Skip to main content

Skeleton-based bio-inspired human activity prediction for real-time human–robot interaction

Abstract

Activity prediction is an essential task in practical human-centered robotics applications, such as security, assisted living, etc., which is targeted at inferring ongoing human activities based on incomplete observations. To address this challenging problem, we introduce a novel bio-inspired predictive orientation decomposition (BIPOD) approach to construct representations of people from 3D skeleton trajectories. BIPOD is invariant to scales and viewpoints, runs in real-time on basic computer systems, and is able to recognize and predict activities in an online fashion. Our approach is inspired by biological research in human anatomy. To capture spatio-temporal information of human motions, we spatially decompose 3D human skeleton trajectories and project them onto three anatomical planes (i.e., coronal, transverse and sagittal planes); then, we describe short-term time information of joint motions and encode high-order temporal dependencies. By using Extended Kalman Filters to estimate future skeleton trajectories, we endow our BIPOD representation with the critical capabilities to reduce noisy skeleton observation data and predict the ongoing activities. Experiments on benchmark datasets have shown that our BIPOD representation significantly outperforms previous methods for real-time human activity classification and prediction from 3D skeleton trajectories. Empirical studies using TurtleBot2 and Baxter humanoid robots have also validated that our BIPOD method obtains promising performance, in terms of both accuracy and efficiency, making BIPOD a fast, simple, yet powerful representation for low-latency online activity prediction in human–robot interaction applications.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Notes

  1. 1.

    The code and data are publicly available at: http://hcr.mines.edu/code/bipod.html.

  2. 2.

    MSR Daily Activity 3D dataset: http://research.microsoft.com/en-us/um/people/zliu/actionrecorsrc.

  3. 3.

    HDM05 motion capture dataset: http://resources.mpi-inf.mpg.de/HDM05.

References

  1. Aggarwal, J., & Xia, L. (2014). Human activity recognition from 3D data: A review. Pattern Recognition Letters, 48, 70–80.

    Article  Google Scholar 

  2. Akgun, B., Cakmak, M., Jiang, K., & Thomaz, A. (2012). Keyframe-based learning from demonstration. Internation Journal of Social Robotics, 4(4), 343–355.

    Article  Google Scholar 

  3. Berndt, H., Emmert, J., & Dietmayer, K. (2008). Continuous driver intention recognition with hidden Markov models. In Intelligent Transportation Systems (pp. 1189–1194).

  4. Bi, L., Yang, X., & Wang, C. (2013). Inferring driver intentions using a driver model based on queuing network. In Intelligent Vehicles Symposium (pp. 1387–1391).

  5. Bosurgi, G., D’Andrea, A., & Pellegrino, O. (2014). Prediction of drivers’ visual strategy using an analytical model. Journal of Transportation Safety & Security, 7, 153–173.

    Article  Google Scholar 

  6. Boubou, S., & Suzuki, E. (2015). Classifying actions based on histogram of oriented velocity vectors. Journal of Intelligent Information Systems, 44(1), 49–65.

    Article  Google Scholar 

  7. Boussemart, Y., & Cummings, M. L. (2011). Predictive models of human supervisory control behavioral patterns using hidden semi-Markov models. Engineering Applications of Artifical Intelligence, 24, 1252–1262.

    Article  Google Scholar 

  8. Chang, C. C., & Lin, C. J. (2011). LIBSVM: A library for support vector machines. ACM Transaction on Intelligent Systems and Technology, 2, 27:1–27:27.

    Google Scholar 

  9. Charles, J., Everingham, M. (2011). Learning shape models for monocular human pose estimation from the Microsoft Xbox Kinect. In IEEE international conference on computer vision.

  10. Chaudhry, R., Ofli, F., Kurillo, G., Bajcsy, R., & Vidal, R. (2013). Bio-inspired dynamic 3D discriminative skeletal features for human action recognition. In IEEE conference on computer vision and pattern recognition workshop.

  11. Chen, G., Giuliani, M., Clarke, D., Gaschler, A., & Knoll, A. (2014). Action recognition using ensemble weighted multi-instance learning. In IEEE international conference on robotics and automation.

  12. Dai, F., Zhang, J., & Lu, T. (2011). The study of driver’s starting intentions. In Mechanic Automation and Control Engineering (pp. 2758–2761).

  13. Du, Y., Wang, W., & Wang, L. (2015). Hierarchical recurrent neural network for skeleton based action recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1110–1118).

  14. Einicke, G., & White, L. (1999). Robust extended Kalman filtering. IEEE Transactions on Signal Processing, 47(9), 2596–2599.

    Article  MATH  Google Scholar 

  15. Ellis, C., Masood, S. Z., Tappen, M. F., Laviola, J. J, Jr., & Sukthankar, R. (2013). Exploring the trade-off between accuracy and observational latency in action recognition. International Journal of Computer Vision, 101(3), 420–436.

    Article  Google Scholar 

  16. Ganapathi, V., Plagemann, C., Koller, D., & Thrun, S. (2010). Real time motion capture using a single time-of-flight camera. In IEEE conference on computer vision and pattern recognition.

  17. Georgiou, T., & Demiris, Y. (2015). Predicting car states through learned models of vehicle dynamics and user behaviours. In Intelligent vehicles symposium (pp. 1240–1245).

  18. Girshick, R., Shotton, J., Kohli, P., Criminisi, A., & Fitzgibbon, A. (2011). Efficient regression of general-activity human poses from depth images. In IEEE international conference on computer vision.

  19. Gowayyed, M. A., Torki, M., Hussein, M. E., & El-Saban, M. (2013). Histogram of oriented displacements (HOD): Describing trajectories of human joints for action recognition. In International joint conference on artificial intelligence.

  20. Gray, H. (1973). Anatomy of the human body. Philadelphia: Lea & Febiger.

    Google Scholar 

  21. Han, F., Reily, B., Hoff, W., & Zhang, H. (2016). Space-time representation of people based on 3D skeletal data: A review. ArXiv e-prints 1601.01006.

  22. Han, F., Reily, B., Hoff, W., & Zhang, H. (2017). Space-time representation of people based on 3d skeletal data: A review. Computer Vision and Image Understanding, 158, 85–105.

    Article  Google Scholar 

  23. Harandi, M., Sanderson, C., Hartley, R., & Lovell, B. (2012). Sparse coding and dictionary learning for symmetric positive definite matrices: A kernel approach. Computer Vision-ECCV, 2012, 216–229.

    Google Scholar 

  24. He, L., Cf, Zong, & Wang, C. (2012). Driving intention recognition and behaviour prediction based on a double-layer hidden Markov model. Journal of Zhejiang University, 13, 208–217.

    Article  Google Scholar 

  25. Hoai, M., & De la Torre, F. (2014). Max-margin early event detectors. International Journal of Computer Vision, 107(2), 191–202.

    MathSciNet  Article  Google Scholar 

  26. Hoare, J., & Parker, L. (2010). Using on-line conditional random fields to determine human intent for peer-to-peer human robot teaming. In IEEE/RSJ international conference on intelligent robots and systems.

  27. Hussein, M. E., Torki, M., Gowayyed, M. A., & El-Saban, M. (2013). Human action recognition using a temporal hierarchy of covariance descriptors on 3D joint locations. In International joint conference on artificial intelligence.

  28. Jin, L., Hou, H., & Jiang, Y. (2011). Driver intention recognition based on continuous hidden Markov model. In Transportation, Mechanical, and Electrical Engineering (pp. 739–742).

  29. Jung, H. Y., Lee, S., Heo, Y. S., & Yun, I. D. (2015). Random tree walk toward instantaneous 3D human pose estimation. In IEEE conference on computer vision and pattern recognition.

  30. Kim, Y., Chen, J., Chang, M. C., Wang, X., Provost, E. M., & Lyu, S. (2015). Modeling transition patterns between events for temporal human action segmentation and classification. In IEEE international conference and workshops on automatic face and gesture recognition (FG), Ljubljana (pp. 1–8).

  31. Koppula, H. S., Rudhir, G., & Saxena, A. (2013). Learning human activities and object affordances from RGB-D videos. The International Journal of Robotics Research, 32, 951–970.

    Article  Google Scholar 

  32. Li, K., & Fu, Y. (2014). Prediction of human activity by discovering temporal sequence patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36, 1644–1657.

    Article  Google Scholar 

  33. Li, K., Hu, J., & Fu, Y. (2012). Modeling complex temporal composition of actionlets for activity prediction. In European conference on computer vision.

  34. Liu, Q., & Cao, X. (2012). Action recognition using subtensor constraint. In European conference on computer vision.

  35. López-Mendez, A., Gall, J., Casas, J. R., & Gool, L. J. V. (2012). Metric learning from poses for temporal clustering of human motion. In British machine vision conference.

  36. Luo, J., Wang, W., & Qi, H. (2013). Group sparsity and geometry constrained dictionary learning for action recognition from depth maps. In IEEE international conference on computer vision.

  37. Mandel, J. (1982). Use of the singular value decomposition in regression analysis. The American Statistician, 36(1), 15–24.

    Google Scholar 

  38. McGinnis, M. (1999). Bioregionalism: The tug and pull of place. London: Routledge.

    Google Scholar 

  39. Meiring, G. A. M., & Myburgh, H. C. (2015). A review of intelligent driving style analysis systems and related artificial intelligence algorithms. Sensors, 15, 30653–30682.

    Article  Google Scholar 

  40. Mori, A., Uchida, S., Kurazume, R., Taniguchi, R. I., Hasegawa, T., & Sakoe, H. (2006). Early recognition and prediction of gestures. In International conference on pattern recognition.

  41. Müller, M., Röder, T., Clausen, M., Eberhardt, B., Krüger, B., & Weber, A. (2007). Documentation mocap database HDM05. Technical report, Universität Bonn.

  42. Niebles, J. C., & Fei-Fei, L. (2007). A hierarchical model of shape and appearance for human action classification. In IEEE conference on computer vision and pattern recognition.

  43. Nikolaidis, S., Hsu, D., & Srinivasa, S. (2017). Human-robot mutual adaptation in collaborative tasks: Models and experiments. The International Journal of Robotics Research, 36(5–7), 618–634.

    Article  Google Scholar 

  44. Ofli, F., Chaudhry, R., Kurillo, G., Vidal, R., & Bajcsy, R. (2014). Sequence of the most informative joints (SMIJ): A new representation for human skeletal action recognition. Journal of Visual Communication and Image Representation, 25(1), 24–38.

    Article  Google Scholar 

  45. Pentland, A., & Liu, A. (1999). Modeling and prediction of human behavior. Neural Computation, 11(1), 229–242.

    Article  Google Scholar 

  46. Perez-D’Arpino, C., & Shah, J. A. (2015). Fast target prediction of human reaching motion for cooperative human-robot manipulation tasks using time series classification. In 2015 IEEE international conference on robotics and automation (ICRA) (pp. 6175–6182). IEEE.

  47. Pieropan, A., Salvi, G., Pauwels, K., & Kjellstrom, H. (2014). Audio-visual classification and detection of human manipulation actions. In IEEE/RSJ international conference on intelligent robots and systems.

  48. Plagemann, C., Ganapathi, V., Koller, D., & Thrun, S. (2010). Real-time identification and localization of body parts from depth images. In IEEE international conference on robotics and automation.

  49. Rahmani, H., Mahmood, A., Mian, A., & Huynh, D. (2014). Real time action recognition using histograms of depth gradients and random decision forests. In IEEE winter conference on applications of computer vision.

  50. Ryoo, M. S. (2011). Human activity prediction: Early recognition of ongoing activities from streaming videos. In International conference on computer vision.

  51. Ryoo, M., Fuchs, T. J., Xia, L., Aggarwal, J. K., & Matthies, L. (2015). Robot-centric activity prediction from first-person videos: What will they do to me? In Proceedings of the tenth annual ACM/IEEE international conference on human–robot interaction (pp. 295–302). ACM.

  52. Ryoo, M. S., Grauman, K., & Aggarwal, J. K. (2010). A task-driven intelligent workspace system to provide guidance feedback. Computer Vision and Image Understanding, 114(5), 520–534.

    Article  Google Scholar 

  53. Schwarz, L. A., Mkhitaryan, A., Mateus, D., & Navab, N. (2012). Human skeleton tracking from depth data using geodesic distances and optical flow. Image and Vision Computing, 30(3), 217–226.

    Article  Google Scholar 

  54. Seidenari, L., Varano, V., Berretti, S., Del Bimbo, A., & Pala, P. (2013). Recognizing actions from depth cameras as weakly aligned multi-part bag-of-poses. In IEEE conference on computer vision and pattern recognition workshops.

  55. Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., & Blake, A. (2011). Real-time human pose recognition in parts from single depth images. In IEEE conference on computer vision and pattern recognition.

  56. Sung, J., Ponce, C., Selman, B., & Saxena, A. (2012). Unstructured human activity detection from RGBD images. In IEEE international conference on robotics and automation.

  57. Vantigodi, S., & Babu, R. V. (2013). Real-time human action recognition from motion capture data. In National conference on computer vision, pattern recognition, image processing and graphics.

  58. Vedaldi, A., & Zisserman, A. (2012). Efficient additive kernels via explicit feature maps. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(3), 480–492.

    Article  Google Scholar 

  59. Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In IEEE conference on computer vision and pattern recognition.

  60. Wang, J., Liu, Z., Wu, Y., & Yuan, J. (2012). Mining actionlet ensemble for action recognition with depth cameras. In IEEE conference on computer vision and pattern recognition.

  61. Wang, J., Liu, Z., Wu, Y., & Yuan, J. (2014a). Learning actionlet ensemble for 3D human action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(5), 914–927.

    Article  Google Scholar 

  62. Wang, W., Xi, J., & Chen, H. (2014b). Modeling and recognizing driver behavior based on driving data: A survey. Mathematical Problems in Engineering, 2014, 245641. https://doi.org/10.1155/2014/245641.

  63. Wang, Z., Boularias, A., Mulling, K., Scholkopf, B., & Peters, J. (2014c). Anticipatory action selection for human–robot table tennis. Artificial Intelligence, 247, 399–414.

    MathSciNet  Article  MATH  Google Scholar 

  64. Wu, D., & Shao, L. (2014). Leveraging hierarchical parametric networks for skeletal joints action segmentation and recognition. In IEEE conference on computer vision and pattern recognition.

  65. Xia, L., & Aggarwal, J. K. (2013). Spatio-temporal depth cuboid similarity feature for activity recognition using depth camera. In IEEE conference on computer vision and pattern recognition.

  66. Yang, X., Tian, Y. (2012). EigenJoints-based action recognition using Naï–Bayes-Nearest-Neighbor. In IEEE conference on computer vision and pattern recognition workshop.

  67. Yang, X., & Tian, Y. (2014). Effective 3D action recognition using EigenJoints. Journal of Visual Communication and Image Representation, 25(1), 2–11.

    MathSciNet  Article  Google Scholar 

  68. Yokochi, C., & Rohen, J. W. (2006). Color atlas of anatomy: A photographic study of the human body. Philadelphia: Lippincott Williams & Wilkins.

    Google Scholar 

  69. Yu, G., Yuan, J., & Liu, Z. (2012). Predicting human activities using spatio-temporal structure of interest points. In ACM international conference on multimedia.

  70. Yu, M., Liu, L., & Shao, L. (2016). Structure-preserving binary representations for RGB-D action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(8), 1651–1664.

    Article  Google Scholar 

  71. Zanfir, M., Leordeanu, M., & Sminchisescu, C. (2013). The moving pose: An efficient 3D kinematics descriptor for low-latency action recognition and detection. In IEEE international conference on computer vision.

  72. Zhang, H., & Parker, L. (2011). 4-dimensional local spatio-temporal features for human activity recognition. In IEEE/RSJ international conference on intelligent robots and systems.

  73. Zhang, H., Reardon, C. M., & Parker, L. E. (2013). Real-time multiple human perception with color-depth cameras on a mobile robot. IEEE Transactions on Cybernetics, 43(5), 1429–1441.

    Article  Google Scholar 

  74. Zhao, X., Li, X., Pang, C., Zhu, X., & Sheng, Q. Z. (2013). Online human gesture recognition from motion data streams. In ACM international conference on multimedia.

  75. Zhu, W., Lan, C., Xing, J., Zeng, W., Li, Y., Shen, L., & Xie, X. (2016). Co-occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks. arXiv preprint arXiv:160307772.

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Brian Reily.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Reily, B., Han, F., Parker, L.E. et al. Skeleton-based bio-inspired human activity prediction for real-time human–robot interaction. Auton Robot 42, 1281–1298 (2018). https://doi.org/10.1007/s10514-017-9692-3

Download citation

Keywords

  • Human representation
  • Activity classification
  • Activity prediction
  • Real-time human–robot interaction