期刊
METHODS IN ECOLOGY AND EVOLUTION
卷 10, 期 9, 页码 1490-1500出版社
WILEY
DOI: 10.1111/2041-210X.13246
关键词
cetaceans; convolutional neural network; deep learning; drones; photogrammetry; population assessments; species identification; unoccupied aerial systems
类别
资金
- Division of Integrative Organismal Systems [1656676]
- Division of Antarctic Sciences [0823101, 1440435]
- Office of Polar Programs [1644209]
- North Carolina Space Grant [1440435]
- Stanford University
- Microsoft
- Direct For Biological Sciences
- Division Of Integrative Organismal Systems [1656676] Funding Source: National Science Foundation
- Office of Polar Programs (OPP)
- Directorate For Geosciences [1644209] Funding Source: National Science Foundation
The flourishing application of drones within marine science provides more opportunity to conduct photogrammetric studies on large and varied populations of many different species. While these new platforms are increasing the size and availability of imagery datasets, established photogrammetry methods require considerable manual input, allowing individual bias in techniques to influence measurements, increasing error and magnifying the time required to apply these techniques. Here, we introduce the next generation of photogrammetry methods utilizing a convolutional neural network to demonstrate the potential of a deep learning-based photogrammetry system for automatic species identification and measurement. We then present the same data analysed using conventional techniques to validate our automatic methods. Our results compare favorably across both techniques, correctly predicting whale species with 98% accuracy (57/58) for humpback whales, minke whales, and blue whales. Ninety percent of automated length measurements were within 5% of manual measurements, providing sufficient resolution to inform morphometric studies and establish size classes of whales automatically. The results of this study indicate that deep learning techniques applied to survey programs that collect large archives of imagery may help researchers and managers move quickly past analytical bottlenecks and provide more time for abundance estimation, distributional research, and ecological assessments.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据