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
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I., & Leonard, J. J. (2016) · IEEE Transactions on Robotics · doi:10.1109/tro.2016.2624754 · Cited by 3,596
Self-citationPast, present, and future of simultaneous localization and mapping: Toward the robust-perception age
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I. D., & Leonard, J. J. (2016) · Zurich Open Repository and Archive (University of Zurich) · doi:10.5167/uzh-138892 · Cited by 3,048
Self-citationScience, technology and the future of small autonomous drones
Floreano, D., & Wood, R. J. (2015) · Nature · doi:10.1038/nature14542 · Cited by 1,476
Deepvo: towards end-to-end visual odometry with deep recurrent convolutional neural networks
Wang, S., Clark, R., Wen, H., & Trigoni, N. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989236 · Cited by 970
“1, a classic pipeline [1], [2], which typically consists of camera calibration, feature detection, feature matching (or tracking), outlier rejection (e.”
BackgroundSimultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving
Bresson, G., Alsayed, Z., Yu, L., & Glaser, S. (2017) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2017.2749181 · Cited by 885
“In [89] and [90], the authors cover the topic of Visual Odometry (VO) where the focus is on the localization (and the trajectory) and not on the map.”
Visual SLAM algorithms: a survey from 2010 to 2016
Taketomi, T., Uchiyama, H., & Ikeda, S. (2017) · IPSJ Transactions on Computer Vision and Applications · doi:10.1186/s41074-017-0027-2 · Cited by 725
“According to the survey papers in robotics [18, 19], the relationship between vSLAM and VO can be represented as follows.”
BackgroundEvolution of Indoor Positioning Technologies: A Survey
Brena, R. F., García-Vázquez, J. P., Galván-Tejada, C. E., Muñoz-Rodriguez, D., Vargas-Rosales, C., & Fangmeyer, J. (2017) · Journal of Sensors · doi:10.1155/2017/2630413 · Cited by 478
“VO is not a recent approach and has been around for some 30 years but has been gradually improved both in efficiency and in precision [81].”
BackgroundVisual SLAM and Structure from Motion in Dynamic Environments: A Survey
Saputra, M. R. U., Markham, A., & Trigoni, N. (2019) · ACM Computing Surveys · doi:10.1145/3177853 · Cited by 398
“Under RANSAC, the number of iterations required to guarantee a correct solution is where s is the number of data points, ε is the percentage of outliers, and p is the probability of success (confidence level) [39].”
BackgroundAn Overview to Visual Odometry and Visual SLAM: Applications to Mobile Robotics
Yousif, K., Bab-Hadiashar, A., & Hoseinnezhad, R. (2015) · Intelligent Industrial Systems · doi:10.1007/s40903-015-0032-7 · Cited by 322
“In general, the cost function to be minimized can be formulated as [45]: arg min where X i is the i th 3D point, p is its corresponding image point observed in the k th frame and g ( X i , C k ) is the re-projection function according to the camera pose C k .”
BackgroundMultiple-Robot Simultaneous Localization and Mapping: A Review
Saeedi, S., Trentini, M., Seto, M., & Li, H. (2016) · Journal of Field Robotics · doi:10.1002/rob.21620 · Cited by 324
“Various features, such as scale-invariant feature transform (SIFT) and speeded up robust features (SURF), have been introduced in (Fraundorfer & Scaramuzza, 2012).”
BackgroundMethodInfluentialKalaitzakis, M., Cain, B., Carroll, S., Ambrosi, A., Whitehead, C., & Vitzilaios, N. (2021) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-020-01307-9 · Cited by 296
Scaramuzza, D., Achtelik, M. C., Doitsidis, L., Friedrich, F., Kosmatopoulos, E., Martinelli, A., Achtelik, M. W., Chli, M., Chatzichristofis, S., Kneip, L., et al. (2014) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2014.2322295 · Cited by 299
Self-citationReview of visual odometry: types, approaches, challenges, and applications
Aqel, M. O. A., Marhaban, M. H., Saripan, M. I., & Ismail, N. B. (2016) · SpringerPlus · doi:10.1186/s40064-016-3573-7 · Cited by 292
“VO is considered a cost-effective solution compared with LIDAR systems (Fraundorfer and Scaramuzza 2012).”
BackgroundMethodAdaptive Structure from Motion with a Contrario Model Estimation
Moulon, P., Monasse, P., & Marlet, R. (2013) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-37447-0_20 · Cited by 232
End-to-end, sequence-to-sequence probabilistic visual odometry through deep neural networks
Wang, S., Clark, R., Wen, H., & Trigoni, N. (2018) · The International Journal of Robotics Research · doi:10.1177/0278364917734298 · Cited by 238
“As shown in Figure 1(a), a classic pipeline (Scaramuzza and Fraundorfer 2011; Fraundorfer and Scaramuzza 2012), which typically consists of camera calibration, feature detection, feature matching (or tracking), outlier rejection (e.g., RANSAC), motion estimation, scale estimation and optimisation…”
BackgroundMethodSuleiman, A., Zhang, Z., Carlone, L., Karaman, S., & Sze, V. (2019) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2018.2886342 · Cited by 158
Active Mapping and Robot Exploration: A Survey
Lluvia, I., Lazkano, E., & Ansuategi, A. (2021) · Sensors · doi:10.3390/s21072445 · Cited by 200
“Combining visual information from cameras or inertial sensors with wheel motion information allows us to overcome the drift and provides much more accurate localization [5].”
BackgroundVisual and Visual‐Inertial SLAM: State of the Art, Classification, and Experimental Benchmarking
Servières, M., Renaudin, V., Dupuis, A., & Antigny, N. (2021) · Journal of Sensors · doi:10.1155/2021/2054828 · Cited by 181
“Depending on whether the feature correspondences in two successive frames are in 2D or 3D, there are three di ff erent ways to perform visual odometry [11].”
Perception and Navigation in Autonomous Systems in the Era of Learning: A Survey
Tang, Y. S., Zhao, C., Wang, J., Zhang, C., Sun, Q., Zheng, W. X., Du, W., Qian, F., & Kurths, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3167688 · Cited by 199
“The difference between traditional VO and vSLAM is that VO system lacks the loop-closure detection and global optimization [34].”
BackgroundMethodInfluentialLocalization and Mapping for Robots in Agriculture and Forestry: A Survey
Aguiar, A., dos Santos, F. N., Boaventura‐Cunha, J., Sobreira, H., & Sousa, A. J. (2020) · Robotics · doi:10.3390/robotics9040097 · Cited by 168
“Firstly, the input image is processed so that features can be extracted from it [55].”
BackgroundLIFT-SLAM: A deep-learning feature-based monocular visual SLAM method
Bruno, H. M. S., & Colombini, E. L. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.05.027 · Cited by 154
“On the other side, the LIFT keypoints matched are spread within the whole image (Figures 3c and 3e), this aspect can improve accuracy of VO systems, as discussed in [23].”
BackgroundCvišić, I., Ćesić, J., Marković, I., & Petrović, I. (2018) · Journal of Field Robotics · doi:10.1002/rob.21762 · Cited by 133
“Rk ′′ k−1 = ( Rk−1 k−2 )−1 Rk r k−2 (6)”
Chen, C., Zhu, H. J., Li, M., & You, S. (2018) · Robotics · doi:10.3390/robotics7030045 · Cited by 146
Simultaneous Localization and Mapping
Stachniss, C., Leonard, J. J., & Thrun, S. (2016) · Springer handbooks · doi:10.1007/978-3-319-32552-1_46 · Cited by 172
Advances in intelligent and autonomous navigation systems for small UAS
Bijjahalli, S., Sabatini, R., & Gardi, A. (2020) · Progress in Aerospace Sciences · doi:10.1016/j.paerosci.2020.100617 · Cited by 123
Han, L., Lin, Y., Du, G., & Lian, S. (2019) · 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968467 · Cited by 125
“Because of low-cost, and easy hardware setup, camera-based solutions [1] have drawn a large attention by the community.”
BackgroundSelfVIO: Self-supervised deep monocular Visual–Inertial Odometry and depth estimation
Almalıoğlu, Y., Turan, M., Saputra, M. R. U., de Gusmão, P. P. B., Markham, A., & Trigoni, N. (2022) · Neural Networks · doi:10.1016/j.neunet.2022.03.005 · Cited by 148
A Review of Technologies and Techniques for Indoor Navigation Systems for the Visually Impaired
Simões, W. C. S. S., Machado, G. S., de Sales, A. M. A., Lucena, M., Jazdi, N., & de Lucena, V. F. (2020) · Sensors · doi:10.3390/s20143935 · Cited by 131
“VO is not a recent approach, but it has been gradually improved in e ffi ciency and accuracy [109].”
BackgroundJoshi, B., Rahman, S., Kalaitzakis, M., Cain, B., Johnson, J. V., Xanthidis, M., Karapetyan, N., Hernandez, A., Li, A. Q., Vitzilaios, N. I., et al. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968049 · Cited by 133
“With the proliferation of visual inertial devices many researchers have designed novel state estimation algorithms for Visual Odometry (VO) [1], [2] or visual SLAM [3].”
State of the Art in Vision-Based Localization Techniques for Autonomous Navigation Systems
Alkendi, Y., Seneviratne, L. D., & Zweiri, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3082778 · Cited by 125
“In addition, odometry algorithms implement local map optimization methods, such as windowed bundle adjustment, to optimize the local map only over the last poses, leading to local map consistency [22], [23].”
MethodThermal Stereo Odometry for UAVs
Mouats, T., Aouf, N., Chermak, L., & Richardson, M. A. (2015) · IEEE Sensors Journal · doi:10.1109/jsen.2015.2456337 · Cited by 104
“Surveys and tutorials have been produced to explain the different sub-tasks that are involved [2], [6], [7].”
BackgroundZhang, Y., Shi, P., & Li, J. (2024) · The Photogrammetric Record · doi:10.1111/phor.12497 · Cited by 121
Unsupervised Deep Visual-Inertial Odometry with Online Error Correction for RGB-D Imagery
Shamwell, E. J., Lindgren, K., Leung, S., & Nothwang, W. D. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2909895 · Cited by 86
“Originally coined to characterize honey bee flight [8], the term “visual odometry” describes the integration of apparent image motions for dead-reckoning-based navigation (literally, as an odometer for vision) [9].”
BackgroundRobust IMU/GPS/VO Integration for Vehicle Navigation in GNSS Degraded Urban Areas
Sun, R., Yang, Y., Chiang, K., Duong, T.-T., Lin, K.-Y., & Tsai, G.-J. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2989332 · Cited by 86
“The VO’s output is referenced in the camera frame originating at the camera center [10].”
BackgroundMethodDeep Learning Techniques for Visual SLAM: A Survey
Mokssit, S., Licea, D. B., Guermah, B., & Ghogho, M. (2023) · IEEE Access · doi:10.1109/access.2023.3249661 · Cited by 93
“The visual odometry module [39], [40] first examines the features, and then uses feature matching and outlier rejection techniques to find reliable pixel-pair correspondences in consecutive frames.”
MethodSimultaneous Localization And Mapping: Present, Future, and the Robust-Perception Age.Preprint
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I. D., & Leonard, J. J. (2016) · arXiv (Cornell University) · Cited by 90
Self-citationSLAM Overview: From Single Sensor to Heterogeneous Fusion
Chen, W., Zhou, C., Shang, G., Wang, X., Li, Z., Xu, C., & Hu, K. (2022) · Remote Sensing · doi:10.3390/rs14236033 · Cited by 91
Experimental Comparison of Open Source Vision-Based State Estimation Algorithms
Li, A. Q., Coskun, A., Doherty, S. M., Ghasemlou, S., Jagtap, A., Modasshir, M., Rahman, S., Singh, A. K., Xanthidis, M., O’Kane, J. M., et al. (2017) · Springer proceedings in advanced robotics · doi:10.1007/978-3-319-50115-4_67 · Cited by 82
“Scaramuzza and Fraundorfer [28, 11] presented a comprehensive overview this work, from the fundamentals of Visual Odometry to recent research challenges and applications.”
BackgroundPractical Infrared Visual Odometry
Borges, P. V. K., & Vidas, S. (2016) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2016.2515625 · Cited by 83
“These salient points can be corners or blobs [12], for example.”
BackgroundOngoing Evolution of Visual SLAM from Geometry to Deep Learning: Challenges and Opportunities
Li, R., Wang, S., & Gu, D. (2018) · Cognitive Computation · doi:10.1007/s12559-018-9591-8 · Cited by 85
Ground-Plane-Based Absolute Scale Estimation for Monocular Visual Odometry
Zhou, D., Dai, Y., & Li, H. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2900330 · Cited by 76
“Some detailed summaries of them can be found in [11], [12], [13] and [14].”
BackgroundYuan, J., Chen, H., Sun, F., & Huang, Y. (2015) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2015.2407512 · Cited by 70
“For example, when the robot uses a single camera to track the target, the techniques of visual MD [7], [32] can be applied to detect the dynamic regions, and the visual odometry [33] can be used to localize the robot.”
MethodDytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environments
Shen, S., Cai, Y., Wang, W., & Scherer, S. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10161306 · Cited by 94
“Learning-based VO solutions aim to avoid hard-coded modules that require significant engineering efforts for design and finetuning in classic pipelines [1], [16].”
BackgroundMulti-body Motion Estimation from Monocular Vehicle-Mounted Cameras
Sabzevari, R., & Scaramuzza, D. (2016) · IEEE Transactions on Robotics · doi:10.1109/tro.2016.2552548 · Cited by 68
“An exhaustive survey on VO is presented in [1] and [12].”
BackgroundSelf-citationSOFT2: Stereo Visual Odometry for Road Vehicles Based on a Point-to-Epipolar-Line Metric
Cvišić, I., Marković, I., & Petrovic, I. K. (2022) · IEEE Transactions on Robotics · doi:10.1109/tro.2022.3188121 · Cited by 82
“Allthismakescamerasanattractivesensormodalityand visuallocalizationhasbeenasubjectofresearchforseveral decadesnow[1],[4],[6].”
Relative Navigation Approach for Vision-Based Aerial GPS-Denied Navigation
Leishman, R. C., McLain, T. W., & Beard, R. W. (2013) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-013-9914-7 · Cited by 76
“Good tutorials on implementing VO are found in [21], [22].”
BackgroundRobust Data Fusion of Multimodal Sensory Information for Mobile Robots
Kubelka, V., Oswald, L., Pomerleau, F., Colas, F., Svoboda, T., & Reinštein, M. (2014) · Journal of Field Robotics · doi:10.1002/rob.21535 · Cited by 71
“It does search for correspondences (i.e., image matching) (Rublee et al., 2011), landmark reconstruction and sliding bundle adjustment (Kummerle et al., 2011; Fraundorfer and Scaramuzza, 2012), which refines the landmark 3D positions and the robot poses.”
BackgroundVisual sensing for autonomous underwater exploration and intervention tasks
Font, F. B., Oliver, G., Wirth, S., Massot‐Campos, M., Negre, P. L., & Beltrán, J. P. (2014) · Ocean Engineering · doi:10.1016/j.oceaneng.2014.11.005 · Cited by 66
Monocular Visual Odometry Based on Depth and Optical Flow Using Deep Learning
Ban, X., Wang, H., Chen, T., Wang, Y., & Xiao, Y. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3024011 · Cited by 67
“The traditional geometry-based VO delivers state-of-the-art performance in terms of accuracy and robustness [2].”
BackgroundMethodAssistive Delivery Robot Application for Real-World Postal Services
Lee, D., Kang, G., Kim, B., & Shim, D. H. (2021) · IEEE Access · doi:10.1109/access.2021.3120618 · Cited by 67
A Practical Survey on Visual Odometry for Autonomous Driving in Challenging Scenarios and Conditions
Agostinho, L. R., Ricardo, N. M., Pereira, M. I., Hiolle, A., & Pinto, A. M. (2022) · IEEE Access · doi:10.1109/access.2022.3188990 · Cited by 77
A Biologically Inspired, Vision‐based Guidance System for Automatic Landing of a Fixed‐wing Aircraft
Thurrowgood, S., Moore, R. J. D., Soccol, D., Knight, M., & Srinivasan, M. V. (2014) · Journal of Field Robotics · doi:10.1002/rob.21527 · Cited by 56
“Thus, the translation is not measured in absolute units, but as a multiple of the instantaneous height above the ground (Fraundorfer & Scaramuzza, 2012; Scaramuzza & Fraundorfer, 2011).”
BackgroundA High-Integrity and Low-Cost Navigation System for Autonomous Vehicles
Bijjahalli, S., & Sabatini, R. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2957876 · Cited by 59
“Given the presence of two sets of features that are tracked across two successive frames k − 1 and k, VO is essentially the computation of the rigid body transformation comprising translation and rotation between the poses camera Ck−1 and Ck [19], [20].”
BackgroundSpoofing Detection of Civilian UAVs Using Visual Odometry
Varshosaz, M., Afary, A., Mojaradi, B., Saadatseresht, M., & Parmehr, E. G. (2019) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi9010006 · Cited by 56
“Since VSLAM has high computational cost due to the process of map production [41,42]; this method is not more suitable for UAV spoofing detection.”
MethodVisual Odometry : Autonomous UAV Navigation using Optic Flow and Stereo
Strydom, R., Thurrowgood, S., & Srinivasan, M. V. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · Cited by 61
Multi-level mapping: Real-time dense monocular SLAM
Greene, W. N., Ok, K., Lommel, P., & Roy, N. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487213 · Cited by 55
Tang, S., & Kumar, V. (2018) · Annual Review of Control Robotics and Autonomous Systems · doi:10.1146/annurev-control-060117-105149 · Cited by 64
A systematic literature review on long‐term localization and mapping for mobile robots
Sousa, R. B., Sobreira, H., & Moreira, A. P. (2023) · Journal of Field Robotics · doi:10.1002/rob.22170 · Cited by 68
Robust visual-based localization and mapping for underwater vehicles: A survey
Ding, S., Zhang, T., Lei, M., Chai, H., & Jia, F. (2024) · Ocean Engineering · doi:10.1016/j.oceaneng.2024.119274 · Cited by 53
Cost-effective visual odometry system for vehicle motion control in agricultural environments
Zaman, S., Comba, L., Biglia, A., Aimonino, D. R., Barge, P., & Gay, P. (2019) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2019.03.037 · Cited by 54
eVO: A realtime embedded stereo odometry for MAV applications
Sanfourche, M., Vittori, V., & Besnerais, G. L. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696651 · Cited by 52
IMU and Multiple RGB-D Camera Fusion for Assisting Indoor Stop-and-Go 3D Terrestrial Laser Scanning
Chow, J., Lichti, D. D., Hol, J. D., Bellusci, G., & Luinge, H. (2014) · Robotics · doi:10.3390/robotics3030247 · Cited by 53
“A blob detector is preferred over edge/corner detectors because such geometric information is already encapsulated in the depth data processing pipeline [85].”
BackgroundLearning and Matching Multi-View Descriptors for Registration of Point Clouds
Zhou, L., Zhu, S., Luo, Z., Shen, T., Zhang, R., Zhen, M., Fang, T., & Quan, L. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01267-0_31 · Cited by 56
“Registration of point clouds integrates 3D data from different sources into a common coordinate system, serving as an essential component of many highlevel applications like 3D modeling [1,2], SLAM [3] and robotic perception [4].”
BackgroundVOLDOR: Visual Odometry From Log-Logistic Dense Optical Flow Residuals
Min, Z., Yang, Y., & Dunn, E. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00495 · Cited by 59
“Visual odometry (VO) [60, 21, 22] addresses the recovery of camera poses from an input video sequence, which supports applications such as augmented reality, robotics and autonomous driving.”
BackgroundSensors and Sensor Fusion Methodologies for Indoor Odometry: A Review
Yang, M., Sun, X. S., Jia, F., Rushworth, A. G. A., Dong, X., Zhang, S., Fang, Z., Yang, G., & Liu, B. (2022) · Polymers · doi:10.3390/polym14102019 · Cited by 55
“There exist several review papers on the VO systems—[13,158–160] provided a comprehensive overview of VO and V-SLAM; the two-part survey [161,162] highlighted feature-based VO; while [163–166] conducted reviews of recent advancements in VO and V-SLAM using state-of-the-art data-driven methods.”
Semantic segmentation–aided visual odometry for urban autonomous driving
An, L., Zhang, X., Gao, H., & Liu, Y. (2017) · International Journal of Advanced Robotic Systems · doi:10.1177/1729881417735667 · Cited by 45
“The VO term had been first used by Nistér in 2004,(1) but the relevant researches in this area had been focused over 30 years.(2,3) VO uses camera as main sensor and takes the current image frames as input and compares with previous frame, then estimates camera’s pose transformation and the trajectory like wheel odome…”
MethodProprioceptive Sensor Fusion for Quadruped Robot State Estimation
Fink, G., & Semini, C. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341521 · Cited by 62
“Much of the current literature on state estimation for mobile robotics has been focused on exteroceptive sensors for simultaneous localization and mapping (SLAM) [5], [6], visual odometry [7], [8], visual SLAM [9], and visual-inertial SLAM [10]–[12].”
BackgroundGräter, J., Schwarze, T., & Lauer, M. (2015) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2015.7225730 · Cited by 50
“Such is done in one of the first real-time applications of MonoVO on affordable sensor systems, established by Klein et al. [3], where the user is asked to move the camera by a certain distance on system startup.”
BackgroundError Analysis for Visual Odometry on Indoor, Wheeled Mobile Robots With 3-D Sensors
Fabian, J. R., & Clayton, G. M. (2014) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2014.2302910 · Cited by 44
“Many algorithms implement some form of the random sample and consensus (RANSAC) outlier-rejection method [11] to augment the feature tracking process [12], [13], since these feature-based visual odometry algorithms are sensitive to incorrect feature matches [14].”
MethodSelective visual odometry for accurate AUV localization
Bellavia, F., Fanfani, M., & Colombo, C. (2015) · Autonomous Robots · doi:10.1007/s10514-015-9541-1 · Cited by 48
“Scaramuzza and Fraundorfer (2011) and Fraundorfer and Scaramuzza (2012) give an in deep review of VO.”
BackgroundDirect visual odometry for a fisheye-stereo camera
Liu, P., Heng, L., Sattler, T., Geiger, A., & Pollefeys, M. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8205988 · Cited by 53
Distributed Formation Estimation Via Pairwise Distance Measurements
Ziegler, T., Karrer, M., Schmuck, P., & Chli, M. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3062347 · Cited by 59
“1) Visual-Inertial Odometry: Following the notation of [20], the agent’s current pose is estimated by concatenating relative transformations between time steps.”
MethodRadar odometry with recursive-RANSAC
Quist, E. B., Niedfeldt, P. C., & Beard, R. W. (2016) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2016.140829 · Cited by 43
“Additionally, their sensitivity and accuracy degrade at the long standoff ranges often experienced by aircraft [1–6].”
BackgroundApplications of image processing in robotics and instrumentation
Kurka, P. R. G., & Diaz, A. (2019) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2019.01.015 · Cited by 44
RADARODO: Ego-Motion Estimation From Doppler and Spatial Data in RADAR Images
Monaco, C. D., & Brennan, S. (2020) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2020.2973536 · Cited by 48
“Furthermore, low-visibility conditions can reduce the measurement range or fine texture required for many camera- or LIDARbased methods [3], [10], [16], [17].”
BackgroundDeepAVO: Efficient pose refining with feature distilling for deep Visual Odometry
Zhu, R., Yang, M., Liu, W., Song, R., Yan, B., & Xiao, Z. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.09.029 · Cited by 50
Review and classification of vision‐based localisation techniques in unknown environments
Afia, A. B., Deambrogio, L., Salós, D., Escher, A., Macabiau, C., Soulier, L., & Gay‐Bellile, V. (2014) · IET Radar Sonar & Navigation · doi:10.1049/iet-rsn.2013.0389 · Cited by 54
“A complete explanation of VO is detailed in [51, 52].”
BackgroundNguyen, Q.-H., Vu, H., Tran, T.-H., & Nguyen, Q.-H. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-015-3204-2 · Cited by 46
“Matching a current view to a position on the created map seems to be the hardest problem [2, 9].”
BackgroundRadar odometry on fixed-wing small unmanned aircraft
Quist, E. B., & Beard, R. W. (2016) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2015.140186 · Cited by 45
“One approach to GPS-denied navigation is to use an existing map consisting of known observable features for position estimation [4, 5].”
BackgroundInfluentialA methodology for measuring the total displacements of structures using a laser–camera system
Nasimi, R., & Moreu, F. (2021) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12652 · Cited by 42
“LiDARs are useful to collect data in a large scale but for normal scale applications, VO is a cost-efficient solution (Fraundorfer & Scaramuzza, 2012).”
MethodThe Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation
Zhao, X., Agrawal, H., Batra, D., & Schwing, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01582 · Cited by 41
Retrieving Scale on Monocular Visual Odometry Using Low-Resolution Range Sensors
Chiodini, S., Giubilato, R., Pertile, M., & Debei, S. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.2964066 · Cited by 40
“An introducing tutorial on VO can be found in [1] and [2].”
A trunk-based SLAM backend for smartphones with online SLAM in large-scale forest inventories
Fan, Y., Feng, Z., Shen, C., Khan, T. U., Mannan, A., Gao, X., Chen, P., & Saeed, S. (2020) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2020.02.006 · Cited by 42
Unifying Offline and Online Multi-Graph Matching via Finding Shortest Paths on Supergraph
Jiang, Z., Wang, T., & Yan, J. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2989928 · Cited by 40
Fularz, M., Kraft, M., Schmidt, A., & Kasinski, A. (2015) · International Journal of Advanced Robotic Systems · doi:10.5772/61434 · Cited by 36
“Point correspondences found in sequences of images are the input data for a wide range of computer vision algo‐ rithms, including tracking [1, 2], 3D reconstruction [3, 4], image stitching [5], visual odometry [6, 7], video surveil‐ lance [8, 9] and simultaneous localization and mapping [10, 11].”
BackgroundAbsolute Localization using Image Alignment and Particle Filtering
van Dalen, G., Magree, D. P., & Johnson, E. N. (2016) · AIAA Guidance, Navigation, and Control Conference and Exhibit · doi:10.2514/6.2016-0647 · Cited by 41
Computer Vision-Assisted 3D Object Localization via COTS RFID Devices and a Monocular Camera
Wang, Z., Xu, M., Ye, N., Xiao, F., Wang, R., & Huang, H. (2019) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2019.2954830 · Cited by 39
Comparative assessment of point feature detectors in the context of robot navigation
Schmidt, A., Kraft, M., Fularz, M., & Domagała, Z. (2013) · Journal of Automation Mobile Robotics & Intelligent Systems · Cited by 37
DRM-SLAM: Towards dense reconstruction of monocular SLAM with scene depth fusion
Ye, X., Ji, X., Sun, B., Chen, S., Wang, Z., & Li, H. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.02.044 · Cited by 41
An UWB/Vision Fusion Scheme for Determining Pedestrians’ Indoor Location
Liu, F., Zhang, J., Wang, J., Han, H., & Deng, Y. (2020) · Sensors · doi:10.3390/s20041139 · Cited by 40
Eudoxus: Characterizing and Accelerating Localization in Autonomous Machines Industry Track Paper
Gan, Y., Bo, Y., Tian, B., Xu, L., Hu, W., Liu, S., Liu, Q., Zhang, Y., Tang, J., & Zhu, Y. (2021) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca51647.2021.00074 · Cited by 57
“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].”
MethodInfluentialFleer, D., & Möller, R. (2016) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2016.12.001 · Cited by 37
Improving multi-modal data fusion by anomaly detection
Šimánek, J., Kubelka, V., & Reinštein, M. (2015) · Autonomous Robots · doi:10.1007/s10514-015-9431-6 · Cited by 41
“An established standard for model estimation in the presence of outliers is represented by the RANSAC based algorithms (Fraundorfer and Scaramuzza 2012; Konolige et al. 2011).”
MethodFast Structure from Motion for Sequential and Wide Area Motion Imagery
Aliakbarpour, H., Palaniappan, K., & Seetharaman, G. S. (2015) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2015.142 · Cited by 35
“The outliers or mismatches may be caused by occlusions, repetitive patterns, illumination changes, shadows, image noise and blur for which the assumptions of the feature detector and descriptors are not satisfied [16].”
BackgroundLSTM and Filter Based Comparison Analysis for Indoor Global Localization in UAVs
Yusefi, A., Durdu, A., Aslan, M. F., & Sungur, C. (2021) · IEEE Access · doi:10.1109/access.2021.3049896 · Cited by 37
SPARTAN: Developing a Vision System for Future Autonomous Space Exploration Robots
Kostavelis, I., Nalpantidis, L., Boukas, E., Rodrigalvarez, M. A., Stamoulias, I., Lentaris, G., Diamantopoulos, D., Siozios, K., Soudris, D., & Gasteratos, A. C. (2013) · Journal of Field Robotics · doi:10.1002/rob.21484 · Cited by 39
“Each detector has its own advantages and disadvantages, and therefore the choice of the appropriate one should be carefully considered, depending on the computational constraints, real-time requirements, environment type, and interframe motion (Fraundorfer and Scaramuzza, 2012).”
BackgroundSurvey of unmanned subterranean exploration, navigation, and localisation
Martz, J., Alsabban, W. H., & Smith, R. N. (2020) · IET Cyber-Systems and Robotics · doi:10.1049/iet-csr.2019.0043 · Cited by 42
“18, with detailed overviews presented in [89, 118, 119].”
Leveraging Deep Learning for Visual Odometry Using Optical Flow
Pandey, T., Peña, D., Byrne, J., & Moloney, D. (2021) · Sensors · doi:10.3390/s21041313 · Cited by 36
“Deep neural networks learn feature representations in higher dimensions and can replace the engineering effort required in integrating and fine-tuning individual components [1,21].”
BackgroundBucci, A., Zacchini, L., Franchi, M., Ridolfi, A., & Allotta, B. (2021) · Applied Ocean Research · doi:10.1016/j.apor.2021.102961 · Cited by 33
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.