Abstract
In image vision we call a ground truth data generator any kind of software tool or algorithm that contributes in a semi or fully automatic way to the extraction of ground truth labels from a data set. The main purpose of such automation is to reduce as much as possible the manual effort of labeling a big number of frames. Above all, such a generator must be precise and avoid false positives because its results shall be used as training data for neural networks. In this paper we present a minimum set of operations required for fully automatic generation of labels from existing grayscale images in automotive image vision problems such as eye detection or traffic sign recognition. Multiple configurations based on these operations have been created to fit various desired features. We shifted the focus from algorithms development for ground truth data generation to understanding the particularities of an object or sign in the grayscale spectrum and defining correct configurations to detect them. We will present these configurations and the results obtained in the ground truth data generation process.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Swirski, L., Bulling, A., Anddodgson, N.: Ro-bust real-time pupil tracking in highly off-axis images. In: Proceedings of the ETRA (2012)
Fuhl, W., Eivazi, S., Hosp, B., Eivazi, A., Rosenstiel, W., Kasneci, E.: BORE: boosted-oriented edge optimization for robust, real time remote pupil center detection. In: Eye Tracking Research and Applications, ETRA, p. 12. (2018)
Fuhl, W., Kübler, T.C., Hospach, D., Bringmann, O., Rosenstiel, W., Kasneci, E.: Ways of improving the precision of eye tracking data: controlling the influence of dirt and dust on pupil detection. J. Eye Mov. Res. 10, 3 (2017)
Fuhl, W., Santini, T., Kübler, T.C., Kasneci, E.: ElSe: ellipse selection for robust pupil detection in real-world environments. In: Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research & Applications (ETRA), pp. 123–130 (2016)
Gu, H., Su, G., Du, C.: Feature points extraction from faces. In: Image and Vision Computing New Zealand. https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.110.519&rep=rep1&type=pdf
Paul, S.K., Uddin, M.S., Bouakaz, S.: Face recognition using eyes, nostrils and mouth features. In: 16th International Conference Computer and Information Technology, pp. 117–120 (2014). https://doi.org/10.1109/ICCITechn.2014.6997378
Demirkus, M., Clark, J.J., Arbel, T.: Robust semi-automatic head pose labeling for real-world face video sequences. Multimed. Tools Appl. 70, 495–523 (2014). https://doi.org/10.1007/s11042-012-1352-1
Tian, Y., Liu, W., Xiao, R., Wen, F., Tang, X.: A Face Annotation Framework with Partial Clustering and Interactive Labeling. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007). https://doi.org/10.1109/CVPR.2007.383282
Le, V., Brandt, J., Lin, Z., Bourdev, L., Huang, T.S.: Interactive facial feature localization. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 679–692. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33712-3_49
Świrski , L., Dodgson, N.: Rendering synthetic ground truth images for eye tracker evaluation. In: Proceedings of the Symposium on Eye Tracking Research and Applications (2014). https://doi.org/10.1145/2578153.2578188
Leon, F., Gavrilescu, M., A review of tracking and trajectory prediction methods for autonomous driving. Mathematics 9(6), 37 (2021). Article number 660. https://doi.org/10.3390/math9060660
Salzmann, T., Ivanovic, B., Chakravarty, P., Pavone, M.: Trajectron++: dynamically-feasible trajectory forecasting with heterogeneous data. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 683–700. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58523-5_40
Valcan, S., Gaianu, M.: Ground truth data generator for eye location on infrared driver recordings. J. Imaging 7, 162 (2021). https://doi.org/10.3390/jimaging7090162
Valcan, S., Gaianu, M.: Eye detection for drivers using convolutional neural networks with automatically generated ground truth data. In: 2022 24th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC) (2022)
Valcan, S., Gaianu, M.: Nostrils and mouth detection for drivers using convolutional neural networks with automatically generated ground truth data. In: 9th Annual Conference on Computational Science & Computational Intelligence (CSCI 2022) (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Valcan, S., Gaianu, M. (2023). Ground Truth Data Generator in Automotive Infrared Sensor Vision Problems Using a Minimum Set of Operations. In: Nguyen, N.T., et al. Advances in Computational Collective Intelligence. ICCCI 2023. Communications in Computer and Information Science, vol 1864. Springer, Cham. https://doi.org/10.1007/978-3-031-41774-0_50
Download citation
DOI: https://doi.org/10.1007/978-3-031-41774-0_50
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-41773-3
Online ISBN: 978-3-031-41774-0
eBook Packages: Computer ScienceComputer Science (R0)