• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

一种深度学习仿生银河系罗盘。

A Deep Learning Biomimetic Milky Way Compass.

作者信息

Tao Yiting, Lucas Michael, Perera Asanka, Teague Samuel, McIntyre Timothy, Ogunwa Titilayo, Warrant Eric, Chahl Javaan

机构信息

School of Engineering, University of South Australia, Mawson Lakes, SA 5095, Australia.

School of Engineering, University of Southern Queensland, Springfield, QLD 4300, Australia.

出版信息

Biomimetics (Basel). 2024 Oct 12;9(10):620. doi: 10.3390/biomimetics9100620.

DOI:10.3390/biomimetics9100620
PMID:39451825
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11505024/
Abstract

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 84.7% 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.

摘要

直线移动是一种使生物体能够寻找食物、远离威胁并最终寻找适宜生存和繁殖环境的行为。本研究探索了一种基于视觉的技术，用于利用银河系（MW）检测航向方向的变化，银河系是已知夜间活动昆虫所使用的导航线索之一。提出了一种结合YOLOv8m-seg模型和归一化二阶中心矩来计算MW方位角的算法。该方法解决了许多通过图像阈值化或边缘检测从背景中分割MW不适用的可能情况，例如当月亮很大或存在人为光时。使用我们自己的MW图像训练数据集，所提出的YOLOv8m-seg模型在验证数据集上实现了84.7%的分割mAP@0.5。为了探索其在自主系统应用中的潜在作用，我们比较了南澳大利亚农村实地试验中的夜空图像和GPS航向数据。比较结果表明，对于短期导航，分割后的MW图像可作为可靠的方位线索。由于路径在某些位置涉及向左或向右90°转弯，所提出的方法与地面真值（GT）之间大约有5-10°的差异。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/d2107743722c/biomimetics-09-00620-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/0b173bb75f43/biomimetics-09-00620-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/2ca26e2e7377/biomimetics-09-00620-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/d3eb56a8bcde/biomimetics-09-00620-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/3beabb017288/biomimetics-09-00620-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/7e44a33e7704/biomimetics-09-00620-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/f388b4c236ac/biomimetics-09-00620-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/4704dd384475/biomimetics-09-00620-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/32b2e64372a2/biomimetics-09-00620-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/dde290737079/biomimetics-09-00620-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/4f9f65db54e6/biomimetics-09-00620-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/8c2bb74ddce7/biomimetics-09-00620-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/16e653648a4d/biomimetics-09-00620-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/57daae59725e/biomimetics-09-00620-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/6fd97fdacf2f/biomimetics-09-00620-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/4707f08688aa/biomimetics-09-00620-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/b138fe5cd0f3/biomimetics-09-00620-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/9df7f4494c2a/biomimetics-09-00620-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/d2107743722c/biomimetics-09-00620-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/0b173bb75f43/biomimetics-09-00620-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/2ca26e2e7377/biomimetics-09-00620-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/d3eb56a8bcde/biomimetics-09-00620-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/3beabb017288/biomimetics-09-00620-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/7e44a33e7704/biomimetics-09-00620-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/f388b4c236ac/biomimetics-09-00620-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/4704dd384475/biomimetics-09-00620-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/32b2e64372a2/biomimetics-09-00620-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/dde290737079/biomimetics-09-00620-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/4f9f65db54e6/biomimetics-09-00620-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/8c2bb74ddce7/biomimetics-09-00620-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/16e653648a4d/biomimetics-09-00620-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/57daae59725e/biomimetics-09-00620-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/6fd97fdacf2f/biomimetics-09-00620-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/4707f08688aa/biomimetics-09-00620-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/b138fe5cd0f3/biomimetics-09-00620-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/9df7f4494c2a/biomimetics-09-00620-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8817/11505024/d2107743722c/biomimetics-09-00620-g018.jpg

相似文献

1
A Deep Learning Biomimetic Milky Way Compass.一种深度学习仿生银河系罗盘。
Biomimetics (Basel). 2024 Oct 12;9(10):620. doi: 10.3390/biomimetics9100620.
2
Computer Vision Techniques Demonstrate Robust Orientation Measurement of the Milky Way Despite Image Motion.计算机视觉技术证明，尽管存在图像运动，但仍能对银河系进行稳健的方向测量。
Biomimetics (Basel). 2024 Jun 21;9(7):375. doi: 10.3390/biomimetics9070375.
3
Dung beetles use the Milky Way for orientation.蜣螂利用银河进行定位。
Curr Biol. 2013 Feb 18;23(4):298-300. doi: 10.1016/j.cub.2012.12.034. Epub 2013 Jan 24.
4
Stellar performance: mechanisms underlying Milky Way orientation in dung beetles.卓越表现：蜣螂中银河系定向的潜在机制。
Philos Trans R Soc Lond B Biol Sci. 2017 Apr 5;372(1717). doi: 10.1098/rstb.2016.0079.
5
Intrarow Uncut Weed Detection Using You-Only-Look-Once Instance Segmentation for Orchard Plantations.基于单目实例分割的行间未切割杂草检测在果园种植中的应用。
Sensors (Basel). 2024 Jan 30;24(3):893. doi: 10.3390/s24030893.
6
The brain behind straight-line orientation in dung beetles.直线定向行为的屎壳郎大脑。
J Exp Biol. 2019 Feb 6;222(Pt Suppl 1):jeb192450. doi: 10.1242/jeb.192450.
7
Two Compasses in the Central Complex of the Locust Brain.两个罗盘在蝗虫中央复合体中。
J Neurosci. 2019 Apr 17;39(16):3070-3080. doi: 10.1523/JNEUROSCI.0940-18.2019. Epub 2019 Feb 12.
8
The Geomagnetic Field Is a Compass Cue in Cataglyphis Ant Navigation.地磁场是 Cataglyphis 蚂蚁导航的罗盘线索。
Curr Biol. 2018 May 7;28(9):1440-1444.e2. doi: 10.1016/j.cub.2018.03.043. Epub 2018 Apr 26.
9
How Dung Beetles Steer Straight.蜣螂如何直线行进
Annu Rev Entomol. 2021 Jan 7;66:243-256. doi: 10.1146/annurev-ento-042020-102149. Epub 2020 Aug 21.
10
Developing Machine Vision in Tree-Fruit Applications-Fruit Count, Fruit Size and Branch Avoidance in Automated Harvesting.树果应用中的机器视觉开发——自动化采摘中的果实计数、果实大小和树枝避让。
Sensors (Basel). 2024 Aug 29;24(17):5593. doi: 10.3390/s24175593.

本文引用的文献

1
Computer Vision Techniques Demonstrate Robust Orientation Measurement of the Milky Way Despite Image Motion.计算机视觉技术证明，尽管存在图像运动，但仍能对银河系进行稳健的方向测量。
Biomimetics (Basel). 2024 Jun 21;9(7):375. doi: 10.3390/biomimetics9070375.
2
Colour vision in nocturnal insects.夜间昆虫的色觉。
Philos Trans R Soc Lond B Biol Sci. 2022 Oct 24;377(1862):20210285. doi: 10.1098/rstb.2021.0285. Epub 2022 Sep 5.
3
How Dung Beetles Steer Straight.蜣螂如何直线行进
Annu Rev Entomol. 2021 Jan 7;66:243-256. doi: 10.1146/annurev-ento-042020-102149. Epub 2020 Aug 21.
4
The Dung Beetle Compass.蜣螂的指南针。
Curr Biol. 2018 Sep 10;28(17):R993-R997. doi: 10.1016/j.cub.2018.04.052.
5
Visual acuity of the honey bee retina and the limits for feature detection.蜜蜂视网膜的视力和特征检测的极限。
Sci Rep. 2017 Apr 6;7:45972. doi: 10.1038/srep45972.
6
Stellar performance: mechanisms underlying Milky Way orientation in dung beetles.卓越表现：蜣螂中银河系定向的潜在机制。
Philos Trans R Soc Lond B Biol Sci. 2017 Apr 5;372(1717). doi: 10.1098/rstb.2016.0079.
7
The remarkable visual capacities of nocturnal insects: vision at the limits with small eyes and tiny brains.夜行性昆虫非凡的视觉能力：小眼睛和微小大脑在视觉极限下的视觉表现。
Philos Trans R Soc Lond B Biol Sci. 2017 Apr 5;372(1717). doi: 10.1098/rstb.2016.0063.
8
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.更快的 R-CNN：基于区域建议网络的实时目标检测。
IEEE Trans Pattern Anal Mach Intell. 2017 Jun;39(6):1137-1149. doi: 10.1109/TPAMI.2016.2577031. Epub 2016 Jun 6.
9
Visual Navigation in Nocturnal Insects.夜间昆虫的视觉导航。
Physiology (Bethesda). 2016 May;31(3):182-92. doi: 10.1152/physiol.00046.2015.
10
Neural Summation in the Hawkmoth Visual System Extends the Limits of Vision in Dim Light.天蛾视觉系统中的神经总和扩展了弱光下的视觉极限。
Curr Biol. 2016 Mar 21;26(6):821-6. doi: 10.1016/j.cub.2016.01.030. Epub 2016 Mar 3.