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 401–500 of 621
Bootstrapping Computer Vision and Sensor Fusion for Absolute and Relative Vehicle Positioning
Janssen, K., Rademakers, E., Boulkroune, B., Ghouti, N. E., & Kleihorst, R. P. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-25903-1_21 · Cited by 2
Multi-frame Feature Integration for Multi-camera Visual Odometry
Chien, H.-J., Geng, H., Chen, C., & Klette, R. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-29451-3_3 · Cited by 3
Mapping services in indoor environments based on image sequences
Nguyen, Q.-H., Hai-Vu, Trân, T. T. H., & Nguyen, Q.-H. (2014) · International Conference on Communications and Electronics (ICCE) · doi:10.1109/cce.2014.6916746 · Cited by 2
Visual odometry system performance for different landmark average distances
Chiodini, S., Pertile, M., & Debei, S. (2016) · IEEE International Workshop on Metrology for AeroSpace (MetroAeroSpace) · doi:10.1109/metroaerospace.2016.7573245 · Cited by 3
“In [5] and [6] has been presented an overview and a tutorial on visual odometry.”
BackgroundEffect of rolling shutter on visual odometry systems suitable for planetary exploration
Pertile, M., Chiodini, S., Giubilato, R., & Debei, S. (2016) · IEEE International Workshop on Metrology for AeroSpace (MetroAeroSpace) · doi:10.1109/metroaerospace.2016.7573284 · Cited by 2
“An interesting overview and an introducing tutorial on VO can be found in [7] and [8].”
BackgroundMobile phone optical sensor usage for navigation tasks
Kornelly, T., Časar, J., Starý, V., & Farlík, J. (2017) · International Conference on Military Technologies · doi:10.1109/miltechs.2017.7988842 · Cited by 2
“This detector was designed for objects and places recognition and thanks to the extensive descriptions of found features [17] it achieves great results.”
BackgroundReliable Planar Object Pose Estimation in Light Fields From Best Subaperture Camera Pairs
Crombez, N., Caron, G., Funatomi, T., & Mukaigawa, Y. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2853267 · Cited by 2
“THE pose estimation of an object is a fundamental task for a variety of purposes in the robotics field such as 3-D tracking [1], visual servoing [2], and motion estimation [3].”
BackgroundThe Indoor Localization of a Mobile Platform Based on Monocular Vision and Coding Images
Liu, F., Zhang, J., Wang, J., & Li, B. (2020) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi9020122 · Cited by 2
Compressive Sensing-Based Reconstruction of Lissajous-Like Nodding Lidar Data
Benson, M. T., Sathishchandra, H., Clayton, G. M., & Andersson, S. B. (2020) · ASME Letters in Dynamic Systems and Control · doi:10.1115/1.4046574 · Cited by 2
Research and Application of Visual SLAM Based on Embedded GPU
Ma, T., Bai, N., Shi, W., Wang, L., & Wu, T. T. (2021) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-77569-8_1 · Cited by 2
Sampson Distance: A New Approach to Improving Visual-Inertial Odometry's Accuracy
Zhang, H., & Ye, C. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636115 · Cited by 3
“From the estimated FM, the relative camera pose change can be retrieved readily ⎯ an essential step for VO [ 11 ] to estimate the camera pose.”
BackgroundQuadruple tripatch-wise modular architecture-based real-time structure from motion
Bai, L., Li, Y., Kirubarajan, T., & Gao, X. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.01.071 · Cited by 3
Vongbunyong, S., & Chen, W. (2015) · Sustainable production, life cycle engineering and management · doi:10.1007/978-3-319-15183-0_4 · Cited by 2
Robot Pose Estimation: A Vertical Stereo Pair Versus a Horizontal One
Ragab, M. E., & Wong, K. H. (2015) · International Journal of Computer Science and Information Technology · doi:10.5121/ijcsit.2015.7502 · Cited by 2
Depth Estimation with Multi-camera Array
Wang, Y., Chen, Q., Wang, P., & Lü, Y. (2022) · International Conference on Automation, Control and Robots (ICACR) · doi:10.1109/icacr55854.2022.9935518 · Cited by 2
“Davide and Friedrich have provided a broad introduction to visual odometry (VO) and the research that has been undertaken in the last decades [5, 6].”
BackgroundReal-Time Stereo Visual Odometry Based on an Improved KLT Method
Guo, G., Dai, Z., & Dai, Y. (2022) · Applied Sciences · doi:10.3390/app122312124 · Cited by 2
“The latter builds upon the former but uses box filters to border on the Gaussian, contributing to a faster computation [3].”
BackgroundMethodNonlinearly Optimized Dual Stereo Visual Odometry Fusion
Cabrera-Avila, E. V., da Silva, B. M. F., & Gonçalves, L. M. G. (2024) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-024-02069-4 · Cited by 2
“Both problems are well formalized [2, 3] and actively investigated in robotics: the former is known as robot localization whereas the latter is known as visual odometry (VO) [6, 7].”
InfluentialGuo, N., Jiang, W., Li, J., Liu, F., & Dong, J. (2021) · Journal of Global Positioning Systems · doi:10.5081/jgps.17.2.164 · Cited by 2
A Performance Analysis of Vision-Based Robot Localization System
Qi, Y. (2013) · Cited by 2
An assisted bilateral control strategy for 3D pose estimation of visual features
Battilani, N., Spica, R., Giordano, P. R., & Secchi, C. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206080 · Cited by 2
“For a recent literature review in this field we refer the reader to [6], [7].”
Visual Tilt Estimation for Planar-Motion Methods in Indoor Mobile Robots
Fleer, D. (2017) · Robotics · doi:10.3390/robotics6040032 · Cited by 2
“These include relative-pose estimation [1], visual odometry [2,3], place recognition [4], and simultaneous localization and mapping (SLAM) [5].”
BackgroundVisual Odometry Based on Convolutional Neural Networks for Large-Scale Scenes
Meng, X., Fan, C., & Ming, Y. (2018) · International Conference on Graphics and Image Processing (ICGIP) · doi:10.1117/12.2524278 · Cited by 2
“Compared with the traditional wheel odometry, VO has no error caused by wheel slip, and is suitable for non-planar motion environments and non-wheeled mobile robots [2].”
Costanzi, R., Callieri, M., Barbieri, C., Colonna, F., Gaino, F., Moretto, P., Pepe, C. E., Romanelli, A., Gasparri, A., Pacienza, F., et al. (2019) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceanse.2019.8867123 · Cited by 2
“visual odometry techniques to further refine the navigation state estimation of the SDS with respect to the acoustic positioning only [4].”
MethodPerception and Decision-Making of Autonomous Systems in the Era of Learning: An Overview.
Tang, Y. S., Zhao, C., Wang, J., Zhang, C., Sun, Q., & Qian, F. (2020) · Cited by 3
Visual Odometry Drift Reduction Based on LiDAR Point Clouds Alignment
Golban, C.-C., Cobârzan, C.-P., & Nedevschi, S. (2021) · IEEE International Conference on Intelligent Computer Communication and Processing (ICCP) · doi:10.1109/iccp53602.2021.9733667 · Cited by 2
Wheel-INS: A Wheel-mounted MEMS IMU-based Dead Reckoning SystemPreprint
Niu, X., Wu, Y., & Kuang, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.07805 · Cited by 2
“Over last decades, extensive researches have focused on vision based state estimation approaches for autonomous robots, such as simultaneous localization and mapping (SLAM) [12-14] and visual odometry (VO) [15-18].”
BackgroundThree-Dimensional Mapping in Underwater Environment
Nunes, A. P., & Matos, A. C. (2019) · U Porto Journal of Engineering · doi:10.24840/2183-6493_005.002_0002 · Cited by 1
“For the mapping process it is necessary the correct motion estimation, where visual odometry techniques can be used throughout input images from one or multiple cameras (Scaramuzza and Fraundorfer 2011; Fraundorfer and Scaramuzza 2012).”
MethodElahian, S., Atashgah, M. A. A., & Tarvirdizadeh, B. (2023) · Aviation · doi:10.3846/aviation.2023.18461 · Cited by 2
Muhammad, F., Poerbandono, P., Sternberg, H., Djunarsjah, E., & Abidin, H. Z. (2025) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2025.200476 · Cited by 1
Bioinspired perception: Advancements for underwater robots
Nie, F., Zhang, C., Zhang, Q., Qin, H., Li, Y., Zhang, Y., Du, H., Yang, L., Ma, Y., & Liu, L. (2026) · Ocean Engineering · doi:10.1016/j.oceaneng.2026.125943 · Cited by 1
Koncepcja platformy mobilnej do wsparcia badań kryminalistycznych
Głębocki, R., Kopyt, A., Kicman, P., & Kowalski, G. (2013) · Szybkobieżne Pojazdy Gąsienicowe · Cited by 1
An Application of the Frame Theory for Signature Extraction in the Analysis of 3D Point Clouds
Martino, F., Patruno, C., Marani, R., & Stella, E. (2015) · Smart sensors, measurement and instrumentation · doi:10.1007/978-3-319-21671-3_13 · Cited by 1
Zhao, B., Hu, T., Niu, Y., Tang, D., Ma, Z., Kong, W., & Shen, L. (2015) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2015.7279258 · Cited by 1
Visual and inertial multi-rate data fusion for motion estimation via Pareto-optimization
Loianno, G., Lippiello, V., Fischione, C., & Siciliano, B. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696927 · Cited by 1
“(10) Thus, the estimated position depends on the estimated position at time k − 1 and on the acceleration measurement.”
BackgroundDevelopment of visual odometry algorithm for mobile robot navigation
Kicman, P. (2013) · International Conference on Methods and Models in Automation and Robotics · doi:10.1109/mmar.2013.6669935 · Cited by 1
Liu, H., Liu, Y., Yu, Y., & Sun, F. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907153 · Cited by 1
3D egomotion from stereo cameras using constrained search window and bundle adjustment
Chen, C., Zhang, J., Chen, T.-I., & Chen, C.-F. (2013) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2013.6727055 · Cited by 1
EFFICIENT INERTIALLY AIDED VISUAL ODOMETRY TOWARDS MOBILE AUGMENTED REALITY
Aksoy, G. (2013) · Cited by 1
Loop detection in robotic navigation using MPEG CDVS
de Gusmão, P. P. B., Rosa, S., Magli, E., Lepsøy, S., & Francini, G. (2015) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2015.7340871 · Cited by 1
Introduction to Autonomous Flight
de Croon, G., Perçin, M., Remes, B. D. W., Ruijsink, R., & Wagter, C. D. (2015) · Springer eBooks · doi:10.1007/978-94-017-9208-0_7 · Cited by 1
Wide bandwidth sensing of micro angular motion
Fan, Y., Li, H.-Y., Yang, L., & Tan, U.-X. (2016) · International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS) · doi:10.1109/marss.2016.7561743 · Cited by 1
“Here, corner detector is chosen because it is fast to compute and can be used in real-time application [16].”
BackgroundMethodMotion-Aware Iterative Closest Point Estimation for Fast Visual Odometry
Lin, T., Chen, C., Wang, J., & Shieh, M. (2016) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar-adjunct.2016.0091 · Cited by 1
“Estimating the camera pose by frame-to-frame matching is inherently prone to drift [4].”
BackgroundLu, H., Xiao, J., Zhang, L., Yang, S., & Zell, A. (2016) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2016.7866387 · Cited by 2
“More introductions about visual odometry including the history, fundamentals, important algorithms related to different stages and applications, can be found on the two-part tutorial [2] [3].”
BackgroundFrame-to-Frame Visual Odometry: The Importance of Local Transformations
Kostusiak, A. (2017) · International Conference on Computer Recognition Systems · doi:10.1007/978-3-319-59162-9_37
Registration of RGB-D Images: Components of the System
Kornuta, T., & Łępicka, M. (2017) · Pomiary, Automatyka, Robotyka · doi:10.14313/par_223/19 · Cited by 1
Observer design for visual inertial SLAM scale on a quadrotor UAV
Fink, G., Franke, M., Lynch, A. F., Röbenack, K., & Godbolt, B. (2017) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas.2017.7991497 · Cited by 1
“com intensive, are similar to VSLAM, but without the mapping functionality [3]–[5].”
BackgroundEnhanced visual odometry algorithm based on elite selection method and voting system
Shen, H., Hsu, C.-C. J., Wang, W., & Wang, Y.-T. (2017) · IEEE International Conference on Consumer Electronics - Berlin (ICCE-Berlin) · doi:10.1109/icce-berlin.2017.8210602 · Cited by 1
“To have better understanding of the conventional VO system, [3, 4] can be referred to for more details.”
BackgroundMethodTracking Spatially Distributed Features in KLT Algorithms for RGB-D Visual Odometry
da Silva, B. M. F., Correia, L. F. M., Bezerra, K. D. A., & Gonçalves, L. M. G. (2017) · Workshop of Computer Vision (WVC) · doi:10.1109/wvc.2017.00019 · Cited by 1
“It is well known that false correspondences, originated from occlusions, bad lighting, moving objects in the scene, or incorrect tracking, severely corrupt the quality of the computed camera poses [4], [5].”
BackgroundMethodInfluentialVedadi, F., & Valaee, S. (2017) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc.2017.8292486 · Cited by 1
Observer design for monocular visual inertial SLAM
Fink, G., Franke, M., Lynch, A. F., & Röbenack, K. (2018) · at - Automatisierungstechnik · doi:10.1515/auto-2017-0082 · Cited by 1
“Visual odometry (VO) is the process of determining a camera’s pose with respect to its environment [9, 18].”
BackgroundTesting a Biologically-Based System for Extracting Depth from Brief Monocular 2-D Video Sequences
Perrone, J. A., Cree, M. J., Hedayati, M., & Corlett, D. (2018) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2018.8634781 · Cited by 1
“Our whole system is feedforward only and we would argue that this gives it an advantage over schemes that rely on iterative searches for solving the velocity or odometry stages [7], [8].”
Consensus Dynamics With Application to Vision-based Localization
Miao, Z., Liu, Y., & Wang, Y. (2018) · World Congress on Intelligent Control and Automation · doi:10.1109/wcica.2018.8630496 · Cited by 1
“In the last decade, due to the wide availability of camera sensors and the progress in computer vision, a lot of vision-based techniques have been developed for the localization problem [21], [22].”
BackgroundImproving RANSAC for Efficient and Precise Model Fitting with Statistical Analysis
Zhang, Y., Tian, H., Deng, Y., & Wang, J. (2019) · European Journal of Electrical Engineering and Computer Science · doi:10.24018/ejece.2019.3.5.111 · Cited by 1
“This hypothesize-and-verify loop is repeated until the number of iterations reaches a predefined success rate for finding a model constructed with an uncontaminated subset [1].”
BackgroundHow to Match Tracks of Visual Features for Automotive Long-Term SLAM
Luthardt, S., Ziegler, C., Willert, V., & Adamy, J. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8916895 · Cited by 2
“These prominent points in the camera image are called visual features and detecting and matching them is one of the key issues in V-SLAMs and similar methods [2]–[4].”
BackgroundMethodScale Estimation of Monocular SLAM Using Direct Acceleration Pair Measurements
Yathirajam, B., Vaitheeswaran, S. M., & Ananda, C. M. (2019) · doi:10.1145/3352593.3352630 · Cited by 1
Wang, H., Guo, W. P., & Fu, Y. (2021) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar52367.2021.9517330 · Cited by 1
Quan, Q. (2017) · Springer eBooks · doi:10.1007/978-981-10-3382-7_9 · Cited by 1
Study on Optimization Method of Visual Odometry Based on Feature Matching
Song, H., Zhao, Z., Ren, B., Xue, Z., Li, J., & Zhang, H. (2022) · Mathematical Problems in Engineering · doi:10.1155/2022/6785066 · Cited by 1
Mapped-RRT* a Sampling Based Mobile Path Planner Algorithm
Chaudhuri, R., Deb, S., & Saha, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-24848-1_11 · Cited by 1
Learning to Predict Stability of Visual Features
Zou, H., Lin, X., He, L., & Guan, Y. (2022) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc55256.2022.10033807 · Cited by 2
“These erroneous associations will significantly increase the number of iterations for RANSAC to find the correct hypothesis, and if the proportion of erroneous associations exceeds a certain percentage, RANSAC often fails to work [8].”
BackgroundSelf-supervised Visual Odometry Based on Geometric Consistency
Song, R., Liu, J., Liao, K., Xiao, Z., & Yan, B. (2023) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas46773.2023.10181492 · Cited by 4
“Thanks to that, visual odometry estimates the frame-to-frame (F2F) ego-motion by exploiting the consistency between pairs of consecutive frames [3].”
BackgroundA New Visual Front-end Combining KLT with Descriptor Matching for Visual-inertial Odometry
Wu, Z., Yu, B., Li, R., Deng, Z., & Shi, Y. (2023) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-023-02008-9 · Cited by 1
“In contrast, the descriptor-matching tracker performs better in finding corresponding features with a long baseline and is more robust when the image changes significantly [20].”
A comparative study of pose estimation algorithms for visual navigation in autonomous robots
Sreeja, S., & Jacob, S. S. (2023) · International Robotics & Automation Journal · doi:10.15406/iratj.2023.09.00274 · Cited by 1
Detection of special zones as a basis for the method of topographic affinity of images
DZHEBRAILOV, R. Y., & Gospodarchuk, O. (2024) · Cybernetics and computer engineering · doi:10.15407/kvt215.01.020 · Cited by 1
“…траєкторії ( від точки до точки ), беручи до уваги лише її локальну узгодженість ( розташування поточної точки траєкторії відносно попередніх її точок у локальній системі координат за невідомих глобальних координат ), для чого будується лише локальна карта просторових положень ознак [5, 6].”
Cultivating Navigational Autonomy in the Visually Impaired: A Novel Approach with VirtualEYE
Singh, A. P., & Smitha, K. G. (2024) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai59869.2024.00081 · Cited by 1
“3) Computer Vision-based IPS: These systems use cameras and image processing algorithms for indoor navigation, with users capturing and processing images or videos on smartphones [8].”
MethodA VISION-BASED TRAVELLED DISTANCE ESTIMATION ALGORITHM IN AN INDOOR ENVIRONMENT USING A MOBILE ROBOT
Diop, M., Lim, C. H., Lim, T. S., & Ong, L.-Y. (2014) · Journal of Computer Science · doi:10.3844/jcssp.2014.2469.2480 · Cited by 1
Pose graph for improved monocular visual odometry
Kicman, P., & Narkiewicz, J. P. (2014) · International Conference on Methods and Models in Automation and Robotics · doi:10.1109/mmar.2014.6957413 · Cited by 1
“The recent progress of research in visual odometry is summarized in a two part tutorial by Scaramuzza and Fraundorfer [2] [3].”
BackgroundVisual Localization Using Voting Based Image Retrieval and Particle Filtering in Indoor Scenes
Kawamoto, K., Kazama, H., & Okamoto, K. (2013) · International Conference on Robot, Vision and Signal Processing · doi:10.1109/rvsp.2013.44 · Cited by 1
“For accurate visual localization, 3D estimation based approaches such as visual SLAM (Simultaneous Localization And Mapping) [2], [3]), visual odometry [4], and SfM (Structure from Motion) [5], [6] have been used widely.”
MethodResearch on Monocular Visual Odometry Based on 3D-2D Motion Estimation
Zhang, Y., & Zhang, Y. (2016) · International Symposium on Parallel and Distributed Computing · doi:10.1109/ispdc.2016.57 · Cited by 1
“Finally, camera pose will be solved through these correspondences by PnP algorithm[9].”
MethodComparison of odometry techniques for vehicle navigation
Yu, S.-L., Tsou, D.-W., & Juang, J. (2016) · International Automatic Control Conference · doi:10.1109/cacs.2016.7973877 · Cited by 1
Feature-Based Monocular Real-Time Localization for UAVs in Indoor Environment
Zhang, Y., Cai, Z., Zhao, J. B., You, Z., & Wang, Y. (2017) · Lecture notes in electrical engineering · doi:10.1007/978-981-10-6445-6_39 · Cited by 1
Enhanced outlier removal for extended Kalman filter based visual inertial odometry
Teng, C.-H. (2018) · 2018 IEEE International Conference on Applied System Invention (ICASI) · doi:10.1109/icasi.2018.8394370 · Cited by 1
“VIO is the integration of visual odometry (VO) [1] [2] [3] with IMU, and it is closely related with the techniques of simultaneous localization and mapping (SLAM) [4] [5] .”
MethodFive-point algorithm: An efficient cloud-based FPGA implementation
Rabozzi, M., Sozzo, E. D., Tucci, L. D., & Santambrogio, M. D. (2018) · IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP) · doi:10.1109/asap.2018.8445097 · Cited by 1
“Furthermore, the 5-point relative pose problem appears in many applications ranging from visual odometry [4], scene reconstruction [5] and video stabilization [6].”
BackgroundSystematic and comparative analysis of techniques for SLAM development in mobile robotics
Quimbita, S., Chuquitarco, D., Hallo, V., Velasco, N., & Chipantasi, D. J. M. (2019) · International Conference on Machine Vision · doi:10.1117/12.2522937 · Cited by 1
“By 2008 [12] there were approaches on filtering, visual odometry appears in 2012 [13] by Scaramuzza and Fraundofer.”
MethodRevisiting Visual Odometry for Real-Time Performance
Singh, G., Wu, M., & Lam, S.-K. (2019) · Machine Vision Applications · doi:10.23919/mva.2019.8757936 · Cited by 1
“They usually consist of feature correspondence setup, outlier removal and pose optimization [10].”
BackgroundResearch on Simultaneous localization and Mapping Scheme of Robot in Challenging Scenarios
He, G. Z., Dian, S., & Li, C. (2019) · International Conference on Automation, Control and Robotics Engineering (CACRE) · doi:10.1145/3351917.3351943 · Cited by 1
“According to whether the feature points need to be calculated, the visual odometer can be divided into the feature point method and the direct method independent of the feature point calculation[4, 5].”
MethodMobile Phone as a Sensor for Robot Navigation System
Doskočil, R., Křivánek, V., Bergeon, Y. T., & Kornelly, T. (2019) · International Conference on Applied Electronics · doi:10.23919/ae.2019.8867020 · Cited by 1
A Review on Visual Odometry Techniques for Mobile Robots: Types and Challenges
Thapa, V., Sharma, A., Gairola, B., Mondal, A. K., Devalla, V., & Patel, R. K. (2019) · Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering) · doi:10.2174/2352096512666191004142546 · Cited by 1
Real Time Feature Point Detectors for Determining Ego Motions
Sivamani, K., Sharmila, B., & Nedumaran, D. (2019) · Procedia Computer Science · doi:10.1016/j.procs.2020.01.069 · Cited by 1
Unsupervised Learning of Metric Representations with Slow Features from Omnidirectional Views
Franzius, M., Metka, B., Haris, M., & Bauer-Wersing, U. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00327 · Cited by 1
“The precision of the resulting metric mapping, and hence also the localization accuracy, might be further improved using visual odometry [20– 22] instead of wheel odometry since it is not affected by wheel slippage.”
MethodNguyen, H. H., Nguyen, Q. T., Tran, M. C., & Kim, D. (2020) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-63083-6_10 · Cited by 1
Comparative study of SURF, KAZE and MSER for visual odometry in presence of noise
Dhatrak, S., & Gharpure, D. (2021) · AIP conference proceedings · doi:10.1063/5.0043916 · Cited by 1
Vehicle Motion Estimation Using Visual Observations of the Elevation Surface
Fursov, V., Minaev, E. Y., & Петрович, К. А. (2021) · Automation and Remote Control · doi:10.1134/s0005117921100106 · Cited by 1
Encoding A Mathematically Faithful DeepVIO Solution
Khan, A. A. N., & Aouf, N. (2021) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas52745.2021.9649964 · Cited by 1
Wang, Y., & Peng, X. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-9423-3_39 · Cited by 1
Wang, Y., Fu, Y., Zheng, R., Wang, L., & Qi, J. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-9423-3_38 · Cited by 2
SCVO: Scale-Consistent Depth and Pose for Unsupervised Visual Odometry
Zhang, H., Yang, Y., Li, J., & Li, W. (2022) · Chinese Control Conference (CCC) · doi:10.23919/ccc55666.2022.9902340 · Cited by 1
“Since the camera is low-cost and light-weighted, visual positioning that recovers ego-motion through inter-frame consistency has attracted a great deal of interest in the computer vision community [2].”
BackgroundNoise Tolerance of Linear vs Non-Linear LiDAR Based Ego-Motion Drift Correction Methods
Cobârzan, C.-P., Golban, C.-C., & Nedevschi, S. (2022) · IEEE International Conference on Intelligent Computer Communication and Processing (ICCP) · doi:10.1109/iccp56966.2022.10053981 · Cited by 1
“The methods for visual odometry estimation are reviewed in survey papers such as [12], [13], [14] and [15], while the basic principles can be found in tutorial papers such as [16] and [17].”
MethodConstrained Motion Estimation for a Multi-Camera System
Tehrani, M. M. (2015) · Libraries and Cultural Resources (University of Calgary) · doi:10.11575/prism/25425 · Cited by 1
Personal and Domestic Robotics
Contreras, L., & Okada, H. (2021) · Springer eBooks · doi:10.1007/978-3-642-41610-1_207-1 · Cited by 1
Probabilistic Qualitative Localization and MappingPreprint
Mor, R., & Indelman, V. (2023) · Research Square · doi:10.21203/rs.3.rs-2596163/v1 · Cited by 1
Indoor navigation of mobile robots based on visual memory and image-based visual servoing
Bista, S. R. (2016) · theses.fr (ABES) · doi:10.70675/e9fcf885zb689z44d7z96d6z18bf32e7588b · Cited by 2
Algorithmes SLAM : Vers une implémentation embarquée
Abouzahir, M. (2017) · theses.fr (ABES) · doi:10.70675/d2f56ec0z2dcdz439ezb354z4509bb628b7b · Cited by 3
On Tracking and Matching in Vision Based Navigation
Schmidt, A., Kraft, M., & Fularz, M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-11755-3_51
Robust feature matching for aerial visual odometry
Mouats, T., & Aouf, N. (2014) · International Symposium ELMAR (ELMAR) · doi:10.1109/elmar.2014.6923324
“Indeed, as noted in [13], the stereo case can sometimes degenerate to monocular if this ratio is too small.”
BackgroundEstimating and Correcting Bias in Stereo Visual Odometry
Farboud-Sheshdeh, S. (2014) · TSpace (University of Toronto)
A Simple Visual Odometry Approach Based on Point Clouds
Silveira, J., Freire, E. O., Molina, L., & Carvalho, E. Á. N. (2015) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars-sbr.2015.39
Stereo Visual Odometry without Relying on RANSAC for the Measurement of Vehicle Motion
Song, G.-Y., & Lee, J.-W. (2015) · Journal of Institute of Control Robotics and Systems · doi:10.5302/j.icros.2015.14.0106
“단원 II에서 언급하였듯 제안된 알고리즘에서 Harris 코너 검출기는 두 가지 역할을 한다.”
InfluentialENHANCEMENT STRATEGIES FOR FRAME-TO-FRAME UAS STEREO VISUAL ODOMETRY
Kersten, J., & Rodehorst, V. (2016) · 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-xli-b3-511-2016
“According to a rule of thumb stated in (Fraundorfer and Scaramuzza, 2012), 1000 features is a good number for an image with 640×480 pixel.”
BackgroundKubelka, V., & Reinštein, M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-13823-7_30
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.