particular, we created a proof of concept of a pipeline
that uses techniques related to the object detection in
video record to detect all visible traffic signals at any
given time; object tracking methodologies to assign a
unique identity to each object detected through time;
convolutional neural networks to filter out noise
images and to get the class of each road sign; colour
quantization and processing about colour distribution
to get details of the road signs not pictogram-based.
With the pipeline developed so far, we showed
how it is possible to implement a simple process that
is able, with existing architectures even with low
parametrization, to create a tool that aids the operators
of road maintenance to have a clear status, both in
terms of positioning and in terms of quantity, of the
installed road signs.
Further work must be done to make the overall
system to be more effective in a production
environment automating the workflow as much as
possible.
ACKNOWLEDGEMENTS
The project has been funded and supported in the
context of a wider project of processes automatization
of Sias S.p.A., that provided data we used to create
the PoC and the support to create and evaluate the
datasets and the entire workflow. We would also like
to thank the key figures in Sias S.p.A. Luca Furloni,
Paolo Strazzullo, and Matteo Lazzarini, which
actively supported us throughout all the
implementation stages.
REFERENCES
He K., Gkioxari G., Dollar P., Girshick R. (2017) Mask R-
CNN, in Proceedings of the IEEE International
Conference on Computer Vision (ICCV), pp. 2961-
2969
Redmon J., Divvala S., Girshick R., Farhadi A. (2016) You
Only Look Once: Unified, Real-Time Object Detection,
in Proceedings of the IEEE Conference on Computer
Vision and Pattern Recognition (CVPR), pp. 779-788
Wojke N., Bewley A., Paulus D. (2017) Simple online and
realtime tracking with a deep association metric, in
IEEE International Conference on Image Processing
(ICIP) 3645-3649
Krizhevsky A., Sutskever I., Hinton G. (2012) ImageNet
Classification with Deep Convolutional Neural
Networks, in Neural Information Processing Systems.
25
Stallkamp J., Schlipsing M., Salmen J., Igel C. (2011) The
German traffic sign recognition benchmark: a multi-
class classification competition, in Neural Networks
(IJCNN), The 2011 International Joint Conference on,
pages 1453–1460. IEEE
Houben S., Stallkamp J., Salmen J., Schlipsing M., Igel C.,
(2013) Detection of traffic signs in real-world images:
The German traffic sign detection benchmark, in The
2013 International Joint Conference on Neural
Networks (IJCNN), pp. 1-8, doi:
10.1109/IJCNN.2013.6706807
Wong A., Shafiee M. J., St. Jules M., (2018) MicronNet: A
Highly Compact Deep Convolutional Neural Network
Architecture for Real-Time Embedded Traffic Sign
Classification, in IEEE Access, vol. 6, pp. 59803-
59810, doi: 10.1109/ACCESS.2018.2873948
Dogancan T., Min-Hung C., Ghassan A. (2019) Traffic Sign
Detection Under Challenging Conditions: A Deeper
Look into Performance Variations and Spectral
Characteristics, in IEEE Transactions on Intelligent
Transportation Systems. PP. 1-11.
10.1109/TITS.2019.2931429.
Shanxin Z., Cheng W., Lili L., Chenglu W., Chenhui Y.,
Zhemin Z., Jonathan L. (2019) Automated Visual
Recognizability Evaluation of Traffic Sign Based on 3D
LiDAR Point Clouds, in Remote Sensing. 11. 1453.
10.3390/rs11121453
Youssef A., Albani D., Nardi D., Bloisi D. (2016) Fast
traffic sign recognition using colour segmentation and
deep convolutional networks, in International
conference on advanced concepts for intelligent vision
systems. Springer, Cham, p. 205-216.
Tabernik D., Skočaj D., (2020) Deep Learning for Large-
Scale Traffic-Sign Detection and Recognition, in IEEE
Transactions on Intelligent Transportation Systems,
vol. 21, no. 4, pp. 1427-1440, doi:
10.1109/TITS.2019.2913588.
Neuhold G., Ollmann T., Bulò S. R., Kontschieder P.
(2017) The Mapillary Vistas Dataset for Semantic
Understanding of Street Scenes, in 2017 IEEE
International Conference on Computer Vision (ICCV),
pp. 5000-5009, doi: 10.1109/ICCV.2017.534
Cermelli F., Mancini M., Rota Bulò S., Ricci E., Caputo B.
(2020) Modeling the Background for Incremental
Learning in Semantic Segmentation. 9230-9239.
10.1109/CVPR42600.2020.00925.
Tomz M., King G., Zeng, L. (2003) ReLogit: Rare Events
Logistic Regression, in Journal of Statistical Software,
8(2), 1–27. https://doi.org/10.18637/jss.v008.i02
Redmon J. (2016) Open Source Neural Networks in C, URL
http://pjreddie.com/darknet/
Lecun Y., Bottou L., Bengio Y., Haffner P. (1998)
Gradient-based learning applied to document
recognition, in Proceedings of the IEEE, vol. 86, no. 11,
pp. 2278-2324, doi: 10.1109/5.726791.
He K., Zhang X., Ren S., Sun J. (2016) Deep Residual
Learning for Image Recognition, in 2016 IEEE
Conference on Computer Vision and Pattern
Recognition (CVPR), pp. 770-778, doi:
10.1109/CVPR.2016.90.