Abstract
Automatic human posture recognition in surveillance videos has real world applications in monitoring old-homes, restoration centers, hospitals, disability, and child-care centers. It also has applications in other areas such as security and surveillance, sports, and abnormal activity recognition. Human posture recognition is a challenging problem due to occlusion, background clutter, illumination variations, camouflage, and noise in the captured video signal. In the current study, which is an extension of our previous work (Ali et al. Sensors, 18(6):1918, 2018), we propose a novel combination of a number of spatio-temporal features computed over human blobs in a temporal window. These features include aspect ratios, shape descriptors, geometric centroids, ellipse axes ratio, silhouette angles, and silhouette speed. In addition to these features, we also exploit the radon transform to get better shape based analysis. In order to obtain improved posture classification accuracy, we used J48 classifier under a boosting framework by employing the AdaBoost algorithm.The proposed algorithm is compared with eighteen existing state-of-the-art approaches on four publicly available datasets including MCF, UR Fall detection, KARD, and NUCLA. Our results demonstrate the excellent performance of the proposed algorithm compared to these existing methods.
Similar content being viewed by others
References
Adhikari K, Bouchachia H, Nait-Charif H (2019) Deep learning based fall detection using simplified human posture. Int J Comput Syst Eng 13 (5):255–260
Ali S, Khan R, Mahmood A, Hassan M, Jeon M (2018) Using temporal covariance of motion and geometric features via boosting for human fall detection. Sensors 18(6):1918
Auvinet E, Rougier C, Meunier J, St-Arnaud A, Rousseau J (2010) Multiple cameras fall dataset. DIRO-Université de Montréal, Tech. Rep., 1350
Bouwmans T, Silva C, Marghes C, Zitouni MS, Bhaskar H, Frelicot C (2018) On the role and the importance of features for background modeling and foreground detection. Comput Sci Rev 28:26–91
Darwish A, Hassanien AE (2011) Wearable and implantable wireless sensor network solutions for healthcare monitoring. Sensors 11(6):5561–5595
Debard G, Karsmakers P, Deschodt M, Vlaeyen E, Van den Bergh J, Dejaeger E, Milisen K, Goedemé T, Tuytelaars T, Vanrumste B (2011) Camera based fall detection using multiple features validated with real life video. In: Workshop proceedings of the 7th international conference on intelligent environments, vol 10, pp 441–450. IOS Press
Dhiman C, Vishwakarma D (2019) A review of state-of-the-art techniques for abnormal human activity recognition. Eng Appl Artif Intel 77:21–45
Dhiman C, Vishwakarma D (2019) A robust framework for abnormal human action recognition using r-transform and zernike moments in depth videos. IEEE Sensors J 19(13):5195–5203
Doukas CN, Maglogiannis I (2011) Emergency fall incidents detection in assisted living environments utilizing motion, sound, and visual perceptual components. IEEE Trans Inf Technol Biomed 15(2):277–289
Edgcomb AD (2014) Automated video-based fall detection. Ph.D. thesis, UC Riverside
Elforaici MEA, Chaaraoui I, Bouachir W, Ouakrim Y, Mezghani N (2018) Posture recognition using an rgb-d camera: exploring 3d body modeling and deep learning approaches. In: 2018 IEEE Life Sciences Conference (LSC), pp 69–72. IEEE
Fan K, Wang P, Hu Y, Dou B (2017) Fall detection via human posture representation and support vector machine. Int J Distrib Sensor Netw 13 (5):1550147717707418
Fan K, Wang P, Zhuang S (2019) Human fall detection using slow feature analysis. Multimed Tools Appl 78(7):9101–9128
Feng Q, Gao C, Wang L, Zhao Y, Song T, Li Q (2020) Spatio-temporal fall event detection in complex scenes using attention guided lstm. Pattern Recogn Lett 130:242–249
Foroughi H, Naseri A, Saberi A, Yazdi HS (2008) An eigenspace-based approach for human fall detection using integrated time motion image and neural network. In: 9th International conference on signal processing, 2008. ICSP 2008. pp 1499–1503. IEEE
Foroughi H, Rezvanian A, Paziraee A (2008) Robust fall detection using human shape and multi-class support vector machine. In: Sixth Indian conference on computer vision, graphics & image processing, 2008. ICVGIP’08, pp 413–420. IEEE
Freund Y, Schapire R, Abe N (1999) A short introduction to boosting. Journal-Japanese Society For Artificial Intelligence 14(771-780):1612
Gaglio S, Re GL, Morana M (2014) Human activity recognition process using 3-d posture data. IEEE Trans Human-Mach Syst 45(5):586–597
Gasparrini S, Cippitelli E, Gambi E, Spinsante S, Wåhslén J, Orhan I, Lindh T (2015) Proposal and experimental evaluation of fall detection solution based on wearable and depth data fusion. In: International conference on ICT innovations, pp 99–108. Springer
Ge C, Gu IYH, Yang J (2017) Human fall detection using segment-level cnn features and sparse dictionary learning. In: 2017 IEEE 27th International workshop on machine learning for signal processing (MLSP), pp 1–6. IEEE
Gonzalez RC, Woods RE, Eddins SL (2004) Digital image processing using MATLAB. Pearson Education India
Iazzi A, Rziza M, Thami ROH (2018) Fall detection based on posture analysis and support vector machine. In: 2018 4th International conference on advanced technologies for signal and image processing (ATSIP), pp 1–6. IEEE
Javed S, Mahmood A, Bouwmans T, Jung SK (2017) Background–foreground modeling based on spatiotemporal sparse subspace clustering. IEEE Trans Image Process 26(12):5840–5854
Ji X, Zhou L, Li Y (2014) Human action recognition based on adaboost algorithm for feature extraction. In: 2014 IEEE International conference on computer and information technology, pp 801–805. IEEE
Kamal S, Jalal A (2016) A hybrid feature extraction approach for human detection, tracking and activity recognition using depth sensors. Arabian J Sci Eng 41(3):1043–1051
Kaur G, Chhabra A (2014) Improved j48 classification algorithm for the prediction of diabetes. International Journal of Computer Applications 98(22)
Kepski M, Kwolek B (2015) Embedded system for fall detection using body-worn accelerometer and depth sensor. In: 2015 IEEE 8th International conference on intelligent data acquisition and advanced computing systems: technology and applications (IDAACS), vol 2, pp 755–759. IEEE
Khalifa OO, Htike KK (2013) Human posture recognition and classification. In: 2013 International conference on computing, electrical and electronic engineering(ICCEEE), pp 40–43. https://doi.org/10.1109/ICCEEE.2013.6633905
Kong Y, Huang J, Huang S, Wei Z, Wang S (2019) Learning spatiotemporal representations for human fall detection in surveillance video. J Vis Commun Image Represent 59:215–230
Kyrkou C, Theocharides T (2011) A flexible parallel hardware architecture for adaboost-based real-time object detection. IEEE Transactions on very large scale integration (VLSI) systems 19(6):1034–1047
Lahiri D, Dhiman C, Vishwakarma D (2017) Abnormal human action recognition using average energy images. In: 2017 Conference on information and communication technology (CICT), pp 1–5. IEEE
Leroux A, Boussard M, Dès R (2018) Information gain ratio correction: improving prediction with more balanced decision tree splits. arXiv:1801.08310
Li C, R, Tong M (2018) Modelling human body pose for action recognition using deep neural networks. Arabian J Sci Eng 43(12):7777–88
Li G, Liu Z, Cai L, Yan J (2020) Standing-posture recognition in human–robot collaboration based on deep learning and the Dempster–Shafer evidence theory. Sensors 20(4):1158
Li N, Cheng X, Zhang S, Wu Z (2013) Recognizing human actions by bp-adaboost algorithm under a hierarchical recognition framework. In: 2013 IEEE International conference on acoustics, speech and signal processing, pp 3407–3411. IEEE
Liu E, Zhao H, Guo F, Liang J, Tian J (2011) Fingerprint segmentation based on an adaboost classifier. Front Comput Sci China 5(2):148–157
Liu J, Akhtar N, Mian A (2017) Learning human pose models from synthesized data for robust rgb-d action recognition. arXiv:1707.00823
Liu M, Liu H, Sun Q, Zhang T, Ding R (2016) Salient pairwise spatio-temporal interest points for real-time activity recognition. CAAI Trans Intell Technol 1(1):14–29
Lmberis A, Dittmar A (2007) Advanced wearable health systems and applications-research and development efforts in the European union. IEEE Eng Med Biol Mag 26(3):29–33
Lv F, Nevatia R (2006) Recognition and segmentation of 3-d human action using hmm and multi-class adaboost. In: European conference on computer vision, pp 359–372. Springer
Makhlouf A, Nedjai I, Saadia N, Ramdane-Cherif A (2017) Multimodal system for fall detection and location of person in an intelligent habitat. Procedia Comput Sci 109:969–974
Memmesheimer R, Mykhalchyshyna I, Paulus D (2018) Gesture recognition on human pose features of single images. In: 2018 International conference on intelligent systems (IS), pp 813–819. IEEE
Min W, Cui H, Rao H, Li Z, Yao L (2018) Detection of human falls on furniture using scene analysis based on deep learning and activity characteristics. IEEE Access 6:9324–9335
Moussa M, Mona E, Elsayed, Hemayed A, Heba N, El B, Magda F (2018) Human action recognition utilizing variations in skeleton dimensions. Arabian J Sci Eng 43(2):597–610
Mousse MA, Motamed C, Ezin EC (2016) A multi-view human bounding volume estimation for posture recognition in elderly monitoring system. In: International conference on pattern recognition systems (ICPRS-16), pp 2–6
Mousse MA, Motamed C, Ezin EC (2017) Percentage of human-occupied areas for fall detection from two views. Vis Comput 33(12):1529–1540
Munoz-Organero M, Lotfi A (2016) Human movement recognition based on the stochastic characterisation of acceleration data. Sensors 16(9):1464
Nizam Y, Mohd MNH, Jamil MMA (2016) A study on human fall detection systems: daily activity classification and sensing techniques. International Journal of Integrated Engineering 8(1)
Ramanathan M, Yau WY, Teoh EK (2014) Human action recognition with video data: research and evaluation challenges. IEEE Trans Human-Mach Syst 44(5):650–663
Rimmer JH (1999) Health promotion for people with disabilities: the emerging paradigm shift from disability prevention to prevention of secondary conditions. Phys Therapy 79(5):495–502
Ronchetti F, Quiroga F, Lanzarini L, Estrebou C (2015) Distribution of action movements (dam): a descriptor for human action recognition. Front Comput Sci 9(6):956–965
Schapire R, Freund Y, et al. (1995) A decision-theoretic generalization of on-line learning and an application to boosting. In: Second European conference on computational learning theory, pp 23–37
Shi H, Liu C (2018) A new foreground segmentation method for video analysis in different color spaces. In: 2018 24th International conference on pattern recognition (ICPR), pp 2899–2904. IEEE
Shih HC (2017) A survey of content-aware video analysis for sports. IEEE Trans Circuits Syst Video Technol 28(5):1212–1231
Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. In: Advances in neural information processing systems, pp 568–576
Stork JA, Spinello L, Silva J, Arras KO (2012) Audio-based human activity recognition using non-markovian ensemble voting. In: 2012 IEEE RO-MAN: The 21st IEEE international symposium on robot and human interactive communication, pp 509–514. IEEE
Sultani W, Chen C, Shah M (2018) Real-world anomaly detection in surveillance videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6479–6488
Tabbone S, Wendling L, Salmon JP (2006) A new shape descriptor defined on the radon transform. Comput Vis Image Underst 102(1):42–51
Tanwani AK, Afridi J, Shafiq MZ, Farooq M (2009) Guidelines to select machine learning scheme for classification of biomedical datasets. In: European conference on evolutionary computation, machine learning and data mining in bioinformatics, pp 128–139. Springer
Tinetti ME (2003) Preventing falls in elderly persons. N Engl j Med 2003(348):42–49
Tomoya A, Nakayama S, Hoshina A, Sugaya M (2017) A mobile robot for following, watching and detecting falls for elderly care. Procedia Comput Sci 112:1994–2003
Vishwakarma D, Kapoor R, Dhiman A (2016) Unified framework for human activity recognition: an approach using spatial edge distribution and -transform. AEU-Int J Electron Commun 70(3):341–353
Walse KH, Dharaskar RV, Thakare VM (2016) A study of human activity recognition using adaboost classifiers on wisdm dataset. The Institute of Integrative Omics and Applied Biotechnology Journal 7(2):68–76
Wang J, Huang Z, Zhang W, Patil A, Patil K, Zhu T, Shiroma EJ, Schepps MA, Harris TB (2016) Wearable sensor based human posture recognition. In: 2016 IEEE International conference on big data (big data), pp 3432–3438. IEEE
Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van Gool L (2016) Temporal segment networks: towards good practices for deep action recognition. In: European conference on computer vision, pp 20–36. Springer
Wang S, Chen L, Zhou Z, Sun X, Dong J (2016) Human fall detection in surveillance video based on pcanet. Multimed Tools Appl 75 (19):11603–11613
Wang SM, Gao Y, Luo L (2014) Human posture recognition based on dag-svms. In: Advanced materials research, vol 1042, pp 117–120. Trans Tech Publ
Wang WJ, Chang JW, Haung SF, Wang RJ (2016) Human posture recognition based on images captured by the kinect sensor. Int J Adv Robot Syst 13(2):54
Yan S, Xiong Y, Lin D (2018) Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-second AAAI conference on artificial intelligence
Youssfi Alaoui A, Tabii Y, Oulad Haj Thami R, Daoudi M, Berretti S, Pala P (2021) Fall detection of elderly people using the manifold of positive semidefinite matrices. J Imag 7(7):109
Yu M, Yu Y, Rhuma A, Naqvi SMR, Wang L, Chambers JA (2013) An online one class support vector machine-based person-specific fall detection system for monitoring an elderly individual in a room environment. IEEE J Biomed Health Inform 17(6):1002–1014
Zhang B, Wang L, Wang Z, Qiao Y, Wang H (2018) Real-time action recognition with deeply transferred motion vector cnns. IEEE Trans Image Process 27(5):2326–2339
Zhou K, Zhu Y, Zhao Y (2017) A spatio-temporal deep architecture for surveillance event detection based on convlstm. In: 2017 IEEE visual communications and image processing (VCIP), pp 1–4. IEEE
Acknowledgements
We are very grateful to Noman Nazar and Reamsha Khan for his support and guidance. We also like to extend our special gratitude to Ms. Sumaira Zafar, Muhammad Junaid and Mahzaib Khalid for their assistance. We are grateful to all the anonymous reviewers for their useful comments. This work was supported by the National ICT R& D under grant no. NICTRDF/NGIRI/2012-13/Corsp/3; and University of Management & Technology, Lahore, Pakistan
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
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Aftab, S., Ali, S.F., Mahmood, A. et al. A boosting framework for human posture recognition using spatio-temporal features along with radon transform. Multimed Tools Appl 81, 42325–42351 (2022). https://doi.org/10.1007/s11042-022-13536-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13536-1