Abstract
For highly automated driving in urban regions it is essential to know the precise position of the car. Furthermore it is important to understand the surrounding context in complex situations, e.g. multilane crossings and turn lanes. To understand those situations there is not only the task to detect the lane border, but to detect the painted information inside the lane. The paper is facing and evaluating two methods to classify this additional lane information. Therefore the images from five cameras mounted around the car are used. Four of them with fisheye lenses. The methods have in common, that the input images are transformed into a bird view projection. First introduced method is to extract contours from the transformed images and collect geometrical features and Fourier coefficients. The second introduced way, is to calculate histograms of oriented gradients and use it as input for the classification step. Both classification approaches are implemented and evaluated as multiclass and single class detectors for each arrow type. Furthermore, the classification results from a support vector machine and random forest were faced for this classification problem. The results from the multiclass detectors are evaluated and presented in form of confusion matrices. With the introduced approaches a high detection confidence could be achieved, proofed with validation datasets and in practical use.
Similar content being viewed by others
Abbreviations
- avg:
-
average
- f :
-
fisher discriminant
- FP:
-
false positive
- HMI:
-
human machine interface
- HOG:
-
histogram of oriented gradients
- m :
-
mean
- n :
-
normalized moment
- OCR:
-
optical character recognition
- p:
-
probability
- RBF:
-
radial base function
- σ :
-
standard deviation
- SVM:
-
support vector machine
- TP:
-
true positive
- μ :
-
moment
- z:
-
fourier descriptor
- Z:
-
complex value
- X,Y | u,v:
-
image pixel components
References
Danescu, R. and Nedevschi, S. (2010). Detection and classification of painted road objects for intersection assistance applications. Proc. IEEE Int. Conf. Intelligent Transportation Systems (ITSC), 433–438.
Hu, M. K. (1962). Visual pattern recognition by moment invariants. IRE Trans. Information Theory 8, 2, 179–187.
Kum, C.-H., Cho, D.-C. and Ra, M.-S. (2013). Lane detection system with around view monitoring for intelligent vehicle. Int. SOC Design Conf. (ISOCC), Busan, Korea, 215–218.
Li, S. and Shimomura, Y. (2008). Lane marking detection by side Fisheye Camera. Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems, Nice, France, 606–611.
Maier, G., Pangerl, S. and Schindler, A. (2011). Real-time detection and classification of arrow markings using curve-based prototype fitting. Proc. IEEE Intelligent Vehicles Symp., 442–447.
Philipp, F., Tadjine, H. H., Schumacher, S. and Rojás, R. (2016). Real time detection and classification of arrow markings in urban streets. Proc. FISITA 2016, BEXCO, Korea.
Schreiber, M., Knöppel, C. and Franke, U. (2013). Laneloc: Lane marking based localization using highly accurate maps. Proc. IEEE Intelligent Vehicles Symp., 449–454.
Vacek, S., Schimmel, C. and Dillmann, R. (2007). Roadmarking analysis for autonomous vehicle guidance. Proc. 3rd European Conf. Mobile Robots, EMCR, 1–6.
Wang, N., Liu, W., Zhang, C., Yuan, H. and Liu, J. (2009). The detection and recognition of arrow markings recognition based on monocular vision. Proc. 21st Annual Int. Conf. Chinese Control and Decision Conf., 4416–4422, ser. CCDC’09. Piscataway, NJ, USA. IEEE Press.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Philipp, F., Schumacher, S., Tadjine, H.H. et al. Real Time Detection and Classification of Arrow Markings in Urban Streets. Int.J Automot. Technol. 19, 379–386 (2018). https://doi.org/10.1007/s12239-018-0036-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12239-018-0036-x