Deep Image Representations for Coral Image Classification
Deep Image Representations for Coral Image Classification
复制标题
DOI：
10.1109/joe.2017.2786878
复制
发表时间：
2019-01-01
影响因子：
4.1
通讯作者：
Fisher, Robert B.
中科院分区：
文献类型：
--
作者：
Mahmood, Ammar;Bennamoun, Mohammed;Fisher, Robert B.
健康的珊瑚礁在维持热带海洋生态系统的生物多样性方面发挥着至关重要的作用。远程成像技术促进了对这些复杂生态系统的科学调查，特别是在超过10米深的地方，那里的潜水技术既不省时也不划算。由于使用遥控潜水器和自动水下航行器(AUV)收集了数百万张海底数字图像，海洋专家对这些数据进行手动注释是一项繁琐、重复和耗时的任务。海洋专家需要10-30分钟才能对一张图像进行细致的注释。监测海洋健康的自动化技术将使探测和识别物种的方法标准化，从而产生变革性的生态结果。本文旨在通过开发先进的深度学习工具来实现对大量可用AUV图像的自动化分析，以便快速、大规模地对海洋珊瑚物种进行自动注释。这种自动化技术将在成本、速度和准确性方面极大地有利于海洋生态研究。为此，我们提出了一种基于深度学习的珊瑚礁分类方法，并报道了该方法在澳大利亚Abrolhos群岛未标记珊瑚礁马赛克自动标注中的应用。我们提出的方法自动量化了该地区的珊瑚覆盖率，并检测到珊瑚数量有减少的趋势，这与海洋生态学家得出的结论是一致的。
Healthy coral reefs play a vital role in maintaining biodiversity in tropical marine ecosystems. Remote imaging techniques have facilitated the scientific investigations of these intricate ecosystems, particularly at depths beyond 10mwhere SCUBA diving techniques are not time or cost efficient. With millions of digital images of the seafloor collected using remotely operated vehicles and autonomous underwater vehicles (AUVs), manual annotation of these data by marine experts is a tedious, repetitive, and time-consuming task. It takes 10-30 min for a marine expert to meticulously annotate a single image. Automated technology to monitor the health of the oceans would allow for transformational ecological outcomes by standardizing methods to detect and identify species. This paper aims to automate the analysis of large available AUVimagery by developing advanced deep learning tools for rapid and large-scale automatic annotation of marine coral species. Such an automated technology would greatly benefit marine ecological studies in terms of cost, speed, and accuracy. To this end, we propose a deep learning based classificationmethod for coral reefs and report the application of the proposed technique to the automatic annotation of unlabeled mosaics of the coral reef in the Abrolhos Islands, W. A., Australia. Our proposed method automatically quantified the coral coverage in this region and detected a decreasing trend in coral population, which is in line with conclusions drawn by marine ecologists.