ABSTRACT
We present a real-time gesture classification system for skeletal wireframe motion. Its key components include an angular representation of the skeleton designed for recognition robustness under noisy input, a cascaded correlation-based classifier for multivariate time-series data, and a distance metric based on dynamic time-warping to evaluate the difference in motion between an acquired gesture and an oracle for the matching gesture. While the first and last tools are generic in nature and could be applied to any gesture-matching scenario, the classifier is conceived based on the assumption that the input motion adheres to a known, canonical time-base: a musical beat. On a benchmark comprising 28 gesture classes, hundreds of gesture instances recorded using the XBOX Kinect platform and performed by dozens of subjects for each gesture class, our classifier has an average accuracy of 96:9%, for approximately 4-second skeletal motion recordings. This accuracy is remarkable given the input noise from the real-time depth sensor.
Supplemental Material
Available for Download
- {AF02} Arikan O., Forsyth D. A.: Interactive motion generation from examples. ACM Trans. Graph. (2002). 2 Google ScholarDigital Library
- {BD01} Bobick A., Davis J.: The recognition of human movement using temporal templates. IEEE Trans. on Pattern Anal. and Machine Intell (2001). 2 Google ScholarDigital Library
- {BH00} Brand M., Hertzmann A.: Style machines. In Proc. of the conf. on Computer graphics and interactive techniques (2000), SIGGRAPH '00. 2 Google ScholarDigital Library
- {Bis06} Bishop C.: Pattern recognition and machine learning, vol. 4. Springer New York, 2006. 6, 7 Google ScholarDigital Library
- {BSP*04} Barbič J., Safonova A., Pan J.-Y., Faloutsos C., Hodgins J. K., Pollard N. S.: Segmenting motion capture data into distinct behaviors. In Proc. of Graphics Interface (2004). 2 Google ScholarDigital Library
- {CB95} Campbell L., Bobick A.: Recognition of human body motion using phase space constraints. In Proc. of Intl. Conf. of Computer Vision (1995). 2 Google ScholarDigital Library
- {FF05} Forbes K., Fiume E.: An efficient search algorithm for motion data using weighted pca. In Proc. of the ACM SIGGRAPH/Eurographics Symposium on Computer animation (2005). 3 Google ScholarDigital Library
- {FRM94} Faloutsos C., Ranganathan M., Manolopoulos Y.: Fast subsequence matching in time-series databases. In Proc. of the ACM SIGMOD (1994). 3 Google ScholarDigital Library
- {Har} Harmonix Music Systems: www.dancecentral.com. 1Google Scholar
- {HGP04} Hsu E., Gentry S., Popović J.: Example-based control of human motion. In Proc. of the ACM SIGGRAPH/Eurographics symposium on Computer animation (2004). 1 Google ScholarDigital Library
- {IWZL09} Ishigaki S., White T., Zordan V. B., Liu C. K.: Performance-based control interface for character animation. ACM Trans. Graph. (2009). 2 Google ScholarDigital Library
- {Joh73} Johansson G.: Visual perception of biological motion and a model for its analysis. Perceiving events and objects (1973). 2Google Scholar
- {Keo02} Keogh E.: Exact indexing of dynamic time warping. In Proc of the Intl. conf. on VLDB (2002). 3 Google ScholarDigital Library
- {KGP02} Kovar L., Gleicher M., Pighin F.: Motion graphs. ACM Trans. Graph. (2002). 2 Google ScholarDigital Library
- {KOF05} Kirk A., O'Brien J., Forsyth D.: Skeletal parameter estimation from optical motion capture data. In Proc. of Conf. Computer Vision and Pattern Recognition (2005). 3 Google ScholarDigital Library
- {KPS03} Kim T., Park S., Shin S.: Rhythmic-motion synthesis based on motion-beat analysis. ACM Trans. Graph. (2003). 1 Google ScholarDigital Library
- {KPZ*04} Keogh E., Palpanas T., Zordan V., Gunopulos D., Cardle M.: Indexing large human-motion databases. In Proc. of the Intl. Conf. on VLDB (2004). 2, 3 Google ScholarDigital Library
- {LCR*02} Lee J., Chai J., Reitsma P., Hodgins J., Pollard N.: Interactive control of avatars animated with human motion data. ACM Trans. Graph. (2002). 2 Google ScholarDigital Library
- {LNL05} Lv F., Nevatia R., Lee M. W.: 3D human action recognition using spatio-temporal motion templates. In Computer Vision in Human-Computer Interaction (2005). 2 Google ScholarDigital Library
- {LZWM05} Liu G., Zhang J., Wang W., McMillan L.: A system for analyzing and indexing human-motion databases. In Proc. of the ACM SIGMOD (2005). 3 Google ScholarDigital Library
- {MR06} Müller M., Röder T.: Motion templates for automatic classification and retrieval of motion capture data. In Proc. of the ACM SIGGRAPH/Eurographics Symposium on Computer animation (2006). 2, 3 Google ScholarDigital Library
- {MRC05} Müller M., Röder T., Clausen M.: Efficient content-based retrieval of motion capture data. In ACM SIGGRAPH (2005). 3 Google ScholarDigital Library
- {OFH08} Onuma K., Faloutsos C., Hodgins J.: FMDistance: A fast and effective distance function for motion capture data. Short Papers Proc. of EUROGRAPHICS (2008). 3, 9Google Scholar
- {RCB02} Rose C., Cohen M. F., Bodenheimer B.: Verbs and adverbs: Multidimensional motion interpolation. IEEE Computer Graphics and Applications (2002). 10 Google ScholarDigital Library
- {SFC*11} Shotton J., Fitzgibbon A., Cook M., Sharp T., Finocchio M., Moore R., Kipman A., Blake A.: Real-time human pose recognition in parts from single depth images. In Proc. Conf. Computer Vision and Pattern Recognition (2011). 3 Google ScholarDigital Library
- {SH08} Slyper R., Hodgins J.: Action capture with accelerometers. In Proc. of the ACM SIGGRAPH/Eurographics Symposium on Computer Animation (2008). 9 Google ScholarDigital Library
- {SLC04} Schuldt C., Laptev I., Caputo B.: Recognizing human actions: A local SVM approach. In Proc. Intl. Conf. on Pattern Recognition (2004). 2 Google ScholarDigital Library
- {TC02} Tzanetakis G., Cook P.: Musical genre classification of audio signals. IEEE Trans. on Speech and Audio Processing (2002). 5Google Scholar
- {WTK87} Witkin A., Terzopoulos D., Kass M.: Signal matching through scale space. Intl. Journal of Computer Vision (1987). 6Google Scholar
Index Terms
- Real-time classification of dance gestures from skeleton animation
Recommendations
A real time vision-based hand gestures recognition system
ISICA'10: Proceedings of the 5th international conference on Advances in computation and intelligenceHand gesture recognition is an important aspect in Human-Computer interaction, and can be used in various applications, such as virtual reality and computer games. In this paper, we propose a real time hand gesture recognition system. It includes three ...
Real-Time Natural Hand Gestures
The authors introduces the methods and implementations of a hand visualization system they created that can generate natural hand gestures in real time. This system can be used to provide ground truth data for research on human hand gesture analysis and ...
Real-Time Robotic Hand Control Using Hand Gestures
ICMLC '10: Proceedings of the 2010 Second International Conference on Machine Learning and Computingthis paper presents a new approach for controlling robotic hand or an individual robot by merely showing hand gestures in front of a camera. With the help of this technique one can pose a hand gesture in the vision range of a robot and corresponding to ...
Comments