<-上一篇/Previous Article 下一篇/Next Article->

[1]郑毅,郑苹.增强现实光照方向估计方法评述与展望[J].智能系统学报,2012,7(5):389-397.
　ZHENG Yi,ZHENG Ping.Comments and perspectives on illumination direction estimation methods in augmented reality[J].CAAI Transactions on Intelligent Systems,2012,7(5):389-397.

点击复制

增强现实光照方向估计方法评述与展望

PDF下载 HTML

《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷: 7 期数: 2012年第5期页码: 389-397 栏目: 综述出版日期: 2012-10-25

Title:: Comments and perspectives on illumination direction estimation methods in augmented reality

文章编号:: 1673-4785(2012)05-0389-09

作者:: 郑毅^1,2,3，郑苹⁴; 1.南京航空航天大学民航/飞行学院，江苏南京 210016；
2.山东工商学院信息与电子工程学院，山东烟台 264005；
3.山东工商学院智能信息处理山东省高校重点实验室，山东烟台 264005；
4.华中科技大学图像识别与人工智能研究所，湖北武汉 430074

Author(s):: ZHENG Yi^1,2, ZHENG Ping³; 1. College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China;
2. School of Information and Electronic Engineering, Shandong Institute of Business and Technology, Yantai 264005, China;
3. Institute for Pattern Recognition and Artificial Intelligence, Huazhong University of Science and Technology, Wuhan 430074, China

关键词:: 增强现实; 光照一致性; 光照方向估计; 立体视觉; 人工智能

Keywords:: augmented reality; illumination consistency; illumination direction estimation; stereo vision; artificial intelligence

分类号:: TP391.41

文献标志码:: A

摘要:: 光照一致性是增强现实中实现虚实融合的重要方面，实时地估计出户外场景中的光照方向，对实现户外场景光照一致性和增强真实感具有重要意义.针对光照方向估计问题，首先归纳了户外场景光照方向估计的特点，把现有的光照方向估计方法分为借助光测球等特殊标定物的估算方法、立体视觉法和人工智能法3类方法.然后总结了各类方法的基本原理和有代表性的研究工作，并且比较了各类方法的优缺点和适用范围.最后，根据实际应用中存在的问题和挑战，展望了户外增强现实系统光照方向估计的研究方向.

Abstract:: Illumination consistency plays an important role in merging virtual objects into real scenes for augmented reality. Realtime illumination direction estimation for outdoor scenes is important for both illumination consistency and high realism of augmented reality. Aiming at problems of illumination direction estimation, characteristics of illumination direction estimation for outdoor scenes are generalized, and the taxonomy of illumination direction estimation methods is presented. Existing illumination direction estimation methods consist of light probe sphere based method, stereo vision based method and artificial intelligence based method. Relevant fundamental principles and typical algorithms are concluded, and their advantages and disadvantages are compared in detail. Finally, according to existing problems and challenges in actual applications, future research trends of illumination direction estimation for outdoor augmented reality systems are foreseen.

参考文献/References:: ［1］朱淼良，姚远，蒋云良．增强现实综述［J］．中国图象图形学报, 2004, 9(7): 767774. 
ZHU Miaoliang, YAO Yuan, JIANG Yunliang. A survey on augmented reality［J］. Journal of Image and Graphics, 2004, 9(7): 767774.
［2］赵沁平．虚拟现实综述［J］．中国科学F辑：信息科学, 2009, 39(1): 246. 
ZHAO Qinping. Overview of virtual reality［J］. Science in China Series F: Information Sciences, 2009, 39(1): 246.
［3］科技部863计划信息技术领域办公室．国家高技术研究发展计划（863计划）信息技术领域“虚实融合的协同工作环境技术与系统”重点项目申请指南［EB/OL］. (20081119)［20120420］. http://www.most.gov.cn/tztg/200811/P020081217461996567919.pdf.
［4］全红艳，王长波，林俊隽．基于视觉的增强现实技术研究综述［J］．机器人, 2008, 30(4): 379384. QUAN Hongyan, WANG Changbo, LIN Junjuan. Survey of visionbased augmented reality technologies［J］. Robot, 2008, 30(4): 379384.
［5］刘艳丽．室外场景的光照分析研究［D］．杭州：浙江大学, 2009: 12. LIU Yanli. Illumination estimation of outdoor scenes［D］. Hangzhou: Zhejiang University, 2009: 12.
［6］常勇，何宗宜．户外增强现实技术及其在地下管网3维可视化中的应用［J］．测绘通报, 2005, 51(11): 5457. 
CHANG Yong, HE Zongyi. Technology of augmented reality and its application in 3D visualization of underground pipeline［J］. Bulletin of Surveying and Mapping, 2005, 51(11): 5457.
［7］杜清运，刘涛．户外增强现实地理信息系统原型设计与实现［J］．武汉大学学报：信息科学版, 2007, 32(11): 10461049. 
DU Qingyun, LIU Tao. Design and implementation of a prototype outdoor augmented reality GIS［J］. Geomatics and Information Science of Wuhan University, 2007, 32(11): 10461049.
［8］石刚，田洪波，马小虎．基于增强现实的户外导航系统的设计与实现［J］．苏州大学学报：自然科学版, 2010, 26(3): 4447. 
SHI Gang, TIAN Hongbo, MA Xiaohu. Design and implementation of outdoor navigation system based on augmented reality［J］. Journal of Suzhou University: Natural Science Edition, 2010, 26(3): 4447.
［9］赵新灿，左洪福．增强现实技术在航空领域中的应用及展望［J］．航空维修与工程, 2008(6): 2325. 
ZHAO Xincan, ZUO Hongfu. Aviation applications and prospect of augmented reality［J］. Aviation Maintenance & Engineering, 2008(6): 2325.
［10］陈靖，王涌天，林精敦，等．基于增强现实技术的圆明园景观数字重现［J］．系统仿真学报, 2010, 22(2): 424428.
CHEN Jing, WANG Yongtian, LIN Jingdun, et al. Digital reconstruction of Yuan Ming Yuan based on augmented reality technology［J］. Journal of System Simulation, 2010, 22(2): 424428.
［11］贾庆轩，高欣，孙汉旭，等．面向机器人遥操作的预测图形仿真技术［J］．航空制造技术, 2011(7): 6063. 
JIA Qingxuan, GAO Xin, SUN Hanxu, et al. Predictive graphical simulation technology for robot teleoperation［J］. Aeronautical Manufacturing Technology, 2011(7): 6063.
［12］HICKS J D, FLANAGAN R A, PETROV P V, et al. Eyekon: augmented reality for battlefield soldiers［C］//Proceedings of the 27th Annual NASA Goddard/IEEE Software Engineering Workshop. Greenbelt, USA, 2002: 156163.
［13］黄天智，刘越，王涌天，等．增强现实技术的军事应用与前景展望［J］．兵工学报, 2006, 27(6): 10431046. 
HUANG Tianzhi, LIU Yue, WANG Yongtian, et al. Military applications and prospect of augmented reality［J］. Acta Armamentarii, 2006, 27(6): 10431046.
［14］卿来云，山世光，陈煕霖，等．基于球面谐波基图像的任意光照下的人脸识别［J］．计算机学报, 2006, 29(5): 760768. 
QING Laiyun, SHAN Shiguang, CHEN Xilin, et al. Face recognition under varying lighting based on the harmonic images［J］. Chinese Journal of Computers, 2006, 29(5): 760768.
［15］孙雪梅，苏菲，蔡安妮．基于分叉树和SVM的人脸图像光照方向估计［J］．中国图象图形学报, 2007, 12(10): 18851888. 
SUN Xuemei, SU Fei, CAI Anni. Illumination direction estimation in face recognition based on bifurcate tree and SVM［J］. Journal of Image and Graphics, 2007, 12(10): 18851888.
［16］陈晓钢，陆玲，刘向阳．经典光照模型实现人脸图像光照方向准确估计［J］．计算机工程与应用, 2009, 45(11): 203205. 
CHEN Xiaogang, LU Ling, LIU Xiangyang. Accurate estimation of face image illuminating direction based on classical lighting model［J］. Computer Engineering and Applications, 2009, 45(11): 203205.
［17］张雯，梁艳梅，常胜江．基于方向扫描的图像光照补偿算法［J］．光电子?激光, 2010, 21(3): 435439. ZHANG Wen, LIANG Yanmei, CHANG Shengjiang. Line scanning for illumination compensation of image［J］. Journal of Optoelectronics?Laser, 2010, 21(3): 435439.
［18］吴琼，李国辉，涂丹，等．面向真实性鉴别的数字图像盲取证技术综述［J］．自动化学报, 2008, 34(12): 14581466.
WU Qiong, LI Guohui, TU Dan, et al. A survey of blind digital image forensics technology for authenticity detection［J］. Acta Automatica Sinica, 2008, 34(12): 14581466.
［19］FARID H. Image forgery detection［J］. IEEE Signal Processing Magazine, 2009, 26(2): 1625.
［20］吕颖达，申铉京，苗健，等．基于光源方向不一致性的局部光源图像盲鉴别方法［J］．吉林大学学报：工学版, 2010, 40(6): 16731677. 
Li Yingda, SHEN Xuanjing, MIAO Jian, et al. Blind identification for light source images based on inconsistency in light source direction［J］. Journal of Jilin University: Engineering and Technology Edition, 2010, 40(6): 16731677.
［21］李叶舟，胡静，牛少彰，等．基于光照方向不一致的图像盲取证技术［J］．北京邮电大学学报, 2011, 34(3): 2630.
LI Yezhou, HU Jing, NIU Shaozhang, et al. Exposing digital image forgeries by detecting inconsistence in light source direction［J］. Journal of Beijing University of Posts and Telecommunications, 2011, 34(3): 2630.
［22］张闯，吕东辉．单幅图像估计光照方向算法研究及其应用［J］．电视技术, 2011, 35(15): 4145. 
ZHANG Chuang, L Donghui. Research and application of single image light direction estimation algorithm［J］. Video Engineering, 2011, 35(15): 4145.
［23］ZHANG Yufei, YANG Y H. Multiple illuminant direction detection with application to image synthesis［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(8): 915920.
［24］BOUGANIS C S, BROOKES M. Multiple light source detection［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(4): 509514.
［25］FENG Yan. Estimation of light source environment for illumination consistency of augmented reality［C］//Proceedings of the 1st International Congress on Image and Signal Processing. Sanya, China, 2008, 3: 771775.
［26］ZHOU Wei, KAMBHAMETTU C. Estimation of illuminant direction and intensity of multiple light sources［C］//Proceedings of the 7th European Conference on Computer Vision. Copenhagen, Denmark, 2002: 206220.
［27］ZHOU Wei, KAMBHAMETTU C. Estimation of the size and location of multiple area light sources［C］//Proceedings of the 17th International Conference on Pattern Recognition. Cambridge, UK, 2004, 3: 214217.
［28］ZHOU Wei, KAMBHAMETTU C. A unified framework for scene illuminant estimation［J］. Image and Vision Computing, 2008, 26(3): 415429.
［29］MA Jintao, ZHOU Ya, HAO Qun, et al. Efficient estimation of multiple illuminant directions using cmeans clustering and selfcorrection for augmented reality［C］//Proceedings of the 2009 8th IEEE/ACIS International Conference on Computer and Information Science. Shanghai, China, 2009: 11061110.
［30］ZHENG Qinfen, CHELLAPPA R. Estimation of illuminant direction, albedo, and shape from shading［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13(7): 680702.
［31］HARA K, NISHINO K, IKEUCHI K. Light source position and reflectance estimation from a single view without the distant illumination assumption［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(4): 493505.
［32］XIE Feng, TAO Linmi, XU Guangyou. Estimating illumination parameters using spherical harmonics coefficients in frequency space［J］. Tsinghua Science and Technology, 2007, 12(1): 4450.
［33］BINGHAM M, TAYLOR D, GLEDHILL D, et al. Illuminant condition matching in augmented reality: a multivision, interest point based approach［C］//Proceedings of the 2009 6th International Conference on Computer Graphics, Imaging and Visualization: New Advances and Trends. Tianjin, China, 2009: 5761.
［34］SATO I, SATO Y, IKEUCHI K. Illumination distribution from shadows［C］//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Fort Collins, USA, 1999, 1: 306312.
［35］WANG Yang, SAMARAS D. Estimation of multiple directional light sources for synthesis of augmented reality images［J］. Graphical Models, 2003, 65(4): 185205.
［36］WANG Yang, SAMARAS D. Estimation of multiple directional illuminants from a single image［J］. Image and Vision Computing, 2008, 26(9): 11791195.
［37］LI Yuanzhen, LIN S, LU Hanqing, et al. Multiplecue illumination estimation in textured scenes［C］//Proceedings of the Ninth IEEE International Conference on Computer Vision. Nice, France, 2003, 2: 13661373.
［38］姚远，朱淼良，卢广．增强现实场景光源的实时检测方法和真实感渲染框架［J］．计算机辅助设计与图形学学报, 2006, 18(8): 12701275. 
YAO Yuan, ZHU Miaoliang, LU Guang. A framework for lighting detection and scene rendering in AR environment［J］. Journal of ComputerAided Design & Computer Graphics, 2006, 18(8): 12701275.
［39］田英利，马颂德，徐孔达．未知光源位置环境中物体形状恢复的神经网络方法研究［J］．自动化学报, 1999, 25(2): 210214. 
TIAN Yingli, MA Songde,TSUI H T. Shape recovery in unknown environment by neural networks［J］. Acta Automatica Sinica, 1999, 25(2): 210214.
［40］CHO S Y, CHOW T W S. Neural computation approach for developing a 3D shape reconstruction model［J］. IEEE Transactions on Neural Networks, 2001, 12(5): 12041214.
［41］KARUNGARU S, FUKUMI M, AKAMATSU N. Identifying scene illumination using genetic algorithms and neural networks［C］//Proceedings of the 9th International Conference on Neural Information Processing. Singapore, 2002, 2: 881885.
［42］KARUNGARU S, FUKUMI M, AKAMATSU N. Neural networks and genetic algorithms for learning the scene illumination in color images［C］//Proceedings of the 2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation. Kobe, Japan, 2003, 3: 10851089.
［43］CHOW C K, YUEN S Y. Illumination direction estimation for augmented reality using a surface input real valued output regression network［J］. Pattern Recognition, 2010, 43(4): 17001716.
［44］NILLIUS P, EKLUNDH J O. Automatic estimation of the projected light source direction［C］//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Kauai, USA, 2001: I1076I1083.
［45］CHANTLER M, PETROU M, PENIRSCHE A, et al. Classifying surface texture while simultaneously estimating illumination direction［J］. International Journal of Computer Vision, 2005, 62(1/2): 8396.
［46］BASRI R, JACOBS D W. Lambertian reflectance and linear subspaces［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(2): 218233.
［47］吴恩华．图形处理器用于通用计算的技术、现状及其挑战［J］．软件学报, 2004, 15(10): 14931504. 
WU Enhua. State of the art and future challenge on general purpose computation by graphics processing unit［J］. Journal of Software, 2004, 15(10): 14931504.
［48］PHARR M. GPU精粹2——高性能图形芯片和通用计算编程技巧［M］. 龚敏敏，译．北京：清华大学出版社, 2007: 327422.
［49］NGUYEN H. GPU精粹3［M］. 杨柏林，陈根浪，王聪，译．北京：清华大学出版社, 2010: 582692.
［50］卢风顺，宋君强，银福康，等．CPU/GPU协同并行计算研究综述［J］．计算机科学, 2011, 38(3): 59, 46. 
LU Fengshun, SONG Junqiang, YIN Fukang, et al. Survey of CPU/GPU synergetic parallel computing［J］. Computer Science, 2011, 38(3): 59, 46.
［51］ECKHORN R, REITBOECK H J, ARNDT M, et al. Feature linking via synchronization among distributed assemblies: simulation of results from cat cortex［J］. Neural Computation, 1990, 2(3): 293307.
［52］JOHNSON J L, PADGETT M L. PCNN models and applications［J］. IEEE Transactions on Neural Networks, 1999, 10(3): 480498.
［53］LINDBLAD T, KINSER J M. Image processing using pulsecoupled neural networks［M］. 2nd ed. ［S.l.］, The Netherlands: Springer, 2005: 3567.
［54］马义德，李廉，绽琨，等．脉冲耦合神经网络与数字图像处理［M］．北京：科学出版社, 2008: 30271.

备注/Memo

收稿日期： 2012-04-20.
网络出版日期：2012-09-07.
基金项目：国家自然科学基金资助项目（60970105，61173173）；山东省住房和城乡建设厅科技计划项目（2011YK060）；山东省高等学校科研计划项目（J11LG12）.
通信作者：郑毅.
E-mail: zhengyi@nuaa.edu.cn.
作者简介：
郑毅，男，1975年生，讲师，博士后，主要研究方向为增强现实、图像测量、三维重建和图像融合.主持或参与国家自然科学基金、总装备部技术改造项目、省住建厅和省教育厅项目多项，发表学术论文10余篇，其中被EI检索9篇. 
郑苹，女，1973年生，博士研究生，主要研究方向为模式识别与计算机视觉.参与国家自然科学基金和总装备部预研项目多项，发表学术论文10篇，其中被EI检索8篇、SCI检索1篇.

更新日期/Last Update: 2012-11-13

增强现实光照方向估计方法评述与展望 PDF下载HTML

备注/Memo

增强现实光照方向估计方法评述与展望

PDF下载 HTML