Corpus ID: 13756381

Adaptive View Planning for Aerial 3D Reconstruction of Complex Scenes

  title={Adaptive View Planning for Aerial 3D Reconstruction of Complex Scenes},
  author={Cheng Peng and Volkan Isler},
With the proliferation of small aerial vehicles, acquiring close up aerial imagery for high quality reconstruction of complex scenes is gaining importance. [...] Key Method We start by sampling a small set of views to build a coarse proxy to the scene. We then present (i)~a method that builds a view manifold for view selection, and (ii) an algorithm to select a sparse set of views. The vehicle then visits these viewpoints to cover the scene, and the procedure is repeated until reconstruction quality converges…Expand
Adaptive View Planning for Aerial 3D Reconstruction
This work presents a method that builds a set of adaptive viewing planes for efficient view selection and an algorithm to plan a trajectory that guarantees high reconstruction quality which does not deviate too much from the optimal one. Expand
Next best view planning with an unstructured representation
Qualitative results show that both approaches are able to obtain highly complete observations of several scenes with varying size and structural complexity using multiple sensor modalities and the best performing strategies for addressing each of these challenges are integrated with SEE to create SEE++. Expand
Automatic and Semantically-Aware 3D UAV Flight Planning for Image-Based 3D Reconstruction
This work proposes a 3D UAV path planning framework designed for detailed and complete small-scaled 3D reconstructions considering the semantic properties of the environment allowing for user-specified restrictions on the airspace. Expand
AR HMD Guidance for Controlled Hand-Held 3D Acquisition
A novel approach to photogrammetric acquisition that uses an AR HMD to predict a set of covering views and to interactively guide an operator to capture imagery from each view, which provides specific acquisition guidance tailored to the geometry of the scene being captured. Expand
View Selection with Geometric Uncertainty Modeling
A multi-resolution view selection method which extends the techniques to non-planar scenes and it is shown that the method can produce rich and accurate dense reconstructions with a small number of views. Expand
Automatic Pose Generation for Robotic 3-D Scanning of Mechanical Parts
This article presents an automatic pose generation approach for robotic 3-D scanning systems designed for the reverse engineering of mechanical parts, and suggests the next-best-view of the scanner from the scarce measurements. Expand


Submodular Trajectory Optimization for Aerial 3 D Scanning Supplementary Material
This section describes the high-level strategy for data acquisition, as well as the multi-view stereo processing pipeline for estimating the scene geometry and free space, and the similarity transform that maps from reconstruction coordinates to UTM coordinates using standard numerical techniques. Expand
View planning for 3D object reconstruction
A novel algorithm to select the next-best-view (NBV) for a range camera to model 3D arbitrary objects, using a volumetric representation and voxel labeling and two novel strategies to make faster the search of the NBV. Expand
Next Best View Planning for Active Model Improvement
The proposed method deploys a hierarchical uncertainty driven model refinement process designed to select vantage viewpoints based on the model’s covariance structure and appearance, as well as the camera characteristics, to determine the Next Best View (NBV). Expand
Occlusions as a Guide for Planning the Next View
A strategy for acquiring 3-D data of an unknown scene, using range images obtained by a light stripe range finder is addressed, where the foci of attention are occluded regions and the system can resolve the appearance of occlusions by analyzing them. Expand
View planning for automated three-dimensional object reconstruction and inspection
This paper surveys and compares view planning techniques for automated 3D object reconstruction and inspection by means of active, triangulation-based range sensors and suggests adequate solutions to semiautomate the scan-register-integrate tasks. Expand
Photogrammetric Camera Network Design for Micro Aerial Vehicles
This work proposes a novel camera network design algorithm suitable for MAVs for close range photogrammetry that exploits prior knowledge of the surrounding and automatically determines a set of camera positions that guarantees important constraints for image based 3D reconstruction. Expand
Next-Best-View Planning for 3D Object Reconstruction under Positioning Error
A method to plan “safe views” which are successful even when there is positioning error is proposed, based on a reevaluation of the candidate views according to their neighbors, so view points which are safer against positioning error are preferred. Expand
Optimal Reconstruction with a Small Number of Views
The results provide a view selection mechanism with provable performance guarantees which can drastically increase the speed of scene reconstruction algorithms. Expand
View Selection Strategies for Multi-View, Wide-Baseline Stereo
A multi-baseline, coarse-to-fine stereo algorithm which utilizes any number of images and multiple image scales to recover 3D depth information and the resulting depth maps are of good accuracy with a depth resolution of approximately 5mm. Expand
Overlapping camera clustering through dominant sets for scalable 3D reconstruction
This method uses camera view information available from Structure-from-Motion for computing a set of overlapping clusters suited for Multi-View Stereo reconstruction, which allows more scalable and higher quality reconstructions, while speeding up 6 times with respect to a MVS which uses all images at once. Expand