Journal
PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW)
Volume -, Issue -, Pages 1466-1474Publisher
IEEE
DOI: 10.1109/CVPRW.2018.00187
Keywords
-
Categories
Funding
- European Union's Horizon 2020 research and innovation program [773753]
- Leona M. and Harry B. Helmsley Charitable Trust
- Maurice Hatter Foundation
- Technion Ollendorff Minerva Center for Vision and Image Sciences
- H2020 Societal Challenges Programme [773753] Funding Source: H2020 Societal Challenges Programme
Ask authors/readers for more resources
Monitoring of the marine environment requires large amounts of data, simply due to its vast size. Therefore, underwater autonomous vehicles and drones are increasingly deployed to acquire numerous photographs. However, ecological conclusions from them are lagging as the data requires expert annotation and thus realistically cannot be manually processed. This calls for developing automatic classification algorithms dedicated for this type of data. Current out-of-the-box solutions struggle to provide optimal results in these scenarios as the marine data is very different from everyday data. Images taken under water display low contrast levels and reduced visibility range thus making objects harder to localize and classify. Scale varies dramatically because of the complex 3 dimensionality of the scenes. In addition, the scarcity of labeled marine data prevents training these dedicated networks from scratch. In this work, we demonstrate how transfer learning can be utilized to achieve high quality results for both detection and classification in the marine environment. We also demonstrate tracking in videos that enables counting and measuring the organisms. We demonstrate the suggested method on two very different marine datasets, an aerial dataset and an underwater one.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available