This thesis work will focus on the optimization of a state-of-the-art monocular Visual-Inertial Odometry (VIO) algorithm for real-time application with limited resources on an embedded system. We will be using a multi-processor unit equipped with a Digital Signal Processor (DSP) to accelerate and offload tasks from the CPU. The goal is to reduce resource consumption without damaging the algorithm performance in speed and accuracy. To this end, we will first identify OpenVINS [1] as a suitable algorithm for this work and find the functions to optimize. When comparing the version of the optimized algorithm with the DSP and its original version, we achieved a similar performance accuracy with more than x1.5 power consumption saving on the CPU ...
Visual odometry (VO) is an important part of egomotion estimation in mobile robot applications. This...
Estimating relative camera pose is the key problem of visual odometry (VO). To achieve better effici...
© 2018 Dr. Milad RamezaniReal-time, accurate and seamless localization forms the backbone of various...
This thesis work will focus on the optimization of a state-of-the-art monocular Visual-Inertial Odom...
This thesis presents the design, implementation, and validation of a novel nonlinearfiltering based...
Visual Inertial Simultaneous Localization and Mapping (VI-SLAM) and Visual Inertial Odometry (VIO) s...
Mobile devices are increasingly expected to support high-performance cyber- physical applications in...
Denne masteroppgaven dekker implementasjonen av DVO (Direct Visual Odometry) algoritmen på en GPGPU ...
Visual inertial odometry (VIO) is a technique to estimate the change of a mobile platform in positio...
The expectations in performing high-performance cyber-physical applications in resource-constrained ...
This electronic version was submitted by the student author. The certified thesis is available in th...
The paper evaluates the performance of a VIO algorithms Vins-Mono, Vins-Fusion, MSCKF and Open-Vins ...
We present HybVIO, a novel hybrid approach for combining filtering-based visual-inertial odometry (V...
Current existing stereo visual odometry algorithms are computationally too expensive for robots with...
International audienceThis paper deals with the evaluation of a dedicated architecture to be integra...
Visual odometry (VO) is an important part of egomotion estimation in mobile robot applications. This...
Estimating relative camera pose is the key problem of visual odometry (VO). To achieve better effici...
© 2018 Dr. Milad RamezaniReal-time, accurate and seamless localization forms the backbone of various...
This thesis work will focus on the optimization of a state-of-the-art monocular Visual-Inertial Odom...
This thesis presents the design, implementation, and validation of a novel nonlinearfiltering based...
Visual Inertial Simultaneous Localization and Mapping (VI-SLAM) and Visual Inertial Odometry (VIO) s...
Mobile devices are increasingly expected to support high-performance cyber- physical applications in...
Denne masteroppgaven dekker implementasjonen av DVO (Direct Visual Odometry) algoritmen på en GPGPU ...
Visual inertial odometry (VIO) is a technique to estimate the change of a mobile platform in positio...
The expectations in performing high-performance cyber-physical applications in resource-constrained ...
This electronic version was submitted by the student author. The certified thesis is available in th...
The paper evaluates the performance of a VIO algorithms Vins-Mono, Vins-Fusion, MSCKF and Open-Vins ...
We present HybVIO, a novel hybrid approach for combining filtering-based visual-inertial odometry (V...
Current existing stereo visual odometry algorithms are computationally too expensive for robots with...
International audienceThis paper deals with the evaluation of a dedicated architecture to be integra...
Visual odometry (VO) is an important part of egomotion estimation in mobile robot applications. This...
Estimating relative camera pose is the key problem of visual odometry (VO). To achieve better effici...
© 2018 Dr. Milad RamezaniReal-time, accurate and seamless localization forms the backbone of various...