Abstract
Human action recognition in recordings acquired from reconnaissance cameras discovers application in fields like security, health care and medicine, sports, programmed gesture-based communication acknowledgment, and so on. The task is challenging due to variations in motion, recording settings, and inter-personal differences. In this paper, novel DWT & PC-based profile generation algorithm is proposed which incorporates notion of energy in extracting features from video frames. Seven energy-based features are calculated using unique energy profiles of each action. Proposed algorithm is applied to three widely used classifiers—SVM, Naive bayes, and J48 to classify video actions. Algorithm is tested on Weizmann’s dataset & performance is measured with evaluation metrics such as precision, sensitivity, specificity, and accuracy. Finally, it is compared with the existing method of template matching using MACH filter. Simulation results give good accuracy than existing 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
A K, C S, I G (2008) A spatio-temporal descriptor based on 3d-gradients. In: British machine vision conference
Battiato S, Coquillart S, Laramee RS, Kerren A, Braz J (2014) Computer vision, imaging and computer graphics—theory and applications. In: International joint conference, VISIGRAPP 2013. Springer Publishing Company, Barcelona, Spain
D Z, G L (2004) Review of shape representation and description techniques. Pattern Recogn 1:1–19
D Z, G L (20003) A comparative study on shape retrieval using fourier descriptors with different shape signatures J Vis Commun Image Represent 1:41–60
D Z, G L (2003) A comparative study on shape retrieval using fourier descriptors with different shape signatures. In: IEEE conference on computer vision and pattern recognition (CVPR2005), vol 1, pp 886–893
Dollár P, Rabaud V, Cottrell G, Belongie S (2005) Behavior recognition via sparse spatiotemporal features. In: In VS-PETS, pp 65–72
H K, T S, P M (1995) An experimental comparison of autoregressive and fourier-based descriptors in 2d shape classification. IEEE Trans Pattern Anal Mach Intell 2:201–207
Kacprzyk J (2015) Advances in intelligent and soft computing. Springer, Berlin
Koves P (2016) Feature detection via phase congruency. http://homepages.inf.ed.ac.uk/rbf/CVonline/. [Online Accessed 11 Nov 2016]
Laptev I (2005) On space-time interest points. Int J Comput Vision 64(2–3):107–123. https://doi.org/10.1007/s11263-005-1838-7
Laptev I, Marszałek M, Schmid C, Rozenfeld B (2008) Learning realistic human actions from movies. CVPR (2008)
N D, B T, C S (2006) Human detection using oriented histograms of flow and appearance. In: European conferences on computer vision (ECCV 2006), pp 428–441
R C, A R, G H, R V (2012) Histograms of oriented optical flow and binet-cauchy kernels on nonlinear dynamical systems for the recognition of human actions. In: IEEE conferences on computer vision and pattern recognition (CVPR 2009), vol 4, pp 1932–1939
RD L, L S (2000) Human silhouette recognition with fourier descriptors. In: 15th international conferences on pattern recognition (ICPR 2000), vol 3, pp 709–712
Rodriguez M, Ahmed J, Shah M (2008) Action mach a spatio-temporal maximum average correlation height filter for action recognition. In: IEEE conference on computer vision and pattern recognition, (CVPR 2008), pp 1–8
R G, R W, S E (2009) Digital image processing using Matlab, 2nd edn
S S, A AH, B M, U S (2012) Chord length shape features for human activity recognition. In: ISRN machine vision
Scovanner P, Ali S, Shah M (2007) A 3-dimensional sift descriptor and its application to action recognition. In: proceedings of the 15th ACM international conference on multimedia, MM –07. ACM, New York, NY, USA, pp 357–360. https://doi.org/10.1145/1291233.1291311
Wang H, Ullah MM, KlÃser A, Laptev I, Schmid C (2009) Evaluation of local spatio-temporal features for action recognition. University of Central Florida, USA
Weinland D, Ronfard R, Boyer E (2011) A survey of vision-based methods for action representation, segmentation and recognition, vol 115
Willems G, Tuytelaars T, Gool LV Gool l (2008) An efficient dense and scale-invariant spatiotemporal interest point detector. Technical Report
Z W, AC B, HR S, EP S (2004) Image quality assessment: from error visibility to structure similarity. IEEE Trans Image Process 4:600–612
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Zaveri, T., Prajapati, P., Shah, R. (2021). Novel DWT and PC-Based Profile Generation Method for Human Action Recognition. In: Verma, G.K., Soni, B., Bourennane, S., Ramos, A.C.B. (eds) Data Science. Transactions on Computer Systems and Networks. Springer, Singapore. https://doi.org/10.1007/978-981-16-1681-5_12
Download citation
DOI: https://doi.org/10.1007/978-981-16-1681-5_12
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-1680-8
Online ISBN: 978-981-16-1681-5
eBook Packages: Computer ScienceComputer Science (R0)