A trajectory recovery method based on depth learning and Kalman filter correction

Abstract

The invention discloses a trajectory recovery method based on depth learning and Kalman filter correction, which comprises the following steps: S1, discretization of trajectory points; S2,loop NeuralNetwork and Trajectory Modeling; S3, trajectory recovery; S4, using spatio-temporal attention mechanism, obtains attention model based on sequence-to-sequence model; S5, combines Kalman filter and circulating neural network, introduces Kalman filter to optimize the mean square error, cooperatively trains the Kalman filter and the attention model, and obtains the final model. The invention providesa trajectory recovery method based on depth learning and Kalman filter correction, the transfer law between the trajectory points is modeled by the loop neural network. The attention mechanism in depth learning is used to help trajectory recovery. Finally, Kalman filter is introduced to model the movement of the object in time and space, which reduces the unexplainability and error of depth learning model, has stronger explainability, and reduces the error of trajectory recovery.

Description

technical field [0001] The present invention relates to the field of trajectory data mining, and more specifically relates to a trajectory recovery method based on deep learning and Kalman filter correction. Background technique [0002] The biggest difference between the current solution to the trajectory recovery problem and the previous trajectory recovery scheme is that the existing solutions are all data-driven. By mining and analyzing a large amount of historical data, it is possible to restore the trajectory from a low sampling rate to a high sampling rate very accurately. [0003] However, the existing schemes are still not enough for the utilization of data. Most of the solutions stop at simply counting the data, and then search for the optimal trajectory through complex heuristic search schemes. These schemes cannot capture to complex transfer laws between trajectory points. [0004] On the other hand, with the rise of deep learning, although the deep learning mo...

AI Technical Summary

Problems solved by technology

[0003] However, the existing schemes are still not enough for the utilization of data. Most of the solutions stop at simply counting the data, and then search for the optimal trajectory through complex heuristic search schemes. These schemes cannot capture to complex transfer laws between trajectory points

[0004] On the other hand, with the rise of deep learning, although the deep learning model can capture the complex laws of the data and can integrate multiple information to help, the behavior of the deep learning model is difficult to explain, and it cannot show the modeling Spatiotemporal information, which can also cause problems when modeling trajectories

Images