GRU-Based Estimation Method Without the Prior Knowledge of the Noise
The state estimation method is one of the important techniques for target tracking and those techniques based on Kalman filtering have attracted the attention of many researchers. Among these existing methods, the very basic and necessary premise is that the model of the target is with high precision and good prior knowledge of process noise as well as measurement noise are also available. However, it is quite difficult to achieve in the practical applications. Therefore, in this paper, the Gated Recurrent Unit (GRU)-based estimation method is proposed to estimate the actual moving trajectory via the simulated GPS data with noise. GRU has a good advantage in the processing of time series data, and it has a memory function for data information. In the experiment part, by comparing with the traditional Kalman method, it is found that the GRU can obtain better estimation results.
KeywordsObject tracking State estimation Kalman filtering GRU
This work was supported by National Natural Science Foundation of China (No. 61673002), and Beijing Municipal Education Commission with project No. KM201810011005 and KM201910011010.
- 1.Chavda, H.K., Dhamecha M.: Moving object tracking using PTZ camera in video surveillance system. In: 2017 International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS), pp. 263–266. IEEE (2017)Google Scholar
- 3.Shajideen, S.M.S., Preetha, V.H.: Human-computer interaction system using 2D and 3D hand gestures. In: 2018 International Conference on Emerging Trends and Innovations in Engineering and Technological Research (ICETIETR), pp. 1–4. IEEE (2018)Google Scholar
- 4.Zhou, Y., Zhou X.D., Yuan, J.H., et al.: Tracking method of moving target in complex environment. In: 2017 International Conference on Information Networking (ICOIN).pp. 668–673. IEEE (2017)Google Scholar
- 6.Jin, X.B., Lian, X.F., Shi, Y., et al.: Data driven modeling under irregular sampling. In: Proceedings of the 32nd Chinese Control Conference, pp. 4731–4734. IEEE (2013)Google Scholar
- 7.Su, W.X.: Application of Sage-Husa adaptive filtering algorithm for high precision SINS initial alignment. In: 2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing (ICCWAMTIP), pp. 359–364. IEEE (2014)Google Scholar
- 10.Zhang, Y.S., Yue, M., Zhang, R.S.: Object detection and tracking based on recurrent neural networks. In: 2018 14th IEEE International Conference on Signal Processing (ICSP), pp. 338–343. IEEE (2018)Google Scholar
- 11.Xiao, Y., Du, S., Xie, X., et al.: A Modified Speaking Rate Estimation Based on Frame-Level LSTM. In: 2018 14th IEEE International Conference on Signal Processing (ICSP), pp. 600–603. IEEE (2018)Google Scholar