Repetitive motion detection for human behavior understanding from video images

Kumdee, Orrawan; Ritthipravat, Panrasee

doi:10.1109/isspit.2015.7394384

Cited by 7 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another widely recognized technique for periodicity quantification [6], derives periodicity measures based on self-similarity matrices of L1 pixel differences. This technique has inspired a diverse array of applications, including analyzing the cycles of expanding/contracting jellyfish [33], analyzing bat wings [2], and analyzing videos of autistic spectrum children performing characteristic repetitive motions such as "hand flapping" [22]. We compare to this technique in Section 4.2.…”

Section: Self-similarity Matricesmentioning

confidence: 99%

(Quasi)Periodicity Quantification in Video Data, Using Topology

Tralie¹,

Perea²

2018

SIAM J. Imaging Sci.

View full text Add to dashboard Cite

This work introduces a novel framework for quantifying the presence and strength of recurrent dynamics in video data. Specifically, we provide continuous measures of periodicity (perfect repetition) and quasiperiodicity (superposition of periodic modes with non-commensurate periods), in a way which does not require segmentation, training, object tracking or 1-dimensional surrogate signals. Our methodology operates directly on video data. The approach combines ideas from nonlinear time series analysis (delay embeddings) and computational topology (persistent homology), by translating the problem of finding recurrent dynamics in video data, into the problem of determining the circularity or toroidality of an associated geometric space. Through extensive testing, we show the robustness of our scores with respect to several noise models/levels; we show that our periodicity score is superior to other methods when compared to human-generated periodicity rankings; and furthermore, we show that our quasiperiodicity score clearly indicates the presence of biphonation in videos of vibrating vocal folds, which has never before been accomplished end to end quantitatively. *

show abstract

Section: Self-similarity Matricesmentioning

confidence: 99%

(Quasi)Periodicity Quantification in Video Data, Using Topology

Tralie¹,

Perea²

2018

SIAM J. Imaging Sci.

View full text Add to dashboard Cite

show abstract

“…Although the above methods lay the foundation for the video repetitive counting task, they only realized the simple repetitive motion estimation of a fixed scene and had a poor performance on the diversity and non-stationary motion, which commonly exist in the real applications. In recent years, Kumdee et al [3] used the image selfsimilarity measure as the input of the multi-layer the perceptron neural network to determine whether the input video is a repetitive action. This method is relatively stable to image changes, noise, and low-resolution images.…”

Section: Periodic Movement Analysismentioning

confidence: 99%

“…Then the transformation matrix F is computed using F = F − F . Finally, the covariance matrix is calculated according to equation (3).…”

Section: Periodic Signal Generationmentioning

confidence: 99%

“…(2) We give an important insight that the periodic self-similarity movement information can be well modeled by the deep features of the action used in action recognition. (3) We propose the Fourier transform with Multi-stage threshold Filter (FMF) scheme to automatically mine the interesting repetitive action and remove noises to improve the repetition counting performance. The remainder of the paper is organized as follows.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Energy-based Periodicity Mining with Deep Features for Action Repetition Counting in Unconstrained Videos

Yin¹,

Wu²,

Liu³

et al. 2020

Preprint

View full text Add to dashboard Cite

Action repetition counting is to estimate the occurrence times of the repetitive motion in one action, which is a relatively new, important but challenging measurement problem. To solve this problem, we propose a new method superior to the traditional ways in two aspects, without preprocessing and applicable for arbitrary periodicity actions. Without preprocessing, the proposed model makes our method convenient for real applications; processing the arbitrary periodicity action makes our model more suitable for the actual circumstance. In terms of methodology, firstly, we analyze the movement patterns of the repetitive actions based on the spatial and temporal features of actions extracted by deep ConvNets; Secondly, the Principal Component Analysis algorithm is used to generate the intuitive periodic information from the chaotic high-dimensional deep features; Thirdly, the periodicity is mined based on the high-energy rule using Fourier transform; Finally, the inverse Fourier transform with a multi-stage threshold filter is proposed to improve the quality of the mined periodicity, and peak detection is introduced to finish the repetition counting. Our work features two-fold: 1) An important insight that deep features extracted for action recognition can well model the self-similarity periodicity of the repetitive action is presented. 2) A high-energy based periodicity mining rule using deep features is presented, which can process arbitrary actions without preprocessing. Experimental results show that our method achieves comparable results on the public datasets YT Segments and QUVA.

show abstract

Technology Contribution to Improve Autistic Children Life Quality

Comas-González

Sánchez-Comas

De-la-Hoz-Franco

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

o review published literature on the use of technology and how it has improved autistic children life style. A systematic review of the English literature was performed using the PRISMA guideline. Papers indexed in WOS and Scopus databases were included, adjusted to a timeline between 2016 and 2020 and focused on mobile technology, interventions, improvement of social behavior and communication and autism, aimed to describe the most used mechanism to improve autistic life style. Thirty two (32) papers were included in the review. We obtained 14 papers on the Scopus database and 18 on the WOS database. The majority of studies evidenced the use of virtual reality, mobile devices, video modelling and robots as the most common applications for autism therapies. Technology has caused an improvement in autistic children life quality. The development of mobile applications, virtual reality applications and robots have showed a positive impact reflected in the performance of daily activities and a better understanding of how they feel, how to behave, how to express themselves and interact with others. Technology gives the opportunity to monitor children status; and offers adaptability, safety, and accuracy of the information.

show abstract

Repetitive motion detection for human behavior understanding from video images

Cited by 7 publications

References 18 publications

(Quasi)Periodicity Quantification in Video Data, Using Topology

(Quasi)Periodicity Quantification in Video Data, Using Topology

Energy-based Periodicity Mining with Deep Features for Action Repetition Counting in Unconstrained Videos

Technology Contribution to Improve Autistic Children Life Quality

Contact Info

Product

Resources

About