At local or regional scales,where Landsat has been extensively applied to monitor burned areas,semi-or fully automated methods are not very common.Koutsias et al.([2013].“A Rule-Based Semi-Automatic Method to map Bur...At local or regional scales,where Landsat has been extensively applied to monitor burned areas,semi-or fully automated methods are not very common.Koutsias et al.([2013].“A Rule-Based Semi-Automatic Method to map Burned Areas:Exploring the USGS Historical Landsat Archives to Reconstruct Recent Fire History.”International Journal of Remote Sensing 34(20):7049–7068)developed a semi-automatic method to map burned areas consisted of a set of rules that are valid especially when the post-fire image has been captured shortly after the fire.However,the rule-based approach is not free of errors that eventually create limitations to adopt this method for reconstructing the fire history in a fully automated mode.In this work,we improved the method by revisited and improving the rules that have been developed in the first paper,especially for reducing the omission errors.Minor changes have been made to almost all rules;however,one of the rules has been revised and changed the most as compared to the others by also considering the short-wave infrared channel TM5(in Landsat-5 or Landsat-7).In this case,the algorithm could successfully capture the fire scar in dry vegetated areas as well.Due to the lack of reference data collected in the field,we used reference data collected by photo interpretation,and the accuracy assessment showed that these had a high agreement with the burned land mapping results.展开更多
A hybrid approach to English Part-of-Speech(PoS) tagging with its target application being English-Chinese machine translation in business domain is presented,demonstrating how a present tagger can be adapted to learn...A hybrid approach to English Part-of-Speech(PoS) tagging with its target application being English-Chinese machine translation in business domain is presented,demonstrating how a present tagger can be adapted to learn from a small amount of data and handle unknown words for the purpose of machine translation.A small size of 998 k English annotated corpus in business domain is built semi-automatically based on a new tagset;the maximum entropy model is adopted,and rule-based approach is used in post-processing.The tagger is further applied in Noun Phrase(NP) chunking.Experiments show that our tagger achieves an accuracy of 98.14%,which is a quite satisfactory result.In the application to NP chunking,the tagger gives rise to 2.21% increase in F-score,compared with the results using Stanford tagger.展开更多
本文将小波算法、分水岭算法及基于区域的模糊 C 均值算法相结合,提出了一种基于规则的二次分割方法实现对脑组织磁共振图像的分割。首先,采用一种基于小波的滤波器去除图像中的噪声;然后采用分水岭算法实现对图像的初始分割。为克服分...本文将小波算法、分水岭算法及基于区域的模糊 C 均值算法相结合,提出了一种基于规则的二次分割方法实现对脑组织磁共振图像的分割。首先,采用一种基于小波的滤波器去除图像中的噪声;然后采用分水岭算法实现对图像的初始分割。为克服分水岭算法的过度分割问题,本文提出了基于区域的模糊 C 均值(RFCM)聚类算法实现对过度分割区域的合并。尽管分水岭算法存在过度分割现象,仍有一些区域分割得并不完全,尤其是在脑脊液与灰质,或灰质与白质的过渡区域。为此,本文提出一种局部区域连续性与全局信息相结合的基于规则的多阈值分割方法,对分水岭算法初始分割不完全的区域再次分割。通过对大量模拟数据和真实数据分割的实验证明了此方法的准确性和可靠性。展开更多
基金funding from the European Union’s Horizon 2020 research and innovation program under grant agreement no.633464(https://cordis.europa.eu/project/id/633464).
文摘At local or regional scales,where Landsat has been extensively applied to monitor burned areas,semi-or fully automated methods are not very common.Koutsias et al.([2013].“A Rule-Based Semi-Automatic Method to map Burned Areas:Exploring the USGS Historical Landsat Archives to Reconstruct Recent Fire History.”International Journal of Remote Sensing 34(20):7049–7068)developed a semi-automatic method to map burned areas consisted of a set of rules that are valid especially when the post-fire image has been captured shortly after the fire.However,the rule-based approach is not free of errors that eventually create limitations to adopt this method for reconstructing the fire history in a fully automated mode.In this work,we improved the method by revisited and improving the rules that have been developed in the first paper,especially for reducing the omission errors.Minor changes have been made to almost all rules;however,one of the rules has been revised and changed the most as compared to the others by also considering the short-wave infrared channel TM5(in Landsat-5 or Landsat-7).In this case,the algorithm could successfully capture the fire scar in dry vegetated areas as well.Due to the lack of reference data collected in the field,we used reference data collected by photo interpretation,and the accuracy assessment showed that these had a high agreement with the burned land mapping results.
基金supported by the National Natural Science Foundation of China under Grant No.61173100the Fundamental Research Funds for the Central Universities under Grant No.GDUT10RW202
文摘A hybrid approach to English Part-of-Speech(PoS) tagging with its target application being English-Chinese machine translation in business domain is presented,demonstrating how a present tagger can be adapted to learn from a small amount of data and handle unknown words for the purpose of machine translation.A small size of 998 k English annotated corpus in business domain is built semi-automatically based on a new tagset;the maximum entropy model is adopted,and rule-based approach is used in post-processing.The tagger is further applied in Noun Phrase(NP) chunking.Experiments show that our tagger achieves an accuracy of 98.14%,which is a quite satisfactory result.In the application to NP chunking,the tagger gives rise to 2.21% increase in F-score,compared with the results using Stanford tagger.
文摘本文将小波算法、分水岭算法及基于区域的模糊 C 均值算法相结合,提出了一种基于规则的二次分割方法实现对脑组织磁共振图像的分割。首先,采用一种基于小波的滤波器去除图像中的噪声;然后采用分水岭算法实现对图像的初始分割。为克服分水岭算法的过度分割问题,本文提出了基于区域的模糊 C 均值(RFCM)聚类算法实现对过度分割区域的合并。尽管分水岭算法存在过度分割现象,仍有一些区域分割得并不完全,尤其是在脑脊液与灰质,或灰质与白质的过渡区域。为此,本文提出一种局部区域连续性与全局信息相结合的基于规则的多阈值分割方法,对分水岭算法初始分割不完全的区域再次分割。通过对大量模拟数据和真实数据分割的实验证明了此方法的准确性和可靠性。
