Human action recognition using Dynamic Time Warping

By Samsu Sempena, N. Maulidevi, Peb Ruswono Aryan. 2011

187 citations recorded by the source corpus.

Human action recognition is gaining interest from many computer vision researchers because of its wide variety of potential applications. For instance: surveillance, advanced human computer interaction, content-based video retrieval, or athletic performance analysis. In this research, we focus to recognize some human actions such as waving, punching, clapping, etc. We choose exemplar-based sequential single-layered approach using Dynamic Time Warping (DTW) because of its robustness against variation in speed or style in performing action. For improving recognition rate, we perform body part tracking using depth camera to recover human joints body part information in 3D real world coordinate system. We build our feature vector from joint orientation along time series that invariant to human body size. Dynamic Time Warping is then applied to the resulted feature vector. We examine our approach to recognize several actions and we confirm our method can work well with several experiments. Further experiment for benchmarking the result will be held in near future.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (2017, methodology): “[36] apply dynamic time warping based on the feature vector built from joint orientation along time series.”
A Review on Video-Based Human Activity Recognition (2013, methodology): “An exemplar-based sequential single-layered approach (as categorized in [95], where the approaches for human activity recognition are categorized into single-layered approaches and hierarchical approaches) for DTW is proposed in [16], and is used to attack speed variation.”
Structure-Preserving Binary Representations for RGB-D Action Recognition (2016, methodology): “Due to the time-sequential property, DTW was also widely used as a measurement method in human action recognition for both depth data [41] and body joints of skeletons [42].”
Spatio-Temporal Naive-Bayes Nearest-Neighbor (ST-NBNN) for Skeleton-Based Action Recognition (2017, methodology): “On the temporal domain, graphical models [11, 30], temporal pyramid matching [28, 32], and dynamic time warping [20] are the common methods for temporal modeling.”
Depth Induced Feature Representation for 4D Human Activity Recognition (2014, methodology): “proposed exemplar-based sequential single-layered approach using Dynamic Time Warping (DTW) to recognize actions, and performed body part tracking using depth information to recover human body joints in 3D coordinate system [29].”
Mining 3D Key-Pose-Motifs for Action Recognition (2016, background): “At the other extreme, the second class of work [30] classifies pose sequences by modeling all poses in a sequence, for example by Hidden Markov Models [30] or by dynamic time warping [18].”
Efficient Interaction Recognition through Positive Action Representation (2013, unknown): “Then, the Dynamic Time Warping (DTW) model is used to align the sequences of the same activity class as mentioned in [29].”