基于可视范围的图像检索方法

doi:10.3724/SP.J.1047.2016.01030

地球信息科学学报 ›› 2016, Vol. 18 ›› Issue (8): 1030-1036.doi: 10.3724/SP.J.1047.2016.01030

• 地球信息科学理论与方法 • 上一篇下一篇

基于可视范围的图像检索方法

吴勇^1,²(), 姚凌³, 童为民¹

1. 福建师范大学地理科学学院,福州 350007
2. 福建省陆地灾害监测评估工程技术研究中心,福州 350007
3. 中国科学院地理科学与资源研究所资源与环境信息系统国家重点实验室,北京 100101

收稿日期:2016-05-12 修回日期:2016-07-01 出版日期:2016-08-10 发布日期:2016-08-10
作者简介:
作者简介:吴勇(1981-),男,福建福州人,博士,主要从事视频GIS、移动GIS研究。E-mail:wuyong3216@163.com
基金资助:
国家自然科学基金项目(41201417);资源与环境信息系统国家重点实验室青年人才培养基金项目(O8R8B6E0YA);福建省自然科学基金项目(2016J01186);福建省测绘地理信息局局校合作科技项目(2016JX02)

A New Image Retrieval Method Based on Image Viewshed

WU Yong^1,^2,^*(), YAO Ling³, TONG Weimin¹

1. College of Geographical Science, Fujian Normal University, Fuzhou 350007, China
2. Fujian Provincial Engineering Research Center for Monitoring and Assessing Terrestrial Disasters, Fuzhou 350007, China
3. State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China

Received:2016-05-12 Revised:2016-07-01 Online:2016-08-10 Published:2016-08-10
Contact: WU Yong

摘要/Abstract

摘要：

图像是视觉所及环境的自然再现,具有表达直观、内容丰富的特性,其已成为GIS空间数据采集与应用中一种重要的可视数据源。随着硬件终端的高速发展,集成的传感器愈加丰富,多源传感器信息融合已成为移动GIS数据釆集的发展趋势。针对移动终端获取方位角偏差问题,本文重点阐述了基于移动终端的重力传感器与磁力传感器获取镜头拍摄朝向的算法,并基于EXIF图像格式实现了图像元数据、定位信息、方位信息一体化采集生成可定位图像。针对现有可定位图像以点代面建模方式的不足,本文以镜头视野范围AOV（Angle of View）模型为基础,提出了以图像元数据、位置信息以及方位信息构建图像可视域的方法,并采用多级网格方式对图像可视域面状特征建立空间索引,实现基于可视域的图像检索。在此基础上,针对福建省野外遥感核查采集的8022幅可定位图像,采用点建模及可视域建模2种方式建立检索图像集。从检索速度、检索结果2个方面进行对比分析,表明基于可视域图像检索方法不仅能检索出拍摄位置在检索区域内的图像,还可检索出拍摄位置在检索区域外但实际拍摄场景在检索范围内的图像。同时,通过多级空间网格索引可提升6.22-8.64倍检索速度。

关键词: 可定位图像, EXIF格式, 图像可视域, 多级网格空间索引, 图像检索

Abstract:

Image is a natural representation of the real world, which has the characteristics of intuitionistic expression and rich content. It has become an important visual data source in GIS data acquisition and application. With the rapid development of hardware terminal, the sensors integrated in mobile terminal become more abundant, and multi-sensor data fusion has become a trend in mobile GIS data collection. Aiming at the problem of obtaining azimuth deviation of mobile terminal, this paper emphasized on the acquisition algorithm of camera shooting directions, which was based on a gravity sensor and a magnetic sensor embedded in mobile terminals. Based on the EXIF format, locatable images were generated by the integrated collection of image metadata, location and direction. To overcome the disadvantages of existing modeling method of taking a surface as a point for locatable image, this paper proposed a method to build image viewshed by using image metadata, location and direction based on the model of lens’ angle of view. Multi-level grid was used to build the spatial index for the polygon feature of the image viewshed. Based on this method, a case study was conducted in Fujian province. In the experiment, 8022 locatable images were collected by field verification of remote sensing. Point based modeling and polygon based modeling were utilized to build the retrieved image set. Retrieval speed and results were compared and analyzed. It showed that the image retrieval results could be more accurate based on image viewshed modeling. It could retrieve images of which the actual shooting position located inside and outside of the retrieval area. Meanwhile, the image retrieval speed could increase 6.22 to 8.64 times by using the multi-level grid spatial index.

Key words: locatable image, exchangeable image file (EXIF) format, image viewshed, multi-level grid spatial index, image retrieval

吴勇, 姚凌, 童为民. 基于可视范围的图像检索方法[J]. 地球信息科学学报, 2016, 18(8): 1030-1036.DOI:10.3724/SP.J.1047.2016.01030

WU Yong,YAO Ling,TONG Weimin. A New Image Retrieval Method Based on Image Viewshed[J]. Journal of Geo-information Science, 2016, 18(8): 1030-1036.DOI:10.3724/SP.J.1047.2016.01030

图/表 9

图1

表1

图2

图3

图4

图5

图6

表2

图7

参考文献 20

[1]	Sakire A A, Zhang L Y, Seon H K, et al.GRVS: A georeferenced video search engine[C]. International Conference on Multimedia, 2009:977-978.
[2]	李德仁,郭晟,胡庆武.基于3S集成技术的LD2000系列移动道路测量系统及其应用[J].测绘学报,2008,37(3):272-276. doi: 10.3321/j.issn:1001-1595.2008.03.002
	[ Li D R, Guo S, Hu Q W.3S(RS,GPS,GIS) integration technology based LD2000 series mobile mapping system and its applications[J]. Acta Geodaetica et Cartographica Sinica, 2008,37(3):272-276. ] doi: 10.3321/j.issn:1001-1595.2008.03.002
[3]	罗腾元,吴勇,陈友飞.有声可定位图像采集方法[J].计算机工程与设计,2015,36(5):2872-2876. doi: 10.16208/j.issn1000-7024.2015.10.051
	[ Luo T Y, Wu Y, Chen Y F.Acquisition method of phonic-locatable image[J]. Computer Engineering and Design, 2015,36(5):2872-2876. ] doi: 10.16208/j.issn1000-7024.2015.10.051
[4]	Xu X B, Mei T, Zeng W J, et al.AMIGO: Accurate mobile image geotagging[C]. ACM International Conference on Internet Multimedia Computing and Services, 2012:11-14.
[5]	Luo Z, Li H, Tang J, et al.Estimating poses of world's photos with geographic metadata[C]. Advances in Multimedia Modelling, 2010:695-700.
[6]	Yue J, Li Z B, Liu L, et al.Content-based image retrieval using color and texture fused features[J]. Mathematical and Computer Modelling, 2011,54:1121-1127. doi: 10.1016/j.mcm.2010.11.044
[7]	Zhu Z L, Zhao C X, Hou Y K.Research on similarity measurement for texture image retrieval[J]. PLoS ONE, 2012,7(9):1-14. doi: 10.1371/journal.pone.0045302 pmid: 23049785
[8]	Qi H, Li K Q, Shen Y M, et al.Statistics based features combining method for figurative image retrieval[J]. ICIC Express Letters, 2011,5(6):1941-1946.
[9]	Sergieh H M, Watzinger D, Huber B, et al.World-wide scale geotagged image dataset for automatic image annotation and reverse geotagging[C]. ACM Multimedia Systems Conference, 2014:47-52.
[10]	Toyama K, Logan R, Roseway A.Geographic location tags on digital images[C]. Proceedings of the Eleventh ACM International Conference on Multimedia, 2003:156-166.
[11]	吴勇,王美珍,罗腾元.可定位图像采集与检索方法研究[J].计算机工程,2015(7):207-211,220.
	[ Wu Y, Wang M Z, Luo T Y.Research on acquisition and retrieval method of locatable image[J]. Computer Engineering, 2015,7:207-211,220.
[12]	Blank D, Allali S E, Muller W.Henrich: sample-based creation of peer summaries for efficient similarity search in scalable peer-to-peer networks[C]. ACM SIGMM Workshop on Multimedia Information Retrieval, 2007:143-152.
[13]	Liu Q, Yoo J J, Jang B T, et al.A scalable videogis system for GPS-guided vehicles[J]. Signal Processing: Image Communication, 2005,20:205-218. doi: 10.1109/ICASSP.2004.1327267
[14]	宋宏权,刘学军,闾国年,等.基于视频的地理场景增强表达研究[J].地理与地理信息科学,2012,28(5):6-9.
	[ Song H Q, Liu X J, Lv G N, et al.Research on augmenting aerial earth maps using videos[J]. Geography and Geo-Information Science, 2012,28(5):6-9. ]
[15]	Pau L, Stewart F, Adam W.Spatial video and GIS[J]. International Journal of Geographical Information Science, 2011,25(5):697-716.
[16]	武文波,刘向锋.GIS中数字图像与地理位置的整合方法与应用[J].微计算机信息,2011,27(4):235-237. doi: 10.3969/j.issn.2095-6835.2011.04.094
	[ Wu W B, Liu X F.Integration methods and applications of digital image and location in GIS[J]. Microcomputer Information, 2011,27(4):235-237. ] doi: 10.3969/j.issn.2095-6835.2011.04.094
[17]	李文闯,章永平,潘瑜春.移动地理信息系统中多源异构数据融合模型[J].计算机应用,2012,32(9):2672-2674,2678. doi: 10.3724/SP.J.1087.2012.02672
	[ Li W C, Zhang Y P, Pan Y C.Multi-source heterogeneous data fusion model in mobile geographic information system[J]. Journal of Computer Applications, 2012,32(9):2672-2674,2678. doi: 10.3724/SP.J.1087.2012.02672
[18]	Jeita CP-3451. Exchangeable image file format for digital still cameras: Exif version 2.2[S]. Japan Electronics and Information Technology Industries Association, Tokyo: Jap, 2002:1-72.
[19]	Tim D.Matchmoving: the invisible art of camera tracking, 2nd Edition[M]. John Wiley & Sons, 2012:115-118.
[20]	周勇,何建农,涂平.自动调配的层次网格空间索引技术[J].计算机应用,2005,25(6):1401-1404. doi: 10.3724/SP.J.1087.2005.1401
	[ Zhou Y, He J N, Tu P.Technique of auto-selection multi-Layers grid spatial index[J]. Journal of Computer Applications, 2005,25(6):1401-1404. ] doi: 10.3724/SP.J.1087.2005.1401

EXIF	存储参数	参数描述及存储位置
EXIF IFD	图像高度	图像纵向像素数,存储于ImageLength标签
	图像宽度	图像横向像素数,存储于ImageWidth标签
	拍摄时间	图像拍摄时间,存储于DateTime标签
	焦距	拍摄图像时镜头焦距长度,存储于FocalLength 标签
	水平视角	当前焦距下镜头水平视角,其值小于180°,以<水平视角>参数值</水平视角>存储于UserComment标签
	垂直视角	当前焦距下镜头垂直视角,其值小于180°,以<垂直视角>参数值</垂直视角>存储于UserComment标签
	放大倍数	图像拍摄时镜头数码变焦倍数,定焦时默认为0,变焦时为大于1的浮点数,储存于DigitalZoom标签
GPS IFD	经度值	拍摄位置经度,存储于GPSLongitude标签
	经度参考	经度参考,东经为“E”,西经为“W”,存储于GPSLongitudeRef标签
	纬度值	拍摄位置纬度,存储于GPSLatitude标签
	纬度参考	纬度参考,北纬为“N”,南纬为“S”,存储于GPSLatitudeRef标签
	拍摄方位	拍摄时镜头朝向,其值范围为0~360°,存储于GPSImgDirection标签

组别	数据集构建方式	检索面积/km²	检索耗时/ms		耗时比（无索引/索引）	检索结果/幅
组别	数据集构建方式	检索面积/km²	无索引	多级网格索引	耗时比（无索引/索引）	检索结果/幅
1	点模型	100.1	136.7	15.8	8.65	1
1	面模型	100.1	148.2	22.5	6.58	1
2	点模型	119.1	137.6	16.0	8.60	3
2	面模型	119.1	152.8	22.2	6.88	4
3	点模型	121.6	133.5	18.0	7.41	5
3	面模型	121.6	155.4	25.0	6.22	5
4	点模型	133.3	135.9	16.4	8.29	4
4	面模型	133.3	154.7	22.2	6.97	6
5	点模型	165.4	134.5	18.8	7.15	13
5	面模型	165.4	162	23.4	6.92	15

基于可视范围的图像检索方法

A New Image Retrieval Method Based on Image Viewshed

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 20

相关文章 2

Metrics

本文评价

推荐阅读 0

[1]	万其明, 汪闽, 张星月, 蒋圣, 谢玉林. 基于五叉树分解与多特征直方图匹配的高分辨遥感图像检索[J]. 地球信息科学学报, 2010, 12(2): 275-281.
[2]	朱光良, 陆丽珍. 遥感图像检索系统的设计与实现[J]. 地球信息科学学报, 2005, 7(4): 15-19,24.