J-MOD2: Joint Monocular Obstacle Detection and Depth Estimation

M Mancini, G Costante, P Valigi… - IEEE Robotics and …, 2018 - ieeexplore.ieee.org
In this letter, we propose an end-to-end deep architecture that jointly learns to detect
obstacles and estimate their depth for MAV flight applications. Most of the existing …

FPGA applications in unmanned aerial vehicles-a review

M Bouhali, F Shamani, ZE Dahmane, A Belaidi… - … Symposium, ARC 2017 …, 2017 - Springer
Most of the existing Unmanned Aerial Vehicles (UAVs) in different scales, use
microcontrollers as their processing engine. In this paper, we provide a wide study on how …

Semi-global stereo matching with surface orientation priors

D Scharstein, T Taniai, SN Sinha - … International Conference on …, 2017 - ieeexplore.ieee.org
Semi-Global Matching (SGM) is a widely-used efficient stereo matching technique. It works
well for textured scenes, but fails on untextured slanted surfaces due to its fronto-parallel …

[HTML][HTML] ReS2tAC—UAV-Borne Real-Time SGM Stereo Optimized for Embedded ARM and CUDA Devices

B Ruf, J Mohrs, M Weinmann, S Hinz, J Beyerer - Sensors, 2021 - mdpi.com
With the emergence of low-cost robotic systems, such as unmanned aerial vehicle, the
importance of embedded high-performance image processing has increased. For a long …

Real-time on-board obstacle avoidance for UAVs based on embedded stereo vision

B Ruf, S Monka, M Kollmann, M Grinberg - ar** stable and reprogrammable Unmanned Aerial Systems has
increased between researchers and engineers due to increasing interest in many …

Efficient surface-aware semi-global matching with multi-view plane-sweep sampling

B Ruf, T Pollok, M Weinmann - arxiv preprint arxiv:1909.09891, 2019 - arxiv.org
Online augmentation of an oblique aerial image sequence with structural information is an
essential aspect in the process of 3D scene interpretation and analysis. One key aspect in …