge Infrastructure database. Three co-word matrixes are built by BibExcel, and also used to make multivariate statistical analyses by SPSS 22.0. Based on the above analyses, three proposals are put forward: implementation of smart city needs multilateral cooperation under government orientation; smart city construction should integrate developing visions, present diversities with urban characteristics; the development of smart city needs to pay full attention to technological progress and economic growth.
{"title":"Current status of smart city researches in China using the co-word analysis method","authors":"Qinghong Cui, H. Kan, Jinxian Zhao, Jianhong Shen, Kai Xue","doi":"10.1049/CP.2017.0129","DOIUrl":"https://doi.org/10.1049/CP.2017.0129","url":null,"abstract":"As challenges of urban development are progressively prominent, smart city provides a new solution and brings important opportunities. In order to grasp main research hotspots and explore evolution process of the smart city in China, data sources of this paper are journal articles about smart city from China National Knowledge Infrastructure database. Three co-word matrixes are built by BibExcel, and also used to make multivariate statistical analyses by SPSS 22.0. Based on the above analyses, three proposals are put forward: implementation of smart city needs multilateral cooperation under government orientation; smart city construction should integrate developing visions, present diversities with urban characteristics; the development of smart city needs to pay full attention to technological progress and economic growth.","PeriodicalId":424212,"journal":{"name":"4th International Conference on Smart and Sustainable City (ICSSC 2017)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134277179","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 acquisition of location-based services (LBS) has become a powerful tool to connect and link people with similar interest across long distances. To observe human mobility behavior and patterns it is very important to understand and measure the frequency of location based social network (LBSN) use. In this paper, we investigate the check-in behavior difference during middle week of the month, for whom we observe the gender and their frequency of using Chinese microblog Sina Weibo over a period of time in Shanghai. Current study allows us to examine how check-in behavior vary in same weeks but in different years, it also helps study mobility patterns and practices in terms of time & space in Shanghai. In order to produce smooth density surface of check-ins, we analyze the overall spatial patterns by using the kernel density estimation (KDE). Initial results indicates difference in social media usage behavior during middle week in different years. We interpret these findings as suggestive evidence that location-based social media data can provide a new outlook to observe mobility patterns and intensity of check-ins. It can also help to observe variations in population density over the period of time and act as a tool to estimate mobility demand in the city.
{"title":"Location based social media data analysis for observing check-in behavior and city rhythm in Shanghai","authors":"M. Rizwan, S. Mahmood, Wan Wanggen, Sagib Ali","doi":"10.1049/CP.2017.0107","DOIUrl":"https://doi.org/10.1049/CP.2017.0107","url":null,"abstract":"The acquisition of location-based services (LBS) has become a powerful tool to connect and link people with similar interest across long distances. To observe human mobility behavior and patterns it is very important to understand and measure the frequency of location based social network (LBSN) use. In this paper, we investigate the check-in behavior difference during middle week of the month, for whom we observe the gender and their frequency of using Chinese microblog Sina Weibo over a period of time in Shanghai. Current study allows us to examine how check-in behavior vary in same weeks but in different years, it also helps study mobility patterns and practices in terms of time & space in Shanghai. In order to produce smooth density surface of check-ins, we analyze the overall spatial patterns by using the kernel density estimation (KDE). Initial results indicates difference in social media usage behavior during middle week in different years. We interpret these findings as suggestive evidence that location-based social media data can provide a new outlook to observe mobility patterns and intensity of check-ins. It can also help to observe variations in population density over the period of time and act as a tool to estimate mobility demand in the city.","PeriodicalId":424212,"journal":{"name":"4th International Conference on Smart and Sustainable City (ICSSC 2017)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122789324","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 Speed-up Robust Features (SURF) algorithm has a good scale invariance in the image matching process. Its speed is fast, but it is not stable enough in the feature point extraction. Harris algorithm is an efficient corner detection algorithm, but it cannot handle the issue of scale variance in the image. Therefore, this paper considers the combination of the Speedup Robust Features algorithm and Harris algorithm in the image matching process. First, we use the Harris algorithm to extract the corner points of the two images and obtain the feature point set. Then we use the SURF algorithm to extract the feature points of the two corner set and obtain the new point set. Finally, we use the random sample consensus method to remove the error points, achieve an exact match points set and match the two images. Experiments show that the combination of the two algorithms can improve the quality of Unmanned Aerial Vehicle image matching with high efficiency and strong robustness.
{"title":"UAV image matching based on surf feature and harris corner algorithm","authors":"Cheng Cheng, Xuzhi Wang, Xiangjie Li","doi":"10.1049/CP.2017.0116","DOIUrl":"https://doi.org/10.1049/CP.2017.0116","url":null,"abstract":"The Speed-up Robust Features (SURF) algorithm has a good scale invariance in the image matching process. Its speed is fast, but it is not stable enough in the feature point extraction. Harris algorithm is an efficient corner detection algorithm, but it cannot handle the issue of scale variance in the image. Therefore, this paper considers the combination of the Speedup Robust Features algorithm and Harris algorithm in the image matching process. First, we use the Harris algorithm to extract the corner points of the two images and obtain the feature point set. Then we use the SURF algorithm to extract the feature points of the two corner set and obtain the new point set. Finally, we use the random sample consensus method to remove the error points, achieve an exact match points set and match the two images. Experiments show that the combination of the two algorithms can improve the quality of Unmanned Aerial Vehicle image matching with high efficiency and strong robustness.","PeriodicalId":424212,"journal":{"name":"4th International Conference on Smart and Sustainable City (ICSSC 2017)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127457130","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：