City Bus Monitoring Supported by Computer Vision and Machine Learning Algorithms
In this paper there are proposed methods and algorithms supporting city traffic controllers in effective perception and analysis of the visual information from the public transport monitoring system implemented in the City of Warsaw. To achieve this goal, public transport vehicles must be recognised and tracked in camera view. In this work, we describe a structure and give preliminary results for the detection and tracking system proposed. The algorithms discussed in this paper uses background subtraction to extract moving vehicles from the scene and the classification system to reject objects that are not city buses. Furthermore, a custom tracking module is utilized to enable labeling of city buses instances. During the test performed in the City of Warsaw the system was able to successfully detect 89% bus instances giving less than 15% erroneous detections.
KeywordsComputer vision Detection Tracking Traffic monitoring
This research has been supported by the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 688380 VaVeL: Variety, Veracity, VaLue: Handling the Multiplicity of Urban Sensors.
- 1.Csurka, G., Dance, C.R., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: Workshop on Statistical Learning in Computer Vision, ECCV, pp. 1–22 (2004)Google Scholar
- 4.Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004). https://doi.org/10.1023/B:VISI.0000029664.99615.94MathSciNetCrossRefGoogle Scholar
- 5.Nesheli, M.M., Ceder, A.A., Estines, S.: Public transport user’s perception and decision assessment using tactic-based guidelines. Transp. Policy 49, 125–136 (2016). http://www.sciencedirect.com/science/article/pii/S0967070X16301998CrossRefGoogle Scholar
- 6.Suzuki, S., Abe, K.: Topological structural analysis of digitized binary images by border following. Comput. Vis. Graph. Image Process. 30(1), 32–46 (1985). http://www.sciencedirect.com/science/article/pii/0734189X85900167CrossRefGoogle Scholar
- 9.Wilkowski, A., Luckner, M.: Low-cost canoe counting system for application in a natural environment. In: Szewczyk, R., Zieliński, C., Kaliczyńska, M. (eds.) Challenges in Automation, Robotics and Measurement Techniques, pp. 705–715. Springer (2016)Google Scholar
- 10.Zivkovic, Z.: Improved adaptive Gaussian mixture model for background subtraction. In: Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, vol. 2, pp. 28–31, August 2004Google Scholar