2016/05/06 by Christian Mostegel, Markus Rumpler, Mostegel, Christian +5 · 1 citation
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Infrared Target Detection Methodologies #Robotics (cs.RO)
paper · pdf · doi:10.48550/arxiv.1605.01923
openalex publication_date 2016/05/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this paper we present an autonomous system for acquiring close-range\nhigh-resolution images that maximize the quality of a later-on 3D\nreconstruction with respect to coverage, ground resolution and 3D uncertainty.\nIn contrast to previous work, our system uses the already acquired images to\npredict the confidence in the output of a dense multi-view stereo approach\nwithout executing it. This confidence encodes the likelihood of a successful\nreconstruction with respect to the observed scene and potential camera\nconstellations. Our prediction module runs in real-time and can be trained\nwithout any externally recorded ground truth. We use the confidence prediction\nfor on-site quality assurance and for planning further views that are tailored\nfor a specific multi-view stereo approach with respect to the given scene. We\ndemonstrate the capabilities of our approach with an autonomous Unmanned Aerial\nVehicle (UAV) in a challenging outdoor scenario.\n