Pedestrian Crowd Detection Based Unmanned Aerial Vehicle Infrared Imagery

Abstract:

Human detection is a keyproblem in computer vision. Recently, some research has been focusing on the detection ofpedestrianusing infrared images. The infrared images have outstanding merit. It depends only on object's temperature, but not on color or texture. In this paper, the pedestrian crowd detection approach is proposed. The approach is compose of ROI blocks extraction and crowd block recognition. ROI blocks can be extracted with circle gradient operator and weighted geometric filtering. Crowd blocks are recognized by support vector machine, which combines histogram of oriented gradient and circle gradient. The experimental results show thatthe approach works effectively in different scenes.

• Periodical: Applied Mechanics and Materials (Volume 873)
• Pages: 347-352
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.873.347
• Online since: November 2017
• Authors: Yong Hao Xiao, Hong Zhen*
• Keywords: Circle Gradient, Crowd Detection, Infrared Image, Support Vector Machine

References

[1] J. T. Wang. D. B. Chen. H. Y. Chen. J. Y. Yang. On pedestrian detection and tracking in infrared videos, Patt. Recog. Lett. 33 (2012) 775-785.

[2] F. Xu. X. Liu. K. Fujimura. Pedestrian detection and tracking with night vision. IEEE Trans. Intell. Transp. Syst. 6 (2005) 63-71.

DOI: 10.1109/tits.2004.838222

[3] J. Li. W. Gong. W. Li. X. Liu. Robust pedestrian detection in thermal infrared imagery using the wavelet transform, Infr. Phys. Tech. 53 (2010) 267-273.

DOI: 10.1016/j.infrared.2010.03.005

[4] H. Sun. C. Wang. B. Wang. E. S. Naser. Pyramic binary pattern features for real-time pedestrian detection from infrared videos, Neuro Comp. 74 (2011) 797-804.

DOI: 10.1016/j.neucom.2010.10.009

[5] A. D. Ciotec, V. E. Neagoe, A. P. Barar, Concurrent self-organizing maps for pedestrian in thermal imagery, Sci. Bull. Ser. C75(4) (2013) 45-56.

[6] H. Sun, C. Wang, B. Wang, N. EI-Sheimy, Pyramid binary pattern features for real-time pedestrian detection from infrared videos, Elsevier Neuro Comput. 74 (2011) 797-804.

DOI: 10.1016/j.neucom.2010.10.009

[7] A. Fernandez-Caballero, M. T. Lopez. J. Serrano-Cuerda, Thermal-Infrared Pedestrian ROI Extraction through Thermal and Motion Information Fusion, Sensors 14 (2014) 6666-6676.

DOI: 10.3390/s140406666

[8] Ge. J. Luo, Y. Tei. G, Real-Time Pedestrian Detection and Tracking at Nighttime for Driver-Assistance Systems, IEEE Trans. Intel. Transp. Syst. 10 (2009) 283-298.

DOI: 10.1109/tits.2009.2018961

[9] X. Y. Zhao. Z. X. He. S. Y. Zhang. D. Liang. Robust pedestrian detection in thermal infrared imagery using a shape distribution histogram feature and modified sparse representation classification, Patt. Recognit. 48 (2015) 1947-(1960).

DOI: 10.1016/j.patcog.2014.12.013

[10] E. S. Jeon. J. S. Choi. J. H. Lee. K. Y. Shin. Y. G. Kim. T. T. Le. K. R. Park. Human Detection Based on the Generation of a Background Image by Using a Far-Infrared Light Camera, Sensors, 15 (2015) 6763-6788.

DOI: 10.3390/s150306763

[11] J. Portmann. S. Lynen. M. Chli. R. Siegwart. People detection and tracking from aerial thermal views, In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), (2014) 1794-1800.

DOI: 10.1109/icra.2014.6907094

[12] Y. L. Ma, X. K. Wu, Pedestrian Detection and Tracking from Low-Resolution Unmanned Aerial Vehicle, Sensors, 16 (2016) 446-471.

DOI: 10.3390/s16040446

[13] I. Rhone-Alps, Histograms of Oriented Gradients for Human Detection, Intel Conferences on Computer Vision & Pattern Recognition. (2005) 886-893.