Abstract
In this paper, we consider direction estimation of pedestrian group for video surveillance and intelligent vehicles applications. A theoretical study of the position of vanishing points in image plane associated with all directions in the scene leads to the definition of the notion of directional areas. Image plane is divided along the x-axis into a set of bounded areas; each one is associated with a specific direction. The pedestrian direction is inferred directly depending on the belonging area of the vanishing points computed from video sequence. Top and bottom points of walking pedestrian define two parallel lines in 3D. The vanishing point is estimated from video sequence and from the direction of the pedestrian. The obtained results demonstrate the efficacy and robustness of the proposed method and confirm the improvement with respect to state-of-the-art approaches.
Similar content being viewed by others
References
Shimizu, H., Poggio, T.: Direction estimation of pedestrian from multiple still images. In: IEEE, Intelligent Vehicles Symposium, Parma, Italy, 14–17 June 2004
Gandhi, T., Trivedi, M.M.: Image based estimation of pedestrian orientation for improving path prediction. In: IEEE Intelligent Vehicles Symposium, Eindhoven University of Technology, Eindhoven, The Netherlands, 4–6 June 2008
Chen, C., Heili, A., Odobez, J.M.: Combined estimation of location and body pose in surveillance video. In: 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 5–10 (2011)
Guangzhen, Z., Mrutani, T., Kajita, S., Mase, K.: Video based estimation of pedestrian walking direction for pedestrian protection system. J. Electron. 29(1/2), 72–81 (2012)
Baltieri, D., Vezzani, R., Cucchira, R.: People orientation recognition by mixtures of wrapped distributions on random trees. In: Proceedings of European Conference on Computer Vision (ECCV), pp. 270–283 (2012)
Tao, J., Klette, R.: Integrated pedestrian and direction classification using a random decision forest. In: Conference: IEEE International Conference on Computer Vision (ICCV), Sydney, pp. 230–237 (2013)
Flohr, F., Dumitru-Guzu, M., Kooij, J.F.P., Gavrila, D.M.: Joint probabilistic pedestrian head and body orientation estimation. In: IEEE Intelligent Vehicles Symposium (IV), Dearborn, Michigan, USA, 8–11 June 2014
Ricci, E., Varadarajan, J., Subramanian, R., Bulo, S.R., Ahuja, N., Lanz, O.: Uncovering interactions and interactors: joint estimation of head, body orientation and F-formations from surveillance videos. In: IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 7–13 Dec 2015
Liu, H., Ma, L.: Online person orientation estimation based on classifier update. In: Proceeding of IEEE International Conference on Image Processing ICIP, pp. 1568–1572 (2015)
Raman, R., Sa, P.K., Majhi, B., Bakshi, S.: Direction estimation for pedestrian monitoring system in smart cities: an HMM based approach. IEEE Access 4, 5788–5808 (2016)
Yu, S., Tan, D., Tan, T.: A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. In: ICPR, Hong Kong, China (2006)
Huang, S., Ying, X., Rong, J., Shang, Z., Zha, H.: Camera calibration from periodic motion of a pedestrian. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA (2016)
Junejo, I.N.: Using pedestrians walking on uneven terrains for camera calibration. Mach. Vis. Appl. 22(1), 137–144 (2011)
Guan, J., Deboeverie, F., Slembrouck, M.: Extrinsic calibration of camera networks based on pedestrians. Sensors 16, 654 (2016). https://doi.org/10.3390/s16050654
Raza, M., Chen, Z., Rehman, S., Wang, P., Bao, P.: Appearance based pedestrians head pose and body orientation estimation using deep learning. Neurocomputing 272, 647–659 (2018)
Varadarajan, J., Subramanian, R., Rota Bulo, S., Ahuja, N., Lanz, O., Ricci, E.: Joint estimation of human pose and conversational groups from social scenes. Int. J. Comput. Vis. 126(2–4), 410–429 (2018)
Cucchiara, R., Grana, C., Piccardi, M., Prati, A., Sirotti, S.: Improving shadow suppression in moving object detection with HSV color information. In: IEEE Intelligent Transportation Systems Conference Proceedings, Oakland, 25–29 Aug 2001
MGP01, http://perso.usthb.dz/~slarabi/MGP01/index.html (2017)
Lv, F., Zhao, T., Nevatia, R.: Self-calibration of a camera from video of a walking human. In: IEEE International Conference of Pattern Recognition, pp. 281–304 (2002)
Berclaz, J., Fleuret, F., Turetken, E., Fua, P.: Multiple object tracking using K-shortest paths optimization. IEEE Trans. Pattern Anal. Mach. Intell. 33(9), 1806–1819 (2011)
Fleuret, F., Berclaz, J., Lengagne, R., Fua, P.: Multi-camera people tracking with a probabilistic occupancy map. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 267–282 (2008)
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors Amina Bensebaa and Slimane Larabi declare no competing financial interests.
Funding
This research was not funded.
Rights and permissions
About this article
Cite this article
Bensebaa, A., Larabi, S. Direction estimation of moving pedestrian groups for intelligent vehicles. Vis Comput 34, 1109–1118 (2018). https://doi.org/10.1007/s00371-018-1520-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-018-1520-z