Semi-supervised Visual Tracking of Marine Animals Using Autonomous Underwater Vehicles
Semi-supervised Visual Tracking of Marine Animals Using Autonomous Underwater Vehicles
复制标题
DOI：
10.1007/s11263-023-01762-5
复制
发表时间：
2023-02
影响因子：
19.5
通讯作者：
Levi Cai;Nathan McGuire;R. Hanlon;T. Mooney;Yogesh A. Girdhar
中科院分区：
文献类型：
--
作者：
Levi Cai;Nathan McGuire;R. Hanlon;T. Mooney;Yogesh A. Girdhar
对海洋生物进行现场目视观察，对于了解其行为及其与周围生态系统的关系至关重要。通常情况下，这些观察结果是通过潜水员，标签和远程操作或人类驾驶的车辆收集的。然而，最近，配备有摄像头和具有GPU能力的嵌入式计算机的自主水下航行器正在开发用于各种应用，特别是可以用于补充这些现有的数据收集机制，其中人类操作或标签更加困难。现有的方法主要集中在使用完全监督的跟踪方法，但许多水下物种的标记数据严重缺乏。半监督跟踪器可以提供替代跟踪解决方案，因为它们需要的数据比完全监督的同行少。然而，由于没有现实的水下跟踪数据集，半监督跟踪算法在海洋领域的性能还没有得到很好的理解。为了更好地评估它们的性能和实用性，在本文中，我们提供了（1）一个新的数据集，具体到海洋动物位于http：//warp.whoi.edu/vmat/，（2）最先进的半监督算法在水下动物跟踪的背景下进行评估，和（3）通过使用半监督算法在船上的自主水下航行器在野外跟踪海洋动物的演示，评估真实世界的性能。
In-situ visual observations of marine organisms is crucial to developing behavioural understandings and their relations to their surrounding ecosystem. Typically, these observations are collected via divers, tags, and remotely-operated or human-piloted vehicles. Recently, however, autonomous underwater vehicles equipped with cameras and embedded computers with GPU capabilities are being developed for a variety of applications, and in particular, can be used to supplement these existing data collection mechanisms where human operation or tags are more difficult. Existing approaches have focused on using fully-supervised tracking methods, but labelled data for many underwater species are severely lacking. Semi-supervised trackers may offer alternative tracking solutions because they require less data than fully-supervised counterparts. However, because there are not existing realistic underwater tracking datasets, the performance of semi-supervised tracking algorithms in the marine domain is not well understood. To better evaluate their performance and utility, in this paper we provide (1) a novel dataset specific to marine animals located at http://warp.whoi.edu/vmat/, (2) an evaluation of state-of-the-art semi-supervised algorithms in the context of underwater animal tracking, and (3) an evaluation of real-world performance through demonstrations using a semi-supervised algorithm on-board an autonomous underwater vehicle to track marine animals in the wild.