首页 > 论文 > 红外技术 > 39卷 > 12期(pp:1114-1119)

一种基于CNN与梯度分水岭算法的卫星图像区域分割识别方法

Method of Satellite Images Region Segmentation and Recognition Based on CNN and Gradient Watershed Algorithm

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

卫星图像的准确分割与识别在军事、环境、民生方面都有着重要的研究意义与价值。传统的区域分割算法如分水岭算法、k-means 算法等在错综复杂的卫星图像中表现不佳,且不能同时给出区域的类别。为解决上述问题,本文提出一种结合CNN 与分水岭算法的图像区域分割方法。该方法首先使用人工标记的区域图像训练CNN(卷积神经网络)分类器,且使其具有旋转不变性及平移不变性,从而能适应不同状态下的图像分类。然后用分水岭算法对图像进行区域粗粒度的聚类,针对分割出的每一个候选区域,使用CNN 分类器对其迭代打分,最后得到分割区域并给出识别结果。实验结果表明,该方法较传统方法有更好效果。

Abstract

The accurate segmentation and recognition of satellite images is very important in military and environmental matters and for people's livelihoods. Traditional region segmentation algorithms, such as the watershed algorithm, k-means algorithm, etc., do not perform well on complex satellite images, and cannot simultaneously display the region category. To address this problem, a method of satellite images region segmentation is proposed based of a convolutional neural network (CNN) and the gradient watershed algorithm. Firstly, the artificial markers of regional images are used to train the CNN classifier to adapt to the different categories of image classification with rotation in variant and translation in variant. Then, the watershed algorithm is used for regional images’ coarse-grained clustering. For each candidate region segmented, CNN classifiers were used to iterate and mark. The experimental region segmentation and the recognition results show that the proposed method is better than the traditional methods.

投稿润色
补充资料

中图分类号:TP389.1

所属栏目:图像处理与仿真

基金项目:重庆市科技研发基地能力提升项目(cstc2014ptsy40003)。

收稿日期:2017-01-10

修改稿日期:2017-12-01

网络出版日期:--

作者单位    点击查看

张日升:重庆通信学院应急通信重庆市重点实验室重庆 400035
朱桂斌:重庆通信学院应急通信重庆市重点实验室重庆 400035
张燕琴:中国人民解放军95894 部队,北京 102211
陈威静:重庆通信学院应急通信重庆市重点实验室重庆 400035

联系人作者:张日升(15320339816@163.com)

备注:张日升(1988-),男,硕士研究生。研究方向:智能信号与信息处理。

【1】Acharya J, Gadhiya S, Raviya K. Segmentation techniques for image analysis: A review[J]. International Journal of Computer Science and Management Research, 2013, 2(1): 1218-1221.

【2】CHEN J, Pappas T N, Mojsilovic A, et al. Adaptive image segmentation based on color and texture[C]// Proceedings of IEEE International Conference on Image Processing, 2002, 3: 777-780.

【3】Fowlkes C, Martin D, Malik J. Learning affinity functions for image segmentation: Combining patch-based and gradient-based approaches[C] //IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003, 2: II-54-61.

【4】Sharif Razavian A, Azizpour H, Sullivan J, et al. CNN features off-the-shelf: an astounding baseline for recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2014: 806-813.

【5】Girshick R. Fast r-cnn[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.

【6】Ciregan D, Meier U, Schmidhuber J. Multi-column deep neural networks for image classification[C]// 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012: 3642-3649.

【7】MA J, BAI H, FENG J, et al. Image segmentation algorithm based on wavelet transformation and watershed[C]//Eighth International Conference on Digital Image Processing of International Society for Optics and Photonics, 2016: 100331L-100331L-5.

【8】YAN R, SHAO L, LIU Y. Nonlocal hierarchical dictionary learning using wavelets for image denoising[J]. IEEE Transactions on Image Processing, 2013, 22(12): 4689-4698.

【9】Hsieh M H, CHENG F C, Shie M C, et al. Fast and efficient median filter for removing 1%-99% levels of salt-and-pepper noise in images[J]. Engineering Applications of Artificial Intelligence, 2013, 26(4): 1333 -1338.

引用该论文

ZHANG Risheng,ZHU Guibin,ZHANG Yanqin,CHEN Weijing. Method of Satellite Images Region Segmentation and Recognition Based on CNN and Gradient Watershed Algorithm[J]. Infrared Technology, 2017, 39(12): 1114-1119

张日升,朱桂斌,张燕琴,陈威静. 一种基于CNN与梯度分水岭算法的卫星图像区域分割识别方法[J]. 红外技术, 2017, 39(12): 1114-1119

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF