Pedestrian trajectory prediction method based on Informer

Abstract

The invention relates to a pedestrian trajectory prediction method based on Informer, and belongs to the technical field of computer vision and automatic driving. The method comprises the following steps: (1) carrying out position coding on a track sequence, and inputting the track sequence into an Informer-encoder to obtain a feature vector; (2) enabling a hidden variable predictor to generate hidden variables according to the feature vectors; (3) generating a track key point according to the hidden variable, and initializing a position corresponding to an Informer-decoder by using the track key point; and (4) carrying out position coding on the initialization sequence of the Informer-decoder, generating a prediction track by combining the hidden variables again, and calculating a loss function. According to the method, an Informer self-attention distillation technology, a probability sparse self-attention mechanism and a generative decoder are adopted as core technologies of a basic network, trajectory key points are predicted based on a hidden state, and then the trajectory key points are used for initializing the position corresponding to the decoder. The method can be used for trajectory prediction of an automatic driving vehicle for pedestrians, vehicles and other agents, helps the vehicle to make decisions better, and protects traffic safety.

Description

technical field [0001] The invention relates to an Informer-based pedestrian trajectory prediction method, which belongs to the technical fields of computer vision and automatic driving. Background technique [0002] The autonomous driving industry has also been hot for many years, but there is still no consensus in the industry on when it will truly realize unmanned driving. One of the most important reasons is that in complex scenes, it is difficult to make reasonable predictions about the trajectories of surrounding pedestrians. Therefore, if this problem cannot be overcome, no matter how perfect the decision-making and control technology is, it is impossible to achieve absolutely safe driverless driving. Therefore, pedestrian trajectory prediction has gradually become a hot research problem in the field of computer vision in recent years. As a vulnerable group, pedestrians most need protection from the outside world. In human driving, drivers can make correct decision...

AI Technical Summary

Problems solved by technology

[0011] The purpose of the present invention is to provide an Informer-based pedestrian trajectory prediction method with strong performance and high accuracy. To solve the problem of large memory overhead, the present invention adopts Informer's self-attention distillation technology to greatly reduce key information while retaining key information. Small memory footprint; for the problem of slow training and reasoning speed, the present invention adopts Informer's probabilistic sparse self-attention mechanism and generative decoder; for the limitations of GAN, the present invention is based on the encoder-decoder structure, and proposes a method based on implicit State Prediction Techniques for Trajectory Key Points

Images