# Enhanced pedestrian trajectory prediction via overlapping field-of-view domains and integrated Kolmogorov-Arnold networks

## TL;DR

This paper introduces a new model for predicting pedestrian movement that improves accuracy by better capturing interactions and using advanced network techniques.

## Contribution

The paper introduces OV-SKTGCNN, which enhances pedestrian trajectory prediction by integrating overlapping visual domains and Kolmogorov-Arnold Networks.

## Key findings

- The model reduces Final Displacement Error by 23% on average compared to previous models.
- Average Displacement Error is reduced by 18% on the ETH and UCY datasets.
- OV-SKTGCNN better captures subtle pedestrian movement patterns.

## Abstract

Accurate pedestrian trajectory prediction is crucial for applications such as autonomous driving and crowd surveillance. This paper proposes the OV-SKTGCNN model, an enhancement to the Social-STGCNN model, aimed at addressing its low prediction accuracy and limitations in dealing with forces between pedestrians. By rigorously dividing monocular and binocular overlapping visual regions and utilizing different influence factors, the model pedestrian interactions more realistically. The Kolmogorov-Arnold Networks (KANs) combined with Temporal Convolutional Networks (TCNs) greatly improve the ability to extract temporal features. Experimental results on the ETH and UCY datasets demonstrate that the model reduces the Final Displacement Error (FDE) by an average of 23% and the Average Displacement Error (ADE) by 18% compared to Social-STGCNN. The proposed OV-SKTGCNN model demonstrates improved prediction accuracy and better captures the subtleties of pedestrian movements.