Monocular Video-Based Trailer Coupler Detection Using Multiplexer Convolutional Neural Network
Authors:
- Yousef AtoumYAYousef Atoum
- Joseph RothJRJoseph Roth
- Michael BlissMBMichael Bliss
- Wende ZhangWZWende Zhang
- Xiaoming LiuXLXiaoming Liu
- 1 October 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5478-5486
Abstract
This paper presents an automated monocular-camera-based computer vision system for autonomous self-backing-up a vehicle towards a trailer, by continuously estimating the 3D trailer coupler position and feeding it to the vehicle control system, until the alignment of the tow hitch with the trailers coupler. This system is made possible through our proposed distance-driven Multiplexer-CNN method, which selects the most suitable CNN using the estimated coupler-to-vehicle distance. The input of the multiplexer is a group made of a CNN detector, trackers, and 3D localizer. In the CNN detector, we propose a novel algorithm to provide a presence confidence score with each detection. The score reflects the existence of the target object in a region, as well as how accurate is the 2D target detection. We demonstrate the accuracy and efficiency of the system on a large trailer database. Our system achieves an estimation error of 1.4 cm when the ball reaches the coupler, while running at 18.9 FPS on a regular PC.Keywords
This publication has 22 references indexed in Scilit:
- Precise trajectory optimization for articulated wheeled vehicles in cluttered environmentsAdvances in Engineering Software, 2016
- A Visual Template-Matching Method for Articulation Angle Measurement2015
- Joint SFM and detection cues for monocular 3D localization in road scenes2015
- MUlti-Store Tracker (MUSTer): A cognitive psychology inspired approach to object tracking2015
- Long-term correlation tracking2015
- High-Speed Tracking with Kernelized Correlation FiltersIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Facial Contour Labeling via Congealing2010
- Projective Factorization of Multiple Rigid-Body Motions2007
- Active Appearance Models RevisitedInternational Journal of Computer Vision, 2004