联合显著性与多层卷积神经网络的高分影像场景分类_何小飞.pdfVIP

45 9 测 绘 学 报 Vol． 45 ，No． 9 第 卷 第 期 20 16 9 Acta Geodaetica et Cartographica Sinica September ，20 16 年 月 : ， ， ， ． ［J］． ，20 16 ，45 (9 ):1073-1080 ． DOI : 引文格式 何小飞 邹峥嵘 陶超 等 联合显著性和多层卷积神经网络的高分影像场景分类 测绘学报 10 ． 11947 /j ． AGCS． 20 16 ． 20 150612 ． HE Xiaofei ，ZOU Zhengrong ，TAO Chao ，et al． Combined Saliency with Multi-Convolutional Neural Network for High Ｒesolution Ｒemote Sensing Scene Classification ［J］． Acta Geodaetica et Cartographica Sinica ，20 16 ，45 (9):1073-1080 ． DOI :10 ． 11947 /j ． AGCS． 20 16 ． 20 150612 ． 联合显著性和多层卷积神经网络的高分影像场景分类 ， ， ， 何小飞 邹峥嵘 陶 超 张佳兴 ， 4 10083 中南大学地球科学与信息物理学院 湖南长沙 Combined Saliency with Multi-Convolutional Neural Network for High Ｒesolution Ｒemote Sensing Scene Classification HE Xiaofei ，ZOU Zhengrong ，TAO Chao ，ZHANG Jiaxing School of Geosciences and Info-Physics ，Central South University ，Changsha 4 10083 ，China Abstract :The scene information existing in high resolution remote sensing images is important for image interpretation and understanding of the real world． Traditional scene classification methods often use middle and low-level artificial features，but high resolution images have rich information and complex scene configuration ， which need high-level feature to express． A joint saliency and multi-convolutional neural network method is proposed in this paper． Firstly ，we obtain meaningful patches that include dominant image information by saliency sampling． Secondly ，these patches will be set as a sample input to the convolutional neural network for training ， obtain feature expression on different levels． Finally ，we embed the multi-layer f