Human action recognition using MHI and SHI based GLAC features and Collaborative Representation Classifier

Bulbul, Mohammad Farhad; Islam, Saiful; Ali, Hazrat

doi:10.3233/jifs-181136

Cited by 15 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e model complexity of the support vector machine is determined by the number of support vectors, and the optimal classification function obtained after the solution is [22]…”

Section: Use Support Vector Machine Model For Actionmentioning

confidence: 99%

Computer Aided Teaching System Based on Artificial Intelligence in Football Teaching and Training

Zhang

2021

Mobile Information Systems

View full text Add to dashboard Cite

As the world's largest sport, football has affected a wide area and a large number of participants and had a great impact on political economy and culture, which has become the best embodiment of the social function of football. Throughout the experience of football in developed countries in the world, the stable development of youth football is the best way to improve the level of football in a country, and the Chinese Football Association has invested more energy in professional leagues and national teams. The development of youth campus football is basically in a state of no management. Therefore, people gradually realize the concept that “football should serve education.” In order to solve the problem of football players' lack of exercise in multiple subjects, it is particularly important to design systems and make plans for their respective physical characteristics. After the failure of various important competitions, the Chinese national football team reflected on the specific factors of backwardness. Under today's system, no one manages the specific development of youth campus football. Especially for young people, training programs that adapt to their individual characteristics should be formulated according to their growth stage and physical characteristics. It can effectively improve the efficiency of football teaching and training (FTT) by managing football players' training information and coaches' teaching information in an intelligent and informatized way. The different sports in which athletes participate in training are identified through the motion recognition layer. The data generated during the entire exercise process, including exercise time, number of exercises, score settlement, and other data, are stored, and the data are finally uploaded to the server, to carry out scientific analysis and management and generate sports training prescriptions in line with their own characteristics. This paper proposes research methods based on the intelligent integrated system of FTT, including literature retrieval, questionnaire survey, training empirical method, comparative analysis method, interview method, and support vector machine model for action recognition, which are used in football teaching and the design experiment of the intelligent integrated system for training; the overall architecture design of the football teaching intelligent integration system and the specific design of the football teaching intelligent integration system are proposed. The experimental results of this article show that 90.70% of players like the teaching mode of intelligent FTT, and the intelligent FTT system can help improve the enthusiasm of players in training and learning.

show abstract

“…e model complexity of the support vector machine is determined by the number of support vectors, and the optimal classification function obtained after the solution is [22]…”

Section: Use Support Vector Machine Model For Actionmentioning

confidence: 99%

Computer Aided Teaching System Based on Artificial Intelligence in Football Teaching and Training

Zhang

2021

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…Classification accuracy (%) DCSF [54] 89.3 HON4D [15] 88.9 Super Normal Vector [16] 93.1 Skeletons Lie group [17] 89.5 DMM-LBP-DF [55] 93.0 2D-CNN on DMM-Pyramid [44] 91.1 3D-CNN on DMM-Cube [44] 86.1 HOG3D + LLC [56] 90.9 Hierarchical 3D Kernel [57] 92.7 GLAC on DMM [13] 89.4 DMM-GLAC-STACOG [13] 94.8 3DHoT + MBC [58] 95.2 Subspace encoding [59] 94.06 LSTM + trust gates [60] 94.8 Extended SNV [61] 93.5 Trust Gates [62] 94.8 ST-NBNN [63] 94.8 SSTKDes [64] 95.6 3D-CNN + DHI + relief + SVM [65] 92.8 WDMM + HOG [66] 91.9 WDMM + LBP [66] 91.6 WDMM + CNN [66] 90.0 Deep activations [67] 92.3 Deep activations + attributes [67] 93.4 Hierarchical Gaussian [68] 95.6 GMHI + GSHI + CRC [69] 94.5 MHF + SHF + KELM [36] 95.97 Spatiotemporal + HMM [70] 92. Experimental evaluation of our approach on UTD-MHAD dataset is represented by Table 5.…”

Section: Approachmentioning

confidence: 99%

Gradient local auto-correlation features for depth human action recognition

Bulbul¹,

Ali

2021

SN Appl. Sci.

Self Cite

View full text Add to dashboard Cite

Human action classification is a dynamic research topic in computer vision and has applications in video surveillance, human–computer interaction, and sign-language recognition. This paper aims to present an approach for the categorization of depth video oriented human action. In the approach, the enhanced motion and static history images are computed and a set of 2D auto-correlation gradient feature vectors is obtained from them to describe an action. Kernel-based Extreme Learning Machine is used with the extracted features to distinguish the diverse action types promisingly. The proposed approach is thoroughly assessed for the action datasets namely MSRAction3D, DHA, and UTD-MHAD. The approach achieves an accuracy of 97.44% for MSRAction3D, 99.13% for DHA, and 88.37% for UTD-MHAD. The experimental results and analysis demonstrate that the classification performance of the proposed method is considerable and surpasses the state-of-the-art human action classification methods. Besides, from the complexity analysis of the approach, it is turn out that our method is consistent for the real-time operation with low computational complexity.

show abstract

“…They extracted histograms of gradient and local binary patterns from a weighted depth motion map (WDMM). In [ 33 ], an action recognition scheme based on two types of depth images (generated using 3D Motion Trail Model (3DMTM)) was introduced. They obtained two features by using the GLAC algorithm from the images respectively and the features were fused in a vector.…”

Section: Related Workmentioning

confidence: 99%

Exploring 3D Human Action Recognition Using STACOG on Multi-View Depth Motion Maps Sequences

Bulbul¹,

Tabussum²,

Ali

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

This paper proposes an action recognition framework for depth map sequences using the 3D Space-Time Auto-Correlation of Gradients (STACOG) algorithm. First, each depth map sequence is split into two sets of sub-sequences of two different frame lengths individually. Second, a number of Depth Motion Maps (DMMs) sequences from every set are generated and are fed into STACOG to find an auto-correlation feature vector. For two distinct sets of sub-sequences, two auto-correlation feature vectors are obtained and applied gradually to L2-regularized Collaborative Representation Classifier (L2-CRC) for computing a pair of sets of residual values. Next, the Logarithmic Opinion Pool (LOGP) rule is used to combine the two different outcomes of L2-CRC and to allocate an action label of the depth map sequence. Finally, our proposed framework is evaluated on three benchmark datasets named MSR-action 3D dataset, DHA dataset, and UTD-MHAD dataset. We compare the experimental results of our proposed framework with state-of-the-art approaches to prove the effectiveness of the proposed framework. The computational efficiency of the framework is also analyzed for all the datasets to check whether it is suitable for real-time operation or not.

show abstract

Human action recognition using MHI and SHI based GLAC features and Collaborative Representation Classifier

Cited by 15 publications

References 34 publications

Computer Aided Teaching System Based on Artificial Intelligence in Football Teaching and Training

Computer Aided Teaching System Based on Artificial Intelligence in Football Teaching and Training

Gradient local auto-correlation features for depth human action recognition

Exploring 3D Human Action Recognition Using STACOG on Multi-View Depth Motion Maps Sequences

Contact Info

Product

Resources

About