Abstract
Digitization of human motion using skeleton representations offers exciting possibilities for a large number of applications but, at the same time, requires innovative techniques for their effective and efficient processing. Content-based processing of skeleton data has developed rapidly in recent years, focusing mainly on specialized prototypes with limited consideration of generic data management possibilities. In this survey article, we synthesize and categorize the existing approaches and outline future research challenges brought by the increasing availability of human motion data. In particular, we first discuss the problems of suitable representation and segmentation of continuous skeleton data obtained from various sources. Then, we concentrate on comparison models for assessing the similarity of time-restricted pieces of motions, as required by any content-based management operation. Next, we review the techniques for evaluating similarity queries over collections of motion sequences and filtering query-relevant parts from continuous motion streams. Finally, we summarize the usability of existing techniques in perspective application domains and discuss the new challenges related to current technological and infrastructural developments. We especially assess the existing techniques from the perspective of scalability and propose future research directions for dealing with large and diverse volumes of skeleton data.
Highlights
With the ever-increasing number of everyday facts becoming digital, the permanent computational research challenge is to develop tools that provide relevant information needed by individual users
We focus on processing similarity-based user queries over motion data provided in the form of (1) a large collection of short pre-segmented motions that often correspond to specific application semantics, (2) a large collection of long motions without explicit information about their partitioning, or (3) a pseudo-infinite stream in which a limited motion content is available at a given time moment
We mainly review different approaches for query-by-example searching in collections of pre-segmented motions, sub-sequence searching in unsegmented long motions, and detecting events in continuous streams
Summary
With the ever-increasing number of everyday facts becoming digital, the permanent computational research challenge is to develop tools that provide relevant information needed by individual users. We focus on processing similarity-based user queries over motion data provided in the form of (1) a large collection of short pre-segmented motions that often correspond to specific application semantics, (2) a large collection of long motions without explicit information about their partitioning, or (3) a pseudo-infinite stream in which a limited motion content is available at a given time moment Other works map the action recognition methods in specific application domains, e.g., gait recognition [11], martial arts [13], rehabilitation [14], or sports [15] All these surveys focus on the processing of short pre-segmented motions, leaving aside the inherent continuous character of skeleton-data recordings. Several studies cover skeleton-data acquisition approaches [5], [8], [10], [12], [13] or summarize publicly-available datasets [6]–[10]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
