Search

A major focus of recent developments in stereo vision has been on how to obtain accurate dense disparity maps in passive stereo vision. Active vision systems enable more accurate estimations of dense disparity compared to passive stereo. However, subpixel-accurate disparity estimation remains an open problem that has received little attention. In this paper, we propose a new learning strategy to train neural networks to estimate high-quality subpixel disparity maps for semi-dense active stereo vision. The key insight is that neural networks can double their accuracy if they are able to jointly learn how to refine the disparity map while invalidating the pixels where there is insufficient information to correct the disparity estimate. Our approach is based on Bayesian modeling where validated and invalidated pixels are defined by their stochastic properties, allowing the model to learn how to choose by itself which pixels are worth its attention. Using active stereo datasets such as Active-Passive SimStereo, we demonstrate that the proposed method outperforms the current state-of-the-art active stereo models. We also demonstrate that the proposed approach compares favorably with state-of-the-art passive stereo models on the Middlebury dataset., Comment: 15 pages, 15 figures

Cost-based image patch matching is at the core of various techniques in computer vision, photogrammetry and remote sensing. When the subpixel disparity between the reference patch in the source and target images is required, either the cost function or the target image have to be interpolated. While cost-based interpolation is the easiest to implement, multiple works have shown that image based interpolation can increase the accuracy of the subpixel matching, but usually at the cost of expensive search procedures. This, however, is problematic, especially for very computation intensive applications such as stereo matching or optical flow computation. In this paper, we show that closed form formulae for subpixel disparity computation for the case of one dimensional matching, e.g., in the case of rectified stereo images where the search space is of one dimension, exists when using the standard NCC, SSD and SAD cost functions. We then demonstrate how to generalize the proposed formulae to the case of high dimensional search spaces, which is required for unrectified stereo matching and optical flow extraction. We also compare our results with traditional cost volume interpolation formulae as well as with state-of-the-art cost-based refinement methods, and show that the proposed formulae bring a small improvement over the state-of-the-art cost-based methods in the case of one dimensional search spaces, and a significant improvement when the search space is two dimensional., 29 pages, 10 figures

Low cost and low weight unmanned aerial vehicle (UAV) systems with imaging capability have enjoyed a rapid development over the past years and are increasingly deployed as carriers for mapping purposes. They present a well-established tool for local-area remote sensing in the fields of agriculture, forestry, mining and hydrology as well as in scientific research. An important part of MAV mapping system is the ground station with a mission planner which serves for flight scheduling and mission execution. The traditional mission planners for MAVs are not dedicated to precise photogrammetry in complicated terrain. They allow planning and executing of autonomous flight as well as setting up of the autopilot systems. However, they lack functions for advanced flight planning, such as those motivated by achieving certain precision and reliability of the determined coordinates of features within the mapped area. The goal of this work is to create a software tool that given a planned trajectory (i.e. planned position and orientation of camera exposure), preliminary digital elevation model (DEM), assumptions on surface texture (i.e. number, distribution and accuracy of image observations) and (optionally) a certain number and distribution of ground control points (GCPs), allow to quantify the quality of the mapping.

BRDF (for bidirectional reflectance distribution function) are functions used in computer graphics and optics to describe how an opaque surface reflect the incoming light. The goal of this project is to study technics to separate different components of the BRDF real objects, measured by a static camera with different incoming light direction. There’s different applications for such separation. The main one being es- timating parameters of approximation models used to reduce the space needed to store the BRDF, or reconstruct the full continious signal (sampled during acquisition). LCAV1445050917

Refereed/Peer-reviewed Estimating depth from RGB images is a long-standing ill-posed problem, which has been explored for decades by the computer vision, graphics, and machine learning communities. Among the existing techniques, stereo matching remains one of the most widely used in the literature due to its strong connection to the human binocular system. Traditionally, stereo-based depth estimation has been addressed through matching hand-crafted features across multiple images. Despite the extensive amount of research, these traditional techniques still suffer in the presence of highly textured areas, large uniform regions, and occlusions. Motivated by their growing success in solving various 2D and 3D vision problems, deep learning for stereo-based depth estimation has attracted a growing interest from the community, with more than 150 papers published in this area between 2014 and 2019. This new generation of methods has demonstrated a significant leap in performance, enabling applications such as autonomous driving and augmented reality. In this paper, we provide a comprehensive survey of this new and continuously growing field of research, summarize the most commonly used pipelines, and discuss their benefits and limitations. In retrospect of what has been achieved so far, we also conjecture what the future may hold for deep learning-based stereo for depth estimation research.