{"title":"Automatic urban remote sensing images registration based on road networks","authors":"Xirong Guo, Wenyi Zhang, G. Ma","doi":"10.1109/URS.2009.5137685","DOIUrl":"https://doi.org/10.1109/URS.2009.5137685","url":null,"abstract":"This paper proposes a new method of automatic registration of urban remote sensing images that has combined bilinear interpolation which is a classic method of image registration and road networks which are the characters of urban remote sensing images. It comprises of extracting the road network in an urban and computing the Ground Control Points (GCP) from the road junctions, then estimating the parameters of the mapping function and transforming the sensed image at last.","PeriodicalId":154334,"journal":{"name":"2009 Joint Urban Remote Sensing Event","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134267173","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}
{"title":"On-flight calibration and atmospheric correction over city water for wide-field -of-view Hypersepctral Imager","authors":"Bing Zhang, Hao Zhang, Junsheng Li","doi":"10.1109/URS.2009.5137556","DOIUrl":"https://doi.org/10.1109/URS.2009.5137556","url":null,"abstract":"Radioactive calibration and atmospheric correction are two important steps when encountering a new sensor and its remote sensing images. Wide field-of-view Hyperspectral Imager(WHI) is an airborne imaging spectrometer with a 5nm spectral resolution, whose spectrum range is from 406nm to 985nm. For evaluating its applications in city water monitoring, a flight was carried out in Taihu in January 9, 2006, which was the third largest freshwater lake. Meanwhile, the in-situ measured spectra by ASD and measured atmosphere parameters by sun photometer CE318 were also obtained. It is an efficient way to monitoring change of the water-quality by airborne or satellite remote sensing data. To accurately retrieve water-quality parameters, two crucial recalibration processes were done for WHI: 1) Field recalibration was accomplished by comparing the two calibration targets' modeling radiance at sensor level and their lab calibrated radiance ; 2) Vicarious calibration was done by comparing the atmosphere corrected remote sensing reflectance (Rrs) with the in-situ measured Rrs of a synchronous station. Then, atmosphere correction Rrs was performed by 6SV1 model combined with Motran4 to retrieve Rrs of Taihu and the accuracy was no more than 5% from 532nm to 750nm validated by other synchronous stations.","PeriodicalId":154334,"journal":{"name":"2009 Joint Urban Remote Sensing Event","volume":"429 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113995863","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}
Huifang Zhang, Runhe Shi, H. Zhong, P. Qu, Juan Sun, Wenpeng Lin, Su Li
{"title":"Improvement of MODIS 8-day LAI/FPAR product with temporal filters to generate high quality time-series product","authors":"Huifang Zhang, Runhe Shi, H. Zhong, P. Qu, Juan Sun, Wenpeng Lin, Su Li","doi":"10.1109/URS.2009.5137494","DOIUrl":"https://doi.org/10.1109/URS.2009.5137494","url":null,"abstract":"Numerous studies have reported that the time-series terrestrial parameters such as the Normalized Difference Vegetation Index (NDVI), Leaf Area of Index (LAI), Fraction of Absorbed Photosynthetic Active Radiation (FPAR), derived from NOAA/AVHRR, SPOT/VEGETATION, TERRA or AQUA/MODIS, have played significant roles in researching the global environment, terrestrial ecosystems and related ecological researches. However, the remotely sensed signals are interfered severely by atmospheric conditions especially clouds and such noises exists in the time-series products as well. Therefore, to obtain a high quality time-series of terrestrial parameter is a necessary step before further studies. At present several methods have been applied to reduce the noise to construct a fine time-series of NDVI, but few studies concerning the other key terrestrial parameters, such as LAI, FPAR etc. In this paper, after comparing general methods in literatures, we designed a new method based on the Savitzky-Golay filter, which was applied to improve the quality of MODIS 8-Day LAI/FPAR Product to generate time-series of LAI and FPAR with high quality. Our validation results indicate that more smooth and realistic time-series curves of LAI/FPAR can be obtained by using this new method, which exemplify the dynamic change of forests, crop or plants and key input parameters in modeling the complex land surface processing.","PeriodicalId":154334,"journal":{"name":"2009 Joint Urban Remote Sensing Event","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115224306","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}
{"title":"Monitoring water quality of urban water supply sources using optical remote sensing","authors":"Bing Zhang, Q. Shen, Junsheng Li","doi":"10.1109/URS.2009.5137559","DOIUrl":"https://doi.org/10.1109/URS.2009.5137559","url":null,"abstract":"Remote sensing monitors water quality information with wide coverage to monitor spatial change of water bodies easily. Landsat TM has high spatial resolution of 30 meters to monitor details of water bodies. MODIS has its advantage with frequent return visits to monitor algae blooms. Lake Taihu is the third largest freshwater lake in China with cyanophytes blooms annually, which dominates the water sources of Wuxi and Suzhou. The pollution of Taihu Lake has become more and more serious, which leads to contaminated drinking water in Wuxi and Suzhou city. This paper applies 250-meter MODIS level 1B images and Landsat-5 TM images to detect algae blooms, also uses a simplified bio-optical model to estimate concentration of chlorophyll-a in Lake Taihu. The results showed the distribution of algae blooms and chlorophyll a concentration in Lake Taihu at 29th July to 1st August of 2006. The algae blooms often appear at the north and the west of Lake Taihu, which agree with the actual situation. The chlorophyll-a concentrations estimated from MODIS and TM imagery are in appropriate value range in Lake Taihu in summer. The relative errors between in-situ measured and estimated chlorophyll-a concentrations are less than 30%. This study could be helpful to monitor water quality with remote sensing imagery just having red and near-infrared channels such as 250-meter MODIS imagery.","PeriodicalId":154334,"journal":{"name":"2009 Joint Urban Remote Sensing Event","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114291432","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}
{"title":"A modified method for relevance feedback in high-resolution SAR image retrieval system based on SVM","authors":"Chen Rong, Yongfeng Cao, Sun Hong","doi":"10.1109/URS.2009.5137523","DOIUrl":"https://doi.org/10.1109/URS.2009.5137523","url":null,"abstract":"Relevance feedback (RF) is an importance technique in CBIR (Content-Based Image Retrieval) systems to bridge the semantic gap between low-level visual features (eg. color, shape, texture) and high-level human perception. One of the most frequently used methods to do RF is Support Vector Machine (SVM), which has a good generalization ability in pattern recognition. But when the training data is insufficient, the performance of SVM may drop dramatically. In this paper, we proposed a method to alleviate the small sample problem in SVM based RF by using a new piecewise similarity measure function and ensemble learning. We compared our method with standard SVM based RF on a high-resolution SAR (Synthetic Aperture Radar) image database, the experiment results show that our method has a better performance and prove that it's an effective algorithm for RF.","PeriodicalId":154334,"journal":{"name":"2009 Joint Urban Remote Sensing Event","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116169449","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}
Wei Hu, Manchun Li, Zhenjie Chen, Lu Tan, Dong Cai
{"title":"Research of urban space expansion based on GIS and CA Model: — A case study in Wuxi New District","authors":"Wei Hu, Manchun Li, Zhenjie Chen, Lu Tan, Dong Cai","doi":"10.1109/URS.2009.5137545","DOIUrl":"https://doi.org/10.1109/URS.2009.5137545","url":null,"abstract":"Urban planning is human purposeful, conscious social activity. It is influenced by nature and human society. Research of urban planning and urban space expansion is in the forefront of global urban research, and is one of the hot topics. China is troubled by population growth, lack of resources, ecological and environmental degradation, and rational urban development is closely related to sustainable development of important issues. It is needed and valuable to carry out a comprehensive study on urban space expansion because of multi-cause and problem's complex structure. The simulation of urban planning is a kind of effective way to understand how urban space expands. The aim of this paper is to simulate and study urban space expansion by the realization of USE-CA (Urban Space Expansion-Cellular Automata) model.","PeriodicalId":154334,"journal":{"name":"2009 Joint Urban Remote Sensing Event","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125026375","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}
A. Kukko, A. Jaakkola, Matti Lehtomaki, H. Kaartinen, Yuwei Chen
{"title":"Mobile mapping system and computing methods for modelling of road environment","authors":"A. Kukko, A. Jaakkola, Matti Lehtomaki, H. Kaartinen, Yuwei Chen","doi":"10.1109/URS.2009.5137703","DOIUrl":"https://doi.org/10.1109/URS.2009.5137703","url":null,"abstract":"Mobile mapping is a new way of efficiently collecting three-dimensional data from the road environment. Mobile mapping systems are cost efficient and robust technique to acquire information about even highly dynamic environments like highways and urban streets, where the data collection has previously been laborious and even dangerous for the staff performing the surveying. The dynamic mobile mapping systems could access the site with less risk to the personnel and with less need for road closures. The need for high resolution and details captured in to the data for street and road inventories, or city modelling, are the main reasons for the rapid adoption of the mobile mapping techniques in these fields.","PeriodicalId":154334,"journal":{"name":"2009 Joint Urban Remote Sensing Event","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125072799","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}
{"title":"A target detection algorithm for urban areas using HSRH imagery","authors":"Du Bo, Zhang Liangpei, Li Pingxiang, Zhong Yanfei","doi":"10.1109/URS.2009.5137636","DOIUrl":"https://doi.org/10.1109/URS.2009.5137636","url":null,"abstract":"This paper presents an target detection algorithm focusing on making full use of both spatial and spectral features of the high spatial resolution hyperspectral (HSRH) imagery. It use the spatial relationship between pixels in the finite impulse filter with the low dimension data transferred from the original imagery. Experiments show it performs better than the method solely depending on spectral features.","PeriodicalId":154334,"journal":{"name":"2009 Joint Urban Remote Sensing Event","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121428953","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}
Xiaogu Sun, Manchun Li, Yong-xue Liu, Lu Tan, Wei Liu
{"title":"Accelerated segmentation approach with CUDA for high spatial resolution remotely sensed imagery based on improved Mean Shift","authors":"Xiaogu Sun, Manchun Li, Yong-xue Liu, Lu Tan, Wei Liu","doi":"10.1109/URS.2009.5137568","DOIUrl":"https://doi.org/10.1109/URS.2009.5137568","url":null,"abstract":"In conventional researches, satisfying results cannot be achieved when directly applying Mean Shift segmentation onto high spatial resolution (HR) remote sensing image. The proposed method addresses this problem and extents Mean Shift clustering algorithm into high-dimensional feature space by extracting texture and shape descriptor. The dilemma in image segmentation is that the algorithms with good performance are also the ones with much computational cost. To improve the performance of the standard Mean Shift segmentation for HR remote sensing images, an accelerated segmentation approach is proposed under Compute Unified Device Architecture (CUDA) framework. The experimental results demonstrate that the CUDA-based implementation works 20-30 times faster than the original implementation in CPU.","PeriodicalId":154334,"journal":{"name":"2009 Joint Urban Remote Sensing Event","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121470582","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}
{"title":"Boosting cross-modality image registration","authors":"Adrian Barbu, R. Ionasec","doi":"10.1109/URS.2009.5137482","DOIUrl":"https://doi.org/10.1109/URS.2009.5137482","url":null,"abstract":"Cross-modality image registration is a difficult problem because the same structures have different intensity patterns in the two modalities, making straightforward methods based on SSD or cross-correlation not applicable. This paper presents a learning based approach to cross-modality image registration. First, it describes a method to map the image registration problem into a problem of binary classification. Then, it presents a method to select a number of image registration algorithms from a larger pool and combine them by AdaBoost into a boosted algorithm that is more accurate than any of the algorithms in the pool. Finally, it presents a method named virtual boosting that allows to directly obtain the result of the boosted algorithm without performing any parameter search. In our cross-modality image registration application, the algorithm pool consists of many feature-based registration algorithms with different configurations. An experimental validation on the registration of thousands of aerial video frames with satellite images from Google Maps showed that the boosted algorithm has a 20–30% smaller error than the best registration algorithm from the pool (based on SIFT features). More generally, the method presented can be applied to combine a number of algorithms aimed at solving the same problem into a boosted algorithm that is more accurate than any of them.","PeriodicalId":154334,"journal":{"name":"2009 Joint Urban Remote Sensing Event","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126180487","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}