Human Motion Prediction Based on Bidirectional-GRU and Attention Mechanism Model

被引：0
|
作者：
Sang H. [1 ]
Chen Z. [1 ]
He D. [2 ]
机构：
[1] School of Information Science & Engineering, Shenyang University of Technology, Shenyang
[2] College of Information Science & Engineering, Northeastern University, Shenyang
来源：
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics | 2019年 / 31卷 / 07期
关键词：
Deep learning; End-to-end model; Human motion prediction; Recurrent neural network;
D O I：
10.3724/SP.J.1089.2019.17354
中图分类号：
学科分类号：
摘要：
Aiming at the problem that the first frame of human motion prediction is discontinuous and the accurate prediction time is short due to the influence of uncertain factors such as motion speed and amplitude, a sequence to sequence model (BiAGRU-seq2seq) based on bidirectional GRU and attention mechanism is proposed. The model encoder section uses a bidirectional GRU, which allows data to be input from two opposite directions at the same time. The decoder section uses the GRU plus attention mechanism structure to encode the encoder output into a vector sequence containing multiple subsets. The input and output of the decoder are then simultaneously sent to the residual architecture to simulate the speed of the human body and bring the predicted value closer to the true value. In the TensorFlow framework, human motion prediction experiments were performed using the public motion capture dataset human3.6m. Experimental results demonstrate that the proposed model can not only greatly reduce the short-term motion prediction error but also accurately predict multiple motion frames. © 2019, Beijing China Science Journal Publishing Co. Ltd. All right reserved.
引用
收藏
页码：1166 / 1174
页数：8
相关论文
共 10 条
  • [1] Koppula H.S., Saxena A., Anticipating human activities for reactive robotic response, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, (2013)
  • [2] Shi J.B., Likhachev M., Sim J., Et al., Multi-hypothesis motion planning for visual object tracking, Proceedings of the IEEE International Conference on Computer Vision, pp. 619-626, (2011)
  • [3] Xu W.W., Umentani N., Chao Q.W., Et al., Sensitivity-optimized rigging for example-based real-time clothing synthesis, ACM Transactions on Graphics, 33, 4, (2014)
  • [4] Pentland A., Liu A., Modeling and prediction of human behavior, Neural Computation, 11, 1, pp. 229-242, (1999)
  • [5] Wang Z.H., Shi Q.F., Shen C.H., Et al., Bilinear programming for human activity recognition with unknown MRF graphs, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1690-1697, (2013)
  • [6] Cho K., Van Merrienboer B., Gulcehre C., Et al., Learning phrase representations using RNN encoder-decoder for statistical machine translation
  • [7] Fragkiadaki K., Levine S., Felsen P., Et al., Recurrent network models for human dynamics, Proceedings of the IEEE International Conference on Computer Vision, pp. 4346-4354, (2015)
  • [8] Jain A., Zamir A.R., Savarese S., Et al., Structural-RNN: deep learning on spatio-temporal graphs, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5308-5317, (2016)
  • [9] Martinez J., Black M.J., Romero J., On human motion prediction using recurrent neural networks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1, pp. 4674-4683, (2017)
  • [10] He K.M., Zhang X.Y., Ren S.Q., Et al., Deep residual learning for image recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1, pp. 770-778, (2016)
1