Fast Region of Interest Proposals on Maritime UAVs
This addresses the need for efficient object detection in maritime search and rescue missions, where limited hardware and bandwidth constraints require fast processing, though it is incremental as it builds on existing prediction techniques.
The paper tackles the problem of generating fast region of interest proposals for maritime UAV video streams on embedded hardware, proposing an end-to-end future frame prediction model that runs in real-time and outperforms traditional and modern methods on large-scale maritime datasets.
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.