کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
6949133 1451233 2018 11 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
A light and faster regional convolutional neural network for object detection in optical remote sensing images
ترجمه فارسی عنوان
یک شبکه عصبی پیچیده کانونی نور و سریع برای تشخیص شی در تصاویر نوری سنجش از راه دور
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر سیستم های اطلاعاتی
چکیده انگلیسی
Detection of objects from satellite optical remote sensing images is very important for many commercial and governmental applications. With the development of deep convolutional neural networks (deep CNNs), the field of object detection has seen tremendous advances. Currently, objects in satellite remote sensing images can be detected using deep CNNs. In general, optical remote sensing images contain many dense and small objects, and the use of the original Faster Regional CNN framework does not yield a suitably high precision. Therefore, after careful analysis we adopt dense convoluted networks, a multi-scale representation and various combinations of improvement schemes to enhance the structure of the base VGG16-Net for improving the precision. We propose an approach to reduce the test-time (detection time) and memory requirements. To validate the effectiveness of our approach, we perform experiments using satellite remote sensing image datasets of aircraft and automobiles. The results show that the improved network structure can detect objects in satellite optical remote sensing images more accurately and efficiently.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: ISPRS Journal of Photogrammetry and Remote Sensing - Volume 141, July 2018, Pages 208-218
نویسندگان
, , , , ,