Fast Region of Interest Proposals on Maritime UAVs

TL;DR

This paper introduces a real-time, end-to-end future frame prediction model for maritime UAVs to generate region of interest proposals efficiently on embedded GPUs, enhancing search and rescue operations.

Contribution

It presents a novel fast region proposal method based on future frame prediction tailored for embedded hardware in maritime UAV applications.

Findings

Outperforms traditional methods in speed and accuracy

Operates effectively on limited hardware with large image resolutions

Demonstrates benefits on large-scale maritime datasets

Abstract

Unmanned aerial vehicles assist in maritime search and rescue missions by flying over large search areas to autonomously search for objects or people. Reliably detecting objects of interest requires fast models to employ on embedded hardware. Moreover, with increasing distance to the ground station only part of the video data can be transmitted. In this work, we consider the problem of finding meaningful region of interest proposals in a video stream on an embedded GPU. Current object or anomaly detectors are not suitable due to their slow speed, especially on limited hardware and for large image resolutions. Lastly, objects of interest, such as pieces of wreckage, are often not known a priori. Therefore, we propose an end-to-end future frame prediction model running in real-time on embedded GPUs to generate region proposals. We analyze its performance on large-scale maritime data sets and demonstrate its benefits over traditional and modern methods.