Tekane, YCTwala, BMarwala, T2015-10-052015-10-052015-01Tekane, YC, Twala, B and Marwala, T. 2015. Landscape mapping MAV using single image perspective cues. In: International Conference on Mechatronics and Robotics Engineering (ICMRE 2015), Kuala Lumpur, 17-18 January 2015, 9pp.http://hdl.handle.net/10204/8144International Conference on Mechatronics and Robotics Engineering (ICMRE 2015), Kuala Lumpur, 17-18 January 2015We consider the problem of mapping with Miniature Aerial Vehicles (MAVs) in outdoor sites with distinguishable landscapes. The primary long range sensor in these MAVs is a miniature camera. While previous approaches first try to build a 3D model in order to do mapping, our method does require a 3D model. Instead, our method first classifies the type of site the MAV is in, and the uses vision algorithms based on perspective cues to estimate the landscape location and the do mapping. We tested our method on a number of sites with different landscapes. Our experiments show that our vision algorithms are reliable, and the enable the MAV to identify landscapes and map them.enMiniature Aerial VehiclesMAVsLandscape mappingVanishing pointVision algorithmHough transformsMiniature aerial vehicleCanny edge detectorPerspective cueGraph SLAMConference PresentationTekane, Y., Twala, B., & Marwala, T. (2015). Landscape mapping MAV using single image perspective cues. http://hdl.handle.net/10204/8144Tekane, YC, B Twala, and T Marwala. "Landscape mapping MAV using single image perspective cues." (2015): http://hdl.handle.net/10204/8144Tekane Y, Twala B, Marwala T, Landscape mapping MAV using single image perspective cues; 2015. http://hdl.handle.net/10204/8144 .TY - Conference Presentation AU - Tekane, YC AU - Twala, B AU - Marwala, T AB - We consider the problem of mapping with Miniature Aerial Vehicles (MAVs) in outdoor sites with distinguishable landscapes. The primary long range sensor in these MAVs is a miniature camera. While previous approaches first try to build a 3D model in order to do mapping, our method does require a 3D model. Instead, our method first classifies the type of site the MAV is in, and the uses vision algorithms based on perspective cues to estimate the landscape location and the do mapping. We tested our method on a number of sites with different landscapes. Our experiments show that our vision algorithms are reliable, and the enable the MAV to identify landscapes and map them. DA - 2015-01 DB - ResearchSpace DP - CSIR KW - Miniature Aerial Vehicles KW - MAVs KW - Landscape mapping KW - Vanishing point KW - Vision algorithm KW - Hough transforms KW - Miniature aerial vehicle KW - Canny edge detector KW - Perspective cue KW - Graph SLAM LK - https://researchspace.csir.co.za PY - 2015 T1 - Landscape mapping MAV using single image perspective cues TI - Landscape mapping MAV using single image perspective cues UR - http://hdl.handle.net/10204/8144 ER -