DROW: Real-Time Deep Learning-Based Wheelchair Detection in 2-D Range Data
- 23 December 2016
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 2 (2) , 585-592
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.Keywords
All Related Versions
Funding Information
- EU project STRANDS (ICT-2011-600623)
This publication has 18 references indexed in Scilit:
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition2015
- Voting for Voting in Online Point Cloud Object Detection2015
- 2D laser based road obstacle classification for road safety improvement2015
- Unsupervised feature learning for 3D scene labeling2014
- Hough Networks for Head Pose Estimation and Facial Feature Localization2014
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Multi-Part People Detection Using 2D Range DataInternational Journal of Social Robotics, 2010
- Wheelchair Detection Using Cascaded Decision TreeIEEE Transactions on Information Technology in Biomedicine, 2009
- Robust Object Detection with Interleaved Categorization and SegmentationInternational Journal of Computer Vision, 2007
- Robotic assistance: an automatic wheelchair tracking and following functionality by omnidirectional vision2005