Visual Odometry : Part II: Matching, Robustness, Optimization, and Applications
Open accessThe DOI matches its Crossref record; 92 of the 99 references it cites were found in a registry or an index.
Abstract
Part II of the tutorial has summarized the remaining building blocks of the VO pipeline: specifically, how to detect and match salient and repeatable features across frames and robust estimation in the presence of outliers and bundle adjustment. In addition, error propagation, applications, and links to publicly available code are included. VO is a well understood and established part of robotics. VO has reached a maturity that has allowed us to successfully use it for certain classes of applications: space, ground, aerial, and underwater. In the presence of loop closures, VO can be used as a building block for a complete SLAM algorithm to reduce motion drift. Challenges that still remain are to develop and demonstrate large-scale and long-term implementations, such as driving autonomous cars for hundreds of miles. Such systems have recently been demonstrated using Lidar and Radar sensors [86]. However, for VO to be used in such systems, technical issues regarding robustness and, especially, long-term stability have to be resolved. Eventually, VO has the potential to replace Lidar-based systems for egomotion estimation, which are currently leading the state of the art in accuracy, robustness, and reliability. VO offers a cheaper and mechanically easier-to-manufacture solution for egomotion estimation, while, additionally, being fully passive. Furthermore, the ongoing miniaturization of digital cameras offers the possibility to develop smaller and smaller robotic systems capable of ego-motion estimation.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Fischler, M. A., & Bolles, R. C. (1981) · Communications of the ACM · doi:10.1145/358669.358692 · Cited by 25,893
Multiple View Geometry in Computer Vision
Hartley, R., & Zisserman, A. (2004) · doi:10.1017/cbo9780511811685 · Cited by 21,070
(2012) · Encyclopedia of the Sciences of Learning · doi:10.1007/978-1-4419-1428-6_5195 · Cited by 19,370
SURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955 · cited 6×
“Notice that SIFT, SURF, and CENSURE are not true affine invariant detectors but were empirically found to be invariant up to certain changes of the viewpoint.”
BackgroundInfluentialRobust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097
ORB: An efficient alternative to SIFT or SURF
Rublee, E., Rabaud, V., Konolige, K., & Bradski, G. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126544 · Cited by 11,037
Horn, B. K. P., & Schunck, B. G. (1981) · Artificial Intelligence · doi:10.1016/0004-3702(81)90024-2 · Cited by 10,312
Shi, J., & Tomasi (1994) · Proceedings of IEEE Conference on Computer Vision and Pattern Recognition CVPR-94 · doi:10.1109/cvpr.1994.323794 · Cited by 7,724 · cited 3×
“The VO literature is characterized by many point-feature detectors, such as corner detectors (e.g., Moravec [2], For-stner [10], Harris [11], Shi-Tomasi [12], and FAST [13]) and blob detectors (SIFT [14], SURF [15], and CENSURE [16]).”
BackgroundMethodHorn, B. K., & Schunck, B. G. (1981) · SPIE Proceedings · doi:10.1117/12.965761 · Cited by 7,394
Research works printed but not linked: 5
- dacuda, 2011, Dacuda scanner mouse
- kruppa, 0, Zur ermittlung eines objektes aus zwei perspektiven mit innerer orientierung, Sitz -Ber Akad Wiss Wien math naturw Abt IIa, 122, 1939
- forstner, 1986, A feature based correspondence algorithm for image matching, Int Archives of Photogrammetry, 26, 150
- daimler, 2011, 6d vision
- guizzo, 2011, How Google's Self-driving Car Works
Cited by
Items 301–400 of 621
Application of Active Driving Assist to Remotely Controlled Car in Collision Avoidance
Rouzier, B., Hazaz, M., Murakami, T., & Xu, W. (2018) · IEEJ Journal of Industry Applications · doi:10.1541/ieejjia.7.289 · Cited by 6
Monocular VO Based on Deep Siamese Convolutional Neural Network
Wang, H., Ban, X., Ding, F., Xiao, Y., & Zhou, J. (2020) · Complexity · doi:10.1155/2020/6367273 · Cited by 6
“In robotics and automatic transmission, VO is the process of determining the position and orientation of a robot by using associated camera images [6].”
BackgroundMethodA Comparison Study on Replacing Stereo Disparity with LiDAR in Visual Odometry Methods
Golban, C., Cobarzan, P., & Nedevschi, S. (2020) · IEEE International Conference on Intelligent Computer Communication and Processing (ICCP) · doi:10.1109/iccp51029.2020.9266228 · Cited by 6
Combining photogrammetric and bathymetric data to build a 3D model of a canal tunnel
Moisan, E., Heinkelé, C., Foucher, P., Charbonnier, P., Grussenmeyer, P., Guillemin, S., & Koehl, M. (2021) · The Photogrammetric Record · doi:10.1111/phor.12379 · Cited by 6
Simultaneous calibration of odometry and camera extrinsic for a differential driven mobile robot
Tang, H., Liu, Y., & Li, L. (2015) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2015.7419108 · Cited by 6
A fusion algorithm of visual odometry based on feature-based method and direct method
Feng, J., Zhang, C., Sun, B., & Song, Y. H. (2017) · Chinese Automation Congress · doi:10.1109/cac.2017.8243070 · Cited by 6
“Motion Estimation After the feature matching, motion estimation is to be done, the result of motion estimation could be used as demonstrate how robot moves [7].”
Method3D SLAM in texture-less environments using rank order statistics
Yousif, K., Bab‐Hadiashar, A., & Hoseinnezhad, R. (2015) · Robotica · doi:10.1017/s0263574715000831 · Cited by 6
Gallo, E., & Barrientos, A. (2023) · Aerospace · doi:10.3390/aerospace10080708 · Cited by 12
“Visual Odometry (VO) consists on employing the ground images generated by one or more onboard cameras without the use of prerecorded image databases or any other sensors, incrementally estimating the vehicle pose (position plus attitude) based on the changes that its motion induces on the images [33, 34, 35, 36, 37].”
BackgroundMusleh, B., Martín, D., Armingol, J. M., & de la Escalera, A. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907437 · Cited by 5
“The autocalibration method has been applied to an algorithm of visual odometry [13][14].”
MethodZhuk, R. S., Zalesky, B. A., & Trotski, P. S. (2020) · Informatics · doi:10.37661/1816-0301-2020-17-2-17-24 · Cited by 7
“На сегодняшний день хорошо развиты два подхода к решению этой задачи: V-SLAM [1, 2] и визуальная одометрия [3, 4].”
Guo, G., Dai, Z., & Dai, Y. (2022) · Journal of Navigation · doi:10.1017/s0373463322000236 · Cited by 5
“The robustness experiments under different percentages of outlier conditions The tutorial by Friedrich and Davide (Fraundorfer and Scaramuzza, 2012) only presents a comparison of the number of RANSAC iterations versus percentages of outliers between five-point RANSAC, two-point RANSAC and one-point RANSAC.”
BackgroundMethodInfluentialFeature Extraction Towards Underwater SLAM using Imaging Sonar
Oliveira, A. J., Ferreira, B. M., & Cruz, N. A. (2023) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceanslimerick52467.2023.10244414 · Cited by 5
“According to the characteristics of the feature detector, specific shapes are targeted, which usually consist of corners, blobs or junctions, whose image position can be accurately measured [10].”
BackgroundUAV assisted landing on moving UGV
Bergeon, Y. T., Doskočil, R., Křivánek, V., Motsch, J., & Štefek, A. (2015) · International Conference on Military Technologies · doi:10.1109/miltechs.2015.7153646 · Cited by 5
Visual Odometry and Mapping for Indoor Environments Using RGB-D Cameras
da Silva, B. M. F., & Gonçalves, L. M. G. (2015) · Communications in computer and information science · doi:10.1007/978-3-662-48134-9_2 · Cited by 6
“The problem of map building and localization can also be solved by Visual Odometry [9,28].”
BackgroundXian, Z., Lian, J., Shan, M., Zhang, L., He, X., & Hu, X. (2016) · International Journal of Advanced Robotic Systems · doi:10.1177/1729881416664850 · Cited by 5
Signature Extraction from 3D Point Clouds using Frame Theory for Environmental Modeling
Martino, F., Patruno, C., Marani, R., & Stella, E. (2014) · International Journal on Smart Sensing and Intelligent Systems · doi:10.21307/ijssis-2019-071 · Cited by 4
Keypoint Description by Descriptor Fusion Using Autoencoders
Dai, Z., Huang, X., Chen, W., Chen, C., He, L., Wen, S., & Zhang, H. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197205 · Cited by 5
“Keypoint matching is an important step in many computer vision and robotics applications, such as structure-from-motion (SfM) [1], multi-view stereo (MVS) [2], image retrieval [3] and visual simultaneous localization and mapping (SLAM) [4].”
BackgroundYusefi, A., Durdu, A., & Sungur, C. (2020) · European Journal of Science and Technology · doi:10.31590/ejosat.819735 · Cited by 5
Probabilistic Qualitative Localization and Mapping
Mor, R., & Indelman, V. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341269 · Cited by 7
“An overview of basic methods can be found in [11], [12].”
MethodLocalization of leader-follower formations using kinect and RTK-GPS
Li, R., & Li, Y. (2014) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2014.7090448 · Cited by 5
User Centered Design of an Autonomous Mobile Robot Vending Machine Concept
Navarro, A. S. P. H., Cardeira, C., & Monteiro, C. M. F. (2016) · IEEE International Conference on Autonomous Robot Systems and Competitions · doi:10.1109/icarsc.2016.67 · Cited by 5
Improving the Robustness of a Direct Visual Odometry Algorithm for Planetary Rovers
Martínez, G. (2018) · International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE) · doi:10.1109/iceee.2018.8534000 · Cited by 5
“Refer to [15], [16] for a comprehensive tutorial on visual odometry.”
BackgroundFeature Regions Segmentation Based RGB-D Visual Odometry in Dynamic Environment
Zhang, Y., Dai, W., Peng, Z., Ping, L., & Fang, Z. (2018) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon.2018.8591053 · Cited by 5
“The FRSVO is based on sparse features referring to the method [6] and follows the traditional pipeline of VO [2], [13].”
BackgroundMethodVisual-Inertial Odometry for Unmanned Aerial Vehicle using Deep Learning
Lee, H., McCrink, M. H., & Gregory, J. (2019) · AIAA SciTech Forum · doi:10.2514/6.2019-1410 · Cited by 5
A Survey on sensing Methods and Feature Extraction Algorithms for Slam Problem
Ajay, A., & Venkataraman, D. (2013) · International Journal of Computer Science Engineering and Applications · doi:10.5121/ijcsea.2013.3105 · Cited by 9
Kernel learning for visual perception
Wang, C. (2019) · doi:10.32657/10220/47835 · Cited by 12
Simultaneous Localization and Mapping ( SLAM )
Birk, A., & Pfingsthorn, M. F. (2016) · Wiley eBooks · doi:10.1002/047134608x.w8322 · Cited by 12
Yang, M., Jia, F., Rushworth, A. G. A., Sun, X. S., Fang, Z., & Yang, G. (2024) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea61579.2024.10665033 · Cited by 4
“Moreover, uneven feature distribution can result in certain region of the environment being under sampled or poorly represented [15] [16] [17].”
BackgroundDevelopment of a navigation system for the SnowEater robot
Rivas, E., & Mitobe, K. (2012) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii.2012.6426934 · Cited by 4
Wang, Z., Xu, M. G., Ye, N., Wang, R., & Huang, H. (2018) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2018.00059 · Cited by 4
“Visual odometry (VO) enables the estimation of the locations and orientations of a camera by analyzing a sequence of captured images [12], [13].”
BackgroundVision-Aided Localization and Mapping in Forested Environments Using Stereo Images
Wells, L. A., & Chung, W. (2023) · Sensors · doi:10.3390/s23167043 · Cited by 5
“, using mutual consistency or constrained matching [35]; and (3) pose recovery by minimizing the 3D-2D reprojection error using a perspective from n point (PnP) algorithm, e.”
MethodA comparison of deep learning-based visual odometry algorithms in challenging scenarios
Bruno, H. M. S., Cabral, K., Colombini, E. L., & Givigi, S. N. (2024) · IEEE International Systems Conference (SysCon) · doi:10.1109/syscon61195.2024.10553552 · Cited by 5
“In this way, the estimated trajectories would be more accurate since global optimization can significantly reduce the error accumulated in the trajectories [44].”
BackgroundTQU-SLAM Benchmark Feature-based Dataset for Building Monocular VO
Le, V.-H., Do, H.-S., Phan, V.-N., & Te, T.-H. (2024) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.7611 · Cited by 5
“This problem can be solved with the five-point algorithm or 5-point RANSAC [30, 31].”
MethodComparison of Visual-Inertial Sensor Fusion Techniques for GNSS-Resilient Navigation
Turci, L., Vitiello, F., Causa, F., Opromolla, R., & Fasano, G. (2024) · IEEE/AIAA Digital Avionics Systems Conference (DASC) · doi:10.1109/dasc62030.2024.10748659 · Cited by 4
3D Indoor Map Building with Monte Carlo Localization in 2D Map
Zhao, L., Fan, Z., Li, W., Xie, H., & Yang, X. (2016) · International Conference on Industrial Informatics - Computing Technology, Intelligent Technology, Industrial Information Integration (ICIICII) · doi:10.1109/iciicii.2016.0064 · Cited by 4
Migratory birds-inspired navigation system for unmanned aerial vehicles
Zhang, Y., Chao, A., Zhao, B., Liu, H., & Zhao, X. (2016) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2016.7831835 · Cited by 4
Benchmark system for novel 3D SLAM algorithms
Somlyai, L., Csaba, G., & Vámossy, Z. (2018) · IEEE World Symposium on Applied Machine Intelligence and Informatics (SAMI) · doi:10.1109/sami.2018.8324000 · Cited by 4
“Movement of the robots can be defined more accurate and faster with newer methods [1].”
MethodAn Indoor Navigation System Based on Stereo Camera and Inertial Sensors with Points and Lines
Yang, B., Xu, X., Zhang, T., Li, Y., & Tong, J. (2018) · Journal of Sensors · doi:10.1155/2018/4801584 · Cited by 5
Robust and Optimal Registration of Image Sets and Structured Scenes via Sum-of-Squares Polynomials
Paudel, D. P., Habed, A., Demonceaux, C., & Vasseur, P. (2018) · International Journal of Computer Vision · doi:10.1007/s11263-018-1114-2 · Cited by 4
An Adaptive Unsupervised Learning Framework for Monocular Depth Estimation
Yang, D., Zhong, X., Lin, L., & Peng, X. (2019) · IEEE Access · doi:10.1109/access.2019.2946323 · Cited by 4
“INTRODUCTION Estimating depth of a scene from images is a crucial challenge in computer vision community; it has wide industrial applications such as self-driving platforms [1], robotics [2], augmented reality, localization and navigation systems [3], [4].”
BackgroundRover Relative Localization Testing in Martian Relevant Environment
Chiodini, S., Pertile, M., Giubilato, R., Salvioli, F., Bussi, D., Barrera, M., Franceschetti, P., & Debei, S. (2019) · IEEE International Workshop on Metrology for AeroSpace (MetroAeroSpace) · doi:10.1109/metroaerospace.2019.8869561 · Cited by 5
“In [4] and [5] is presented an overview and a tutorial on visual odometry.”
BackgroundMixed-Degree Cubature H∞ Information Filter-Based Visual-Inertial Odometry
Song, C., Wang, X., & Cui, N. (2018) · Applied Sciences · doi:10.3390/app9010056 · Cited by 4
“Indirect methods have dominated the research field for a long time, and many effective descriptors of features have been developed as shown in [7].”
MethodLü, W., Xiang, Z., & Liu, J. (2015) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.1400139 · Cited by 4
“To deal with this problem, a global position correction algorithm (or loop constraints) was presented and researched (Fraundorfer and Scaramuzza, 2012).”
MethodImproved pose estimation by inlier refinement for visual odometry
More, R., Kottath, R., Jegadeeshwaran, R., Kumar, V., Karar, V., & Poddar, S. (2017) · International Conference on Sensing, Signal Processing and Security (ICSSS) · doi:10.1109/ssps.2017.8071595 · Cited by 4
Improved visual odometry system based on kinect RGB-D sensor
Liu, S.-H., Hsu, C.-C. J., Wang, W., Chen, M.-Y., & Wang, Y.-T. (2017) · IEEE International Conference on Consumer Electronics - Berlin (ICCE-Berlin) · doi:10.1109/icce-berlin.2017.8210581 · Cited by 4
“The remaining details of the VO algorithm can be referred to [6].”
BackgroundMethodLandmarks based human-like guidance for driving navigation in an urban environment
Wang, B., Stafford-Fraser, Q., Robinson, P., Dias, E., & Skrypchuk, L. (2017) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2017.8317802 · Cited by 4
“First, Visual Odometry (VO) is applied to estimate ego-motion parameters and the vehicle’s trajectory.”
BackgroundInfluentialAccurate Image Depth Determination for Autonomous Vehicle Navigation
Sąsiadek, J. Z., & Walker, M. J. (2018) · GeoPlanet: earth and planetary sciences · doi:10.1007/978-3-319-94517-0_5 · Cited by 4
Achievable Stereo Vision Depth Accuracy with Changing Camera Baseline
Sąsiadek, J. Z., & Walker, M. J. (2019) · International Conference on Methods and Models in Automation and Robotics · doi:10.1109/mmar.2019.8864723 · Cited by 4
“UAV navigation using machine vision has been studied previously [6],[7],[8],[9] and [11],[12],[13],[14].”
MethodVisual-inertial odometry with depth sensing using a multi-state constraint Kalman filter
Galfond, M. (2014) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 5
Liu, F. (2018) · Libraries and Cultural Resources (University of Calgary) · doi:10.11575/prism/31740 · Cited by 4
Non-iterative RGB-D-inertial OdometryPreprint
Wang, C., Hoang, M.-C., Xie, L., & Yuan, J. (2017) · arXiv (Cornell University) · Cited by 5
Simultaneous localization and mapping architecture for small bodies and space exploration
Bettens, A., Morrell, B. J., Coen, M. D., Wu, X., Gibbens, P. W., & Chamitoff, G. E. (2023) · Advances in Space Research · doi:10.1016/j.asr.2023.10.048 · Cited by 5
Robot localization using a complementary laser/camera filter
Muhieddine, A., Asmar, D., & Shammas, E. (2014) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2014.7090527 · Cited by 3
“…P.O. Box 11-0236 Lebanon e-mail: (ali.muh.aub@gmail.com, da20@aub.edu.lb, es34@aub.edu.lb ) matching features between different viewpoints, techniques in multiple view geometry [13]—such as the eight-point or five-point algorithm—can be used to extract the transformation between the two views.”
BackgroundStochastic Cloning Unscented Kalman filtering for pedestrian localization applications
Amirhosseini, S. F., Romanovas, M., Schwarze, T., Schwaab, M., Traechtler, M., & Manoli, Y. (2013) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2013.6817893 · Cited by 3
“VO has numerous applications such as robotic, automotive, augmented reality and navigation system for GPSdenied environment [21].”
BackgroundYousif, K., Bab‐Hadiashar, A., & Hoseinnezhad, R. (2014) · RMIT Research Repository (RMIT University Library) · Cited by 3
Estimating heading direction from monocular video sequences using biologically-based sensors
Cree, M. J., Perrone, J. A., Anthonys, G., Garnett, A. C., & Gouk, H. (2016) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2016.7804435 · Cited by 3
“There is enormous attention in the computer vision and robotics communities in developing systems for visual odometry because it is a challenging research problem and has potential to provide better data than is currently obtained from wheel odometry, GPS and inertial sensors [9], [10].”
Visual-based semantic simultaneous localization and mapping for Robotic applications: A review
Atoui, O., Husni, H., & Mat, R. C. (2019) · AIP conference proceedings · doi:10.1063/1.5121082 · Cited by 4
Computer Vision Methods for Automotive Applications
Diaz, A., & Kurka, P. R. G. (2020) · Tecnia · doi:10.21754/tecnia.v30i2.801 · Cited by 3
“The results may be improved in combination with state-ofthe-art techniques in visual navigation for autonomous vehicles [4], [20].”
BackgroundModelling Software Architecture for Visual Simultaneous Localization and Mapping
Mishra, B., Griffin, R. J., & Sevil, H. E. (2021) · Automation · doi:10.3390/automation2020003 · Cited by 3
“Keypoint outlier removal: Often, corresponding feature points are mismatched, and due to a high number of such outliers in the set of correspondences, RANSAC is performed over a camera motion model [10].”
BackgroundMethodInfluentialZwierzchowski, J., Pietrala, D. S., Napieralski, J. A., & Napieralski, A. (2021) · Applied Sciences · doi:10.3390/app11104496 · Cited by 4
“A general discussion of this solution is described in [1,2].”
BackgroundAssumpção, J. P. F., & Cuperschmid, A. R. M. (2021) · Revista de Ciencia y Tecnología · doi:10.36995/j.recyt.2021.35.003 · Cited by 3
Belief functions clustering for epipole localization
Chen, H., Hégarat‐Mascle, S. L., & Aldea, E. (2021) · International Journal of Approximate Reasoning · doi:10.1016/j.ijar.2021.07.003 · Cited by 3
Purposive Sample Consensus: A Paradigm for Model Fitting with Application to Visual Odometry
Wang, J., & Luo, X. (2014) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-07488-7_23 · Cited by 3
“For the sake of robustness, in many practical implementations N is usually multiplied by a factor of ten, which increases much computational costs [1].”
BackgroundMethodInfluentialEvaluation of Feature Detection Algorithms and Epipolar Geometry Based Camera Pose Estimation
Jacob, S. S., Sreeja, S., & Dathan, N. S. (2022) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon49645.2022.9968715 · Cited by 3
“In [2] and [3], the authors have presented a study on Visual odometry, the steps involved, its advantages and applications.”
BackgroundEntropy-based Keyframe Established and Accelerated Fast LiDAR Odometry and Mapping
Zeng, Q.-H., Liu, D., Zhou, Y., & Peng, Y.-X. (2023) · 2023 IEEE 7th Information Technology and Mechatronics Engineering Conference (ITOEC) · doi:10.1109/itoec57671.2023.10291983 · Cited by 6
Nguyen, T.-H., Le, V.-H., Do, H.-S., Te, T.-H., & Phan, V.-N. (2024) · Future Internet · doi:10.3390/fi16050174 · Cited by 4
“To solve this problem, one can use the five-point algorithm, or 5-point RANSAC [22,48].”
MethodOn the Use of Visual Perception for Unmanned Surface Vehicles Navigation
Salgado, A., Bezerra, A. A., Clua, E., & Gonçalves, L. M. G. (2024) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars64411.2024.10786469 · Cited by 3
“This brings us to the problem known as visual odometry (VO) [14], [15], which is an alternative to the localization problem for autonomous vehicles [12].”
A vision-based system supports mapping services for visually impaired people in indoor environments
Nguyen, Q.-H., Vu, H., Tran, T.-H., & Nguyen, Q.-H. (2014) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2014.7064541 · Cited by 3
“Furthermore, matching a current view to a position on the created map seems to be the hardest problem in many works [1], [7].”
BackgroundVisual odometry system simulator
Abdulov, A., & Abramenkov, A. N. (2017) · International Siberian Conference on Control and Communications · doi:10.1109/sibcon.2017.7998584 · Cited by 3
“Keypoint and blob features are very important, since their position may be estimated accurately enough [4].”
BackgroundMethodCompass aided visual-inertial odometry
Wang, Y., Zhang, T., Wang, Y., Ma, J., Li, Y., & Han, J. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.12.029 · Cited by 4
Methods for visual servoing of robotic systems: A state of the art survey
Jokić, A., Petrović, M., & Miljković, Z. (2018) · Tehnika · doi:10.5937/tehnika1806801j · Cited by 4
Salient FlowNet and Decoupled LSTM Network for Robust Visual Odometry
Chen, M., Wang, C., & Liu, H. (2019) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio49542.2019.8961700 · Cited by 3
DIRECT SPARSE VISUAL ODOMETRY WITH STRUCTURAL REGULARITIES FOR LONG CORRIDOR ENVIRONMENTS
Cheng, F., Liu, C., Wu, H., & Ai, M. (2020) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xliii-b2-2020-757-2020 · Cited by 3
“In contrast to a complete SLAM pipeline, visual odometry (VO), which tracks the camera’s pose from a series of images (without global optimization such as loop closure and relocalization), often drifts over time (Fraundorfer, Scaramuzza, 2012).”
BackgroundPredicting the long-term robustness of visual features
Metka, B., Besetzny, A., Bauer-Wersing, U., & Franzius, M. (2015) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2015.7251497 · Cited by 3
“Geometric constraints can be used to reject false matches within a RANSAC [5] based scheme but the number of iterations needed to find a hypothesis grows exponentially with the number of outliers and the outlier ratio must not exceed 50% [6].”
BackgroundTowards the automatic motion recovery using single-view image sequences acquired from bike
Kolecki, J. (2015) · Annals of Computer Science and Information Systems · doi:10.15439/2015f182 · Cited by 3
Direct formulas for stereo-based visual odometry error modeling
Golban, C., Cobarzan, P., & Nedevschi, S. (2015) · IEEE International Conference on Intelligent Computer Communication and Processing (ICCP) · doi:10.1109/iccp.2015.7312629 · Cited by 3
“978-1-4673-8200-7/15/$31.00 ©2015 European Union Keywords—visual odometry error model; visual odometry covarianc matrix; egomotion precision; egomotion synthetic data; I. INTRODUCTION Visual odometry [14] refers to the process of estimating the motion of a system based on one or more video cameras…”
BackgroundInfluentialAdaptive visual odometry using RGB-D cameras
Fabian, J. R., & Clayton, G. M. (2014) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim.2014.6878301 · Cited by 3
“There are three important visual odometry performance issues that must be considered: 1) computational performance, 2) feature tracking accuracy, and 3) feature location accuracy.”
BackgroundSparsely sampled functional magnetic resonance imaging using low-rank and sparsity constraints
Nguyen, H. M., & Glover, G. H. (2014) · International Conference on Communications and Electronics (ICCE) · doi:10.1109/cce.2014.6916747 · Cited by 3
Stereo Visual Odometry for Urban Vehicles Using Ground Features
de la Escalera, A., Ebroul Izquierdo, M., Martín, D., García, F., & Armingol, J. M. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-27146-0_30 · Cited by 3
Accurate stereo visual odometry with gamma distributions
Gomez-Ojeda, R., Moreno, F.-Á., & González-Jiménez, J. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989170 · Cited by 3
“Most stereo visual odometry systems estimate camera motion through the least-squares minimization [1], [2] of a certain cost function C(ξ) of the residuals Δpi(ξ), defined as difference between the observations pi of a set of keypoints and their predictions p̂i(ξ) [3]:”
BackgroundToledo-Moreo, R., Armingol, J. M., Clavijo, M., de la Escalera, A., Ser, J. D., Jiménez, F., Musleh, B., Naranjo, J. E., Olabarrieta, I. I., & Sánchez-Cubillo, J. (2017) · Elsevier eBooks · doi:10.1016/b978-0-12-812800-8.00004-7 · Cited by 4
Remote Laboratory to Study Mobile Robot Odometry
Abdulov, A., & Abramenkov, A. N. (2017) · IEEE International Conference on Application of Information and Communication Technologies (AICT) · doi:10.1109/icaict.2017.8687067 · Cited by 3
“Estimate an object position by means of visual odometry [13]–[16].”
MethodDeep Weakly Supervised Positioning for Indoor Mobile Robots
Wang, R., Xu, X., Ding, L., Huang, Y., & Feng, C. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3138170 · Cited by 3
Monocular Depth Estimation for Autonomous UAV Navigation Based on Deep Learning
Hensel, S., Marinov, M. B., Dreher, A., & Trendafilov, D. (2023) · International Scientific Conference Electronics (ET) · doi:10.1109/et59121.2023.10279533 · Cited by 3
Bredu, J. A. (2022) · The Research Repository @ WVU (West Virginia University) · doi:10.33915/etd.11495 · Cited by 3
Relative pose estimation from panoramic images using a hybrid neural network architecture
Offermann, L. (2024) · Scientific Reports · doi:10.1038/s41598-024-75124-7 · Cited by 2
“Besides local visual homing, visual odometry 6,7 is an example of a map-less application.”
BackgroundSEAL: A Single-Event Architecture for In-Sensor Visual Localization
Hou, R., Twomey, T., Milionis, V., Dikopoulos, E., Ma, T., Zhu, Y., & Tzimpragos, G. (2025) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1145/3695053.3731034 · Cited by 2
“For keypoint detection and tracking, we use the Good Features to Track (GFTT) [65] and pyramidal Lucas-Kanade (LK) algorithms [6], both standard methods for visual localization [14].”
Ruscio, F., Tani, S., Caiti, A., & Costanzi, R. (2025) · Journal of Field Robotics · doi:10.1002/rob.70032 · Cited by 2
“This implies a non ‐ negligible distance between two consecutive frames, making the matching more suitable for solving the feature correspondence searching (Fraundorfer and Scaramuzza 2012).”
A Dense Map Building Approach from Spherical RGBD Images
Gokhool, T., Meilland, M., Rives, P., Fernández-Moral, E., Gokhool, T., Meill, M., Rives, P., Fern, E., Map, E.-M. A. D., Hal, H. I., et al. (2014) · Cited by 2
Visual odometry with high resolution time-of-flight cameras
Dalbah, Y., Dingeldey, N., & Wahl, F. M. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2050903 · Cited by 2
“The performance and the properties of each named detector and descriptor in the context of conventional visual odometry have been evaluated as part of former work [12].”
MethodAutomatic Motion Classification for Advanced Driver Assistance Systems
Desai, A., Lee, D.-J., & Mody, S. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-27863-6_77 · Cited by 2
Image-Based Camera Localization for Large and Outdoor Environments
Teng, C.-H., Chen, Y., & Zhang, X. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-54427-4_11 · Cited by 2
Point cloud registration with rotation-invariant and dissimilarity-based salient descriptor
Jung, S., Shin, Y.-G., & Chung, M. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18577-2 · Cited by 2
“The 3D information produced by these sensors has diverse applications, extending to augmented reality [1, 2], robotics [3–5], autonomous vehicle technology [6, 7], and the field of character recognition [8].”
Enhancing Visual Odometry with Estimated Scene Depth: Leveraging RGB-D Data with Deep Learning
Kostusiak, A., & Skrzypczyński, P. (2024) · Electronics · doi:10.3390/electronics13142755 · Cited by 3
Visual and Inertial Sensor Fusion Approach for Visual Inertial Odometry Used in Vehicle Localization
Jo, H., & Yoon, S. W. (2024) · Proceedings of IEEE Sensors/Proceedings of IEEE Sensors ... · doi:10.1109/sensors60989.2024.10785070 · Cited by 2
“[21] is utilized to estimate the longitudinal velocity using IMU data.”
Incremental Structure from Motion for Small-Scale Scenes Based on Auxiliary Calibration
Li, S., Li, J., Yang, T., Xiaohui, A., & Liu, J. (2025) · Sensors · doi:10.3390/s25020415 · Cited by 2
“Although circular markers [42,43] offer advantages in detection under long-distance observation and visual blur, square planar markers [44–47] are preferred by researchers due to the ease of extracting their corner points.”
On augmenting the visual slam with direct orientation measurement using the 5-point algorithm
Schmidt, A., Kraft, A. L., Fularz, M., & Domagała, Z. (2013) · Journal of Automation Mobile Robotics & Intelligent Systems · Cited by 2
A novel translation estimation for essential matrix based stereo visual odometry
Nguyen, H.-H., Nguyen, T.-T., Tran, M. C., Phung, K.-P., & Nguyen, Q.-T. (2021) · International Conference on Ubiquitous Information Management and Communication (IMCOM) · doi:10.1109/imcom51814.2021.9377372 · Cited by 2
“Scaramuzza and Fraundorfer conducted a comprehensive review of feature-based VO [4], [5].”
BackgroundA New Approach of Monocular Visual Odometry to Trajectory Estimation Within a Plantation
Araujo, G. L., Filho, J. I. F., Higuti, V. A. H., & Becker, M. (2021) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars/sbr/wre54079.2021.9605451 · Cited by 2
An improved visual odometry optimization algorithm based on Kinect camera
Yu, H., Sun, H., Wang, Y., Kan, L., & Wan, Q. (2013) · Chinese Automation Congress · doi:10.1109/cac.2013.6775823 · Cited by 2
“Due to the influence of noise and other factors, the ORB algorithm inevitably exist some mismatching points, which have a significantly damaging effect on the accuracy of motion estimation[16].”
Background
Metadata
- Authors
- Fraundorfer, F., & Scaramuzza, D.
- Affiliations
- ETH Zurich (CH)
- University of Zurich (CH)
- Venue
- IEEE Robotics & Automation Magazine
- Published
- 2012-06
- Volume
- 19
- Issue
- 2
- Pages
- 78-90
- ISSN
- 1070-9932 (ISSN-L)
- 1558-223X
- OpenAlex
- W2166132830
- Cited by
- 620
- References
- 99
- Citations by year
- 2026: 15 · 2025: 14 · 2024: 27 · 2023: 35 · 2022: 43 · 2021: 53 · 2020: 59 · 2019: 59 · 2018: 47 · 2017: 68 · 2016: 49 · 2015: 57 · 2014: 57 · 2013: 36 · 2012: 1
- FWCI
- 81.22
- Type
- journal article
- Language
- en
- Open access
- green
- www.zora.uzh.ch
- Licence
- Locations
- IEEE Robotics & Automation Magazine (publishedVersion)
- Zurich Open Repository and Archive (University of Zurich) (submittedVersion, other-oa)
- Zurich Open Repository and Archive (University of Zurich)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Earth and Planetary Sciences › Geology › 3D Surveying and Cultural Heritage
- Keywords
- visual odometry, feature matching, robust estimation, outlier removal, bundle adjustment, error propagation, loop closure, SLAM, camera motion estimation, long-term stability, autonomous vehicles, LiDAR alternative
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.