1,720,984 research outputs found
Improving Multi-View Stereo via Super-Resolution
Full text linkToday, Multi-View Stereo techniques can reconstruct robust and detailed 3D models, especially when starting from high-resolution images. However, there are cases in which the resolution of input images is relatively low, for instance, when dealing with old photos or when hardware constrains the amount of data acquired. This paper shows how increasing the resolution of such input images through Super-Resolution techniques reflects in quality improvements of the reconstructed 3D models. We show that applying a Super-Resolution step before recovering the depth maps leads to a better 3D model both in the case of patchmatch and deep learning Multi-View Stereo algorithms. In detail, the use of Super-Resolution improves the average fl score of reconstructed models. It turns out to be particularly effective in the case of scenes rich in texture, such as outdoor landscapes
Background subtraction by combining Temporal and Spatio-Temporal histograms in the presence of camera movement
Full text linkBackground subtraction is the classical approach to differentiate moving objects in a scene from the static background when the camera is fixed. If the fixed camera assumption does not hold, a frame registration step is followed by the background subtraction. However, this registration step cannot perfectly compensate camera motion, thus errors like translations of pixels from their true registered position occur. In this paper, we overcome these errors with a simple, but effective background subtraction algorithm that combines Temporal and Spatio-Temporal approaches. The former models the temporal intensity distribution of each individual pixel. The latter classifies foreground and background pixels, taking into account the intensity distribution of each pixels' neighborhood. The experimental results show that our algorithm outperforms the state-of-the-art systems in the presence of jitter, in spite of its simplicity
Efficient moving point handling for incremental 3D manifold reconstruction
Full text linkAs incremental Structure from Motion algorithms become effective, a good sparse point cloud representing the map of the scene becomes available frame-by-frame. From the 3D Delaunay triangulation of these points, state-of-the-art algorithms build a manifold rough model of the scene. These algorithms integrate incrementally new points to the 3D reconstruction only if their position estimate does not change. Indeed, whenever a point moves in a 3D Delaunay triangulation, for instance because its estimation gets refined, a set of tetrahedra have to be removed and replaced with new ones to maintain the Delaunay property; the management of the manifold reconstruction becomes thus complex and it entails a potentially big overhead. In this paper we investigate different approaches and we propose an efficient policy to deal with moving points in the manifold estimation process. We tested our approach with four sequences of the KITTI dataset and we show the effectiveness of our proposal in comparison with state-of-the-art approaches
Incremental Reconstruction of Urban Environments by Edge-Points Delaunay Triangulation
No full textUrban reconstruction from a video captured by a surveying vehicle constitutes a core module of automated mapping. When computational power represents a limited resource and, a detailed map is not the primary goal, the reconstruction can be performed incrementally, from a monocular video, carving a 3D Delaunay triangulation of sparse points; this allows online incremental mapping for tasks such as traversability analysis or obstacle avoidance. To exploit the sharp edges of urban landscape, we propose to use a Delaunay triangulation of Edge-Points, which are the 3D points corresponding to image edges. These points constrain the edges of the 3D Delaunay triangulation to real-world edges. Besides the use of the Edge-Points, a second contribution of this paper is the Inverse Cone Heuristic that preemptively avoids the creation of artifacts in the reconstructed manifold surface. We force the reconstruction of a manifold surface since it makes it possible to apply computer graphics or photometric refinement algorithms to the output mesh. We evaluated our approach on four real sequences of the public available KITTI dataset by comparing the incremental reconstruction against Velodyne measurements
3D image processing of vehicular trajectories in roundabouts
No full textVehicular trajectory analysis is a challenging task both for safety and capacity concerns in road transportation. In particular, vehicular trajectories on roundabouts should be carefully designed in order to achieve desired performance. Therefore, the analysis of what happens on existing roundabouts is a key analytical tool in propelling the drafting of new design norms and in correcting building errors. Difficulties in analysing, by visual tracking, vehicle trajectories on roundabouts are known; for instance, different perspective effects on vehicle outlines during circulation, due to the way cameras are pointed, negatively affect precision
both for vehicle position and speed estimation in 2D tracking. The research described in this paper overcomes the above mentioned problems and faces the trajectory tracking in
roundabouts by estimating the true 3D position of each vehicle. Two different algorithms are investigated both based on a model based smoothing Montecarlo approach: the Viterbi
algorithm and the Particle Smoother. The model used in this research for vehicles is a parallelepiped whose dimensions are directly estimated from images inferring vehicular class:
cars, trucks or motorbikes. Both algorithms are tested and compared on data collected in one working roundabouts with two different set-ups. 3D tracking presents a higher complexity to be implemented since the object to be reconstructed needs to be modelled to retrieve its
position and orientation from its 2D projection on the image plane. On the other hand, performance is enhanced and precision in trajectory and speed reconstruction (especially with the Particle Smoother algorithm) is not far from that obtainable by a RTK-GPS system. This new approach allows a better reconstruction of flow features in roundabouts and hence provides researchers with a very accurate tool for the analysis of roundabout performance, applicable also to other types of road infrastructures
A comparison of two Monte Carlo algorithms for 3D vehicle trajectory reconstruction in roundabouts
Full text linkVisual vehicular trajectory analysis and reconstruction represent two relevant tasks both for safety and capacity concerns in road transportation. Especially in the presence of roundabouts, the perspective effects on vehicles projection on the image plane can be overcome by reconstructing their 3D positions with a 3D tracking algorithm. In this paper we compare two different Monte Carlo approaches to 3D model-based tracking: the Viterbi algorithm and the Particle Smoother. We tested the algorithms on a simulated dataset and on real data collected in one working roundabout with two different setups (single and multiple cameras). The Viterbi algorithm estimates the Maximum A-Posteriori solution from a sample-based state discretization, but, thanks to its continuous state representation, the Particle Smoother overcomes the Viterbi algorithm showing better performance and accuracy
Real-Time CPU-Based Large-Scale Three-Dimensional Mesh Reconstruction
No full textIn robotics, especially in this era of autonomous driving, mapping is one key ability of a robot to be able to navigate through an environment, localize on it, and analyze its traversability. To allow for real-time execution on constrained hardware, the map usually estimated by feature-based or semidense SLAM algorithms is a sparse point cloud; a richer and more complete representation of the environment is desirable. Existing dense mapping algorithms require extensive use of graphics processing unit (GPU) computing and they hardly scale to large environments; incremental algorithms from sparse points still represent an effective solution when light computational effort is needed and big sequences have to be processed in real time. In this letter, we improved and extended the state-of-the-art incremental manifold mesh algorithm proposed by Litvinov and Lhuillier and extended by Romanoni and Matteucci. While these algorithms do not reconstruct the map in real time and they embed points from SLAM or structure from motion only when their position is fixed, in this letter, we propose the first incremental algorithm able to reconstruct a manifold mesh in real time through single core CPU processing, which is aso able to modify the mesh according to three-dimensional points updates from the underlying SLAM algorithm. We tested our algorithm against two state-of-the-art incremental mesh mapping systems on the KITTI dataset, and we showed that, while accuracy is comparable, our approach is able to reach real-time performances thanks to an order of magnitude speed-up
Backward-Simulation Particle Smoother with a hybrid state for 3D vehicle trajectory, class and dimension simultaneous estimation
Full text linkThe estimation of the 3D trajectory, the class and the dimensions of a vehicle represents three relevant tasks for traffic monitoring. They are usually performed by separate sub-systems and only few existing algorithms cope with the three tasks at the same time. However, if these tasks are integrated, the trajectory estimation enforces the classification with temporal consistency, and at the same time, the estimation of the vehicle class and dimensions can be used to increase the trajectory estimate accuracy. In this work, we propose an algorithm to estimate the 3D trajectory, the class and the dimensions of vehicles simultaneously by means of a Backward-Simulation Particle Smoother whose state contains both continuous (vehicle pose and dimensions), and discrete (vehicle class) quantities. To integrate the class estimate in the Particle Smoother we model the class prediction as a Markov Chain. We performed experimental tests on both simulated and real datasets; they show that the pose and dimension estimation reaches centimeter-accuracy and the classification accuracy is higher than 95
Robust Moving Objects Detection in Lidar Data Exploiting Visual Cues
Full text linkDetecting moving objects in dynamic scenes from sequences of lidar scans is an important task in object tracking, mapping, localization, and navigation. Many works focus on changes detection in previously observed scenes, while a very limited amount of literature addresses moving objects detection. The state-of-the-art method exploits Dempster-Shafer Theory to evaluate the occupancy of a lidar scan and to discriminate points belonging to the static scene from moving ones. In this paper we improve both speed and accuracy of this method by discretizing the occupancy representation, and by removing false positives through visual cues. Many false positives lying on the ground plane are also removed thanks to a novel ground plane removal algorithm. Efficiency is improved through an octree indexing strategy. Experimental evaluation against the KITTI public dataset shows the effectiveness of our approach, both qualitatively and quantitatively with respect to the state- of-the-art
Automatic 3D Reconstruction of Manifold Meshes via Delaunay Triangulation and Mesh Sweeping
No full textIn this paper we propose a new approach to incrementally initialize a manifold surface for automatic 3D reconstruction from images. More precisely we focus on the automatic initialization of a 3D mesh as close as possible to the final solution; indeed many approaches require a good initial solution for further refinement via multi-view stereo techniques. Our novel algorithm automatically estimates an initial manifold mesh for surface evolving multi-view stereo algorithms, where the manifold property needs to be enforced. It bootstraps from 3D points extracted via Structure from Motion, then iterates between a state-of-the-art manifold reconstruction step and a novel mesh sweeping algorithm that looks for new 3D points in the neighborhood of the reconstructed manifold to be added in the manifold reconstruction. The experimental results show quantitatively that the mesh sweeping improves the resolution and the accuracy of the manifold reconstruction, allowing a better convergence of state-of-the-art surface evolution multi-view stereo algorithms
- …
