Adaptive Sampling-based Particle Filter for Visual-inertial Gimbal in the Wild

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kang, Xueyang, Herrera, Ariel, Lema, Henry, Valencia, Esteban, Vandewalle, Patrick
Natura: Preprint
Pubblicazione: 2022
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910288652009472
author Kang, Xueyang
Herrera, Ariel
Lema, Henry
Valencia, Esteban
Vandewalle, Patrick
author_facet Kang, Xueyang
Herrera, Ariel
Lema, Henry
Valencia, Esteban
Vandewalle, Patrick
contents In this paper, we present a Computer Vision (CV) based tracking and fusion algorithm, dedicated to a 3D printed gimbal system on drones operating in nature. The whole gimbal system can stabilize the camera orientation robustly in a challenging nature scenario by using skyline and ground plane as references. Our main contributions are the following: a) a light-weight Resnet-18 backbone network model was trained from scratch, and deployed onto the Jetson Nano platform to segment the image into binary parts (ground and sky); b) our geometry assumption from nature cues delivers the potential for robust visual tracking by using the skyline and ground plane as a reference; c) a spherical surface-based adaptive particle sampling, can fuse orientation from multiple sensor sources flexibly. The whole algorithm pipeline is tested on our customized gimbal module including Jetson and other hardware components. The experiments were performed on top of a building in the real landscape.
format Preprint
id arxiv_https___arxiv_org_abs_2206_10981
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Adaptive Sampling-based Particle Filter for Visual-inertial Gimbal in the Wild
Kang, Xueyang
Herrera, Ariel
Lema, Henry
Valencia, Esteban
Vandewalle, Patrick
Robotics
Systems and Control
Image and Video Processing
68T45, 57-06, 60B05
I.4.6; I.2.10
In this paper, we present a Computer Vision (CV) based tracking and fusion algorithm, dedicated to a 3D printed gimbal system on drones operating in nature. The whole gimbal system can stabilize the camera orientation robustly in a challenging nature scenario by using skyline and ground plane as references. Our main contributions are the following: a) a light-weight Resnet-18 backbone network model was trained from scratch, and deployed onto the Jetson Nano platform to segment the image into binary parts (ground and sky); b) our geometry assumption from nature cues delivers the potential for robust visual tracking by using the skyline and ground plane as a reference; c) a spherical surface-based adaptive particle sampling, can fuse orientation from multiple sensor sources flexibly. The whole algorithm pipeline is tested on our customized gimbal module including Jetson and other hardware components. The experiments were performed on top of a building in the real landscape.
title Adaptive Sampling-based Particle Filter for Visual-inertial Gimbal in the Wild
topic Robotics
Systems and Control
Image and Video Processing
68T45, 57-06, 60B05
I.4.6; I.2.10
url https://arxiv.org/abs/2206.10981