Maritime detection framework 2.0: A new approach of maritime target detection in electro-optical sensors
Autor: | Wyke Huizinga, R.J.M. den Hollander, Raimon Pruim, S.P. van den Broek, Judith Dijk, M.M.G. Wilmer, A.G. van Opbroek, N. van der Stap, Klamer Schutte |
---|---|
Rok vydání: | 2018 |
Předmět: |
Infrared devices
Computer science Errors Real-time computing Image processing 02 engineering and technology 01 natural sciences Constant false alarm rate 010309 optics 0103 physical sciences Detection performance 0202 electrical engineering electronic engineering information engineering Detection theory Detection probabilities Electro-optics business.industry Electro-optical sensor Deep learning Detector IRST Automated vessel detection Automation Identification (information) Electrooptical sensors 020201 artificial intelligence & image processing Tracking technology Artificial intelligence Technological trends Optical data processing business Ship detection Signal detection |
Zdroj: | Electro-Optical and Infrared Systems: Technology and Applications XV 2018, 12 September 2018 through 13 September 2018, Hickman, D.L.Bursing, H.Huckridge, D.A., Proceedings of SPIE-The International Society for Optical Engineering, 10795 |
Popis: | Detecting maritime targets with electro-optical sensors is an active area of research. One current trend is to automate target detection through image processing or computer vision. Automation of target detection will decrease the number of people required for lower-level tasks, which frees capacity for higher-level tasks. A second trend is that the targets of interest are changing; more distributed and smaller targets are of increasing interest. Technological trends enable combined detection and identification of targets through machine learning. These trends and new technologies require a new approach in target detection strategies with specific attention to choosing which sensors and platforms to deploy. In our current research, we propose 'maritime detection framework 2.0', in which multi-platform sensors are combined with detection algorithms. In this paper, we present a comparison of detection algorithms for EO sensors within our developed framework and quantify the performance of this framework on representative data. Automatic detection can be performed within the proposed framework in three ways: 1) using existing detectors, such as detectors based on movement or local intensities; 2) using a newly developed detector based on saliency on the scene level; and 3) using a state-of-The-Art deep learning method. After detection, false alarms are suppressed using consecutive tracking approaches. The performance of these detection methods is compared by evaluating the detection probability versus the false alarm rate for realistic multi-sensor data. New types of maritime targets require new target detection strategies. Combining new detection strategies with existing tracking technologies shows potential increase in detection performance of the complete framework. © 2018 SPIE. |
Databáze: | OpenAIRE |
Externí odkaz: |