Graph@FIT Submission to the NVIDIA AI City Challenge 2018 [CVPR Workshops 2018]

Jakub Sochor, Jakub Špaňhel, Roman Juránek, Petr Dobeš, Adam Herout
GRAPH@FIT, Brno University of Technology
Corresponding authors: {isochor,ispanhel,herout} [at] fit.vutbr.cz

Abstract

In our submission to the NVIDIA AI City Challenge, we address speed measurement of vehicles and vehicle re-identification. For both these tasks, we use a calibration method based on extracted vanishing points. We detect and track vehicles by a CNN-based detector and we construct 3D bounding boxes for all vehicles. For the speed measurement task, we estimate the speed from the movement of the bounding box in the 3D space using the calibration. Our approach to vehicle re-identification is based on extraction of visual features from “unpacked” images of the vehicles. The features are aggregated in temporal domain to obtain a single feature descriptor for the whole track. Furthermore, we utilize a validation network to improve the re-identification accuracy.

Downloads

Citation

@InProceedings{Sochor_2018_CVPR_Workshops,
author = {Sochor, Jakub and Spanhel, Jakub and Juranek, Roman and Dobes, Petr and Herout, Adam},
title = {Graph@FIT Submission to the NVIDIA AI City Challenge 2018},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2018}
}

Acknowledgements

This work was supported by The Ministry of Education, Youth and Sports of the Czech Republic from the National Programme of Sustainability (NPU II); project IT4Innovations excellence in science – LQ1602. Also, this work was supported by TACR project “SMARTCarPark”, TH03010529.