Region Based CNN for Foreign Object Debris Detection on Airfield Pavement
| Autor: | Jun Qi, Cai Meng, Xiangzhi Bai, Miaoming Liu, Peng Wang, Xiaoguang Cao, Guoping Gong |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Computer science
convolutional neural network vehicular imaging sensors 02 engineering and technology lcsh:Chemical technology 01 natural sciences Biochemistry Convolutional neural network Article Analytical Chemistry Optical imaging Foreign object damage 0202 electrical engineering electronic engineering information engineering lcsh:TP1-1185 Computer vision Electrical and Electronic Engineering Instrumentation business.industry 010401 analytical chemistry Detector object detection Atomic and Molecular Physics and Optics Object detection 0104 chemical sciences foreign object debris 020201 artificial intelligence & image processing Artificial intelligence business |
| Zdroj: | Sensors (Basel, Switzerland) Sensors, Vol 18, Iss 3, p 737 (2018) Sensors; Volume 18; Issue 3; Pages: 737 |
| ISSN: | 1424-8220 |
| Popis: | In this paper, a novel algorithm based on convolutional neural network (CNN) is proposed to detect foreign object debris (FOD) based on optical imaging sensors. It contains two modules, the improved region proposal network (RPN) and spatial transformer network (STN) based CNN classifier. In the improved RPN, some extra select rules are designed and deployed to generate high quality candidates with fewer numbers. Moreover, the efficiency of CNN detector is significantly improved by introducing STN layer. Compared to faster R-CNN and single shot multiBox detector (SSD), the proposed algorithm achieves better result for FOD detection on airfield pavement in the experiment. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|