State of the art in vision-based localization techniques for autonomous navigation systems

Y Alkendi, L Seneviratne, Y Zweiri - IEEE Access, 2021‏ - ieeexplore.ieee.org
Vision-based localization systems, namely visual odometry (VO) and visual inertial odometry
(VIO), have attracted great attention recently. They are regarded as critical modules for …

Advances in intelligent and autonomous navigation systems for small UAS

S Bijjahalli, R Sabatini, A Gardi - Progress in Aerospace Sciences, 2020‏ - Elsevier
A significant growth in Unmanned Aircraft System (UAS) operations has been observed over
the past decade, largely driven by the emergence of new commercial opportunities and use …

Many-to-many splatting for efficient video frame interpolation

P Hu, S Niklaus, S Sclaroff… - Proceedings of the IEEE …, 2022‏ - openaccess.thecvf.com
Motion-based video frame interpolation commonly relies on optical flow to warp pixels from
the inputs to the desired interpolation instant. Yet due to the inherent challenges of motion …

Exploring representation learning with cnns for frame-to-frame ego-motion estimation

G Costante, M Mancini, P Valigi… - IEEE robotics and …, 2015‏ - ieeexplore.ieee.org
Visual ego-motion estimation, or briefly visual odometry (VO), is one of the key building
blocks of modern SLAM systems. In the last decade, impressive results have been …

Efficient sparse-to-dense optical flow estimation using a learned basis and layers

J Wulff, MJ Black - Proceedings of the IEEE Conference on …, 2015‏ - openaccess.thecvf.com
We address the elusive goal of estimating optical flow both accurately and efficiently by
adopting a sparse-to-dense approach. Given a set of sparse matches, we regress to dense …

LS-VO: Learning dense optical subspace for robust visual odometry estimation

G Costante, TA Ciarfuglia - IEEE Robotics and Automation …, 2018‏ - ieeexplore.ieee.org
This work proposes a novel deep network architecture to solve the camera ego-motion
estimation problem. A motion estimation network generally learns features similar to optical …

Video frame interpolation with many-to-many splatting and spatial selective refinement

P Hu, S Niklaus, L Zhang, S Sclaroff… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
In this work, we first propose a fully differentiable Many-to-Many (M2M) splatting framework
to interpolate frames efficiently. Given a frame pair, we estimate multiple bidirectional flows …

Independent motion detection with event-driven cameras

V Vasco, A Glover, E Mueggler… - 2017 18th …, 2017‏ - ieeexplore.ieee.org
Unlike standard cameras that send intensity images at a constant frame rate, event-driven
cameras asynchronously report pixel-level brightness changes, offering low latency and …

Towards visual ego-motion learning in robots

S Pillai, JJ Leonard - … on Intelligent Robots and Systems (IROS), 2017‏ - ieeexplore.ieee.org
Many model-based Visual Odometry (VO) algorithms have been proposed in the past
decade, often restricted to the type of camera optics, or the underlying motion manifold …

Learning monocular visual odometry with dense 3D map** from dense 3D flow

C Zhao, L Sun, P Purkait, T Duckett… - 2018 IEEE/RSJ …, 2018‏ - ieeexplore.ieee.org
This paper introduces a fully deep learning approach to monocular SLAM, which can
perform simultaneous localization using a neural network for learning visual odometry (L …