原文传递
Convolutional Neural Networks For Detection And Classification Of Maritime Vessels In Electro-Optical Satellite Imagery.
| 题名： | Convolutional Neural Networks For Detection And Classification Of Maritime Vessels In Electro-Optical Satellite Imagery. |
| 作者： | Rice, K. |
| 关键词： | Theses, Satellite imaging, Detectors, Artificial neural networks, Deep learning, Machine learning, Computer vision, Electro-optical sensors, Ships, Maritime vessels, Transfer learningsingle shot detector, Satellite imagery, Convolutional neural network |
| 摘要： | The ability to locate and identify vessels of interest in satellite imagery plays a vital role in maintaining maritime security. Recent studies have demonstrated that convolutional neural networks can be used to automatically classify or detect ships in satellite images; however, this technique requires large amounts of training data and computational power that may not be readily available in an operational environment. We seek to show that the process of transfer learning can be used to adapt open source convolutional neural network architectures pre-trained on large datasets to Department of Defense-specific image classification and detection tasks. We test this hypothesis by retraining both the VGG-16 image classification architecture and a VGG-16 based Single Shot Detector on a dataset comprised of satellite images containing ships. We first examine the performance of these retrained networks on the single category task of classifying or detecting ships in satellite imagery. We then evaluate model performance on datasets in which a fraction of the images contains blur and noise to simulate degraded satellite imagery. Finally, we test the modelsability to distinguish between subcategories of ships. We show that transfer learning can be leveraged toreduce both the size of training set and the training time required to produce an effective classification or detection model to meet the Department of Defenses analysis needs. |
| 报告类型： | 科技报告 |
相关文献
- Small Satellite Sensor and Processing Analysis for Maritime Domain Awareness.
- Using Neural Networks to Correlate Satellite Imagery and Ground-Truth Data; Final rept
- Performance Assessment of a Hybrid Radar and Electro-Optical Debris Detection System.
- Autoencoded Reduced Clusters for Anomaly Detection Enrichment (ARCADE) in Hyperspectral Imagery.
- Transfer Learning in Convolutional Neural Networks for Fine-Grained Image Classification.
- Remote Minehunting System (RMS) as of FY 2017 President's Budget.
检索历史
应用推荐
