原文传递
Toward Automated Aerial Refueling: Automated Visual Aircraft Identification with Convolutional Neural Networks.
| 题名： | Toward Automated Aerial Refueling: Automated Visual Aircraft Identification with Convolutional Neural Networks. |
| 作者： | Mash, R. L. |
| 关键词： | Computer vision, Artificial neural networks, Automata theory, Machine learning, Image recognition, Artificial intelligence software, Pattern recognition, Information processing, Refueling in flight, Data mining, Graphics processing unit, Aircrafts, Identification systems, Deep learning, Aircraft identification, Convolutional neural network |
| 摘要： | In the military domain of autonomous aerial refueling operations, automated visual recognition of an approaching aircraft critically supports mission goals. These scholarly articles leverage recent developments in the field of natural image pattern recognition with deep Convolutional Neural Networks (CNNs). The first article reviews the operational details of CNNs, then demonstrates a hyper parameter optimization process. The second investigates advanced forms of data augmentation in terms of image recognition performance. Finally, the third article demonstrates a novel ensemble confidence measure as well as a modified ensemble compression technique which retains a useful confidence measure in a single student network. |
| 报告类型： | 科技报告 |
相关文献
- Transfer Learning in Convolutional Neural Networks for Fine-Grained Image Classification.
- Learning Robust Radio Frequency Fingerprints Using Deep Convolutional Neural Networks.
- Predicting Adverse Events and their Precursors in Aviation Using Multi-Class Multiple-Instance Learning.
- SPECTRAL BASIS NEURAL NETWORKS FOR REAL-TIME TRAVEL TIME FORECASTING.
- Deep Learning Techniques to Estimate 3D Position in Stereoscopic Imagery.
- DEVELOPMENT OF NEURAL SIGNAL CONTROL SYSTEM--TOWARD INTELLIGENT TRAFFIC SIGNAL CONTROL.
检索历史
应用推荐
