Authors:
Paweł Foszner
1
;
Agnieszka Szczęsna
1
;
Luca Ciampi
2
;
Nicola Messina
2
;
Adam Cygan
3
;
Bartosz Bizoń
3
;
Michał Cogiel
4
;
Dominik Golba
4
;
Elżbieta Macioszek
5
and
Michał Staniszewski
1
Affiliations:
1
Department of Computer Graphics, Vision and Digital Systems, Faculty of Automatic Control, \\Electronics and Computer Science, Silesian University of Technology, Akademicka 2A, 44-100 Gliwice, Poland
;
2
Institute of Information Science and Technologies, National Research Council, Via G. Moruzzi 1, 56124 Pisa, Italy
;
3
QSystems.pro sp. z o.o. Mochnackiego 34, 41-907 Bytom, Poland
;
4
Blees sp. z o.o. Zygmunta Starego 24a/10, 44-100 Gliwice, Poland
;
5
Department of Transport Systems, Traffic Engineering and Logistics, Faculty of Transport and Aviation Engineering, Silesian University of Technology, Krasińskiego 8, 40-019 Katowice, Poland
Keyword(s):
Object Detection, Vehicle Detection, Pedestrian Detection, Synthetic Data, Deep Learning, Crowd Simulation.
Abstract:
Data scarcity has become one of the main obstacles to developing supervised models based on Artificial Intelligence in Computer Vision. Indeed, Deep Learning-based models systematically struggle when applied in new scenarios never seen during training and may not be adequately tested in non-ordinary yet crucial real-world situations. This paper presents and publicly releases CrowdSim2, a new synthetic collection of images suitable for people and vehicle detection gathered from a simulator based on the Unity graphical engine. It consists of thousands of images gathered from various synthetic scenarios resembling the real world, where we varied some factors of interest, such as the weather conditions and the number of objects in the scenes. The labels are automatically collected and consist of bounding boxes that precisely localize objects belonging to the two object classes, leaving out humans from the annotation pipeline. We exploited this new benchmark as a testing ground for some s
tate-of-the-art detectors, showing that our simulated scenarios can be a valuable tool for measuring their performances in a controlled environment.
(More)