Is the Pedestrian going to Cross? Answering by 2D Pose Estimation

TL;DR

This paper evaluates the effectiveness of 2D pose estimation combined with CNNs for predicting pedestrian crossing intentions in naturalistic driving conditions, achieving state-of-the-art results on the JAAD dataset.

Contribution

It introduces a CNN-based pipeline that combines detection, tracking, and pose estimation to predict pedestrian crossing actions from monocular images, validated on the JAAD dataset.

Findings

Achieves state-of-the-art accuracy on JAAD dataset

Demonstrates the usefulness of 2D pose estimation for intention prediction

Validates approach in naturalistic driving conditions

Abstract

Our recent work suggests that, thanks to nowadays powerful CNNs, image-based 2D pose estimation is a promising cue for determining pedestrian intentions such as crossing the road in the path of the ego-vehicle, stopping before entering the road, and starting to walk or bending towards the road. This statement is based on the results obtained on non-naturalistic sequences (Daimler dataset), i.e. in sequences choreographed specifically for performing the study. Fortunately, a new publicly available dataset (JAAD) has appeared recently to allow developing methods for detecting pedestrian intentions in naturalistic driving conditions; more specifically, for addressing the relevant question is the pedestrian going to cross? Accordingly, in this paper we use JAAD to assess the usefulness of 2D pose estimation for answering such a question. We combine CNN-based pedestrian detection, tracking and pose estimation to predict the crossing action from monocular images. Overall, the proposed pipeline provides new state-of-the-art results.