Journal
INTEGRATED COMPUTER-AIDED ENGINEERING
Volume 28, Issue 3, Pages 221-235Publisher
IOS PRESS
DOI: 10.3233/ICA-210649
Keywords
Deep learning; water rescue; ensemble of classifiers; UAV; YOLO; Faster R-CNN; RetinaNet; SSD
Categories
Funding
- Polish National Science Center [2016/21/B/ST6/01461]
Ask authors/readers for more resources
This paper presents a dataset for maritime search and rescue purposes, as well as a novel object detection method based on deep learning architectures. The proposed method achieved impressive results on the new dataset, outperforming existing state-of-the-art deep neural networks.
Today's deep learning architectures, if trained with proper dataset, can be used for object detection in marine search and rescue operations. In this paper a dataset for maritime search and rescue purposes is proposed. It contains aerial-drone videos with 40,000 hand-annotated persons and objects floating in the water, many of small size, which makes them difficult to detect. The second contribution is our proposed object detection method. It is an ensemble composed of a number of the deep convolutional neural networks, orchestrated by the fusion module with the nonlinearly optimized voting weights. The method achieves over 82% of average precision on the new aerial-drone floating objects dataset and outperforms each of the state-of-the-art deep neural networks, such as YOLOv3, -v4, Faster R-CNN, RetinaNet, and SSD300. The dataset is publicly available from the Internet.
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