Made to measure: Bespoke landmarks for 24-hour, all-weather localisation with a camera
The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
This paper is about camera-only localisation in challenging outdoor environments, where changes in lighting, weather and season cause traditional localisation systems to fail. Conventional approaches to the localisation problem rely on point-features such as SIFT, SURF or BRIEF to associate landmark observations in the live image with landmarks stored in the map; however, these features are brittle to the severe appearance change routinely encountered in outdoor environments. In this paper, we propose an alternative to traditional point-features: we train place-specific linear SVM classifiers to recognise distinctive elements in the environment. The core contribution of this paper is an unsupervised mining algorithm which operates on a single mapping dataset to extract distinct elements from the environment for localisation. We evaluate our system on 205km of data collected from central Oxford over a period of six months in bright sun, night, rain, snow and at all times of the day. Our experiment consists of a comprehensive N-vs-N analysis on 22 laps of the approximately 10km route in central Oxford. With our proposed system, the portion of the route where localisation fails is reduced by a factor of 6, from 33.3% to 5.5%.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
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
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 5×
“Landmarks are described by a feature descriptor (e.g. SIFT, SURF, BRIEF).”
MethodInfluentialSpeeded-Up Robust Features (SURF)
Bay, H., Ess, A., Tuytelaars, T., & Van Gool, L. (2008) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2007.09.014 · Cited by 13,557
A Combined Corner and Edge Detector
Harris, C., & Stephens, M. (1988) · Procedings of the Alvey Vision Conference 1988 · doi:10.5244/c.2.23 · Cited by 12,901 · cited 1×
“Many prior works in this area use local, low-level image features such as corners [6][7], blobs [8], or lines [9] as the underlying point of interest detector.”
BackgroundORB: 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
Machine Learning for High-Speed Corner Detection
Rosten, E., & Drummond, T. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_34 · Cited by 4,555 · cited 1×
“Many prior works in this area use local, low-level image features such as corners [6][7], blobs [8], or lines [9] as the underlying point of interest detector.”
BackgroundParallel Tracking and Mapping for Small AR Workspaces
Klein, G., & Murray, D. (2007) · 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2007.4538852 · Cited by 4,346
Edge Boxes: Locating Object Proposals from Edges
Zitnick, C. L., & Dollár, P. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_26 · Cited by 2,656
Scaramuzza, D., & Fraundorfer, F. (2011) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2011.943233 · Cited by 1,550
FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance
Cummins, M., & Newman, P. (2008) · The International Journal of Robotics Research · doi:10.1177/0278364908090961 · Cited by 1,472 · cited 3×
“SeqSLAM, by exploiting the sequence information, demonstrated day-to-night localisation, and noted that FAB-MAP [2] (a point-based feature system) performed poorly in such conditions.”
MethodSelf-citationRobust Wide Baseline Stereo from Maximally Stable Extremal Regions
Matas, J., Chum, O., Urban, M., & Pajdla, T. (2002) · Procedings of the British Machine Vision Conference 2002 · doi:10.5244/c.16.36 · Cited by 1,350
SeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nights
Milford, M. J., & Wyeth, G. F. (2012) · 2012 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2012.6224623 · Cited by 981 · cited 3×
“SeqSLAM [1] and FAB-MAP [2] are examples of place recognition systems – they output the image (or place) to which the robot’s live image is most similar, however there is no information about the robot’s 6-DOF pose in the map.”
MethodSLAM++: Simultaneous Localisation and Mapping at the Level of Objects
Salas-Moreno, R. F., Newcombe, R. A., Strasdat, H., Kelly, P. H. J., & Davison, A. J. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.178 · Cited by 945
Two years of Visual Odometry on the Mars Exploration Rovers
Maimone, M., Cheng, Y., & Matthies, L. (2007) · Journal of Field Robotics · doi:10.1002/rob.20184 · Cited by 655 · cited 2×
“The pose optimisation is performed in a similar manner to [28][29][30].”
MethodVisual odometry for ground vehicle applications
Nistér, D., Naroditsky, O., & Bergen, J. (2006) · Journal of Field Robotics · doi:10.1002/rob.20103 · Cited by 634 · cited 3×
“The pose optimisation is performed in a similar manner to [28][29][30].”
MethodExperience-based navigation for long-term localisation
Churchill, W., & Newman, P. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913499193 · Cited by 225
Self-citation
Cited by
1 year, 1000 km: The Oxford RobotCar dataset
Maddern, W., Pascoe, G., Linegar, C., & Newman, P. (2017) · The International Journal of Robotics Research · doi:10.1177/0278364916679498 · Cited by 1,632
Self-citationTarget-driven visual navigation in indoor scenes using deep reinforcement learning
Zhu, Y., Mottaghi, R., Kolve, E., Lim, J. J., Gupta, A., Fei-Fei, L., & Farhadi, A. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989381 · Cited by 1,533
“Besides, our approach does not require supervised training for recognizing distinctive landmarks, unlike e.g., [21], [22].”
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 [164], one SVM per feature is trained across several images.”
Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions
Sattler, T., Maddern, W., Toft, C., Torii, A., Hammarstrand, L., Stenborg, E., Safari, D., Okutomi, M., Pollefeys, M., Sivic, J., et al. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00897 · Cited by 699
“They learn features with stable appearance over time [17, 47, 49], train classifiers for place recognition [12, 28, 37, 76], and train CNNs to regress 2D-3D matches [8, 9, 60] or camera poses [19, 31, 74].”
BackgroundMethodKendall, A., Hawke, J., Janz, D., Mazur, P., Reda, D., Allen, J.-M., Lam, V.-D., Bewley, A., & Shah, A. (2019) · 2019 International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2019.8793742 · Cited by 694
“Localisation such as [15] facilitates control of the vehicle within the mapped environment, while perception methods such as semantic segmentation [1] enable the robot to interpret the scene.”
Method
Metadata
- Authors
- Linegar, C., Churchill, W., & Newman, P.
- Venue
- 2016 IEEE International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2016-05
- Pages
- 787-794
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2414248975
- Cited by
- 76
- References
- 17
- FWCI
- 26.32
- Type
- conference paper
- Language
- en
- Open access
- closed
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.