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 201–300 of 621
Chiodini, S., Pertile, M., Giubilato, R., Salvioli, F., Barrera, M., Franceschetti, P., & Debei, S. (2019) · Measurement · doi:10.1016/j.measurement.2019.03.036 · Cited by 14
Development of a Signature-based Terrain Relative Navigation System for Precision Landing
Owens, C., Macdonald, K., Hardy, J., Lindsay, R., Redfield, M., Bloom, M., Bailey, E. S., Cheng, Y., Clouse, D. S., Villalpando, C. Y., et al. (2021) · AIAA SciTech Forum · doi:10.2514/6.2021-0376 · Cited by 13
MS-SLAM: Motion State Decision of Keyframes for UAV-Based Vision Localization
Luo, Y., Li, Y., Li, Z., & Shuang, F. (2021) · IEEE Access · doi:10.1109/access.2021.3077591 · Cited by 11
ContextAVO: Local context guided and refining poses for deep visual odometry
Song, R., Zhu, R., Xiao, Z., & Yan, B. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.02.014 · Cited by 14
3D visual SLAM for an assistive robot in indoor environments using RGB-D cameras
Meng, L., de Silva, C. W., & Zhang, J. (2014) · International Conference on Computer Science & Education (ICCSE) · doi:10.1109/iccse.2014.6926426 · Cited by 13
“The solution to outlier removal consists of taking advantage of the geometric constraints introduced by the motion model [35].”
BackgroundRelative navigation approach for vision-based aerial GPS-denied navigation
Leishman, R. C., McLain, T. W., & Beard, R. W. (2013) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas.2013.6564707 · Cited by 13
Measuring Vehicle Velocity in Real Time using Modulated Motion Blur of Camera Image Data
Lee, M., Kim, K.-S., & Kim, S. (2016) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2016.2600281 · Cited by 13
“The approach can be adopted when the magnitude of motion is small and when feature’s appearance has small changes, compared to the appearance taken in the first image of the procedure [12].”
BackgroundForward and Backward Visual Fusion Approach to Motion Estimation with High Robustness and Low Cost
Wang, K., Huang, X., Chen, J., Cao, C., Xiong, Z., & Chen, L. F. (2019) · Remote Sensing · doi:10.3390/rs11182139 · Cited by 13
“D bearing data [27].”
Zhao, X., Min, H., Xu, Z., & Wang, W. (2019) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2019.09.001 · Cited by 13
Planar motion estimation using omnidirectional camera and laser rangefinder
Hoang, V.-D., Le, M.-H., & Jo, K.-H. (2013) · Conference on Human System Interactions · doi:10.1109/hsi.2013.6577891 · Cited by 12
Cycle-SfM: Joint self-supervised learning of depth and camera motion from monocular image sequences
Sun, Q., Tang, Y. S., & Zhao, C. (2019) · Chaos An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/1.5120605 · Cited by 13
Bao, R., Palaniappan, K., Zhao, Y., & Seetharaman, G. S. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3345747 · Cited by 12
“odometry for robotics [8], [9], agriculture [10], and other applications [11], [12], [13], [14], [15].”
BackgroundSchperberg, A. V., Tanaka, Y., Mowlavi, S., Xu, F., Balaji, B., & Hong, D. W. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610160 · Cited by 15
Enabling Context-Aware Indoor Augmented Reality via Smartphone Sensing and Vision Tracking
Liu, K., & Li, X. (2015) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/2808208 · Cited by 14
“Visual odometry (VO) could be another sensing solution for displacement [Fraundorfer and Scaramuzza 2012].”
BackgroundReal-time RGB-D registration and mapping in texture-less environments using ranked order statistics
Yousif, K., Bab‐Hadiashar, A., & Hoseinnezhad, R. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6942925 · Cited by 13
“[4] proposed a similar method called ”RGB-D-SLAM” in which SIFT, SURF [7] or ORB [7] features were used in place of FAST features and posegraph optimization was used instead of Bundle Adjustment for global optimization.”
BackgroundMethodInfluentialReal-time smart and standalone vision/IMU navigation sensor
Chermak, L., Aouf, N., Richardson, M. A., & Visentin, G. (2016) · Journal of Real-Time Image Processing · doi:10.1007/s11554-016-0613-z · Cited by 17
“Reviews and more recent tutorials give a detailed picture of the different visual odometry overall techniques [2, 3] and stereo visual approaches [13].”
BackgroundResearch on the Application of Visual SLAM in Embedded GPU
Ma, T., Bai, N., Shi, W., Wu, X., Wang, L., Wu, T. T., & Zhao, C. (2021) · Wireless Communications and Mobile Computing · doi:10.1155/2021/6691262 · Cited by 12
“The front end is at the lower level in the visual SLAM system, also known as visual odometry (VO) [7].”
BackgroundComparison of visual odometry systems suitable for planetary exploration
Pertile, M., Chiodini, S., & Debei, S. (2014) · IEEE International Workshop on Metrology for AeroSpace (MetroAeroSpace) · doi:10.1109/metroaerospace.2014.6865926 · Cited by 16
“An interesting overview and an introducing tutorial on visual odometry can be found in [11] and [12] Stereo-processing allows estimation of the three dimensional (3D) location of landmarks observed by a stereo-camera.”
BackgroundA Simplified Solution to Motion Estimation Using an Omnidirectional Camera and a 2-D LRF Sensor
Hoang, V.-D., & Jo, K.-H. (2016) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2016.2547869 · Cited by 12
Stereo Visual Odometry Without Temporal Filtering
Deigmoeller, J., & Eggert, J. P. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-45886-1_14 · Cited by 13
Motion Estimation Made Easy: Evolution and Trends in Visual Odometry
Poddar, S., Kottath, R., & Karar, V. (2018) · Studies in computational intelligence · doi:10.1007/978-3-030-03000-1_13 · Cited by 58
Orthogonality Index Based Optimal Feature Selection for Visual Odometry
Nguyen, H. H., & Lee, S. (2019) · IEEE Access · doi:10.1109/access.2019.2916190 · Cited by 13
“Scaramuzza and Fraundorfer conducted a comprehensive review of featurebased VO [5], [6].”
BackgroundWiFi Similarity-Based Odometry
Ismail, K., Liu, R., Athukorala, A., Ng, B. K. K., Yuen, C., & Tan, U.-X. (2023) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2023.3274924 · Cited by 10
“The feature-based approach was utilized in [5] and [6], where feature extraction was used to identify features that will be tracked over a series of images using feature matching by which the odometry can be computed from.”
MethodAdopting Feature-Based Visual Odometry for Resource-Constrained Mobile Devices
Fularz, M., Nowicki, M., & Skrzypczyński, P. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-11755-3_48 · Cited by 11
A discrete-time attitude observer on SO(3) for vision and GPS fusion
Khosravian, A., Chin, T.-J., Reid, I. D., & Mahony, R. E. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989669 · Cited by 11
“Although the structure of the proposed observer (11) is inspired by the novel work of [27], the stability analysis presented in [27, Proposition 4] does not apply here as the cost function (9) does not have a unique global minimum.”
Method3D Reconstruction & Assessment Framework based on affordable 2D Lidar
Kang, X., Yin, S., & Fen, Y. (2018) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim.2018.8452242 · Cited by 11
Interactive Augmented Omnidirectional Video with Realistic Lighting
Michiels, N., Jorissen, L., Put, J., & Bekaert, P. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-13969-2_19 · Cited by 11
“This process is similar to visual odometry (VO) [25, 8] and, as is to be expected with VO, the resulting positions are far from optimal since the pose of the camera is only estimated in relation to the previous pose.”
BackgroundAutomatic Real-Time Pose Estimation of Machinery from Images
Bertels, M., Jutzi, B., & Ulrich, M. (2022) · Sensors · doi:10.3390/s22072627 · Cited by 11
ICP stereo visual odometry for wheeled vehicles based on a 1DOF motion prior
Jiang, Y., Chen, H., Xiong, G., & Scaramuzza, D. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6906914 · Cited by 11
“A comprehensive tutorial on VO can be found in [5], [6].”
BackgroundSelf-citationSTMVO: biologically inspired monocular visual odometry
Li, Y., Zhang, J., & Li, S. (2016) · Neural Computing and Applications · doi:10.1007/s00521-016-2536-9 · Cited by 10
“The history and the discussion of the research can be found in [3].”
BackgroundMethodInfluentialLocalizing Pipe inspection robot using visual odometry
Aghdam, H. H., Kadir, H. A., Arshad, M. R., & Zaman, M. (2014) · IEEE International Conference on Control System, Computing and Engineering · doi:10.1109/iccsce.2014.7072724 · Cited by 11
“Technically, VO methods break down into two different types namely stereo visual odometry and monocular visual odometry.”
MethodMOMA: Visual Mobile Marker Odometry
Acuña, R., Li, Z., & Willert, V. (2018) · International Conference on Indoor Positioning and Indoor Navigation · doi:10.1109/ipin.2018.8533685 · Cited by 11
On-line Smoothing and Error Modelling for Integration of GNSS and Visual Odometry
Duong, T. T., Chiang, K., & Le, D. T. (2019) · Sensors · doi:10.3390/s19235259 · Cited by 11
Nonparametric Continuous Sensor RegistrationPreprint
Clark, W., Ghaffari, M., & Bloch, A. M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.04286 · Cited by 15
“, 2019), visual odometry and SLAM (Nistér et al., 2006; Scaramuzza and Fraundorfer, 2011; Fraundorfer and Scaramuzza, 2012; Strasdat, 2012; Kerl et al., 2013a; Engel et al., 2015; Ghaffari et al., 2019; Rosinol et al., 2019), satellite image registration (Kim and Im, 2003; Bentoutou et al.”
BackgroundFrom Pixels to Precision: A Survey of Monocular Visual Odometry in Digital Twin Applications
Neyestani, A., Picariello, F., Ahmed, I., Daponte, P., & Vito, L. D. (2024) · Sensors · doi:10.3390/s24041274 · Cited by 15
Hussain, A., Memon, A. R., Wang, H., Wang, Y., Miao, Y., & Zhang, X. (2020) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2020.3010415 · Cited by 11
Robotic Seeding or Sowing System in Smart Agriculture
Pradhan, N. C., Naik, M. A., Chowdhury, M., Kushwah, A., Asha, K. R., Dhar, T., Gavhane, K. P., Urhe, S. B., & Satpute, A. N. (2024) · Advances in geographical and environmental sciences · doi:10.1007/978-981-97-0341-8_23 · Cited by 10
Consensus With Persistently Exciting Couplings and Its Application to Vision-Based Estimation
Miao, Z., Liu, Y., Wang, Y., Chen, H., Zhong, H., & Fierro, R. (2019) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2918796 · Cited by 10
“In terms of research methodology, the proposed methods can be divided into two groups: 1) visual odometry (VO) [29], [30] and 2) visual simultaneous localization and mapping (V-SLAM) [31]–[34].”
MethodLocalization Using Single Camera and Lidar in GPS-Denied Environments
Lezki, H., & Yetik, İ. Ş. (2020) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu49456.2020.9302512 · Cited by 10
“Scaramuzza ve Fraundorfer, [5] ve [6]'da görsel odometre probleminin tarihçesi ile temel görsel-odometre yöntemlerini detaylı şekilde açıklamaktadır.”
An aerodynamic model-aided state estimator for multi-rotor UAVs
Wang, R., Zou, D., Xu, C., Pei, L., Liu, P., & Yu, W. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206034 · Cited by 10
“For GPS-denied environments, vision-based techniques such as visual SLAM[1][2][3], visual odometry[4][5], and optical flow[6][7] are widely used.”
MethodAn improved GMS-PROSAC algorithm for image mismatch elimination
Zhao, P., Ding, D., Wang, Y., & Liu, H. (2018) · Systems Science & Control Engineering · doi:10.1080/21642583.2018.1477635 · Cited by 10
“In addition, the number of obtained high quality matching pairs achieves 1 to 2 times more than the ones by traditional algorithms, and thereby the accuracy of VSLAM can be effectively improved.”
InfluentialSimultaneous Localization and Mapping: Through the Lens of Nonlinear Optimization
Saxena, A., Chiu, C.-Y., Shrivastava, R., Menke, J. T., & Sastry, S. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3181409 · Cited by 10
Crowdsourcing as a methodology to obtain large and varied robotic data sets
de Croon, G., Gerke, P. K., & Sprinkhuizen-Kuyper, I. G. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6942768 · Cited by 9
Modified Unscented Kalman Filter for improving the integrated visual navigation system
Norouz, M., Ebrahimi, M., & Arbabmir, M. (2017) · Iranian Conference on Electrical Engineering · doi:10.1109/iraniancee.2017.7985139 · Cited by 9
Visual-based navigation system for unmanned aerial vehicles
Kaniewski, P., & Grzywacz, W. (2017) · Signal Processing Symposium (SPSympo) · doi:10.1109/sps.2017.8053686 · Cited by 9
“It usually employs corner or blob detectors such as Harris, Shi-Tomassi, FAST, SIFT or SURF, feature trackers as KLT and outlier detection methods, such as RANSAC [8].”
MethodInertia constrained visual odometry for navigational applications
Kottath, R., Yalamandala, D. P., Poddar, S., Bhondekar, A. P., & Karar, V. (2017) · International Conference on Image Information Processing (ICIIP) · doi:10.1109/iciip.2017.8313714 · Cited by 9
“(1) as 145 for five point RANSAC [12].”
BackgroundPerformance Degradation Monitoring and Recovery of Vision-Based Control Systems
Xu, Y., Yin, S., Ding, S. X., Luo, H., & Zhao, Z. (2021) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2020.3042883 · Cited by 9
“This is not critical to low dynamic applications [5]–[7].”
BackgroundEfficient probability-oriented feature matching using wide field-of-view imaging
Flores, M., Valiente, D., Gil, A., Reinoso, Ó., & Payá, L. (2021) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2021.104539 · Cited by 10
Stereo-camera visual odometry for outdoor areas and in dark indoor environments
Ruppelt, J. P., & Trommer, G. F. (2016) · IEEE Aerospace and Electronic Systems Magazine · doi:10.1109/maes.2016.150255 · Cited by 8
“In the second part of this tutorial [6] Fraundorfer et al.”
BackgroundMethodA Fast and Accurate Optical Flow Camera for Resource-Constrained Edge Applications
Kühne, J., Magno, M., & Luca Benini, C. (2023) · International Workshop on Advances in Sensors and Interfaces (IWASI) · doi:10.1109/iwasi58316.2023.10164626 · Cited by 8
“For image patches, the similarity between the template and the target patch is calculated using the normalized cross-correlation (NCC) or a similar metric [12].”
MethodNowicki, M., & Skrzypczyński, P. (2014) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc.2014.6906342 · Cited by 8
“Though, while the visual odometry methods are considered, one needs to find minimum 5 or 8 correct matches to calculate the relative transformation between frames with the n-point algorithm [7].”
BackgroundMethodInfluentialAccurate pose determination for autonomous vehicle navigation
Walker, M. J., & Sąsiadek, J. Z. (2013) · International Conference on Methods and Models in Automation and Robotics · doi:10.1109/mmar.2013.6669933 · Cited by 8
Improved Seq SLAM for Real-Time Place Recognition and Navigation Error Correction
Wang, Y., Hu, X., Lian, J., Zhang, L., & Kong, X. (2015) · International Conference on Intelligent Human-Machine Systems and Cybernetics · doi:10.1109/ihmsc.2015.23 · Cited by 8
“By tracking feature primitives between several images, the motion of camera can be estimated[7] [8] [9].”
BackgroundDeep visual gravity vector detection for unmanned aircraft attitude estimation
Ellingson, G. J., Wingate, D., & McLain, T. W. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206443 · Cited by 8
“VO has a long history [22] that includes a large variety of methods and techniques [23].”
BackgroundBUILDING A 3D REFERENCE MODEL FOR CANAL TUNNEL SURVEYING USING SONAR AND LASER SCANNING
Moisan, E., Charbonnier, P., Foucher, P., Grussenmeyer, P., Guillemin, S., & Koehl, M. (2015) · 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/isprsarchives-xl-5-w5-153-2015 · Cited by 8
“Another frequently employed method is visual odometry (Scaramuzza and Fraundorfer, 2011, Scaramuzza and Fraundorfer, 2012), from optical or acoustic imaging in addition to SLAM algorithms see (Guth et al., 2014) and references therein, but it is not suited to static acquisitions.”
MethodThe Impact of the Image Feature Detector and Descriptor Choice on Visual SLAM Accuracy
Schmidt, A., & Kraft, M. (2014) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-10662-5_25 · Cited by 8
Monocular visual odometry aided by a low resolution time of flight camera
Chiodini, S., Giubilato, R., Pertile, M., & Debei, S. (2017) · IEEE International Workshop on Metrology for AeroSpace (MetroAeroSpace) · doi:10.1109/metroaerospace.2017.7999572 · Cited by 8
“An interesting overview and an introducing tutorial on VO can be found in [1] and [2].”
BackgroundLaser Profilometry Aiding Smart Vehicle Control
Patruno, C., Marani, R., Nitti, M., D’Orazio, T., & Stella, E. (2014) · International Journal on Smart Sensing and Intelligent Systems · doi:10.21307/ijssis-2019-055 · Cited by 8
Integration of Wearable Sensors Measurements for Indoor Pedestrian Tracking
Mahmoud, A., Sadruddin, H., Coser, P., & Atia, M. M. (2022) · IEEE Instrumentation & Measurement Magazine · doi:10.1109/mim.2022.9693454 · Cited by 9
Optical encoder neural network: a CNN-based optical encoder for robot localization
Patruno, C., Renò, V., Nitti, M., Pernisco, G., & Mosca, N. (2022) · Optical Engineering · doi:10.1117/1.oe.62.4.041402 · Cited by 10
Stochastic cloning Kalman filter for visual odometry and inertial/magnetic data fusion
Romanovas, M., Schwarze, T., Schwaab, M., Traechtler, M., & Manoli, Y. (2013) · Cited by 8
Multi-sensor fusion robust localization for indoor mobile robots based on a set-membership estimator
Zhou, B., Qian, K., Fang, F., Ma, X., & Dai, X. (2015) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber.2015.7287927 · Cited by 8
Sensor Fusion for Accurate Ego-Motion Estimation in a Moving Platform
Yi, C., & Cho, J. (2015) · International Journal of Distributed Sensor Networks · doi:10.1155/2015/831780 · Cited by 9
“There are alsomany other algorithms regarding this problem [3, 4].”
BackgroundMethodFull 3D navigation correction using low frequency visual tracking with a stereo camera
Pfingsthorn, M. F., Rathnam, R., Łuczyński, T., & Birk, A. (2016) · OCEANS 2016 - Shanghai · doi:10.1109/oceansap.2016.7485520 · Cited by 8
“The general field of visual odometry for terrestrial robots and autonomous cars is much more active [7], [8], showing very impressive results even with monocular systems.”
BackgroundSmall UAV autonomous localization based on multiple sensors fusion
Li, B., Liu, H., Zhang, J., Zhao, X., & Zhao, B. (2017) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac.2017.8054025 · Cited by 8
“VSLAM [3,4] and VO [5,6] are two representative work.”
BackgroundAccurate Stereo Visual Odometry Based on Keypoint Selection
Dias, N. J. B., & Laureano, G. T. (2019) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars-sbr-wre48964.2019.00021 · Cited by 9
“VSLAM rely on a trajectory with loops in order to perform loop closure , whereas BA is not suitable for real-time applications[14].”
BackgroundApproximated Relative Pose Solvers for Efficient Camera Motion Estimation
Ventura, J., Arth, C., & Lepetit, V. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16178-5_12 · Cited by 8
“This method is typically used in visual odometry applications, because it guarantees a fixed computation time for the robust estimation step and is thus ideal for embedded implementation [6].”
MethodEudoxus: Characterizing and Accelerating Localization in Autonomous MachinesPreprint
Gan, Y., Bo, Y., Tian, B., Xu, L., Hu, W., Liu, S., Liu, Q., Zhang, Y., Tang, J., & Zhu, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.01353 · Cited by 8
“On the popular (indoor) drone dataset EuRoC [20], our algorithm has a relative trajectory error of 0.28% (registration) – 0.42% (SLAM), on par with prior algorithms, whose errors are within the 0.1% to 2% range [34].”
MethodInfluentialCamera Rig Extrinsic Calibration Using a Motion Capture System
Chiodini, S., Pertile, M., Giubilato, R., Salvioli, F., Barrera, M., Franceschetti, P., & Debei, S. (2018) · IEEE International Workshop on Metrology for AeroSpace (MetroAeroSpace) · doi:10.1109/metroaerospace.2018.8453603 · Cited by 7
“Many robotics applications require the use of ego-motion estimation techniques such as VO (Visual Odometry) and Visual SLAM (Simultaneous Localization and Mapping), a comprehensive description of VO is given in the well known tutorials [1] and [2], and a survey of the current state of SLAM and of the most recent progr…”
MethodCai, W., Zhang, L., Huang, L., Yu, X., & Zou, Z. (2022) · ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys) · doi:10.1145/3563357.3564054 · Cited by 10
“the main component of visual SLAM, aims to estimate the egomotion of a robot given visual inputs [11].”
BackgroundGNSS-Denied Semi-Direct Visual Navigation for Autonomous UAVs Aided by PI-Inspired Inertial Priors
Gallo, E., & Barrientos, A. (2023) · Aerospace · doi:10.3390/aerospace10030220 · Cited by 8
“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 based on the changes that its motion induces on the images [25, 26, 27].”
Judd, K. M., & Gammell, J. D. (2024) · The International Journal of Robotics Research · doi:10.1177/02783649241229095 · Cited by 16
“The segmentation of static portions of the scene is itself an important focus of visual navigation research (e.g., Nist´er 2004; Fraundorfer and Scaramuzza 2012), but much less research has focused on also analyzing the dynamic regions of the scene that the segmentation rejects.”
Fast localization and 3D mapping using an RGB-D sensor
Loianno, G., Lippiello, V., & Siciliano, B. (2013) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2013.6766558 · Cited by 7
A Fast Visual Odometry and Mapping System for RGB-D Cameras
da Silva, B. M. F., & Gonçalves, L. M. G. (2014) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/sbr.lars.robocontrol.2014.35 · Cited by 7
“The problem of map building and localization can also be solved by Visual Odometry [4], [5].”
BackgroundPHROG: A Multimodal Feature for Place Recognition
Bonardi, F., Aïnouz, S., Boutteau, R., Dupuis, Y., Savatier, X., & Vasseur, P. (2017) · Sensors · doi:10.3390/s17051167 · Cited by 7
“They can be used later for an estimation of relative pose between two cameras through the computation of the fundamental or essential matrices as explained in [12], and even to estimate a sparse 3D structure of the environment thanks to triangulation (further explanations in [13]).”
BackgroundLi, J., Zhang, R., Liu, Y., Zhang, Z., Fan, R., & Liu, W. (2021) · Electronics · doi:10.3390/electronics10161883 · Cited by 8
Ceiling-View Semi-Direct Monocular Visual Odometry with Planar Constraint
Wang, Y., Zhang, S., & Wang, J. (2022) · Remote Sensing · doi:10.3390/rs14215447 · Cited by 9
Estimating Withdrawal Time in Colonoscopies
Katzir, L., Veikherman, D., Dashinsky, V., Goldenberg, R., Shimshoni, I., Rabani, N., Cohen, R., Kelner, O., Rivlin, E., & Freedman, D. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-25066-8_28 · Cited by 7
Evolving Real-time Stereo Odometry for AUV Navigation in Challenging Marine Environments
Nordfeldt-Fiol, B. M., Font, F. B., & Oliver, G. (2023) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-023-01932-0 · Cited by 7
“Moreover, according to Table 1 [49–51], all these combinations are invariant to rotations and scale changes.”
Hu, J. Y., Lei, W., Zhuo, D., Zhu, F., Liu, W., & Zhang, X. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3370759 · Cited by 9
“Besides, the dynamic objects and mismatches will introduce outliers into the visual features, which will be detected and removed by the RANSAC method [33].”
MethodMonocular Visual Odometry Based Navigation for a Differential Mobile Robot with Android OS
Villanueva-Escudero, C., Villegas-Cortéz, J., Zúñiga‐López, A., & Avilés‐Cruz, C. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-13647-9_26 · Cited by 9
The registration system for the evaluation of indoor visual slam and odometry algorithms
Schmidt, A., Kraft, M., Fularz, M., & Domagała, Z. (2013) · Journal of Automation Mobile Robotics & Intelligent Systems · Cited by 7
Toward autonomous navigation using an RGB-D camera for flight in unknown indoor environments
Tang, L., Yang, S. Y., Cheng, N., & Li, Q. (2014) · IEEE CSAA Guidance, Navigation and Control Conference (CGNCC) · doi:10.1109/cgncc.2014.7007485 · Cited by 7
Terrain adaptive detector selection for visual odometry in natural scenes
Otsu, K., Otsuki, M., Ishigami, G., & Kubota, T. (2013) · Advanced Robotics · doi:10.1080/01691864.2013.843789 · Cited by 7
“[13,26,27] Several research groups have compared the performance of interest point detectors.”
BackgroundAn Image-Based Inspection System for Canal Tunnel Heritage
Charbonnier, P., Foucher, P., Chavant, P., Muzet, V., Prybyla, D., Perrin, T., Albert, J.-L., Grussenmeyer, P., Guillemin, S., & Koehl, M. (2014) · International Journal of Heritage in the Digital Era · doi:10.1260/2047-4970.3.1.197 · Cited by 9
Robust Registration of Kinect Range Data for Sensor Motion Estimation
Nowicki, M., & Skrzypczyński, P. (2013) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-00969-8_82 · Cited by 7
Divergent trinocular vision observers design for extended Kalman filter robot state estimation
Martínez‐García, E. A., Rivero-Juárez, J., Torres-Méndez, L. A., & Rodas-Osollo, J. (2018) · Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering · doi:10.1177/0959651818800908 · Cited by 9
“An observer model that accurately describes the disparity observations with respect to depth was nearly exponential equation (31).”
LLama-SLAM: Learning High-Quality Visual Landmarks for Long-Term Mapping and Localization
Luthardt, S., Willert, V., & Adamy, J. (2018) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2018.8569323 · Cited by 10
“There is practical evidence [25] that a good distribution of landmarks in the image leads to more reliable pose estimates.”
BackgroundAutomated Indoor Image Localization to Support a Post-Event Building Assessment
Liu, X., Dyke, S. J., Yeum, C. M., Bilionis, I., Lenjani, A., & Choi, J. B. (2020) · Sensors · doi:10.3390/s20061610 · Cited by 8
“Alternatively, visual odometry (hereafter, VO) provides a potential solution that offers accurate positional output without having prior information about the environment and without relying on other sensors installed in the building [29,30].”
BackgroundZhao, H., Bian, W., Yuan, B., & Tao, D. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/68 · Cited by 15
“Traditional meth-ods generally follow a pipeline [ Fraundorfer and Scaramuzza, 2012 ] including camera calibration, feature detection, feature matching, outlier rejection, motion estimation, scale estimation and Bundle Adjustment.”
Relative Navigation in GPS‐Degraded Environments
Wheeler, D. O., Nyholm, P. W., Koch, D. P., Ellingson, G. J., McLain, T. W., & Beard, R. W. (2016) · Wiley eBooks · doi:10.1002/9780470686652.eae1154 · Cited by 7
“Good general tutorials on visual odometry are found in [8, 9].”
BackgroundGlobal Localization Technology of Lunar Rover by Horizon Line Matching
Tian, Z., Zhang, H., & Hu, Q. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2024.3433838 · Cited by 7
Robust 360-8PA: Redesigning The Normalized 8-point Algorithm for 360-FoV Images
Solarte, B., Wu, C.-H., Lu, K.-W., Tsai, Y., Chiu, W.-C., & Sun, M. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9560888 · Cited by 6
“a RANSAC evaluation, hence increasing its computation time for a large ratio of outliers [12].”
BackgroundZhou, Z., Nie, S., Uprety, S., & Yang, H. (2025) · IEEE Access · doi:10.1109/access.2025.3589161 · Cited by 8
“Both the 3D positions of the tracked features and the camera poses are jointly optimized in a windowed bundle adjustment framework [14].”
Vision-based speedometer regulates human walking
Takamuku, S., & Gomi, H. (2021) · iScience · doi:10.1016/j.isci.2021.103390 · Cited by 7
“Computer vision studies (Fraundorfer and Scaramuzza, 2012; Scaramuzza and Fraundorfer, 2011) have made significant theoretical advances on how self-motion can be estimated.”
BackgroundA Generic Image Processing Pipeline for Enhancing Accuracy and Robustness of Visual Odometry
Sabry, M., Osman, M., Hussein, A., Mehrez, M. W., Jeon, S. J., & Melek, W. (2022) · Sensors · doi:10.3390/s22228967 · Cited by 8
“One of the common methods for localization using cameras is through Visual Odometry (VO) [7,8].”
MethodRobust Motion Estimation with RBG-D Cameras
Leishman, R. C., Koch, D. P., McLain, T. W., & Beard, R. W. (2013) · AIAA Infotech@Aerospace Conference · doi:10.2514/6.2013-4810 · Cited by 6
DEVISING A VISUAL INSPECTION SYSTEM FOR CANAL TUNNELS: PRELIMINARY STUDIES
Albert, J.-L., Charbonnier, P., Chavant, P., Foucher, P., Muzet, V., Prybyla, D., Perrin, T., Grussenmeyer, P., Guillemin, S., & Koehl, M. (2013) · 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/isprsarchives-xl-5-w2-13-2013 · Cited by 6
“In contrast, visual odometry (VO) (Scaramuzza and Fraundorfer, 2011, Scaramuzza and Fraundorfer, 2012), which can be seen as a special case of SFM, estimates the 3D motion of the camera in real-time, in a sequential way.”
BackgroundVision-Controlled Micro Flying Robots
Scaramuzza, D., Achtelik, M. C., Doitsidis, L., Fraundorfer, F., Kosmatopoulos, E. B., Martinelli, A., Achtelik, M., Chli, M., Chatzichristofis, S. A., Kneip, L., et al. (2014) · Cited by 6
Self-citationZhao, X., Min, H., Xu, Z., Wu, X., Li, X., & Sun, P. (2018) · Journal of Sensors · doi:10.1155/2018/2987819 · Cited by 6
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.