Metrics
118 Record Views
Conference proceeding
Marine Vessel Tracking using a Monocular Camera
DeLTA2021-Proceedings of the 2nd International Conference on Deep Learning Theory and Applications, pp.17-28
International Conference on Deep Learning Theory and Applications, 2nd
08/23/2021
Web of Science ID: WOS:000821081200001
Abstract
In this paper, a new technique for camera calibration using only GPS data is presented. A new way of tracking objects that move on a plane in a video is achieved by using the location and size of the bounding box to estimate the distance, achieving an average prediction error of 5.55m per 100m distance from the camera. This solution can be run in real-time at the edge, achieving efficient inference in a low-powered IoT environment, while being also able to track multiple different vessels.
Files and links (1)
Related links
Details
- Title
- Marine Vessel Tracking using a Monocular Camera
- Publication Details
- DeLTA2021-Proceedings of the 2nd International Conference on Deep Learning Theory and Applications, pp.17-28
- Resource Type
- Conference proceeding
- Conference
- International Conference on Deep Learning Theory and Applications, 2nd
- Publisher
- Scitepress
- Copyright
- Copyright © 2021 by SCITEPRESS–Science and Technology Publications, Lda. All rights reserved
- Identifiers
- WOS:000821081200001; 99380178994506600
- Academic Unit
- Hal Marcus College of Science and Engineering ; Computer Science
- Language
- English