Abstract
In real-time based smart video surveillance system, the moving human detection in thermal video is a critical task that filters out redundant information and extracts exigent information. The thermal imaging-based system is used to extract the motion-based object in an unseen or dark environment because it captures heat generated from the human or manmade objects. It also penetrates challenging problems due to cluttered nature, low light, illumination variation, dust, mist, or haze available in the background. So, there is huge demand for identification and monitoring of unwanted activities, minimization of crime or trespassing, etc for safety and security. The state-of-the-art methods worked for various problems raised due to cluttered or illumination variation type of behavior of the background. This paper provides a performance analysis of state-of-the-art literature and also focus on the challenging issues involved. Here, the proposed work developed an adaptive method for the maintenance of the background model and adaptive threshold generation during testing phase. This threshold is applied to classify the moving and non-moving pixels by avoiding the external involvement for threshold selection at run-time. To evaluate the efficacy, the performance of the proposed work is analyzed through numerous parameters that achieved higher accuracy with minimum false alarm rate and impressive detection results. The qualitative and quantitative experimental results demonstrate better real-time performance and usability against considered peer methods.
Similar content being viewed by others
References
Ahmad J, Akula A, Mulaveesala R, Sardana HK (2019) An independent component analysis based approach for frequency modulated thermal wave imaging for subsurface defect detection in steel sample. Inf Phys Technol, Elsevier 98:45–54
Akula A, Khanna N, Ghosh R, Kumar S, Das A, Sardana HK (2013) Adaptive contour based statistical background subtraction method for moving target detection in infrared video sequences. J Infrared Phys Technol Elsevier 63:103–109
Applications of Thermal Imaging: https://www.techimaging.com/applications/infrared-thermal-imaging-applications
Bandarupalli, S 2009 “Vehicle detection and tracking using wireless sensors and video cameras”, University of New Orleans Theses and Dissertations, (https://scholarworks.uno.edu/td/989).
Bouwmans T, Porikli F, Höferlin B, Vacavant A (2014) Background modeling and foreground detection for video surveillance. Chapman & Hall, London, U.K.
Bouwmans T, Sobral A, Javed S, Jung S, Zahzah E (2017) Decomposition into low-rank plus additive matrices for background/foreground separation: a review for a comparative evaluation with a large-scale dataset. Comp Sci Rev 23:1–71
Chen P, Dang Y, Liang R, Zhu W, He X (2018) Real-time object tracking on a drone with multi-inertial sensing data. IEEE Trans Intell Transp Syst 19(1):131–139
Demir B, Ergunay S, Nurlu G et al (2020) Real-time high-resolution omnidirectional imaging platform for drone detection and tracking. J Real-Time Image Proc Springer 17:1625–1635
Dollár P, Appel R, Blondie S, Perona P (2014) Fast feature pyramids for object detection. IEEE Trans Pattern Anal Mach Intell 36(8):1532–1545
Goyette N, Jodoin PM, Porikli F, Ishwar P (2012) changedetection.net. A new change detection benchmark database. Proc IEEE Workshop on Change Detect at CVPR:1–8
Gupta H, Verma OP(2021) “Monitoring and surveillance of urban road traffic using low altitude drone images: a deep learning approach”, J Multimed Tools App, Springer
Haines T, Xiang T (Apr. 2014) Background subtraction with Dirichlet process mixture models. IEEE Trans Pattern Anal Mach Intell 36(4):670–683
Haque M, Murshed M, Paul M 2008 On Stable Dynamic Background Generation Technique using Gaussian Mixture Models for Robust Object Detection. 5th International Conference on Advanced Video and Signal Based Surveillance, IEEE, pp. 41–48. https://doi.org/10.1109/AVSS.2008.12.
Hashemi M, Hall M (2019) Detecting and classifying online dark visual propaganda. J Image Vision Comp Elsevier 89:95–105
Hu W, Tan T, Wang L, Maybank S (2004) A survey on visual surveillance of object motion and behaviours. IEEE transac on syst. Man and Cybernetics – Part C 34:334–352. https://doi.org/10.1109/TSMCC.2004.829274
Infrared detector in thermal imaging: https://www.atncorp.com/howthermalimagingworks
Jung CR 2009 “Efficient Background Subtraction and Shadow Removal for Monochromatic Video Sequences”, IEEE Transactions on Multimedia, vol. 11, no. 3.
Lee S, Lee C Low complexity background subtraction based on spatial similarity. Eurasip J Image and Video Proc, Springer 35:2–16
Mandal M, Dhar V, Mishra A, Vipparthi SK, Abdel-Mottaleb M (2021) 3DCD: scene independent end-to-end spatiotemporal feature learning framework for change detection in unseen videos. IEEE Trans Image Process 30:546–558
Rai M, Husain AA, Maity T, Yadav RK (2018) Advance intelligent video surveillance system (AIVSS): a future aspect, intelligent video surveillance. Publisher IntechOpen, 5th. https://doi.org/10.5772/intechopen.76444
Reddy V, Sanderson C, Lovell B (2013) Improved foreground detection via block based classifier cascade with probabilistic decision integration. IEEE Transac Circuit Syst Video Technol 23(1):175–181
Saboo S, Singha J (May 2021) Vision based two-level hand tracking system for dynamic hand gestures in indoor environment. J Multimedia Tools App Springer 80:20579–20598
Sanin A, Sanderson C, Lovell BC (2012) Shadow detection: a survey and comparative evaluation of recent methods. Elsevier, Pattern Recog 45(4):1684–1695
Security for Infiltration: https://www.git-security.com/topstories/security/thermal-imaging-technology-ready-further-conquer-world
Shahbaz A, Jo K (2020) Improved Change Detector using Dual-Camera Sensors for Intelligent Surveillance Systems. IEEE Sensors J:1–8
Sharma L, Yadav DK (2017) Histogram based Adaptive Learning Rate for Background Modelling and Moving Object Detection in Video Surveillance. Intern J Telemed Clinical Prac, Indersci 2(1):74–92
Sharma L, Yadav DK, Singh A (2016) Fisher’s Linear Discriminant Ratio based Threshold for Moving Human Detection in Thermal Video. Infrared Phys Technol, Elsevier 78:118–128
Song J, Gao B, Woob WL, Tian GY (2020) Ensemble tensor decomposition for infrared thermography 568 cracks detection system. Infr Phys Technol Elsevier 105:1–9 https://www.sciencedirect.com/science/article/abs/pii/S1350449519308618?via%3Dihub https://doi.org/10.1016/j.infrared.2020.103203
Stauffer C, Grimson W (1999) Adaptive background mixture models for real-time tracking. Int Conf On Comp Vision Pattern Recog IEEE Comp Soc 2:252–256. https://doi.org/10.1109/CVPR.1999.784637
St-Charles PL, Bilodeau GA, Bergevin R (2015) SuBSENSE: a universal change detection method with local adaptive sensitivity. IEEE Trans Image Process 24(1):359–373. https://doi.org/10.1109/TIP.2014.2378053
Tezcan MO, Ishwar P, Konrad J (2021) BSUV-net 2.0: Spatio-temporal data augmentations for video-agnostic supervised background subtraction. IEEE Access 9:53849–53860. https://doi.org/10.1109/ACCESS.2021.3071163
Tokmakov P, Alahari K, Schmid C (2017) “Learning Motion Patterns in Videos”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 531–539.
Wang Y, Jodoin PM, Porikli F, Konrad J, Benezeth Y, Ishwar P (2014) CDNET 2014: an expanded change detection benchmark dataset. IEEE Conf Compr Vision and Pattern Recog Workshops:393–400
Xua X, Yanga P, Xiana H, Liu Y (2019) Robust moving objects detection in long-distance imaging through turbulent medium. Inf Phys Technol. Elsevier 100:87–98. https://doi.org/10.1016/j.infrared.2019.02.014
Yadav DK (2019) Chapter-12: detection of moving human in vision based smart surveillance under cluttered background: an application for IoT. Book- Visual Surveil Int Things: Technol App, Taylor & Francis, March:1–296
Yadav DK, Singh K (2016) A Combined Approach of Kullback-Leibler Divergence Method and Background Subtraction for Moving Object Detection in Thermal Video. Infra Phys Technol, Elsevier 76:21–31
Yadav DK, Singh K (Jan, 2019) Adaptive background modeling technique for moving object detection in video under dynamic environment. Intern J Spatio-Temp Data Sci, Indersci 1(1):4–21
Yazdi M, Bouwmans T (March, 2018) New trends on moving object detection in video images captured by a moving camera: a survey. Comp Sci Rev, Elsevier 28:1–66
Zeng Q, Adu J, Liu J, Yang J, Xu Y, Gong M (2020) Real-time adaptive visible and infrared image registration based on morphological gradient and C_SIFT. J Real-Time Image Proc Springer 17:1103–1115
Zhou X, Yang C, Yu W (2014) Moving object detection by detecting contiguous outliers in the low-rank representation”, IEEE transactions on pattern analysis and machine intelligence, vol. 35, issue-3, pp. 597-610, march, 2013.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kumar, M., Ray, S. & Yadav, D.K. Moving human detection and tracking from thermal video through intelligent surveillance system for smart applications. Multimed Tools Appl 82, 39551–39570 (2023). https://doi.org/10.1007/s11042-022-13515-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13515-6