期刊
ICES JOURNAL OF MARINE SCIENCE
卷 77, 期 4, 页码 1308-1317出版社
OXFORD UNIV PRESS
DOI: 10.1093/icesjms/fsz223
关键词
deep learning; lobster detection; marine science; synthetic data; underwater images
资金
- Australian Research Council [DP150104251, DE120102960]
- Integrated Marine Observing System through the Department of Innovation, Industry, Science and Research, National Collaborative Research Infrastructure Scheme
Underwater imaging is being extensively used for monitoring the abundance of lobster species and their biodiversity in their local habitats. However, manual assessment of these images requires a huge amount of human effort. In this article, we propose to automate the process of lobster detection using a deep learning technique. A major obstacle in deploying such an automatic framework for the localization of lobsters in diverse environments is the lack of large annotated training datasets. Generating synthetic datasets to train these object detection models has become a popular approach. However, the current synthetic data generation frameworks rely on automatic segmentation of objects of interest, which becomes difficult when the objects have a complex shape, such as lobster. To overcome this limitation, we propose an approach to synthetically generate parts of the lobster. To handle the variability of real-world images, these parts were inserted into a set of diverse background marine images to generate a large synthetic dataset. A state-of-the-art object detector was trained using this synthetic parts dataset and tested on the challenging task of Western rock lobster detection in West Australian seas. To the best of our knowledge, this is the first automatic lobster detection technique for partially visible and occluded lobsters.
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