Survey on unmanned aerial vehicle networks for civil applications: A communications viewpoint
The days where swarms of unmanned aerial vehicles (UAVs) will occupy our skies are fast
approaching due to the introduction of cost-efficient and reliable small aerial vehicles and …
approaching due to the introduction of cost-efficient and reliable small aerial vehicles and …
Open-source image-based 3D reconstruction pipelines: Review, comparison and evaluation
EK Stathopoulou, M Welponer… - The International Archives …, 2019 - cris.fbk.eu
State-of-the-art automated image orientation (Structure from Motion) and dense image
matching (Multiple View Stereo) methods commonly used to produce 3D information from …
matching (Multiple View Stereo) methods commonly used to produce 3D information from …
CARLA: An open urban driving simulator
We introduce CARLA, an open-source simulator for autonomous driving research. CARLA
has been developed from the ground up to support development, training, and validation of …
has been developed from the ground up to support development, training, and validation of …
Motsynth: How can synthetic data help pedestrian detection and tracking?
Deep learning-based methods for video pedestrian detection and tracking require large
volumes of training data to achieve good performance. However, data acquisition in …
volumes of training data to achieve good performance. However, data acquisition in …
Playing for benchmarks
We present a benchmark suite for visual perception. The benchmark is based on more than
250K high-resolution video frames, all annotated with ground-truth data for both low-level …
250K high-resolution video frames, all annotated with ground-truth data for both low-level …
Need for speed: A benchmark for higher frame rate object tracking
In this paper, we propose the first higher frame rate video dataset (called Need for Speed-
NfS) and benchmark for visual object tracking. The dataset consists of 100 videos (380K …
NfS) and benchmark for visual object tracking. The dataset consists of 100 videos (380K …
LSD-SLAM: Large-scale direct monocular SLAM
We propose a direct (feature-less) monocular SLAM algorithm which, in contrast to current
state-of-the-art regarding direct methods, allows to build large-scale, consistent maps of the …
state-of-the-art regarding direct methods, allows to build large-scale, consistent maps of the …
Scenenet rgb-d: Can 5m synthetic images beat generic imagenet pre-training on indoor segmentation?
J McCormac, A Handa… - Proceedings of the …, 2017 - openaccess.thecvf.com
Abstract We introduce SceneNet RGB-D, a dataset providing pixel-perfect ground truth for
scene understanding problems such as semantic segmentation, instance segmentation, and …
scene understanding problems such as semantic segmentation, instance segmentation, and …
A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM
We introduce the Imperial College London and National University of Ireland Maynooth (ICL-
NUIM) dataset for the evaluation of visual odometry, 3D reconstruction and SLAM algorithms …
NUIM) dataset for the evaluation of visual odometry, 3D reconstruction and SLAM algorithms …
Fast optical flow using dense inverse search
Most recent works in optical flow extraction focus on the accuracy and neglect the time
complexity. However, in real-life visual applications, such as tracking, activity detection and …
complexity. However, in real-life visual applications, such as tracking, activity detection and …