Predicting Road Crossing Behaviour using Pose Detection and Sequence Modelling

TL;DR

This paper presents an end-to-end deep learning framework combining pose detection and sequence modeling to predict pedestrian crossing intent, enhancing autonomous vehicle perception systems.

Contribution

It introduces a novel integration of pose detection with sequence models for predicting crossing intent, comparing GRU, LSTM, and 1D CNN for accuracy and speed.

Findings

GRU outperformed LSTM in prediction accuracy.

1D CNN was the fastest model.

Pose-based sequence modeling improves crossing intent prediction.

Abstract

The world is constantly moving towards AI based systems and autonomous vehicles are now reality in different parts of the world. These vehicles require sensors and cameras to detect objects and maneuver according to that. It becomes important to for such vehicles to also predict from a distant if a person is about to cross a road or not. The current study focused on predicting the intent of crossing the road by pedestrians in an experimental setup. The study involved working with deep learning models to predict poses and sequence modelling for temporal predictions. The study analysed three different sequence modelling to understand the prediction behaviour and it was found out that GRU was better in predicting the intent compared to LSTM model but 1D CNN was the best model in terms of speed. The study involved video analysis, and the output of pose detection model was integrated later on to sequence modelling techniques for an end-to-end deep learning framework for predicting road crossing intents.