De Saxe, Christopher C2018-11-272018-11-272018-09De Saxe, C.C. 2018. Vision-based trailer pose estimation for articulated vehicles. Dissertation submitted for the degree of Doctor of Philosophy, Department of Engineering, University of Cambridgehttps://www.repository.cam.ac.uk/handle/1810/268169http://hdl.handle.net/10204/10541Dissertation submitted for the degree of Doctor of Philosophy, Department of Engineering, University of CambridgeArticulated Heavy Goods Vehicles (HGVs) are more efficient than conventional rigid lorries, but exhibit reduced low-speed manoeuvrability and high-speed stability. Technologies such as autonomous reversing and path-following trailer steering can mitigate this, but practical limitations of the available sensing technologies restrict their commercialisation potential. This dissertation describes the development of practical vision-based articulation angle and trailer off-tracking sensing for HGVs. Chapter 1 provides a background and literature review, covering important vehicle technologies, existing commercial and experimental sensors for articulation angle and off-tracking measurement, and relevant vision-based technologies. This is followed by an introduction to pertinent computer vision theory and terminology in Chapter 2. Chapter 3 describes the development and simulation-based assessment of an articulation angle sensing concept. It utilises a rear-facing camera mounted behind the truck or tractor, and one of two proposed image processing methods: template-matching and Parallel Tracking and Mapping (PTAM). The PTAM-based method was shown to be the more accurate and versatile method in full-scale vehicle tests. RMS measurement errors of 0.4-1.6$^\circ$ were observed in tests on a tractor semi-trailer (Chapter 4), and 0.8-2.4$^\circ$ in tests on a Nordic combination with two articulation points (Chapter 5). The system requires no truck-trailer communication links or artificial markers, and is compatible with multiple trailer shapes, but was found to have increasing errors at higher articulation angles. Chapter 6 describes the development and simulation-based assessment of a trailer off-tracking sensing concept, which utilises a trailer-mounted stereo camera pair and visual odometry. The concept was evaluated in full-scale tests on a tractor semi-trailer combination in which camera location and stereo baseline were varied, presented in Chapter 7. RMS measurement errors of 0.11-0.13 m were obtained in some tests, but a sensitivity to camera alignment was discovered in others which negatively affected results. A very stiff stereo camera mount with a sub-0.5 m baseline is suggested for future experiments. A summary of the main conclusions, a review of the objectives, and recommendations for future work are given in Chapter 8. Recommendations include further refinement of both sensors, an investigation into lighting sensitivity, and alternative applications of the sensors.enArticulated vehiclesArticulation angleAutonomous reversingComputer visionHeavy Goods VehiclesLong Combination VehiclesOff-trackingPose estimationStereo visionTrailer steeringReportDe Saxe, C. C. (2018). <i>Vision-based trailer pose estimation for articulated vehicles</i> (Worklist;21032). University of Cambridge. Retrieved from http://hdl.handle.net/10204/10541De Saxe, Christopher C <i>Vision-based trailer pose estimation for articulated vehicles.</i> Worklist;21032. University of Cambridge, 2018. http://hdl.handle.net/10204/10541De Saxe CC. Vision-based trailer pose estimation for articulated vehicles. 2018 [cited yyyy month dd]. Available from: http://hdl.handle.net/10204/10541TY - Report AU - De Saxe, Christopher C AB - Articulated Heavy Goods Vehicles (HGVs) are more efficient than conventional rigid lorries, but exhibit reduced low-speed manoeuvrability and high-speed stability. Technologies such as autonomous reversing and path-following trailer steering can mitigate this, but practical limitations of the available sensing technologies restrict their commercialisation potential. This dissertation describes the development of practical vision-based articulation angle and trailer off-tracking sensing for HGVs. Chapter 1 provides a background and literature review, covering important vehicle technologies, existing commercial and experimental sensors for articulation angle and off-tracking measurement, and relevant vision-based technologies. This is followed by an introduction to pertinent computer vision theory and terminology in Chapter 2. Chapter 3 describes the development and simulation-based assessment of an articulation angle sensing concept. It utilises a rear-facing camera mounted behind the truck or tractor, and one of two proposed image processing methods: template-matching and Parallel Tracking and Mapping (PTAM). The PTAM-based method was shown to be the more accurate and versatile method in full-scale vehicle tests. RMS measurement errors of 0.4-1.6$^\circ$ were observed in tests on a tractor semi-trailer (Chapter 4), and 0.8-2.4$^\circ$ in tests on a Nordic combination with two articulation points (Chapter 5). The system requires no truck-trailer communication links or artificial markers, and is compatible with multiple trailer shapes, but was found to have increasing errors at higher articulation angles. Chapter 6 describes the development and simulation-based assessment of a trailer off-tracking sensing concept, which utilises a trailer-mounted stereo camera pair and visual odometry. The concept was evaluated in full-scale tests on a tractor semi-trailer combination in which camera location and stereo baseline were varied, presented in Chapter 7. RMS measurement errors of 0.11-0.13 m were obtained in some tests, but a sensitivity to camera alignment was discovered in others which negatively affected results. A very stiff stereo camera mount with a sub-0.5 m baseline is suggested for future experiments. A summary of the main conclusions, a review of the objectives, and recommendations for future work are given in Chapter 8. Recommendations include further refinement of both sensors, an investigation into lighting sensitivity, and alternative applications of the sensors. DA - 2018-09 DB - ResearchSpace DP - CSIR KW - Articulated vehicles KW - Articulation angle KW - Autonomous reversing KW - Computer vision KW - Heavy Goods Vehicles KW - Long Combination Vehicles KW - Off-tracking KW - Pose estimation KW - Stereo vision KW - Trailer steering LK - https://researchspace.csir.co.za PY - 2018 T1 - Vision-based trailer pose estimation for articulated vehicles TI - Vision-based trailer pose estimation for articulated vehicles UR - http://hdl.handle.net/10204/10541 ER -