众包模式在大规模遥感影像信息提取领域的探索

doi:10.11959/j.issn.2096-0271.2016066

Abstract

Abstract:

Based on geospatial data cloud(GSCloud),the application of crowdsourcing in large scale information extraction from satellite images was studied,and a systematic architecture of this paradigm was proposed.By performing an experiment of extracting lakes on Qinghai-Tibetan plateau from landsat images,various aspects of the paradigm like the incentive mechanism,task assignment method,task division and many others were explored.Results show that paying part of the reward in advance and assigning a task to a team instead of individuals do not help attracting more applicants and improving the quality of results.And the accumulation of talents is of critical importance to obtain high-quality task results.Since this paradigm integrates crowdsourcing and machine computing power,and it is generic,it can be applied in more massive remote sensing image processing work which requires much human intervention.

Key words: remote sensing image, information extraction, crowdsourcing, GSCloud

Jianghua ZHAO, Xuezhi WANG, Qinghui LIN, Jianhui LI, Yuanchun ZHOU. Exploration of crowdsourcing in information extraction from remote sensing images[J]. Big Data Research, 2016, 2(6): 53-64.

Figures/Tables 8

References 37

[1]	黄文虎, 曹登庆, 韩增尧 . 航天器动力学与控制的研究进展与展望[J]. 力学进展, 2012,42(4): 367-394. HUANG W H , CAO D Q , HAN Z Y . Advances and trends in dynamics and control of spacecrafts[J]. Advances in Mechanics, 2012,42(4): 367-394.
[2]	BELLO O M , AINA Y A . Satellite remote sensing as a tool in disaster management and sustainable development:towards a synergistic approach[J]. Procedia - Social and Behavioral Sciences, 2014(120): 365-373.
[3]	YAN L , ROY D P . Automated crop field extraction from multi-temporal web enabled landsat data[J]. Remote Sensing of Environment, 2014,144(144): 42-64.
[4]	MUELLER N , LEWIS A , ROBERTS D ,et al. Water observations from space:mapping surface water from 25 years of landsat imagery across Australia[J]. Remote Sensing of Environment, 2016(174): 341-352.
[5]	LESIV M , MOLTCHANOVA E , SCHEPASCHENKO D ,et al. Comparison of data fusion methods using crowdsourced data in creating a hybrid forest cover map[J]. Remote Sensing, 2016,8(3): 261.
[6]	CHU D A , KAUFMAN Y J , ZIBORDI G ,et al. Global monitoring of air pollution over land from the earth observing system-terra moderate resolution imaging spectroradiometer (MODIS)[J]. Journal of Geophysical Research, 2003,108(D21): 1-18.
[7]	吕超, 吕游 . 遥感影像信息提取技术的研究与实现[J]. 黑龙江工程学院学报, 2014,28(1): 34-37. LV C , LV Y . Research and realization of remote sensing image information extraction technologies[J]. Journal of Heilongjiang Institute of Technology, 2014,28(1): 34-37
[8]	兰泽英 . 基于土地利用空间知识挖掘的高分辨率遥感影像分类[D]. 武汉:武汉大学, 2010. LAN Z Y . High resolution RS image classification based on spatial knowledge mining of land use[D]. Wuhan:Wuhan University, 2010
[9]	臧艺 . 基于面向对象和集成学习的高分辨率地物要素半自动提取方法与实现[D]. 北京:中国测绘科学研究院, 2008. ZANG Y . Semi-automatic approach and implementation of feature extraction for high resolution remote sensing image based on object oriented and ensemble learning[D]. Beijing:Chinese Academy of Surveying and Mapping, 2008.
[10]	POHL C , J V G . Review article multisensor image fusion in remote sensing:concepts,methods and applications[J]. International Journal of Remote Sensing, 1998,19(5): 823-854.
[11]	YUAN J . Automatic building extraction in aerial scenes using convolutional networks[J]. 2016:arXiv:1602.06564.
[12]	黄小兵 . 高分辨率遥感影像建筑物提取方法研究[D]. 西安:西安科技大学, 2014. HUANG X B . A study of building exttraction from high resolution remote sensing image[D]. Xi＇an:Xi＇an Technology University, 2014.
[13]	崔卫红 . 基于图论的面向对象的高分辨率影像分割方法研究[D]. 武汉:武汉大学, 2010. CUI W H . Research on graph theory based object oriented high resolution image segmentation[D]. Wuhan:Wuhan University, 2010.
[14]	吴秀芸 . 基于高分辨率遥感影像的建筑物提取及轮廓矢量化研究[D]. 南京:南京大学, 2011. WU X Y . Research on extraction and Contour vectorization of buildings from high-resolution remote sensed images[D]. Nanjing:Nanjing University, 2011.
[15]	MA Y , CHEN F , LIU J ,et al. An automatic procedure for early disaster change mapping based on optical remote sensing[J]. Remote Sensing, 2016,8(4): 272.
[16]	BARRINGTON L , GHOSH S , GREENE M ,et al. Crowdsourcing earthquake damage assessment using remote sensing imagery[J]. Annals of Geophysics, 2011,54(6): 680-687.
[17]	KAZAI G , KAMPS J,MILIC-FRAYLING N . An analysis of human factors and label accuracy in crowdsourcing relevance judgments[J]. Information Retrieval, 2013,16(2): 138-178.
[18]	FIENEN M N , LOWRY C S.Social . water-a crowdsourcing tool for environmental data acquisition[J]. Computers and Geosciences, 2012,49(4): 164-169.
[19]	GAO J , LIU X , OOI B C ,et al. An online cost sensitive decision-making method in crowdsourcing systems[C]// The ACM SIGMOD International Conference on Management of Data,June 22-27,2013, New York,USA.[S.l.:s.n.], 2013: 217-228.
[20]	FRATERNALI P , CASTELLETTI A,SONCINI-SESSA R ,et al. Putting humans in the loop:social computing for water resources management[J]. Environmental Modelling and Software, 2012,37(17): 68-77.
[21]	AHN L V , . Human computation[C]// The 46th Annual Design Automation Conference,July 26-31,20091 SanFranciso,CA. New York: ACM Press 2009: 418-419.
[22]	LIU X , LU M , OOI B C ,et al. CDAS:a crowdsourcing data analytics system[J]. Proceedings of the VLDB Endowment, 2012,5(10): 1040-1051.
[23]	KITTUR A , SMUS B , KRAUT R . CrowdForge:Crowdsourcing Complex Work[C]// The 24th Annual ACM Symposium on Vser interface Software and technology,October 16-19,2011, Santa Barbara,USA. New York: ACM Press 2011: 43-52.
[24]	FRITZ S , SEE L , MCCALLUM I ,et al. Mapping global cropland and field size[J]. Global Change Biology, 2015,21(5): 1980-1992.
[25]	FRITZ S , PERGER C,SEEL , et al . A campaign to collect volunteered geographic information on land cover and human impact information on land cover and human impact[M]. [S.l.:s.n.], 2012: 83-91.
[26]	FRITZ S , MCCALLUM I , SCHILL C ,et al. Geo-wiki:an online platform for improving global land cover[J]. Environmental Modelling and Software, 2012,31(7): 110-123.
[27]	SEE L , COMBER A , SALK C ,et al. Comparing the quality of crowdsourced data contributed by expert and nonexperts[J]. Plos One, 2013,8(7): 670-692.
[28]	OFLI F , MEIER P , IMRAN M ,et al. Combining human computing and machine learning to make sense of big (aerial) data for disaster response[J]. Big Data, 2016,4(1): 47-59.
[29]	路凯 . Kaggle众包平台的隶属网络模型构建与特征分析[D]. 大连:大连理工大学, 2015. LU K . Affiliation network model＇s constructing and characteristics analysis based on Kaggle crowdsourcing platform[D]. Dalian:Dalian University of Technology, 2015.
[30]	FOODY G M . Status of land cover classification accuracy assessment[J]. Remote Sensing of Environment, 2002,80(1): 185-201.
[31]	朱小宁 . 支持任务推送的众包系统的研究与实现[D]. 北京:北京邮电大学, 2014. ZHU X N . Research and implementation of a crowdsourcing system supporting task routing[D]. Beijing:Beijing University of Posts and Telecommunications, 2014.
[32]	DIPALANTINO D , VOJNOCIC M . Crowdsourcing and all-pay auctions[C]// The 10th ACM Conference on Electronic Commerce,July 6-10,2009, Stanford,California. New York: ACM Press 2009: 119-128.
[33]	张志强, 逄居升, 谢晓芹 ,等. 众包质量控制策略及评估算法研究[J]. 计算机学报, 2013,36(8): 1636-1649. ZHANG Z , PANG J , XIE X ,et al. Research on crowdsourcing quality control strategies and evaluation algorithm[J]. Chinese Journal of Computers, 2013,36(8): 1636-1649
[34]	IMRAN M , LYKOURENTZOU I , CASTILLO C . Engineering crowdsourced stream processing systems[J]. Computer Science, 2013(1): 1-32.
[35]	KITTUR A , NICKERSON J V , BERNSTEIN M ,et al. The future of crowd work[C]// Conference on Computer Supported Cooperative Work,June 27-29,2013, Whistler,Canada.[S.l.:s.n.], 2013: 1301-1318.
[36]	HO C J , VAUGHAN J W . Online task assignment in crowdsourcing markets[C]// The TwentySixth AAAI Conference on Artificial Intelligence,July 22-26,2012, Toronto,Canada.[S.l.:s.n.], 2012: 45-51.
[37]	DOW S , KULKARNI A , BUNGE B ,et al. Shepherding the crowd:managing and providing feedback to crowd workers[C]// Extended Abstracts on Human Factors in Computing Systems,April 10-15,2010, Atlanta,USA. New York: ACM Press 2011: 1669-1674.

Metrics

Recommended 0

No Suggested Reading articles found!

子任务	1995年	2000年	2005年	2010年	2015年
生产者精度	92.2%	90.1%	93.4%	91.4%	92.3%
用户精度	97.1%	98.1%	96.5%	97.8%	93.2%
整体精度	96.5%	97.8%	95.7%	96.3%	94.5%

子任务	处理人数量/个	合格结果数量/个	不合格结果报酬/元	总报酬/元
1995-East	2	1	0	12 000
1995-NW	2	1	0
1995-SW	2	1	0
2000-East	2	1	800	16 800
2000-NW	2	2	0
2000-SW	2	1	0
2005-WR	2	1	2 400	14 400
2010-East	2	1	800	13 600
2010-NW	2	1	800
2010-SW	2	1	0
2015-East	1	1	0	12 000
2015-NW	1	1	0
2015-SW	1	1	0

Exploration of crowdsourcing in information extraction from remote sensing images

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 37

Related Articles 4

Metrics

Recommended 0

[1]	Lifan HAN, Zijing JI, Zirui CHEN, Xin WANG. Research on information extraction methods for historical classics under the threshold of digital humanities [J]. Big Data Research, 2022, 8(6): 26-39.
[2]	Haishan GUAN, Yulong ZHENG, Bifan WEI, Zemin ZHANG, Hao YUE, Bin SHI, Bo DONG. Extraction and visualization analysis of key elements of tax preferential policies [J]. Big Data Research, 2022, 8(5): 106-123.
[3]	Zhitao ZHAO, Lijun ZHAO, Zheng ZHANG, Ping TANG. Integration of remote sensing intelligent processing algorithm using container cloud technology [J]. Big Data Research, 2022, 8(2): 58-74.
[4]	Ju FAN, Yueguo CHEN, Xiaoyong DU. Progress on human-in-the-loop data preparation [J]. Big Data Research, 2019, 5(6): 3-18.