Abstract
The action prediction of pedestrians significantly contributes to an intelligent braking system in cars; knowing that the pedestrians will run in several seconds such as for crossing streets, the cars can start braking in advance, to effectively reduce the risk for crash accidents. In this paper, we propose a method to predict how the pedestrian act (run or walk) in the future based on preindication in video frames detected by only appearance-based image features. We empirically mine the distinctive frames that precede the target action, ‘running’ in this case, and are effective for predicting it in the framework of feature selection. By using the most effective frames, we can build the action prediction method by exploiting the image features extracted at those frames. As to the image feature extraction methods, we evaluate two types of features in our method, one is GLAC (Gradient Local AutoCorreration) and the other is HOG (Histogram of Oriented Gradient). In the experiments, the effective frames are successfully found around 0.37 s before running action by using GLAC feature; this is not the case of HOG. We also show that the results are closely related to human motion phases from walking to running via biomechanical analysis.
This is a preview of subscription content, log in via an institution.
Notes
- 1.
This experiment is approved by the Ethical Review Board of Mazda Motor Corporation and the informed consent of all subjects were also obtained.
References
Ishikawa, T.: The analysis of pedestrian accidents. https://www.itarda.or.jp/ws/pdf/h22/13_01hokousyaziko.pdf. In Japanese
Rosen, E., Sander, U.: Pedestrian fatality risk as a function of car impact speed. Accid. Anal. Prev. 41, 536–542 (2009)
Hulshof, W., Knight, I., Edwards, A., Avery, M., Grover, C.: Autonomous emergency braking test results. In: International Technical Conference on the Enhanced Safety of Vehicles (2013)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 886–893 (2005)
Ouyang, W., Wang, X., Zeng, X., Qiu, S., Luo, P., Tian, Y., Li, H., Yang, S., Wang, Z., Loy, C.C., Tang, X.: Deepid-net: deformable deep convolutional neural networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2403–2412 (2015)
Keller, C.G., Gavrila, D.M.: Will the pedestrian cross? A study on pedestrian path prediction. IEEE Trans. Intell. Transp. Syst. 15(2), 494–506 (2014)
Reddy, Y., Krishnaiah, R.: Driving assistance system for identification of sudden pedestrian crossings. Int. J. Res. Inf. Technol. 1(12), 281–295 (2013)
Nishida, K., Kobayashi, T., Iwamoto, T., Yamasaki, S.: Pedestrian action prediction using static image feature. In: Proceedings of 7th International Joint Conference on Computational Intelligence, NCTA, vol. 3, pp. 99–105, Lisbon, Portugal, November 2015
Kobayashi, T., Otsu, N.: Image feature extraction using gradient local auto-correlations. In: European Conference on Computer Vision, pp. 346–358 (2008)
Vapnik, V.: Statistical Learning Theory. Wiley, New York (1998)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Nishida, K., Kobayashi, T., Iwamoto, T., Yamasaki, S. (2017). Preindication Mining for Predicting Pedestrian Action Change. In: Merelo, J.J., et al. Computational Intelligence. IJCCI 2015. Studies in Computational Intelligence, vol 669. Springer, Cham. https://doi.org/10.1007/978-3-319-48506-5_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-48506-5_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-48504-1
Online ISBN: 978-3-319-48506-5
eBook Packages: EngineeringEngineering (R0)