DROW: Real-Time Deep Learning-Based Wheelchair Detection in 2-D Range Data

Abstract

We introduce the DROW detector, a deep learning-based object detector operating on 2-dimensional (2-D) range data. Laser scanners are lighting invariant, provide accurate 2-D range data, and typically cover a large field of view, making them interesting sensors for robotics applications. So far, research on detection in laser 2-D range data has been dominated by hand-crafted features and boosted classifiers, potentially losing performance due to suboptimal design choices. We propose a convolutional neural network (CNN) based detector for this task. We show how to effectively apply CNNs for detection in 2-D range data, and propose a depth preprocessing step and a voting scheme that significantly improve CNN performance. We demonstrate our approach on wheelchairs and walkers, obtaining state of the art detection results. Apart from the training data, none of our design choices limits the detector to these two classes, though. We provide a ROS node for our detector and release our dataset containing 464 k laser scans, out of which 24 k were annotated.