首页 | 本学科首页   官方微博 | 高级检索  
     

深度先验图像特征在城市遥感大数据中的应用
引用本文:申金晟,池明旻. 深度先验图像特征在城市遥感大数据中的应用[J]. 计算机系统应用, 2018, 27(9): 33-39
作者姓名:申金晟  池明旻
作者单位:复旦大学 计算机科学技术学院, 上海 201203;上海市数据科学重点实验室, 上海 201203,复旦大学 计算机科学技术学院, 上海 201203;上海市数据科学重点实验室, 上海 201203
基金项目:国家重点研发计划(2016YFE0100300)
摘    要:图像特征提取始终是计算机视觉和图像处理的核心任务.随着深度学习的快速发展,卷积神经网络逐渐取代传统图像特征算子,成为特征提取的主要算法.本文针对城市遥感数据众包标记系统中的数据关联问题,结合卷积神经网络和池化编码,提出基于深度先验的图像特征提取方法.该特征能有效聚焦室外图像近处物体,并通过图像检索实验验证了其对室外图像的良好表征能力.

关 键 词:图像特征提取  城市遥感大数据  和池化  深度先验
收稿时间:2017-12-06
修稿时间:2017-12-27

Application of Image Feature Extraction Based on Depth Prior in Urban Remote Sensing Big Data
SHEN Jin-Sheng and CHI Ming-Min. Application of Image Feature Extraction Based on Depth Prior in Urban Remote Sensing Big Data[J]. Computer Systems& Applications, 2018, 27(9): 33-39
Authors:SHEN Jin-Sheng and CHI Ming-Min
Affiliation:School of Computer Science, Fudan University, Shanghai 201203, China;Shanghai Key Laboratory of Data Science, Shanghai 201203, China and School of Computer Science, Fudan University, Shanghai 201203, China;Shanghai Key Laboratory of Data Science, Shanghai 201203, China
Abstract:Image feature extraction is always the core task of computer vision and image processing. With the rapid development of deep learning, the Convolutional Neural Network (CNN) has gradually replaced the traditional image feature operator and became the main algorithm for feature extraction. Combined with CNN and sum pooling, we propose a new image feature extraction algorithm based on depth prior aiming at the data association problem in the crowd sourcing labeling system for urban remote sensing data. The feature can effectively focus on the objects in the vicinity of outdoor images and verify their good characterization of outdoor images via image retrieval experiments.
Keywords:image feature extraction  urban remote sensing big data  sum pooling  depth prior
点击此处可从《计算机系统应用》浏览原始摘要信息
点击此处可从《计算机系统应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号