Multi-modal trajectory prediction method for pedestrians in complex scene

Abstract

The invention discloses a multi-modal trajectory prediction method for pedestrians in a complex scene. The method comprises the following steps: performing picture feature extraction by using a 16-layer convolutional neural network of a visual geometry group; performing feature processing on the trajectory data by using a full connection layer; inputting a trajectory data feature vector VS to enter a generative adversarial network to complete a coding and decoding network function; inputting picture feature data and track feature data to physics, wherein a social attention module considers terrain limitation and pedestrian interaction; obtaining a better track generation prediction result through the updated generator part; and obtaining a stable trajectory prediction model SPM. Accordingto the method, the prediction precision can be effectively improved, a plurality of reasonable prediction tracks can be generated, the related terrain limitation information can be extracted accordingto the feature information of the original picture, and the social interaction situation between different pedestrians in the same complex scene can be considered. The method can predict the future track of the pedestrian more quickly and accurately.

Description

technical field [0001] The invention relates to a multimodal trajectory prediction technology, in particular to a multimodal trajectory prediction method for pedestrians in complex scenes. Background technique [0002] In modern Chinese society, as the population continues to increase, the resulting complex situations are becoming more and more common, such as park assemblies, railway station squares, large concert entrances, marathon sports, etc. In these complex scenes, we often have to consider different possible social and even public security issues such as pedestrian gathering, dispersal, risk avoidance, and queuing. In such a vast and complex scene, if only manual recognition is used to regulate and manage the current scene, The efficiency is too low, which greatly affects the speed of crowd diversion and the efficiency of safety avoidance. Therefore, the prediction of the future trend of pedestrian trajectories in complex scenes must be closely related to the latest...

AI Technical Summary

Problems solved by technology

Therefore, so far, for the pedestrian trajectory prediction problem in complex scenes, the overall factors considered are not comprehensive, and the corresponding methods used are not completely prepared for trajectory prediction, resulting in the accuracy of pedestrian trajectory prediction problems in complex scenes. promote

Images