Nienaber, SKroon, RSBooysen, MJ2016-10-132016-10-132015-12Nienaber, S., Kroon, R.S. and Booysen, M.J. 2015. A comparison of low-cost monocular vision techniques for pothole distance estimation. In: IEEE Symposium Series on Computational Intelligence: IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, 8-10 December 2015, Cape Town, South Africa978-1-4799-7560-0http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7376642http://hdl.handle.net/10204/8801IEEE Symposium Series on Computational Intelligence: IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, 8-10 December 2015, Cape Town, South AfricaConsider a single camera mounted on the inside of a vehicle's windscreen used for detecting potholes and other obstacles on the road surface. This paper outlines three approaches to the depth estimation problem of determining the distance to these obstacles in the range of 5 m to 30 m. We provide an empirical evaluation of the accuracy of these approaches under various conditions, and make recommendations for when each approach is most suitable. The approaches are based on the pinhole camera model: the simplest approach is based on the geometry of similar triangles, another employs the cross-ratio of a set of collinear points, and the final approach relies on calibration of the camera matrix. We recommend the use of the cross ratio approach for a fixed camera setup and depth estimation almost directly ahead, and an approach using similar triangles when predicting distances at wide angles or adjusting the camera height may be necessary.enComputational intelligenceMonocular vision techniquesConference PresentationNienaber, S., Kroon, R., & Booysen, M. (2015). A comparison of low-cost monocular vision techniques for pothole distance estimation. IEEE. http://hdl.handle.net/10204/8801Nienaber, S, RS Kroon, and MJ Booysen. "A comparison of low-cost monocular vision techniques for pothole distance estimation." (2015): http://hdl.handle.net/10204/8801Nienaber S, Kroon R, Booysen M, A comparison of low-cost monocular vision techniques for pothole distance estimation; IEEE; 2015. http://hdl.handle.net/10204/8801 .TY - Conference Presentation AU - Nienaber, S AU - Kroon, RS AU - Booysen, MJ AB - Consider a single camera mounted on the inside of a vehicle's windscreen used for detecting potholes and other obstacles on the road surface. This paper outlines three approaches to the depth estimation problem of determining the distance to these obstacles in the range of 5 m to 30 m. We provide an empirical evaluation of the accuracy of these approaches under various conditions, and make recommendations for when each approach is most suitable. The approaches are based on the pinhole camera model: the simplest approach is based on the geometry of similar triangles, another employs the cross-ratio of a set of collinear points, and the final approach relies on calibration of the camera matrix. We recommend the use of the cross ratio approach for a fixed camera setup and depth estimation almost directly ahead, and an approach using similar triangles when predicting distances at wide angles or adjusting the camera height may be necessary. DA - 2015-12 DB - ResearchSpace DP - CSIR KW - Computational intelligence KW - Monocular vision techniques LK - https://researchspace.csir.co.za PY - 2015 SM - 978-1-4799-7560-0 T1 - A comparison of low-cost monocular vision techniques for pothole distance estimation TI - A comparison of low-cost monocular vision techniques for pothole distance estimation UR - http://hdl.handle.net/10204/8801 ER -