视觉slam发展史--从开始到未来
1980年,Hans Moravec的在斯坦福大學的博士論文已經用視覺在機器人導航避障中使用。?Hans Moravec是占據柵格地圖的締造者。
Hans Moravec. Obstacle Avoidance and Navigation in the Real World by a Seeing Robot Rover. Ph.D. thesis.March 1980 Computer Science Department. Stanford University
參考鏈接:Robot Navigation (Hans Moravec 1980 PhD thesis)Preface and Table of Contents
再早一點,1977年? ?towards automatic visual obstacle avoidance的論文。
? ? ? ? ? ? ? ? ? 1979年, visual mapping by a robot rover。
0、視覺slam之前,是各種基于聲吶、雷達、激光等傳感器感知周圍環境的slam技術,代表人物:H. Durrant-Whyte
J. J. Leonard. Directed Sonar Sensing for Mobile Robot Navigation. PhD thesis,University of Oxford, 1990.
?
J. J. Leonard and H. F. Durrant-Whyte. Directed Sonar Navigation. Kluwer AcademicPress, 1992.
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
一、視覺slam早期的幾個重點人物:David Murray、A.J. Davison、Philip Torr, Ian Reid
(主要列舉上世紀90年代,以及20世紀初2010年之前的大師級人物?
? ?orbslam的作者R Mur-Artal,LSD/DSO等作者都是2010年以后的故事了)
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------
二、人物關系:牛津大學的David Murray教授,帶了幾個博士生包括A.J. Davison,最后都去了相應名校當博導了。
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------
三、視覺slam借鑒了很多計算機視覺研究成果,包括:圖像的角點、邊緣、線等;特征點(關鍵點和描述子);光流法;基于圖像特征的運動計算;SFM(structure from motion,有點類似非相鄰幀 非實時的slam技術)
----------------------------------------------------------------------------------------------------------------------------------------------------------------------
H.C. Longuet-Higgins. A computer algorithm for reconstructing a scene from two projections. Nature, 293:133{135, 1981.
?
1987年?C G Harris 論文??Determination of Ego-Motion from Matched Points.?
----------------------------------------------------------------------------------------------------------------------------------------------------------------------
F. Li. Active Stereo for AGV Navigation. PhD thesis, University of Oxford, 1996
?
1999年,A.J. Davison博士論文。?現帝國理工學院研究視覺和slam相關,博導牛津大學的David Murray,同門Philip Torr, Ian Reid
? ? A.J. Davison, “Mobile Robot Navigation Using Active Vision,”PhD dissertation, Univ. of Oxford, 1999.
注意:此時的active navigation在視覺方面都是雙攝像頭的立體視覺,大家都認為立體視覺才能做視覺slam
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
1999年,P.M. Newman, 的博士論文。 現牛津大學的教授,研究視覺和slam相關
? ? P.M. Newman, “On the Structure and Solution of the Simultaneous Localization and Map Building Problem,” PhD dissertation, Univ. of Sydney, 1999.
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
A.J. Davison的單目視覺slam橫空出世,在此之前人們認為只有立體視覺才能實現視覺slam,意義重大。(網上這樣說,在此之前是否有人用單目實現過,未查證。)
2003年,A.J. Davison論文,Google引用率 2000+,很經典,此前幾年發明很多相關論文,未列出。
? ??Real-time simultaneous localisation and mapping with a single camera.AJ Davison.Iccv 3, 1403-1410
基于濾波方案,視頻查看鏈接:Index of /~ajd/Movieshttp://www.doc.ic.ac.uk/~ajd/Movies/
2007年,A.J. Davison論文,Google引用率 3300+,很經典,此前幾年發明很多相關論文,未列出。
? ??MonoSLAM: Real-time single camera SLAM,AJ Davison, ID Reid, ND Molton, O Stasse.IEEE Transactions on Pattern Analysis & Machine Intelligence, 1052-1067
注意:參考A.J. Davison的博士論文,上面四行左右有列舉說明,之前都是雙攝像頭的立體視覺做視覺slam,所以突然出來個單目視覺slam算是開創者了。
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------
2007年,G. Klein and D. Murray論文
? ? PTAM:G. Klein and D. Murray. Parallel tracking and mapping for small AR workspaces. In Proc. Sixth IEEE and ACM International?Symposium on Mixed and Augmented Reality (ISMAR’07), Nara, Japan, November 2007
? ?(注釋:PTAM用的是FAST角點檢測特征,此時ORB特征思想還未被提出。ORB特征2011年才被提出E. Rublee, V. Rabaud, K.? ? ? Konolige, and G. Bradski, “ORB: An efficient alternative to SIFT or SURF,” in Proc. IEEE Int. Conf. Comput.? ? ? ? ?Vision,Barcelona,? ? ? Spain, Nov. 2011, pp. 2564–2571.)
2011年,RA Newcombe論文,A.J. Davison團隊學生,Google引用率 3000+
? ??KinectFusion: Real-time dense surface mapping and tracking,RA Newcombe, S Izadi, O Hilliges, D Molyneaux, D Kim, AJ Davison, ...ISMAR, {127--136}
? ??KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera,S Izadi, D Kim, O Hilliges, D Molyneaux, R Newcombe, P Kohli, J Shotton, ...Proceedings of the 24th annual ACM symposium on User interface software?
? ??DTAM: Dense tracking and mapping in real-time,RA Newcombe, SJ Lovegrove, AJ Davison.2011 international conference on computer vision, 2320-2327
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------
2015年,Raúl Mur-Artal論文。現Research Scientist at Facebook Reality Labs ,西班牙薩拉戈薩大學,博導Tardós Solano, Juan Domingo,是一個人名,簡稱JD Tardos
? ??ORB-SLAM: a Versatile and Accurate Monocular SLAM System,R Mur-Artal, JMM Montiel, JD Tardos. IEEE Transactions on Robotics 31 (5), 1147-1163
? ? (注釋:ORB特征2011年被提出,2013年的一篇論文使用過ORB特征。S. Song, M. Chandraker, and C. C. Guest, “Parallel,? ? ? ? ? ? real-time monocular visual odometry,” in Proc. IEEE Int. Conf. Robot. Autom., 2013,pp. 4698–4705.)
? ??Monocular SLAM for User Viewpoint Tracking in Virtual Reality,R Mur-Artal, JD Tardós. Workshop on Challenges in Virtual Reality, ICRA 2015
2017年,Raúl Mur-Artal論文
? ??ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras,R Mur-Artal, JD Tardos. IEEE Transactions on Robotics 33 (5), 1255-1262
? ??Visual-inertial monocular SLAM with map reuse,R Mur-Artal, JD Tardós.IEEE Robotics and Automation Letters 2 (2), 796-803
? ??Real-Time Accurate Visual SLAM with Place Recognition,R Mur Artal, JD Tardós Solano.Universidad de Zaragoza, Prensas de la Universidad.博士論文
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
ORB-SLAM 發展史(ORB-SLAM、ORB-SLAM2、ORB-SLAM3、以及其他變種版本)
ORB-SLAM 是西班牙薩拉戈薩大學博士生?Raul Murartal于2015年實現發表的論文,實際上ORB特征并非他本人發明,首次使用在slam系統中也并非他, 但是他將ORB特征應用在了vslam 的整個系統中,并給出了開源軟件,這一點很強大。
Murartal R, Montiel J M, Tardos J D, et al. ORB-SLAM: A Versatile and Accurate Monocular SLAM System[J]. IEEE Transactions on Robotics, 2015, 31(5): 1147-1163.(ORB-SLAM原文)
ORB-SLAM 的特征點選擇、匹配用到了ORB特征? ?
Song S, Chandraker M, Guest C C, et al. Parallel, real-time monocular visual odometry[C]. international conference on robotics and automation, 2013: 4698-4705.(首次在slam系統中使用ORB特征的論文,用在了視覺里程計VO)
ORB(Oriented FAST and Rotated BRIEF)
E. Rublee, V. Rabaud, K. Konolige, and G. Bradski. ORB: an ecient alternative to SIFT or SURF. In IEEE International Conference on Computer Vision (ICCV), pages 2564{2571, Barcelona, Spain, 2011.? ?(ORB特征 原文)
和ORB類似的一種用于圖像拼接的方法論文。
M. Brown, S. Winder, and R. Szeliski. Multi-image matching using multi-scale oriented patches. In Computer Vision and Pattern Recognition, pages 510–517, 2005.
ORB參考的FAST detector 和BRIEF descriptor
E. Rosten and T. Drummond. Machine learning for highspeed corner detection. In European Conference on Computer Vision, volume 1, 2006? (FAST原文)
M. Calonder, V. Lepetit, C. Strecha, and P. Fua. Brief: Binary robust independent elementary features. In In European Conference on Computer Vision, 2010.? (BRIEF 原文)
SIFT()? 拿來和ORB比較的特征
D. G. Lowe. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2):91–110, 2004.
SURF(Speeded Up Robust Features)??拿來和ORB比較的特征
H. Bay, T. Tuytelaars, and L. Van Gool. Surf: Speeded up robust features. In European Conference on Computer Vision, May 2006.
點和線的融合用于高性能跟蹤(2005)
Rosten, E., Drummond, T.: Fusing points and lines for high performance tracking. In: 10th IEEE International Conference on Computer Vision. Volume 2., Beijing,China, Springer (2005) 1508–1515
gives an analysis of various ways of measuring orientation of corners(1999)
P. L. Rosin. Measuring corner properties. Computer Vision and Image Understanding, 73(2):291 – 307, 1999.
Shi-Tomasi角點算子原文(1994)
Shi, J., Tomasi, C.: Good features to track. In: 9th IEEE Conference on Computer Vision and Pattern Recognition, Springer (1994)
Harris角點檢測原文,沒有descriptor部分(1988)
C. Harris and M. Stephens. A combined corner and edge detector. In Alvey Vision Conference, pages 147–151, 1988
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
三、視覺slam目前主流的是基于特征的方法、直接法(光流法),前者從PTAM 到ORB-SLAM系列以及SVO等比較經典主流
? ? ? 后者是慕尼黑工業大學的Jakob Engel及其導師D Cremers團隊的DSO/ LSD等作品
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
四、其他的基于特征點、線、面或者組合的形式也多有涉及, 視覺slam融合慣性模塊,視覺slam融合激光等多傳感器,
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
五、下一步:語義slam
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
六、視覺slam研究相關實驗室和大咖 。 轉載:計算機視覺牛人博客和代碼匯總(全) - findumars - 博客園
? ? ? ?圖像配準的前世今生:從人工設計特征到深度學習
? ? ? ? ?從基于特征點或光流直接法,到用深度學習來實現的轉變。?圖像配準的前世今生:從人工設計特征到深度學習
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
七、相關資料
1. 清華大學 高翔的博客,半閑居士。
2. 知乎上各種大咖的專題
3.泡泡機器人論壇
4.計算機視覺life公眾號
5.B站相關的各種視頻資料
6.國內外大咖的主頁網站
7.浙江大學從2017年開始 每年組織一屆 slam技術論壇
8.東北大學的吳同學總結資料:
SLAM - 吳言吳語
9.學習書籍推薦:SLAM學習--視覺slam學習教材推薦(附相關技術文檔下載鏈接)_GGY1102的博客-CSDN博客_slam教材
總結
以上是生活随笔為你收集整理的视觉slam发展史--从开始到未来的全部內容,希望文章能夠幫你解決所遇到的問題。
- 上一篇: Python-Opencv学习-实验-1
- 下一篇: 图像处理学习--前篇--像素相关