Aircraft Visual Identification by Neural Networks
Publish place: 07th Conference of Iranian Aerospace Society
Publish Year: 1386
نوع سند: مقاله کنفرانسی
زبان: English
View: 3,056
This Paper With 6 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
این Paper در بخشهای موضوعی زیر دسته بندی شده است:
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
AEROSPACE07_194
تاریخ نمایه سازی: 1 مرداد 1387
Abstract:
In the present paper, an efficient method for three dimensional aircraft pattern recognition is introduced. In this method, a set of simple area based features extracted from silhouette of aerial vehicles are used to recognize an aircraft type from its optical or infrared images taken by a CCD camera or a FLIR sensor. These images can be taken from any direction and distance relative to the flying aircraft. A multilayer perceptron neural network has been used for the purpose of aircraft classification. The network training has been carried out using a library of images generated by a 3D model of each aircraft. The neural network is successfully trained and used to recognize and classify arbitrary real aircraft images. The results show more than 90% accuracy in ideal conditions and very good robustness in the presence of noise.
Keywords:
Recognition-Visual Identification-Neural Networks-Image Processing
Authors
Fariborz Saghafi
Associate Professor, Aerospace Engineering Department, Sharif University of Technology
Seyed Mohammad Khansari Zadeh
Graduate Student, Graduate Students, Aerospace Engineering Department, Sharif University of Technology
Vadud Etminan Bakhsh
Graduate Student, Graduate Students, Aerospace Engineering Department, Sharif University of Technology
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :