Leveraging Metadata in Representation Learning With Georeferenced Seafloor Imagery

Leveraging Metadata in Representation Learning With Georeferenced Seafloor Imagery
复制标题

利用地理参考海底图像的表示学习中的元数据

DOI:
10.1109/lra.2021.3101881
复制
发表时间:
2021
影响因子:
5.2
通讯作者:
Yamada T
Yamada T
中科院分区:
计算机科学2区
文献类型:
--
作者:
Yamada T

文献摘要

参考文献

被引文献

相似文献

配备摄像机的自主水下航行器(AUV)现在经常用于海底调查。从它们收集的图像中获得有效的表示可以实现感知感知机器人探索,例如信息增益引导的路径规划和目标驱动的视觉导航。这封信开发了一种新的自监督表示学习方法的水下机器人收集的海底图像。该方法允许深度学习卷积自动编码器利用多个元数据源来规范其学习,优先考虑图像中观察到的可与其元数据中的模式相关的特征。拟议的正规化的影响,检查由超过30 K的彩色海底图像收集的塔斯马尼亚海岸的AUV的数据集。用于规范该数据集中的学习的元数据包括观察到的海底的水平位置和深度。结果表明,在自监督表示学习中包含元数据可以将图像分类精度提高15%,并且不会降低学习性能。我们展示了如何有效的表示学习可以应用于实现类平衡的代表性图像识别总结的不平衡类分布的理解在一个无监督的方式。
Camera equipped Autonomous Underwater Vehicles (AUVs) are now routinely used in seafloor surveys. Obtaining effective representations from the images they collect can enable perception-aware robotic exploration such as information-gain-guided path planning and target-driven visual navigation. This letter develops a novel self-supervised representation learning method for seafloor images collected by AUVs. The method allows deep-learning convolutional autoencoders to leverage multiple sources of metadata to regularise their learning, prioritising features observed in images that can be correlated with patterns in their metadata. The impact of the proposed regularisation is examined on a dataset consisting of more than 30 k colour seafloor images gathered by an AUV off the coast of Tasmania. The metadata used to regularise learning in this dataset consists of the horizontal location and depth of the observed seafloor. The results show that including metadata in self-supervised representation learning can increase image classification accuracy by up to 15% and never degrades learning performance. We show how effective representation learning can be applied to achieve class balanced representative image identification for summarised understanding of imbalanced class distributions in an unsupervised way.
DOI: 10.1109/joe.2017.2786878
发表时间: 2019-01-01
影响因子: 4.1
作者:
Mahmood, Ammar;Bennamoun, Mohammed;Fisher, Robert B.
通讯作者: Fisher, Robert B.
DOI: --
发表时间: 2013
期刊: IEEE International Conference on Robotics and Automation
影响因子: --
作者:
A. Bender;Stefan B. Williams;O. Pizarro
通讯作者: O. Pizarro
DOI: 10.1109/tpami.2020.2992393
发表时间: 2021-11-01
影响因子: 23.6
作者:
Jing, Longlong;Tian, Yingli
通讯作者: Tian, Yingli
自主水下航行器语义映射和异常检测的在线数据摘要
DOI: 10.1109/oceans-genova.2015.7271577
发表时间: 2015
期刊: OCEANS 2015 - Genova
影响因子: --
作者:
J. Kaeli;Hanumant Singh
通讯作者: Hanumant Singh
DOI: 10.1109/lra.2019.2929997
发表时间: 2019-10-01
影响因子: 5.2
作者:
Flaspohler, Genevieve;Preston, Victoria;Roy, Nicholas
通讯作者: Roy, Nicholas