结合感知哈希与空间约束的室内连续视觉定位方法

doi:10.11947/j.AGCS.2021.20200286

测绘学报 ›› 2021, Vol. 50 ›› Issue (12): 1639-1649.doi: 10.11947/j.AGCS.2021.20200286

• 位置服务与地理空间信息处理 • 下一篇

结合感知哈希与空间约束的室内连续视觉定位方法

张星^1,2,3, 林静^1,2,3, 李清泉^1,2,3, 刘涛⁴, 方志祥⁵

1. 深圳大学广东省城市空间信息工程重点实验室, 广东深圳 518060;
2. 深圳大学自然资源部大湾区地理环境监测重点实验室, 广东深圳 518060;
3. 深圳大学空间信息智能感知与服务深圳市重点实验室, 广东深圳 518060;
4. 河南财经政法大学资源与环境学院, 河南郑州 450002;
5. 武汉大学测绘遥感信息工程国家重点实验室, 湖北武汉 430079

收稿日期:2020-06-28 修回日期:2021-03-23 发布日期:2022-01-08
通讯作者: 李清泉 E-mail:liqq@szu.edu.cn
作者简介:张星(1982—),男,博士,研究员,研究方向为室内定位和行人导航。
基金资助:
国家自然科学基金（42071434；41801376；41771473）；广东省自然科学基金（2018A030313289）；深圳市科技创新委员会基础研究项目（JCYJ20180305125033478；JCYJ20170818144544900）；中国博士后科学基金（2020M682293）

Continuous indoor visual localization using a perceptual Hash algorithm and spatial constraint

ZHANG Xing^1,2,3, LIN Jing^1,2,3, LI Qingquan^1,2,3, LIU Tao⁴, FANG Zhixiang⁵

1. Guangdong Key Laboratory of Urban Informatics, Shenzhen University, Shenzhen 518060, China;
2. MNR Key Laboratory for Geo-Environmental Monitoring of Great Bay Area, Shenzhen University, Shenzhen 518060, China;
3. Shenzhen Key Laboratory of Spatial Smart Sensing and Services, Shenzhen 518060, China;
4. College of Resources and Environment, Henan University of Economics and Law, Zhengzhou 450002, China;
5. State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China

Received:2020-06-28 Revised:2021-03-23 Published:2022-01-08
Supported by:
The National Natural Science Foundation of China (Nos. 42071434;41801376;41771473);The Natural Science Foundation of Guangdong Province (No. 2018A030313289);The Shenzhen Scientific Research and Development Funding Program (Nos. JCYJ20180305125033478;JCYJ20170818 144544900);The China Postdoctoral Science Foundation (No. 2020M682293)

摘要/Abstract

摘要： 视觉定位主要通过相机视觉信息与环境视觉特征的匹配实现位置计算。然而视觉匹配计算量较大，难以支持室内连续定位。对于视觉数据稀疏的环境，单纯依靠视觉匹配也难以实现连续的轨迹定位。针对这一问题，本文提出一种结合感知哈希与空间约束的室内连续视觉定位方法，通过智能手机采集的连续视频帧与室内图像数据集的匹配，实现精确的视觉定位。为改进视觉匹配效率，构建了一种双层次的匹配图像搜索策略，包括基于感知哈希方法的全局搜索策略和顾及运动连续性的局部搜索策略。在此基础上，设计了一种室内连续视觉定位算法，结合视觉匹配与航位推算提高视觉定位的空间连续性，并利用运动恢复结构方法提高航向角估计精度。试验结果表明，本文方法在图像匹配定位、连续离线定位、连续在线定位模式下的平均定位误差分别为0.70、0.86和0.93 m，能够达到亚米级定位精度。在线定位模式下，本文方法的平均计算时间为0.42 s，能够支持连续的视觉定位。

关键词: 室内定位, 视觉定位, 图像匹配, 感知哈希, 运动恢复结构

Abstract: Visual localization achieves indoor localization by matching visual data (collected by camera) with visual features of an environment. However, visual feature matching requires a long computation time, which makes it difficult to provide a continuous localization result. Besides, for environment with sparse visual data (e.g. images), it is also difficult to achieve continuous indoor localization using only visual feature matching. To solve this problem, this study proposes a continuous indoor localization approach using perceptual Hash algorithm (pHash) and spatial-constrained image searching strategies. It realizes accurate indoor localization by matching the collected video frames (from smartphone) with the images from a generated indoor image dataset. To improve the efficiency of visual feature matching, a two-level image searching and matching strategy is designed, including a pHash-based global searching strategy and a local strategy considering motion continuity. Based on the two-level strategy, a continuous indoor visual localization algorithm is proposed, which can increase the spatial continuity of localization result by integrating both visual localization and dead reckoning. Besides, this algorithm employs a structure from motion method to improve its heading estimation accuracy. Experimental results show that the localization errors of the image querying, continuous offline localization and online localization of this method are approximately 0.70, 0.86 and 0.93 m, respectively, which achieves sub-meter level localization accuracy. In the online localization condition, its average computation time is about 0.42 s, which can provide continuous visual localization.

Key words: indoor localization, visual localization, image matching, perceptual Hash, structure from motion

中图分类号:

P228

张星, 林静, 李清泉, 刘涛, 方志祥. 结合感知哈希与空间约束的室内连续视觉定位方法[J]. 测绘学报, 2021, 50(12): 1639-1649.

ZHANG Xing, LIN Jing, LI Qingquan, LIU Tao, FANG Zhixiang. Continuous indoor visual localization using a perceptual Hash algorithm and spatial constraint[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(12): 1639-1649.

参考文献

[1] 陈锐志,陈亮.基于智能手机的室内定位技术的发展现状和挑战[J].测绘学报, 2017, 46(10):1316-1326.DOI:10.11947/j.AGCS.2017.20170383. CHEN Ruizhi, CHEN Liang. Indoor positioning with smartphones:the state-of-the-art and the challenges[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10):1316-1326. DOI:10.11947/j.AGCS.2017.20170383.
[2] 李清泉,周宝定,马威,等. GIS辅助的室内定位技术研究进展[J].测绘学报, 2019, 48(12):1498-1506.DOI:10.11947/j.AGCS.2019.20190455. LI Qingquan, ZHOU Baoding, MA Wei, et al. Research process of GIS-aided indoor localization[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(12):1498-1506. DOI:10.11947/j.AGCS.2019.20190455.
[3] LIM C H, WAN Yahong, NG B P, et al. A real-time indoor WiFi localization system utilizing smart antennas[J]. IEEE Transactions on Consumer Electronics, 2007, 53(2):618-622.
[4] 吴东金,夏林元.面向室内WLAN定位的动态自适应模型[J].测绘学报, 2015, 44(12):1322-1330.DOI:10.11947/j.AGCS.2015.20130780. WU Dongjin, XIA Linyuan. Dynamic adaptive model for indoor WLAN localization[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(12):1322-1330. DOI:10.11947/j.AGCS.2015.20130780.
[5] ZHUANG Yuan, YANG Jun, LI You, et al. Smartphone-based indoor localization with bluetooth low energy beacons[J]. Sensors, 2016, 16(5):596-615.
[6] HAZAS M, HOPPER A. Broadband ultrasonic location systems for improved indoor positioning[J]. IEEE Transactions on Mobile Computing, 2006, 5(5):536-547.
[7] ATHALYE A, SAVIC V, BOLIC M, et al. Novel semi-passive RFID system for indoor localization[J]. IEEE Sensors Journal, 2013, 13(2):528-537.
[8] DE ANGELIS A, DWIVEDI S, HÄNDEL P. Characterization of a flexible UWB sensor for indoor localization[J]. IEEE Transactions on Instrumentation and Measurement, 2013, 62(5):905-913.
[9] SUBBU K P, GOZICK B, DANTU R. Locate me:magnetic-fields-based indoor localization using smartphones[J]. ACM Transactions on Intelligent Systems and Technology, 2013, 4(4):73-99.
[10] LOWRY S, SVNDERHAUF N, NEWMAN P, et al. Visual place recognition:a survey[J]. IEEE Transactions on Robotics, 2016, 32(1):1-19.
[11] DI Kaichang, WAN Wenhui, ZHAO Hongying, et al. Progress and applications of visual SLAM[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(2):38-49. DOI:10.11947/j.JGGS.2019.0205.
[12] CHENG Chuanqi, HAO Xiangyang, LI Jiansheng, et al. A robust Gaussian mixture model for mobile robots' vision-based pose estimation[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(3):79-90. DOI:10.11947/j.JGGS.2019.0308.
[13] HUANG J Y, LEE S H, TSAI C H. A fast image matching technique for the panoramic-based localization[C]//Proceedings of 2016 IEEE/ACIS:the 15th International Conference on Computer and Information Science (ICIS).Okayama, Japan:IEEE, 2016:1-6.
[14] SATTLER T, LEIBE B, KOBBELT L. Fast image-based localization using direct 2D-to-3D matching[C]//Proceedings of 2011 International Conference on Computer Vision.Barcelona, Spain:IEEE, 2011:667-674.
[15] GAO Ruipeng, TIAN Yang, YE Fan, et al. Sextant:towards ubiquitous indoor localization service by photo-taking of the environment[J]. IEEE Transactions on Mobile Computing, 2016, 15(2):460-474.
[16] XIAO Aoran, CHEN Ruizhi, LI Deren, et al. An indoor positioning system based on static objects in large indoor scenes by using smartphone cameras[J]. Sensors, 2018, 18(7):2229.
[17] WU Dewen, CHEN Ruizhi, CHEN Liang. Visual positioning indoors:human eyes vs. smartphone cameras[J]. Sensors, 2017, 17(11):2645-2650.
[18] WU Teng, LIU Jingbin, LI Zheng, et al. Accurate smartphone indoor visual positioning based on a high-precision 3D photorealistic map[J]. Sensors, 2018, 18(6):1974-1994.
[19] ZHOU Yan, ZHENG Xianwei, CHEN Ruizhi, et al. Image-based localization aided indoor pedestrian trajectory estimation using smartphones[J]. Sensors, 2018, 18(1):258-276.
[20] LOWE D G. Distinctive image features from scale-invariant key points[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[21] BAY H, ESS A, TUYTELAARS T, et al. Speeded-up robust features (SURF)[J]. Computer Vision and Image Understanding, 2008, 110(3):346-359.
[22] SIAGIAN C, ITTI L. Rapid biologically-inspired scene classification using features shared with visual attention[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(2):300-312.
[23] LIU Tao, ZHANG Xing, LI Qingquan, et al. A visual-based approach for indoor radio map construction using smartphones[J]. Sensor,2017, 17(8):1790-1807.
[24] LIU Tao, ZHANG Xing, LI Qingquan, et al. An accurate visual-inertial integrated geo-tagging method for crowdsourcing-based indoor localization[J]. Remote Sensing, 2019, 11(16):1912-1934.
[25] SCHNEIDER M, CHANG S F. A robust content based digital signature for image authentication[C]//Proceedings of the 3rd IEEE International Conference on Image Processing.Lausanne, Switzerland:IEEE, 1996, 3:227-230.
[26] FRIDRICH J, GOLJAN M. Robust hash functions for digital watermarking[C]//Proceedings of 2000 International Conference on Information Technology:Coding and Computing.Las Vegas, NV, USA:IEEE, 2000:178-183.
[27] 乔君.基于图像内容安全的感知哈希方法研究[D].上海:上海应用技术大学, 2017. QIAO Jun. Research on perceptual Hashing based on image content security[D]. Shanghai:Shanghai Institute of Technology, 2017.
[28] 陈斌.基于感知哈希算法的监控视频认证研究[D].深圳:深圳大学, 2017. CHEN Bin. Research on surveillance video authentication based on perceptual Hash algorithm[D]. Shenzhen:Shenzhen University, 2017.
[29] 王前.基于视频感知哈希的动态手势跟踪方法研究[D].兰州:兰州理工大学, 2018. WANG Qian. Research on dynamic hand gesture tracking method based on video perceptual hashing[D]. Lanzhou:Lanzhou University of Technology, 2018.
[30] 陈优良,肖钢,卞焕,等.一种融合动态预测的感知哈希目标跟踪算法[J].测绘通报, 2020(2):17-23.DOI:10.13474/j.cnki.11-2246.2020.0038. CHEN Youliang, XIAO Gang, BIAN Huan, et al. A perceptual Hash target tracking algorithm based on dynamic prediction[J]. Bulletin of Surveying and Mapping, 2020(2):17-23. DOI:10.13474/j.cnki.11-2246.2020.0038.
[31] 丁凯孟.基于感知哈希的遥感影像认证算法研究[J].测绘学报, 2017, 46(9):1205-1205.DOI:10.11947/j.AGCS.2017.20170233. DING Kaimeng. Perceptual Hashing based authentication algorithm research for remote sensing image[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(9):1205-1205. DOI:10.11947/j.AGCS.2017.20170233.
[32] 张洪帅.基于图像感知哈希的场景分类[D].兰州:兰州大学, 2018. ZHANG Hongshuai. Scene classification based on image perception Hashing[D]. Lanzhou:Lanzhou University, 2018.
[33] LOWE D G. Object recognition from local scale-invariant features[C]//Proceedings of the 7th International Conference on Computer Vision.Kerkyra, Greece:IEEE, 1999, 2:1150-1157.
[34] FISCHLER M A, BOLLES R C. Random sample consensus:A paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6):381-395.

结合感知哈希与空间约束的室内连续视觉定位方法

Continuous indoor visual localization using a perceptual Hash algorithm and spatial constraint

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	陈锐志, 钱隆, 牛晓光, 徐诗豪, 陈亮, 裘超. 基于数据与模型双驱动的音频/惯性传感器耦合定位方法[J]. 测绘学报, 2022, 51(7): 1160-1171.
[2]	李广云, 孙森震, 王力, 冯其强. 可见光通信室内定位技术进展与应用[J]. 测绘学报, 2022, 51(6): 909-922.
[3]	杨高朝, 王庆, 蔚保国, 刘鹏飞, 李爽. 基于抗差LM的视觉惯性里程计与伪卫星混合高精度室内定位[J]. 测绘学报, 2022, 51(1): 18-30.
[4]	薛卫星, 李清泉, 周宝定. 虚拟AP支持的室内非线性约束区域定位[J]. 测绘学报, 2021, 50(5): 569-579.
[5]	陈锐志, 郭光毅, 叶锋, 钱隆, 徐诗豪, 李正. 智能手机音频信号与MEMS传感器的紧耦合室内定位方法[J]. 测绘学报, 2021, 50(2): 143-152.
[6]	邸凯昌, 王镓, 邢琰, 刘召芹, 万文辉, 彭嫚, 王晔昕, 刘斌, 于天一, 李立春, 刘传凯. 深空探测车环境感知与导航定位技术进展与展望[J]. 测绘学报, 2021, 50(11): 1457-1468.
[7]	邵晓航, 吴杭彬, 刘春, 陈晨, 蔡天池, 程帆瑾. 语素关联约束的动态环境视觉定位优化[J]. 测绘学报, 2021, 50(11): 1478-1486.
[8]	周哲, 胡钊政, 李娜, 肖汉彪, 伍锦祥. 面向智能车的地下停车场环视特征地图构建与定位[J]. 测绘学报, 2021, 50(11): 1574-1584.
[9]	于英, 张永生, 薛武, 王涛. 一种稳健性增强和精度提升的增量式运动恢复结构方法[J]. 测绘学报, 2019, 48(2): 207-215.
[10]	李清泉, 周宝定, 马威, 薛卫星. GIS辅助的室内定位技术研究进展[J]. 测绘学报, 2019, 48(12): 1498-1506.
[11]	万杰, Alper YILMAZ. 基于深度卷积特征的影像关系表创建方法[J]. 测绘学报, 2018, 47(6): 882-891.
[12]	程传奇, 郝向阳, 李建胜, 胡鹏, 张旭. 移动机器人视觉动态定位的稳健高斯混合模型[J]. 测绘学报, 2018, 47(11): 1446-1456.
[13]	陈锐志, 陈亮. 基于智能手机的室内定位技术的发展现状和挑战[J]. 测绘学报, 2017, 46(10): 1316-1326.
[14]	陈国良, 张言哲, 汪云甲, 孟晓林. WiFi-PDR室内组合定位的无迹卡尔曼滤波算法[J]. 测绘学报, 2015, 44(12): 1314-1321.
[15]	吴东金, 夏林元. 面向室内WLAN定位的动态自适应模型[J]. 测绘学报, 2015, 44(12): 1322-1330.