Abstract
A developing area of computer vision is the identification of human activity from IoT sensor. The size of the feature vectors in such an identification system is a concern. In this paper an intelligent system has been proposed by local spatio-temporal properties which is adjusted to the volume, frequency and speed of changing sequences and can record local occurrences in a video. An intelligent system is created by Tri-axial accelerometers and local space–time feature-based video depictions followed by incorporation into traditional classification algorithms for recognition. The proposed model provides a newly created video database with 3221 combinations of six human activities carried out by 35 participants in four different contexts for analysis purpose. A comparative study is made with available classification algorithms where the Local feature SVM gives highest accuracy and clearly judges the difference between arm and leg activities.
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
References
Ryoo MS, Aggarwal JK (2009) Semantic representation and recognition of continued and recursive human activities. Int J Comput Vis 82(1):1–24
Zelnik-Manor L, Irani M (2006) Statistical analysis of dynamic actions. IEEE Trans Pattern Anal Mach Intell 28(9):530–1535
Xiang T, Gong S (2008) Video behavior profiling for anomaly detection. IEEE Trans Pattern Anal Mach Intell 30(5):893–908
Xiang T, Gong S (2008) Activity based surveillance video content modelling. Pattern Recogn 41(7):2309–2326
Fathi A, Mori G (2008) Action recognition by learning mid-level motion features. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Ali S, Shah M (2008) Human action recognition in videos using kinematic features and multiple instance learning. IEEE Trans Pattern Anal Mach Intell
Liu J, Ali S, Shah M (2008) Recognizing human actions using multiple features. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Davis J, Bobick A (1997) The representation and recognition of action using temporal templates. In: Proceedings of CVPR, pp 928–934
Black M, Jepson A (1998) Eigentracking: robust matching and tracking of articulated objects using view-based representation. IJCV 26(1):63–84
Chomat O, Crowley J (1999) Probabilistic recognition of activity using local appearance. In:Proceedings of CVPR, pp II:104–109
Laptev I, Lindeberg T (2003) Space-time interest points. In: Proceedings of ICCV, pp 432–439
Vapnik V (1998) Statistical learning theory. Wiley, NY
Gorelick L, Blank M, Shechtman E, Irani M, Basri R (2007) Actions as space–time shapes. IEEE Trans Pattern Anal Mach Intell 29(12):2247–2253
Yilmaz A, Shah M (2005) Actions sketch: a novel action representation. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp 984–989
Blank M, Gorelick L, Shechtman E, Irani M, Basri R (2005) Actions as space–time shapes. In: International conference on computer vision, pp 1395–1402
Niebles JC, Li F-F (2007) A hierarchical model of shape and appearance for human action classification. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp 1–8
Luvizon DC, Tabia H, Picard D (2017) Learning features combination for human action recognition from skeleton sequences. Pattern Recogn Lett 99:13–20
Yuan C, Li X, Hu W et al (2013) 3D R transform on spatio-temporal interest points for action recognition. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp 724–730
Wu J, Hu D, Chen F (2014) Action recognition by hidden temporal models
Sharif M, Khan MA, Akram T et al (2017) A framework of human detection and action recognition based on uniform segmentation and combination of Euclidean distance and joint entropy-based features selection
Liu L, Ming A, Ma H, Zhang X (2012) A binary-classification-tree based framework for distributed targe.t classification in multimedia sensor networks. In: 2012 Proceedings IEEE INFOCOM
O’Callaghan BPF, Doheny EP, Goulding C, Fortune E, Lowery MM (2020) Adaptive gait segmentation algorithm for walking bout detection using tri-axial accelerometers. In:2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada, pp 4592–4595
Gupta R, Gupta SH, Agarwal A, Choudhary P, Bansal N, Sen S (2020) A wearable multisensor posture detection system. In: 2020 4th International conference on intelligent computing and control systems (ICICCS), Madurai, India, pp 818–822
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Das, P., Das, I., Dutta, M., Nath, S. (2023). Intelligent Activity Detection System by LF SVM and Tri-axial Accelerometer. In: Chaki, N., Roy, N.D., Debnath, P., Saeed, K. (eds) Proceedings of International Conference on Data Analytics and Insights, ICDAI 2023. ICDAI 2023. Lecture Notes in Networks and Systems, vol 727. Springer, Singapore. https://doi.org/10.1007/978-981-99-3878-0_9
Download citation
DOI: https://doi.org/10.1007/978-981-99-3878-0_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-3877-3
Online ISBN: 978-981-99-3878-0
eBook Packages: EngineeringEngineering (R0)