A Deep Learning Biomimetic Milky Way Compass

Moving in straight lines is a behaviour that enables organisms to search for food, move away from threats, and ultimately seek suitable environments in which to survive and reproduce. This study explores a vision-based technique for detecting a change in heading direction using the Milky Way (MW), o...

Full description

Saved in:
Bibliographic Details
Main Authors: Yiting Tao, Michael Lucas, Asanka Perera, Samuel Teague, Timothy McIntyre, Titilayo Ogunwa, Eric Warrant, Javaan Chahl
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Biomimetics
Subjects:
Online Access:https://www.mdpi.com/2313-7673/9/10/620
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850205909090828288
author Yiting Tao
Michael Lucas
Asanka Perera
Samuel Teague
Timothy McIntyre
Titilayo Ogunwa
Eric Warrant
Javaan Chahl
author_facet Yiting Tao
Michael Lucas
Asanka Perera
Samuel Teague
Timothy McIntyre
Titilayo Ogunwa
Eric Warrant
Javaan Chahl
author_sort Yiting Tao
collection DOAJ
description Moving in straight lines is a behaviour that enables organisms to search for food, move away from threats, and ultimately seek suitable environments in which to survive and reproduce. This study explores a vision-based technique for detecting a change in heading direction using the Milky Way (MW), one of the navigational cues that are known to be used by night-active insects. An algorithm is proposed that combines the YOLOv8m-seg model and normalised second central moments to calculate the MW orientation angle. This method addresses many likely scenarios where segmentation of the MW from the background by image thresholding or edge detection is not applicable, such as when the moon is substantial or when anthropogenic light is present. The proposed YOLOv8m-seg model achieves a segment mAP@0.5 of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>84.7</mn><mo>%</mo></mrow></semantics></math></inline-formula> on the validation dataset using our own training dataset of MW images. To explore its potential role in autonomous system applications, we compare night sky imagery and GPS heading data from a field trial in rural South Australia. The comparison results show that for short-term navigation, the segmented MW image can be used as a reliable orientation cue. There is a difference of roughly 5–10° between the proposed method and GT as the path involves left or right 90° turns at certain locations.
format Article
id doaj-art-4f1aaf1ece5f4eaeba97774ed65edcc9
institution OA Journals
issn 2313-7673
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Biomimetics
spelling doaj-art-4f1aaf1ece5f4eaeba97774ed65edcc92025-08-20T02:10:58ZengMDPI AGBiomimetics2313-76732024-10-0191062010.3390/biomimetics9100620A Deep Learning Biomimetic Milky Way CompassYiting Tao0Michael Lucas1Asanka Perera2Samuel Teague3Timothy McIntyre4Titilayo Ogunwa5Eric Warrant6Javaan Chahl7School of Engineering, University of South Australia, Mawson Lakes, SA 5095, AustraliaSchool of Engineering, University of South Australia, Mawson Lakes, SA 5095, AustraliaSchool of Engineering, University of Southern Queensland, Springfield, QLD 4300, AustraliaSchool of Engineering, University of South Australia, Mawson Lakes, SA 5095, AustraliaSchool of Engineering, University of South Australia, Mawson Lakes, SA 5095, AustraliaSchool of Engineering, University of South Australia, Mawson Lakes, SA 5095, AustraliaLund Vision Group, Department of Biology, University of Lund, 22100 Lund, SwedenSchool of Engineering, University of South Australia, Mawson Lakes, SA 5095, AustraliaMoving in straight lines is a behaviour that enables organisms to search for food, move away from threats, and ultimately seek suitable environments in which to survive and reproduce. This study explores a vision-based technique for detecting a change in heading direction using the Milky Way (MW), one of the navigational cues that are known to be used by night-active insects. An algorithm is proposed that combines the YOLOv8m-seg model and normalised second central moments to calculate the MW orientation angle. This method addresses many likely scenarios where segmentation of the MW from the background by image thresholding or edge detection is not applicable, such as when the moon is substantial or when anthropogenic light is present. The proposed YOLOv8m-seg model achieves a segment mAP@0.5 of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>84.7</mn><mo>%</mo></mrow></semantics></math></inline-formula> on the validation dataset using our own training dataset of MW images. To explore its potential role in autonomous system applications, we compare night sky imagery and GPS heading data from a field trial in rural South Australia. The comparison results show that for short-term navigation, the segmented MW image can be used as a reliable orientation cue. There is a difference of roughly 5–10° between the proposed method and GT as the path involves left or right 90° turns at certain locations.https://www.mdpi.com/2313-7673/9/10/620biomimeticMilky WayYOLOv8instance segmentationorientation
spellingShingle Yiting Tao
Michael Lucas
Asanka Perera
Samuel Teague
Timothy McIntyre
Titilayo Ogunwa
Eric Warrant
Javaan Chahl
A Deep Learning Biomimetic Milky Way Compass
Biomimetics
biomimetic
Milky Way
YOLOv8
instance segmentation
orientation
title A Deep Learning Biomimetic Milky Way Compass
title_full A Deep Learning Biomimetic Milky Way Compass
title_fullStr A Deep Learning Biomimetic Milky Way Compass
title_full_unstemmed A Deep Learning Biomimetic Milky Way Compass
title_short A Deep Learning Biomimetic Milky Way Compass
title_sort deep learning biomimetic milky way compass
topic biomimetic
Milky Way
YOLOv8
instance segmentation
orientation
url https://www.mdpi.com/2313-7673/9/10/620
work_keys_str_mv AT yitingtao adeeplearningbiomimeticmilkywaycompass
AT michaellucas adeeplearningbiomimeticmilkywaycompass
AT asankaperera adeeplearningbiomimeticmilkywaycompass
AT samuelteague adeeplearningbiomimeticmilkywaycompass
AT timothymcintyre adeeplearningbiomimeticmilkywaycompass
AT titilayoogunwa adeeplearningbiomimeticmilkywaycompass
AT ericwarrant adeeplearningbiomimeticmilkywaycompass
AT javaanchahl adeeplearningbiomimeticmilkywaycompass
AT yitingtao deeplearningbiomimeticmilkywaycompass
AT michaellucas deeplearningbiomimeticmilkywaycompass
AT asankaperera deeplearningbiomimeticmilkywaycompass
AT samuelteague deeplearningbiomimeticmilkywaycompass
AT timothymcintyre deeplearningbiomimeticmilkywaycompass
AT titilayoogunwa deeplearningbiomimeticmilkywaycompass
AT ericwarrant deeplearningbiomimeticmilkywaycompass
AT javaanchahl deeplearningbiomimeticmilkywaycompass