Abstract
For autonomous driving to operate safely it is crucial to perceive surrounding objects correctly. Not only detection but also state estimation (track) of a perceived object is urgent. The state is required to enable a safe motion planning, since it allows to predict the future position of an object. To include only valid information, the state estimations must be maintained to determine which track is active and which is not. Mostly, a simple count-based approach is used. For this, we present an investigation of two common approaches from non-cooperative track management in comparison to two new management strategies to maintain tracks in a cooperative scenario. We evaluate them using three simulated scenarios with a varying rate of cooperative vehicles. A confidence-based approach was able to increase the average precision by up to 9 percentage points.
Zusammenfassung
Für den sicheren Betrieb des autonomen Fahrens ist es von entscheidender Bedeutung, die Objekte in der Umgebung korrekt zu detektieren. Nicht nur die Detektion, sondern auch die Schätzung des Zustands (Track) eines wahrgenommenen Objekts ist dringend erforderlich. Der Zustand wird benötigt, um eine sichere Trajektorienplanung zu ermöglichen, da er es erlaubt, die zukünftige Position eines Objekts vorherzusagen. Um nur gültige Informationen einzubeziehen, müssen die Zustandsschätzungen verwaltet werden, um zu bestimmen, welcher Track aktiv ist und welcher nicht. Daher wird meist nur ein Anzahl-basierter Ansatz verwendet. In dieser Arbeit untersuchen wir zwei gängige Ansätze des nicht-kooperativen Trackmanagements im Vergleich zu zwei neuen Managementstrategien zur Verwaltung von Tracks in einem kooperativen Szenario. Wir evaluieren sie anhand von drei simulierten Szenarien mit einer variierenden Rate kooperativer Fahrzeuge. Ein Konfidenz-basierter Ansatz erreichte eine Steigerung der Average Precision um bis zu 9 Prozentpunkte.
About the authors
Jörg Gamerdinger was born in Reutlingen, Germany, 1995. He received the B.S. and M.S. degrees in computer science from University of Tübingen, Germany, in 2020 and 2022, respectively, where he is currently pursuing the doctoral degree (Ph.D.) at the Department of Computer Science. His current research interests include robust and collective perception in autonomous driving.
Sven Teufel was born in Tübingen, Germany, 1998. He received the B.S. and M.S. degrees in computer science from University of Tübingen, Germany, in 2020 and 2022, respectively, where he is currently pursuing the doctoral degree (Ph.D.) at the Department of Computer Science. His current research interests include robust and collective perception in autonomous driving.
Georg Volk was born in Gengenbach, Germany, 1991. He received his B.S. in applied computer science from Baden-Wuerttemberg Cooperative State University (DHBW) Stuttgart, Germany, in 2013. In 2016 he received his M.S. in computer science from University of Tübingen, Germany, where he is currently pursuing the doctoral degree (Ph.D.) at the Department of Computer Science. His research interests include collective perception and robustness optimization.
Anna-Lisa Rüeck received the B.Eng. in electrical engineering from Cooperative State University of Stuttgart, Germany in 2018 and the M.Sc. in computer science from University of Tübingen, Germany, in 2022. She currently works as a software developer for surround view systems in the automotive industry at Robert Bosch GmbH in Stuttgart, Germany, contributing to the next generation of advanced driver assistance systems.
Oliver Bringmann (M’18) received the Diploma degree (M.S.) in computer science from the University of Karlsruhe (KIT), Germany, and the doctoral degree (Ph.D.) in computer science from the University of Tübingen, Germany, in 2001. He was with the FZI Research Center for Information Technology in Karlsruhe, Germany, in various positions as Department and Division Manager and Member of the management board, until 2012. He has been Professor and Director of the Chair for Embedded Systems at the University of Tübingen since 2012, where he is also serving as Vice Head of the department of computer science since 2014. His current research interests include electronic design automation, embedded system design, timing and power analysis of embedded software, embedded AI architectures, and robust perception. He is author and co-author of more than 220 publications in the area of electronic design automation, embedded system design, SoC architectures for automotive electronics and robust local and cooperative perception in autonomous driving.
-
Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
-
Research funding: This work has been partially funded by the German Research Foundation (DFG) in the priority program 1835 under grant BR2321/5-2.
-
Conflict of interest statement: The authors declare no conflicts of interest regarding this article.
References
[1] D. J. Yeong, G. Velasco-Hernandez, J. Barry, and J. Walsh, “Sensor and sensor fusion technology in autonomous vehicles: a review,” Sensors, vol. 21, no. 6, p. 2140, 2021. https://doi.org/10.3390/s21062140.Search in Google Scholar PubMed PubMed Central
[2] J. Janai, F. Güney, A. Behl, and A. Geiger, “Computer vision for autonomous vehicles: problems, datasets and state of the art,” Found. Trends® Comput. Graph. Vis., vol. 12, nos. 1–3, pp. 1–308, 2020. https://doi.org/10.1561/0600000079.Search in Google Scholar
[3] G. Volk, S. Müller, A. Von Bernuth, D. Hospach, and O. Bringmann, “Towards robust CNN-based object detection through augmentation with synthetic rain variations,” in 2019 IEEE Intelligent Transportation Systems Conference (ITSC), IEEE, 2019, pp. 285–292.10.1109/ITSC.2019.8917269Search in Google Scholar
[4] S. Teufel, G. Volk, A. Von Bernuth, and O. Bringmann, “Simulating realistic rain, snow, and fog variations for comprehensive performance characterization of LiDAR perception,” in 2022 IEEE 95th Vehicular Technology Conference:(VTC2022-Spring), IEEE, 2022, pp. 1–7.10.1109/VTC2022-Spring54318.2022.9860868Search in Google Scholar
[5] F. A. Schiegg, I. Llatser, D. Bischoff, and G. Volk, “Collective perception: a safety perspective,” Sensors, vol. 21, no. 1, p. 159, 2020. https://doi.org/10.3390/s21010159.Search in Google Scholar PubMed PubMed Central
[6] G. Volk, A. von Bernuth, and O. Bringmann, “Environment-aware development of robust vision-based cooperative perception systems,” in 2019 IEEE Intelligent Vehicles Symposium (IV), Paris, France, IEEE, 2019, pp. 126–133.10.1109/IVS.2019.8814148Search in Google Scholar
[7] G. Volk, J. Gamerdinger, A. von Bernuth, S. Teufel, and O. Bringmann, “Environment-aware optimization of track-to-track fusion for collective perception,” in 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), IEEE, 2022, pp. 2385–2392.10.1109/ITSC55140.2022.9922388Search in Google Scholar
[8] N. Benbarka, J. Schröder, and A. Zell, “Score refinement for confidence-based 3D multi-object tracking,” in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE Press, 2021, pp. 8083–8090.10.1109/IROS51168.2021.9636032Search in Google Scholar
[9] K. Granström, M. Baum, and S. Reuter, “Extended object tracking: introduction, overview, and applications,” J. Adv. Inf. Fusion, vol. 12, p. 12, 2017.Search in Google Scholar
[10] J. Janai, F. Güney, A. Behl, and A. Geiger, “Computer vision for autonomous vehicles: problems, datasets and state-of-the-art,” CoRR, abs/1704.05519, 2017.Search in Google Scholar
[11] B. Vo, M. Mallick, Y. Bar-Shalom, et al.., Multitarget Tracking, vol. 2015, New Jersey, USA, Wiley Encyclopedia of Electrical and Electronics Engineering, 2015.10.1002/047134608X.W8275Search in Google Scholar
[12] P. Sun, H. Kretzschmar, X. Dotiwalla, et al.., “Scalability in perception for autonomous driving: waymo open dataset,” in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 2443–2451.10.1109/CVPR42600.2020.00252Search in Google Scholar
[13] D. Powers, “Evaluation: from precision, recall and F-factor to ROC, informedness, markedness & correlation,” J. Mach. Learn. Technol., vol. 2, no. 1, pp. 37–63, 2011.Search in Google Scholar
[14] K. Boyd, K. H. Eng, and C. David Page, “Area under the precision-recall curve: point estimates and confidence intervals,” in Machine Learning and Knowledge Discovery in Databases, H. Blockeel, K. Kersting, S. Nijssen, and F. Železný, Eds., Berlin, Heidelberg, Springer Berlin Heidelberg, 2013, pp. 451–466.10.1007/978-3-642-40994-3_29Search in Google Scholar
[15] M. Everingham, L. Van Gool, C. Williams, J. Winn, and A. Zisserman, “The pascal visual object classes (VOC) challenge,” Int. J. Comput. Vis., vol. 88, no. 2, pp. 303–338, 2010. https://doi.org/10.1007/s11263-009-0275-4.Search in Google Scholar
[16] R. Stiefelhagen, K. Bernardin, R. Bowers, J. Garofolo, D. Mostefa, and P. Soundararajan, “The CLEAR 2006 evaluation,” in CLEAR’06: Proceedings of the 1st International Evaluation Conference on Classification of Events, Activities and Relationships, 2006, pp. 1–44.10.1007/978-3-540-69568-4_1Search in Google Scholar
[17] G. Volk, J. Gamerdinger, A. von Bernuth, and O. Bringmann, “A comprehensive safety metric to evaluate perception in autonomous systems,” in 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), IEEE, 2020, pp. 1–8.10.1109/ITSC45102.2020.9294708Search in Google Scholar
[18] A. Dosovitskiy, G. Ros, F. Codevilla, A. Lopez, and V. Koltun, “CARLA: an open urban driving simulator,” in Conference on Robot Learning, PMLR, 2017, pp. 1–16.Search in Google Scholar
[19] S. Mueller, D. Hospach, J. Gerlach, O. Bringmann, and W. Rosenstiel, “Framework for varied sensor perception in virtual prototypes,” in MBMV, Chemnitz, DE, Methoden und Beschreibungssprachen zur Modellierung und Verifikation von Schaltungen und Systemen (MBMV2015), 2015, pp. 145–154.Search in Google Scholar
[20] G. Volk, Q. Delooz, A. F. Schiegg, A. Von Bernuth, A. Festag, and O. Bringmann, “Towards realistic evaluation of collective perception for connected and automated driving,” in 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), 2021, pp. 1049–1056.10.1109/ITSC48978.2021.9564783Search in Google Scholar
[21] H. W. Kuhn, “The Hungarian method for the assignment problem,” Nav. Res. Logist. Q., vol. 2, nos. 1–2, pp. 83–97, 1955. https://doi.org/10.1002/nav.3800020109.Search in Google Scholar
© 2023 Walter de Gruyter GmbH, Berlin/Boston
