Abstract
Formula One, and its accompanying e-sports series, provides viewers with a large selection of camera angles, with the onboard cameras oftentimes providing the most exciting view of events. Through the implementation of three object detection pipelines, namely Haar cascades, Histogram of Oriented Gradient features with a Support Vector Machine, and a Faster Region-based Convolutional Neural Network (Faster R-CNN), we analyse their ability to detect the cars in real-life and virtual onboard footage using training images taken from the official F1 2019 video game. The results of this research concluded that Faster R-CNNs would be best suited for accurate detection of vehicles to identify events such as crashes occurring in real-time. This finding is evident through the precision and recall scores of 97% and 99%, respectively. The speed of detection when using a Haar cascade also makes it an attractive choice in scenarios where precise detection is not important. The Haar cascade achieved the lowest detection time of only 0.14 s per image at the cost of precision (71%). The implementation of HOG features classifier using an SVM was unsuccessful with regards to detection and speed, which took up to 17 s to classify an image. Both the Haar cascade and HOG feature models improved their performance when tested on real-life images (76% and 67% respectively), while the Faster R-CNN showed a slight drop in terms of precision (93%).
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
Similar content being viewed by others
References
First Onboard Camera Telecast in Formula. https://www.auto123.com/en/news/f1-first-onboard-camera-telecast-in-formula-1/35450/. Accessed 23 Oct 2019
Fédération Internationale de l’Automobile: 2020 F1 Technical Regulations, Paris, p. 54 (2019)
Formula 1 launches Virtual Grand Prix Series to replace postponed races. https://www.formula1.com/en/latest/article.formula-1-launches-virtual-grand-Prix-series-to-replace-postponed-races.1znLAbPzBbCQPj1IDMeiOi.html. Accessed 2 Apr 2020
F1 Esports Series 2019. https://f1esports.com/. Accessed 23 Oct 2019
Petkovic, M., Mihajlovic V., Jonker, W., Djordjevic-Kajan, S.: Multi-modal extraction of highlights from TV Formula 1 programs. In: IEEE International Conference on Multimedia and Expo, pp. 817–820. IEEE, Switzerland (2002)
Akkas, S., Maini, S.S., Qiu, J.: A fast video image detection using tensorflow mobile networks for racing cars. In: IEEE International Conference on Big Data, pp. 5667–5672. IEEE, USA (2019)
Mishra, G., Aung, Y.L., Wu, M., Lam, S., Srikanthan, T.: Real-time image resizing hardware accelerator for object detection. In: International Symposium on Electronic System Design, pp. 98–102. IEEE, Singapore (2013)
Sarfraz, M., Taimur, A.: Real time object detection and motion. In: Second International Conference in Visualisation, pp. 235–240. IEEE, Barcelona (2009)
Bui, H.M., Lech, M., Cheng, E., Neville, K., Burnett, I.S.: Object recognition using deep convolutional features transformed by a recursive network structure. Access IEEE 4(1), 10059–10066 (2016)
Jones, M., Viola, P.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of Conference on Computer Vision and Pattern Recognition, pp. 511–518. IEEE, USA (2001)
Park, K., Hwang, S.: An improved Haar-like feature for efficient object detection. Pattern Recogn. Lett. 42(1), 148–154 (2014)
Yan, G., Yu, M., Yu, Y., Fan, L.: Real-time vehicle detection using histograms of oriented gradients and AdaBoost classification. Optik 127(19), 7941–7951 (2016)
Xu, Y., Yu, G., Wang, Y., Wu, X., Ma, Y.: A hybrid vehicle detection method based on Viola-Jones and HOG + SVM from UAV images. Sensors 16(8), 7941–7951 (2019)
Liu, W., Liao, S., Hu, W.: Towards accurate tiny vehicle detection in complex scenes. Neurocomputing 347, 22–33 (2019)
Zhang, Q., Wan, C., Bian, S.: Research on vehicle object detection method based on convolutional neural network. In: 11th International Symposium on Computational Intelligence and Design, pp. 271–274. IEEE, China (2018)
Dai, X.: HybridNet: a fast vehicle detection system for autonomous driving. Sig. Process. Image Commun. 70, 79–88 (2019)
Atibi, M., Atouf, I., Boussaa, M., Bennis, A.: Real-time detection of vehicles using the Haar-like features and artificial neuron networks. In: The International Conference on Advanced Wireless, Information, and Communication Technologies, pp. 24–31. Procedia Computer Science, Tunisia (2015)
Formula 1. https://www.youtube.com/user/Formula1. Accessed 2 Apr 2020
Shao, F., Wang, X., Meng, F., Zhu, J., Wang, D., Dai, J.: Improved faster R-CNN traffic sign detection based on a second region of interest and highly possible regions proposal network. Sensors 19(10), 228–256 (2019)
Tensorflow detection model zoo. https://github.com/tensorflow/models. Accessed 21 Oct 2019
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Spijkerman, R., van der Haar, D. (2020). Video Footage Highlight Detection in Formula 1 Through Vehicle Recognition with Faster R-CNN Trained on Game Footage. In: Chmielewski, L.J., Kozera, R., Orłowski, A. (eds) Computer Vision and Graphics. ICCVG 2020. Lecture Notes in Computer Science(), vol 12334. Springer, Cham. https://doi.org/10.1007/978-3-030-59006-2_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-59006-2_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59005-5
Online ISBN: 978-3-030-59006-2
eBook Packages: Computer ScienceComputer Science (R0)