Finding repetitive patterns in 3D human motion captured data

Tang, Jeff K. T.; Leung, Howard; Komura, Taku; Shum, Hubert P. H.

doi:10.1145/1352793.1352876

Cited by 12 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, users select the interval to be edited. Then, we search for the periodic characteristic in the selected interval by using the method described in [23]. If that characteristic is found, we adjust the user-selected interval to the detected period of movement.…”

Section: Algorithm 1 Searchsimilarintervalsmentioning

confidence: 99%

A Novel Direct Manipulation Technique for Motion-editing using a Timeline-based Interface

Pantuwong

2019

ECTI-CIT

View full text Add to dashboard Cite

Recently, motion data is becoming increasingly available for creating computer animation. Motion capture is one of the systems that can generate such motion data. However, it is not suitable to capture a lot of motion due to the cost of motion capture technique, and the diculty of its postprocessing. This paper presents a timeline-based motion-editing system that enables users to perform motion-editing tasks easily and quickly. A motion sequence is summarized and displayed in the 3D environment as a set of editable icons. Users can edit the motion data by performing a sequence of operations on a single key frame or over an interval. The recorded sequence is then propagated automatically to a set of target key frames or intervals, which can be either user dened or system dened. In addition, we provide a simple interaction method for manipulating the duration of specic intervals in the motion data. Methods for combining and synchronizing two dierent motions are also provided in this system. In contrast with the previous work that allows only temporal editing, the proposed system provides editing functions for both geometry and temporal editing. We describe a user study that demonstrated the eciency of the proposed system.

show abstract

Section: Algorithm 1 Searchsimilarintervalsmentioning

confidence: 99%

A Novel Direct Manipulation Technique for Motion-editing using a Timeline-based Interface

Pantuwong

2019

ECTI-CIT

View full text Add to dashboard Cite

show abstract

“…The importance of identifying repetitive patterns-particularly cyclic patterns-in natural systems can be seen in a number of studies (Forbes & Fiume, 2005;Kovar & Gleicher, 2004;Li & Holstein, 2002;Tang, Leung, Komura, & Shum., 2008). Tang et al (2008), for example, visualize and analyze posture similarity in human motioncapture data for dancers. Posture is represented as a multidimensional vector and plotted on a point-cloud matrix.…”

Section: Evaluating Cyclic Behaviormentioning

confidence: 99%

“…For example, the number, length, and period of cycles can be determined. Tang et al (2008) propose their work as a starting point for the design of artificial systems that can generate cyclic motion, such as automated dance tutors. However, both their visual and numerical analysis techniques can also be adapted to characterize the behavior of an artificial system such as a robot.…”

Section: Evaluating Cyclic Behaviormentioning

confidence: 99%

“…Likewise, the model presented in this article aims to achieve robots capable of multiple behavior cycles of different lengths and durations at different times. To identify and characterize these behaviors, this section uses visualizations and numerical analysis based on point-cloud matrices (Merrick, 2009;Tang et al, 2008).…”

Section: Evaluating Cyclic Behavior In Robotsmentioning

confidence: 99%

“…This provides a way to understand the trade-off between exploratory behavior and exploi- tation of learned cyclic behavior. The numerical analysis described by Tang et al (2008) is adapted for robots in the following sections.…”

Section: Numerical Analysis Of Cyclic Behaviormentioning

confidence: 99%

See 2 more Smart Citations

Modeling Behavior Cycles as a Value System for Developmental Robots

Kasmarik

2010

Adaptive Behavior

View full text Add to dashboard Cite

The behavior of natural systems is governed by rhythmic behavior cycles at the biological, cognitive, and social levels. These cycles permit natural organisms to adapt their behavior to their environment for survival, behavioral efficiency, or evolutionary advantage. This article proposes a model of behavior cycles as the basis for motivated reinforcement learning in developmental robots. Motivated reinforcement learning is a machine learning technique that incorporates a value system with a trial-anderror learning component. Motivated reinforcement learning is a promising model for developmental robotics because it provides a way for artificial agents to build and adapt their skill-sets autonomously over time. However, new models and metrics are needed to scale existing motivated reinforcement learning algorithms to the complex, real-world environments inhabited by robots. This article presents two such models and an experimental evaluation on four Lego Mindstorms NXT robots. Results show that the robots can evolve measurable, structured behavior cycles adapted to their individual physical forms.

show abstract

Emulating human perception of motion similarity

Tang¹,

Leung²,

Komura³

et al. 2008

Computer Animation & Virtual

Self Cite

View full text Add to dashboard Cite

Evaluating the similarity of motions is useful for motion retrieval, motion blending, and performance analysis of dancers and athletes. Euclidean distance between corresponding joints has been widely adopted in measuring similarity of postures and hence motions. However, such a measure does not necessarily conform to the human perception of motion similarity. In this paper, we propose a new similarity measure based on machine learning techniques. We make use of the results of questionnaires from subjects answering whether arbitrary pairs of motions appear similar or not. Using the relative distance between the joints as the basic features, we train the system to compute the similarity of arbitrary pair of motions. Experimental results show that our method outperforms methods based on Euclidean distance between corresponding joints. Our method is applicable to content-based motion retrieval of human motion for large-scale database systems. It is also applicable to e-Learning systems which automatically evaluates the performance of dancers and athletes by comparing the subjects' motions with those by experts.

show abstract

Finding repetitive patterns in 3D human motion captured data

Cited by 12 publications

References 15 publications

A Novel Direct Manipulation Technique for Motion-editing using a Timeline-based Interface

A Novel Direct Manipulation Technique for Motion-editing using a Timeline-based Interface

Modeling Behavior Cycles as a Value System for Developmental Robots

Emulating human perception of motion similarity

Contact Info

Product

Resources

About