Journal
APPLIED INTELLIGENCE
Volume 51, Issue 8, Pages 5809-5821Publisher
SPRINGER
DOI: 10.1007/s10489-020-02155-8
Keywords
Fish detection; Underwater videos; Deep learning; Convolutional neural networks; Multi-stream
Categories
Funding
- Region Bretagne
Ask authors/readers for more resources
This paper introduces a new method for marine biologists to study species diversity and fish abundance using underwater videos. It proposes two fusion approaches that utilize both appearance and motion information for automatic fish detection, significantly improving performance measures compared to existing methods.
Recently, marine biologists have begun using underwater videos to study species diversity and fish abundance. These techniques generate a large amount of visual data. Automatic analysis using image processing is therefore necessary, since manual processing is time-consuming and labor-intensive. However, there are numerous challenges to implementing the automatic processing of underwater images: for example, high luminosity variation, limited visibility, complex background, free movement of fish, and high diversity of fish species. In this paper, we propose two new fusion approaches that exploit two convolutional neural network (CNN) streams to merge both appearance and motion information for automatic fish detection. These approaches consist of two Faster R-CNN models that share either the same region proposal network or the same classifier. We significantly improve the fish detection performances on the LifeClef 2015 Fish benchmark dataset not only compared with the classic Faster R-CNN but also with all the state-of-the-art approaches. The best F-score and mAP measures are 83.16% and 73.69%, respectively.
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