Toward robust multitype and orientation detection of vessels in maritime surveillance
Authors:
- 1 May 2020
- journal article
- research article
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 29 (03) , 033015-18
Abstract
Reliable multitype and orientation vessel detection is of vital importance for maritime surveillance. We develop three separate convolutional neural network (CNN) models for high-performance single-class vessel detection and then multiclass vessel-type/orientation detection. We also propose a modular combined network, which enhances the multiclass operation. The initial three models provide reliable F1 scores of 85%, 82%, and 76%, respectively. In addition, the modular combined approach improves the F1 scores for the multitype and orientation vessel detection by 2% and 3%, respectively. The training and testing were done on a dataset, including the multitype/orientation annotations, covering 31,078 vessel labels (10 vessel types and 5 orientations), which is offered to public access.Keywords
This publication has 28 references indexed in Scilit:
- MARVEL: A Large-Scale Image Dataset for Maritime Vessels2017
- Water Region Extraction in Thermal and RGB Sequences Using Spatiotemporally-Oriented Energy FeaturesElectronic Imaging, 2017
- SSD: Single Shot MultiBox Detector2016
- Ship Detection in Spaceborne Optical Image With SVD NetworksIEEE Transactions on Geoscience and Remote Sensing, 2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- VAIS: A dataset for recognizing maritime imagery in the visible and infrared spectrums2015
- Region-Based Convolutional Networks for Accurate Object Detection and SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Ship Detection From Optical Satellite Images Based on Sea Surface AnalysisIEEE Geoscience and Remote Sensing Letters, 2013
- 50 Years of object recognition: Directions forwardComputer Vision and Image Understanding, 2013
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013