Abstract
Most studies in pedestrian detection from surveillance videos focus on analysing footage from visible image cameras which require external light and are sensitive to illumination changes. The presence or absence of external light determines the possibility of monitoring a scene while variations in illumination determines the degree of detection accuracy. In this paper, pedestrian detection is performed on thermal (infrared) images using a Graph-based background-subtraction technique. First, to address the limitation of thermal images such as polarity changes and halo around objects of extreme temperatures, motion is used as leverage in generating a reliable background which allows for candidate region extraction for further processing. Second, to address the limitations of automatic detection methods in the presence of multiple objects and absence of sharp edges, interactive Graph Cut is used to perform the final labelling of the valid candidate regions. Experiments on the all-inclusive benchmark dataset of thermal imagery from the Ohio State University (OSU) shows the effectiveness of the proposed method.
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
Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Trans. Pattern Anal. Mach. Intell. 26(9), 1124–1137 (2004)
Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In: Proceedings of the Eighth IEEE International Conference on Computer Vision, ICCV 2001, vol. 1, pp. 105–112 (2001)
Davis, J.W., Keck, M.A.: A two-stage template approach to person detection in thermal imagery. In: Proceedings of the Seventh IEEE Workshop on Applications of Computer Science. WACV/MOTION 2005 (2005)
Davis, J.W., Sharma, V.: Robust background-subtraction for person detection in thermal imagery. In: IEEE Workshop on Object Tracking and Classification Beyond the Visible Spectrum (2004)
Funka-Lea, G., et al.: Automatic heart isolation for CT coronary visualization using Graph-Cuts. In: 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, ISBI 2006, pp. 614–617 (2006)
Gawande, U., Hajari, K., Golhar, Y.: Pedestrian detection and tracking in video surveillance system: issues, comprehensive review, and challenges. In: Recent Trends in Computational Intelligence (2020)
Gowsikhaa, D., Abirami, S., Baskaran, R.: Automated human behavior analysis from surveillance videos: a survey. Artif. Intell. Rev. 42(4), 747–765 (2012). https://doi.org/10.1007/s10462-012-9341-3
Greig, D.M., Porteous, B.T., Seheult, A.H.: Exact maximum a posteriori estimation for binary images. J. R. Stat. Soc. Ser. B (Methodol.) 51(2), 271–279 (1989)
Hampapur, A., Brown, L., Connell, J., Pankanti, S., Senior, A., Tian, Y.: Smart surveillance: applications, technologies and implications. In: Fourth International Conference on Information, Communications and Signal Processing 2003 and the Fourth Pacific Rim Conference on Multimedia, Proceedings of the Joint, vol. 2, pp. 1133–1138 (2003)
Jeon, E.S., et al.: Human detection based on the generation of a background image by using a far-infrared light camera. Sensors 15, 6763–6787 (2015)
Jeyabharathi, D.: Dejey: efficient background subtraction for thermal images using reflectional symmetry pattern (RSP). Multimed. Tools Appl. 77(17), 22567–22586 (2018). https://doi.org/10.1007/s11042-018-6220-1
Li, W., Zheng, D., Zhao, T., Yang, M.: An effective approach to pedestrian detection in thermal imagery. In: 2012 8th International Conference on Natural Computation, pp. 325–329 (2012)
Li, Z., Qiang, W., Zhang, J., Geers, G.: SKRWM based descriptor for pedestrian detection in thermal images. In: 2011 IEEE 13th International Workshop on Multimedia Signal Processing, pp. 1–6 (2011)
Oluyide, O.M., Tapamo, J.R., Viriri, S.: Automatic lung segmentation based on graph cut using a distance constrained energy. IET Comput. Vis. 12, 609–615 (2018)
Soundrapandiyan, R., Mouli, C.: Adaptive pedestrian detection in infrared images using background subtraction and local thresholding. Procedia Comput. Sci. 58, 706–713 (2015)
Soundrapandiyan, R., Mouli, C.P.: An approach to adaptive pedestrian detection and classification in infrared images based on human visual mechanism and support vector machine. Arab. J. Sci. Eng. 43, 3951–3963 (2018). https://doi.org/10.1007/s13369-017-2642-8
Webster, C.W.R.: CCTV policy in the UK: reconsidering the evidence base. Surveill. Soc. 6(1), 10–22 (2009)
Wu, D., Wang, J., Liu, W., Cao, J., Zhou, Z.: An effective method for human detection using far-infrared images. In: 2017 First International Conference on Electronics Instrumentation Information Systems (EIIS), pp. 1–4 (2017)
Zhao, Y., Cheng, J., Zhou, W., Zhang, C., Pan, X.: Infrared pedestrian detection with converted temperature map. In: 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 2025–2031 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Oluyide, O.M., Tapamo, JR., Walingo, T. (2021). Fast Background Subtraction and Graph Cut for Thermal Pedestrian Detection. In: Roman-Rangel, E., Kuri-Morales, Á.F., Martínez-Trinidad, J.F., Carrasco-Ochoa, J.A., Olvera-López, J.A. (eds) Pattern Recognition. MCPR 2021. Lecture Notes in Computer Science(), vol 12725. Springer, Cham. https://doi.org/10.1007/978-3-030-77004-4_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-77004-4_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-77003-7
Online ISBN: 978-3-030-77004-4
eBook Packages: Computer ScienceComputer Science (R0)