Abstract
Auto understanding of human activities in video is an increasing necessity in some application realms. The existing methods for human’s activity identification are divided into two methods: activity recognition and activity detection. The most important challenge in activity detection realm is activity boundary false detection which decreases system accuracy. In this research, an activity detection system was suggested denoting rapid interference and sewing it. Although it has improved accuracy it has also accuracy time, activities in suggested system were replayed more usefully and influenced by creating a descriptor denoting movable and apparent form. The suggested system was tested on Weizmann dataset and reached an accuracy of 93.34%. Furthermore, the proposed system in activity recognition was tested on KTH dataset and reached an accuracy of 93.63%. When activity recognition is stated as a learning case, sufficient labeled educational examples must be used. But labeling the video data is expensive, so the useful method uses unlabeled and labeled examples, during the learning process, this idea is the basic foundation of the semi-supervised method. In this research, a semi-supervised method with co-training algorithm appearance and active learning was suggested which improved the efficiency of semi-supervised learning that was tested.
Similar content being viewed by others
Notes
Geometric Properties of Motion
Detection based on the Probability Changes
Support Vector Machine
Dynamic Co_Training
Imperialism Competetive Algorithm with using Information Exchange and Simulated Annealing
Bag Of Words
Dynamic Frame Warping
Discrete Cosine Transform
Principal Component Analysis
Linear Discriminant Analysis
Vector of Locally Aggregated Descriptors
True Positive
False Positive
Histogram of Optical Flow
Histogram Oriented Gradient
Motion Boundary Histogram
Imperialism Competitive Algorithm
Particle Swarm Optimization
Genetic Algorithm
References
Agrawal M, Ahrabian A, Aizawa K, Akansu A et al (2012) A local 3-d motion descriptor for multi-view human aco n recognio n form 4-d spatio-temporal interest points. IEEE Trans IEEE J Sel Top Signal Process 6(5):553–565
Al-Berry MN, Salem MAM, Ebeid HM, Hussein AS (2016) Fusing directional wavelet local binary pattern and moments for human action recognition. IET Comput Vis IEEE 10(2)
Bo Y, Wenjuan Q, Zhiqiang W, Jie N (2012) Indirect human activity recognition based on optical flow method. Image and Signal Processing, 5th International Congress on, Chongqing, Sichuan, China, Oct 16-18, IEEE, pp. 99-103
Cai L, Liu C, Yuan R et al. (2020) Human action recognition using lie group features and convolutional neural networks. Nonlinear Dyn. https://doi.org/10.1007/s11071-020-05468-y.
Carrara F, Elias P, Sedmidubsky J, Zezula P (2019) LSTM-based real-time action detection and prediction in human motion streams. Multimed Tools Appl 78(19):27309–27331
Chang C, Lin C (2011) LIBSVM: A library for support vector machines. ACM Trans Intell Syst Technol (TIST) 2(3):27
Chen L (2019) Analysis of synchronized storage method for multimedia key areas based on machine learning. Multimed Tools Appl. https://doi.org/10.1007/s11042-019-07752-5
Cuentas S, Peñabaena-Niebles R, Garcia E (2017) Support vector machine in statistical process monitoring: a methodological and analytical review. Int J Adv Manuf Technol 91:485–500. https://doi.org/10.1007/s00170-016-9693-y
Daniel W, Ronfard R, Boyer E (2011) A survey of vision-based methods for action representation, segmentation and recognition. Comp Vis Image Underst (CVIU). Elsevier 115(2):224–241
Fang Q, Nguyen H, Bui X et al (2019) Prediction of blast-induced ground vibration in open-pit mines using a new technique based on imperialist competitive algorithm and M5Rules. Nat Resour Res. https://doi.org/10.1007/s11053-019-09577-3
Galvao DF, Lehman J, Urbano P (2016) Novelty-driven particle swarm optimization. Artif Evol Springer 9554:177–190
Gomez LB, Benoit A, Cavelan A et al (2016) Coping with recall and precision of soft error detectors. J Parallel Distrib Comput, Elsevier 98:8–24
Gowsikhaa D, Abirami S, Baskaran R (2012) Automated human behavior analysis from surveillance videos: a survey. Artif Intell Rev 1–19
Guo X, Wang W (2019) Towards making co-training suffer less from insufficient views. Front Comput Sci 13:99–105. https://doi.org/10.1007/s11704-018-7138-5
Guo P, Miao Z, Shen Y et al (2014) Continuous human action recognition in real time. Multimed Tools Appl Springer 68(3):827–844
Guo P, Miao Z, Shen Y, Cheng H (2020) Real time human action recognition in a long video sequence. 2010 Seventh IEEE International Conference on Advanced Video and Signal Based Surveillance, Boston, Aug. 29 -Sept. 1, IEEE, pp. 248 – 255
Haddou Benderbal H, Dahane M, Benyoucef L (2018) Modularity assessment in reconfigurable manufacturing system (RMS) design: an archived multi-objective simulated annealing-based approach. Int J Adv Manuf Technol 94:729–749
He K, Sum J, Tang X (2013) Guided image filtering. IEEE Trans Pattern Anal Mach Intell 35(6):1397–1409
Ko T (2008) A survey on behavior analysis in video surveillance for homeland security applications. In: 37th IEEE Applied Imagery Pattern Recognition Workshop, Washington DC, Oct 15-17, IEEE, pp. 1–8
Koohzadi M, Keyvanpour MR (2014) An analytical framework for event mining in video data. Artif Intell Rev 41:401–413. https://doi.org/10.1007/s10462-012-9315-5
Koohzadi M, Keyvanpour M (2015) OTWC: an efficient object-tracking method. SIViP 9:1235–1247. https://doi.org/10.1007/s11760-013-0557-8
Kulkarni K, Evangelidis G, Cech J, Horaud R (2015) Continuous action recognition based on sequence alignment. Int J Comput Vis 112(1):90–114
Ladjailia A, Bouchrika I, Merouani H et al (2019) Human activity recognition via optical flow: decomposing activities into basic actions. Neural Computing and Applications, IAPR-MedPRAI
Lamberto B, Seidenari L, Serra G et al (2013) Recognizing human action by using effective codbooks and tracking. Adv Top Comput Vis. https://doi.org/10.3389/frobt.2015.00028
Leng L, Zhang J (2011) Dual-key-binding cancelable palmprint cryptosystem for palmprint protection and information security. J Netw Comput Appl 34:1979–1989. https://doi.org/10.1016/j.jnca.2011.07.003
Leng L, Zhang J (2012) Palmhash code for palmprint verification and protection. 25th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), Montreal, QC:1–4. https://doi.org/10.1109/CCECE.2012.6334853
Leng L, Zhang J (2013) PalmHash code vs. palmPhasor code. Neurocomputing 108:1–12. https://doi.org/10.1016/j.neucom.2012.08.028
Leng L, Zhang J, Xu J, Khan K et al (2010) Dynamic weighted discrimination power analysis: a novel approach for face and palmprint recognition in DCT domain. Int J Phys Sci 5:467–471. https://doi.org/10.1109/ICTC.2010.5674791
Leng L, Zhang J, Chen G et al (2011) Two-directional two-dimensional random projection and its variations for face and palmprint recognition. Lect Notes Comput Sci, vol 6786. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21934-4_37
Leng L, Zhang S, Bi X, Khan MK (2012) Two-dimensional cancelable biometric scheme. Int Conf Wavelet Anal Pattern Recognit, pp 164–169. https://doi.org/10.1109/ICWAPR.2012.6294772.
Leng L, Li M, Leng L, Teoh A (2013) Conjugate 2DPalmHash code for secure palm-print-vein verification. 6th International Congress on Image and Signal Processing (CISP), Hangzhou: 1705–1710. https://doi.org/10.1109/CISP.2013.6743951
Leng L, Li M, Kim C et al (2017) Dual-source discrimination power analysis for multi-instance contactless palmprint recognition. Multimed Tools Appl 76:333–354. https://doi.org/10.1007/s11042-015-3058-7
Lin J, Tsai YH, Yu CY, Li MS (2012) Interaction enhanced imperialist competitive algorithms. Algorithms 5(4):433–448
Liu X, Zhang X (2019) NOMA-based resource allocation for cluster-based cognitive industrial internet of things. IEEE Trans Ind Inform 16(8):5379–5388
Liu D, Shyu M, Zhao G (2013) Spatial-temporal motion information integration for action detection and recognition in non-static background. Information Reuse and Integration (IRI), IEEE 14th International Conference on, pp. 626 – 633
Liu X, Sun C, Zhou M et al (2020) Reinforcement learning-based multislot double-threshold spectrum sensing with bayesian fusion for industrial big spectrum data. IEEE Trans Ind Informa 99:1–10
Lu J, Wang G, Moulin P (2014) Human identity and gender recognition from gait sequences with arbitrary walking directions. IEEE Trans Inform Forensics Secur 9(1):51–61
Mahbub U, Imtiaz H, Ahad MAR (2011) An optical flow based approach for action recognition. in Computer and Information Technology (ICCIT), 2011 14th International Conference on, Dhaka, Dec 22–24, IEEE, pp. 646–651
Maji S, Berg AC, Malik J (2013) Efficient classification for additive kernel SVMs. IEEE Trans Pattern Anal Mach Intell 35(1):66–77
Modarres A, Soryani M (2013) Body posture graph: a new graph-based posture descriptor for human behavior recognition. IET Comput Vis 7(6):488–499
Mollinetti F, Antonio M, Almeida M, Ney J (2013) Performance analysis of the imperialist competitive algorithm using benchmark functions. Soft Computing and Pattern Recognition (SoCPaR), Hanoi, Dec 15-18, IEEE, pp. 349 – 353
Mota VF, Oliveira HN, Scalzo S et al. (2020) From video pornography to cancer cells: a tensor framework for spatiotemporal description. Multimed Tools Appl. https://doi.org/10.1007/s11042-020-08642-x
Pan H, Li J (2016) Online human action recognition based on improved dynamic time warping. IEEE International Conference on Big Data Analysis, Hangzhou, 12–14, IEEE, pp. 1–5
Pfister T, Charles J, Zisserman A (2014) Domain-adaptive discriminative one-shot learning of gestures. Comput Vis– ECCV, Springer 8694:814–829
Ryan DA (2013) Crowd monitoring using computer vision. PhD thesis, Queensland University of Technology, US
Savargiv M, Masoumi B, Keyvanpour M (2020) A new ensemble learning method based on learning automata. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-020-01882-7
Selmi M, El-Yacoubi MA, Dorizzi B (2016) Two-layer discriminative model for human activity recognition. IET Comput Vis IEEE 10(4)
Shen H, Yan Y, Chen W (2015) Evaluation of semi-supervised learning method on action recognition. Multimed Tools Appl 74(2):523–542
Shen H, Yan Y, Xu S et al (2015) Evaluation of semi-supervised learning method on action recognition. Multimedia Tools Appl (MTA) 74(2):523–542
Shipetriu F, Petriu E (2011) Human action recognition from local part model. In: IEEE International Workshop on Haptic Audio Visual Environments and Gsmes (HAVE), Hebei, Oct 14–17, IEEE, pp. 35–38
Singh T, Vishwakarma DK (2019) Video benchmarks of human action datasets: a review. Artif Intell Rev 52(2):1107–1154
Su Y, Li Y, Liu A (2019) Open-view human action recognition based on linear discriminant analysis. Multimed Tools Appl 78:767–782. https://doi.org/10.1007/s11042-018-5657-6
Su Z, Li J, Chang J et al (2020) Real-time visual tracking using complementary kernel support correlation filters. Front Comput Sci 14:417–429
SXC Z, Liu T, Lu H (2011) Boosted multi-class semi-supervised learning for human action recognition. Pattern Recogn, Elsevier 44(10–11):2334–2342
Turaga P, Chellappa R, Subrahamanian V, Udrea O (2008) Machine recognition of human activities: a survey. IEEE Trans Circ Syst Vid 18(11):1473–1487
Uijlings JRR, Duta IC, Rostamzadeh N, Sebe N (2010) Realtime video classification using dense HOF/HOG. In: ICMR, Glasgow, UK, April 01–04, IEEE, pp. 145
Uijlings JRR, Duta IC, Sangineto E, Sebe N (2014) Video classification with densely extracted HOG/HOF/MBH features: an evaluation of the accuracy/computational efficiency trade-off. Int J Multimedia Inform Retr, 2014
Vishwakarma S, Agrawal A (2012) A survey on activity recognition and behavior understanding in video surveillance. Springer. https://doi.org/10.1007/s00371-012-0752-6
Wang S, Ma Z, Yang Y, Li X (2013) Semi-supervised multiple feature analysis for action recognition. IEEE Trans Multimedia 16(2):289–298
Wang S, Luo J, Gao S (2014) Imperialist competitive algorithm with trading mechanism for optimization. Commun Comput Inform Sci 462:78–98
Wójcik PI, Kurdziel M (2019) Training neural networks on high-dimensional data using random projection. Pattern Anal Applic 22:1221–1231. https://doi.org/10.1007/s10044-018-0697-0
Yilmaz A, Javed O, Shah M (2006) Object tracking: a survey. ACM Comput Surv 38(4):1–45
Yuan D, Lu X, Li D et al (2019) Particle filter re-detection for visual tracking via correlation filters. Multimed Tools Appl 78:14277–14301. https://doi.org/10.1007/s11042-018-680
Zhang Y, Wenb J, Wanga X, Jiang Z (2013) A semi-supervised learning combining co-training with active learning. Expert Syst Appl Elsevier 41(5):2372–2378
Zhang Y, Tao R, Wang Y (2016) Motion-state-adaptive video summarization via spatio-temporal analysis. IEEE Trans Circ Syst Video Technol 8(99):1
Zhao Y, Chen D, Xie H, Zhang Sh GL (2019) Mammographic image classification system via active learning. J Med Biol Eng 39(4):569–582
Zhou Z, Shi F, Wu W (2015) Learning spatial and temporal extents of human actions for action detection. IEEE Trans Multimedia 17(4):512–525
Zhu X, Liu J, Wang J et al (2014) Sparse representation for robust abnormality detection in crowded scenes. Pattern Recogn. Elsevier 47(5):1791–1799
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
Keyvanpour, M.R., Khanbani, N. & Aliniya, Z. Detection of individual activities in video sequences based on fast interference discovery and semi-supervised method. Multimed Tools Appl 80, 13879–13910 (2021). https://doi.org/10.1007/s11042-020-10418-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-10418-2