A Real-Time Deep Learning Pedestrian Detector for Robot Navigation

TL;DR

This paper presents a real-time deep learning pedestrian detection method that combines ACF and CNN to enable robust and fast robot navigation in environments with pedestrians.

Contribution

It introduces a novel combination of ACF and CNN for real-time pedestrian detection tailored for robot navigation.

Findings

The detector achieves high accuracy in real-world images.

It operates in real-time suitable for robot navigation.

Robust performance demonstrated in two navigation experiments.

Abstract

A real-time Deep Learning based method for Pedestrian Detection (PD) is applied to the Human-Aware robot navigation problem. The pedestrian detector combines the Aggregate Channel Features (ACF) detector with a deep Convolutional Neural Network (CNN) in order to obtain fast and accurate performance. Our solution is firstly evaluated using a set of real images taken from onboard and offboard cameras and, then, it is validated in a typical robot navigation environment with pedestrians (two distinct experiments are conducted). The results on both tests show that our pedestrian detector is robust and fast enough to be used on robot navigation applications.