Abstract
Approaches for detecting roundabouts in maps are heavily dependent on looking at the problem from a machine-learning powered computer vision perspective. In this paper, we propose a fresh approach, taking core map data into account, that supplements existing techniques in a phenomenal way thereby significantly reducing the machine learning effort involved. As a direct consequence, our approach filters the training set to greatly reduce the scope of the ML problem resulting in increased accuracy. At the core of the proposed approach is the fact that data fields, which are used to describe maps, encapsulate geometric details about map points. If interpreted correctly, these details can be used to identify various map features including roundabouts. The proposed approach has two parts. First, an algorithm has been proposed which interprets core map data to identify roundabouts. This algorithm correctly detects roundabouts in more than 80% of the cases. Then, the remaining less than 20% cases are run through a machine learning model having extremely high accuracy because of a very specific training set. This results in an overall roundabout detection rate of more than 97%. Using this approach, we have succeeded in saving thousands of man-hours towards manual roundabout verification and correction.
Similar content being viewed by others
References
Ali MAH, Mailah M (2019) Path Planning and Control of Mobile Robot in Road Environments Using Sensor Fusion and Active Force Control. IEEE Trans Veh Technol 68(3):2176–2195. https://doi.org/10.1109/TVT.2019.2893878
Boichis N, Cocquerez J-P, Airault S (1998) A top down strategy for simple crossroads extraction. In: IntArchPhRS., Vol. XXXII, Part 2/1, pp. 19–26
Boichis N, Viglino J-M, Cocquerez J-P (2000) Knowledge based system for the automatic extraction of road intersections from aerial images. In: IntArchPhRS., Vol. XXXIII, Supplement B3, pp. 27–34
Bordes JB, Roux M (2006) Detection of roundabouts in satellite images. In ISPRS Workshop on Topographic Mapping from Space (Vol. 36, p. 1)
Brandin M, Volvo Car Corp (2019) Roundabout detecting arrangement. US Patent 10:259,322
Chai Z (2007) Design of rural roundabout squares. Technol Gansu China 23(3):176–178
Choksuriwong A, Laurent H, Emile B (2005) Comparison of invariant descriptors for object recognition. In IEEE International Conference of Image Processing
De Gunst M (1996) Knowledge-based interpretation of aerial images for updating of road maps. Ph.D. thesis, Delft University of Technology, the Netherlands
García Cuenca L, Sanchez-Soriano J, Puertas E, Fernandez Andrés J, Aliane N (2019) Machine learning techniques for undertaking roundabouts in autonomous driving. Sensors 19(10):2386
Gerke M (2006) Automatic Quality Assessment of Road Databases Using Remotely Sensed Imagery. PhD thesis, Leibniz Universität Hannover, Germany, No. 261; also in: Deutsche Geodätische Kommission, Reihe C, No. 599, 105 p
Gribov, A. (2017). Approximate Fitting a Circular Arc When Two Points Are Known. In 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) (Vol. 2, pp. 15–16). IEEE
Hels T, Orozova-Bekkevold I (2007) The effect of roundabout design features on cyclist accident rate. Accid Anal Prev 39(2):300–307
Herslund MB, Jørgensen NO (2003) Looked-but-failed-to-see-errors in traffic. Accid Anal Prev 35(6):885–891
Hofmann H, Jehlicka P (2017) U.S. Patent No. 9,672,759. U.S. Patent and Trademark Office, Washington, DC
Jorge F (2012) Detecting roundabout manoeuvres using OpenStreetMap and vehicle state. Master’s thesis in systems, control and mechatronics
Khotanzad A, Hong YH (1990) Invariant image recognition by zernike moments. IEEE Trans Pattern Anal Mach Intell 12(5):489–497
Lee EH, Forsythe GE (1973) Variational study of nonlinear spline curves. SIAM Rev 15(1):120–133
Li X, Zhang W (2017) Automatic object oriented roundabouts extraction from high resolution multi-spectral images. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences, 42
Muñoz-Organero M, Ruiz-Blázquez R (2017) Detecting different road infrastructural elements based on the stochastic characterization of speed patterns. J Adv Transp 2017
Park H (2001) Choosing nodes and knots in closed B-spline curve interpolation to point data. Comput Aided Des 33(13):967–974
Ravanbakhsh M, Fraser CS (2009) Road roundabout extraction from very high resolution aerial imagery. Int Archiv Photogrametry Remote Sens:19–26
Robinson BW, Rodegerdts L, Scarborough W, Kittelson W, Troutbeck R, Brilon W, ... & Mason J (2000) Roundabouts: An informational guide (No. FHWA-RD-00-067; Project 2425). The United States. Federal Highway Administration.
Robusto CC (1957) The cosine-haversine formula. Am Math Mon 64(1):38–40
Sacchi E, Bassani M, Persaud B (2011) Comparison of safety performance models for urban roundabouts in Italy and other countries. Transp Res Rec 2265(1):253–259
Veness C (2012) Movable type scripts: calculate distance, bearing and more between latitude/longitude points. online], Movable Type Scripts, nd. Available at: http://www.movabletype.co.uk/scripts/latlong.html (Accessed: 10 May. 2019)
“What lane should I use on a roundabout?” (n.d.) AXA Insurance Ireland, available online at https://www.axa.ie/articles/driving/what-lane-should-i-use-on-a-roundabout/
Zaverucha GM (2005) Approximating polylines by curved paths. In IEEE International Conference Mechatronics and Automation, 2005 (Vol. 2, pp. 758–763). IEEE
Zhao M, Kathner D, Jipp M, Soffker D, Lemmer K (2017) Modelling driver behaviour at roundabouts: Results from a field study. In 2017 IEEE Intelligent Vehicles Symposium (IV) (pp. 908–913). IEEE
Zinoune C, Bonnifait P, Ibañez-Guzmán J (2012) Detection of missing roundabouts in maps for driving assistance systems. In 2012 IEEE Intelligent Vehicles Symposium (pp. 123–128). IEEE
Zinoune C, Bonnifait P, Ibanez-Guzman J (2012) Detection of missing roundabouts in maps for driving assistance systems. In 2012 IEEE Intelligent Vehicles Symposium (pp. 123–128). IEEE
Acknowledgements
We would like to thank Here Solutions India Pvt. Ltd. for supporting us with data and permissions required to complete this research. Through this approach, we were able to automatically identify roundabouts with an accuracy of 95-99% for our maps in North America, Europe and Taiwan.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Singh, R., Rana, P.S. & Jindal, N. A novel approach for detecting roundabouts in maps based on analysis of core map data. Multimed Tools Appl 79, 30785–30811 (2020). https://doi.org/10.1007/s11042-020-09558-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-09558-2