信号与信息处理

基于PLSA和BoW的高分遥感影像小型港口检测

展开
  • 1. 武汉大学 遥感信息工程学院, 武汉 430079;
    2. 北京洛斯达数字遥感技术有限公司 中南分公司, 武汉 430070;
    3. 国网经济技术研究院有限公司, 北京 102209;
    4. 中国地质大学(武汉)信息工程学院, 武汉 430070

收稿日期: 2018-03-03

  修回日期: 2018-07-15

  网络出版日期: 2019-05-31

基金资助

国家重点研发计划基金(No.2016YFB0502603);国家电网公司科技项目基金(No.JYYKJXM(2017)-011)资助

Small Harbor Detection Based on PLSA and BoW in High Resolution Remotely Sensed Imagery

Expand
  • 1. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China;
    2. Zhongnan Branch, Beijing North-Start Digital Remote Sensing Technology Co. Ltd., Wuhan 430070, China;
    3. State Grid Economic and Technical Research Institute Co. Ltd., Beijing 102209, China;
    4. Faculty of Information Engineering, China University of Geosciences, Wuhan 430070, China

Received date: 2018-03-03

  Revised date: 2018-07-15

  Online published: 2019-05-31

摘要

高分辨率遥感影像可以为小型港口的监管提供有效途径.针对小型港口形态多样、特征难以描述等问题,研究了一种基于概率潜在语义分析(probabilistic latent semanticanalysis,PLSA)模型和词袋(bag of words,BoW)模型的小型港口检测方法.该方法首先提取水岸线以缩小搜索范围;然后将灰度直方图、归一化差分水体指数、分形维数特征引入PLSA模型生成特征描述集,将加速鲁棒特征向量引入BoW模型生成视觉词典;根据以上特征描述集和构建的小型港口样本库训练SVM分类器,利用22幅影像进行小型港口检测实验.实验结果表明,相比于只使用常见单一特征或单一模型,该方法的检测结果更佳,耗时更少.

本文引用格式

毕奇, 童心, 张济勇, 许凯, 张涵, 秦昆 . 基于PLSA和BoW的高分遥感影像小型港口检测[J]. 应用科学学报, 2019 , 37(3) : 301 -312 . DOI: 10.3969/j.issn.0255-8297.2019.03.001

Abstract

Remotely sensed high resolution imaging is an effective way to monitor small harbors along coastlines. Harbors vary a lot in features and are usually difficult to describe. This paper studies a harbor detection method based on probabilistic latent semantic analysis (PLSA) and bag of words (BoW). Firstly, coastlines are extracted to shrink searching areas. Then grey level histogram, normalized differential water index and fractal dimension features are introduced to PLSA model to generate feature description sets. Eigenvectors of speeded up robust features are introduced to BoW model to generate visual dictionary. Finally, after collecting samples of small harbors, support vector machine (SVM) classifiers are trained based on the above features. Based on the trained classifier, small harbor detection is implemented based on 22 images. Experiments show that the proposed method reaches the best accuracy with relatively low time cost than single-feature models and single PLSA or BoW model.

参考文献

[1] 刘扬,付征叶,郑逢斌. 高分辨率遥感影像目标分类与识别研究进展[J]. 地球信息科学学报,2015, 17(9):1080-1091. Liu Y, Fu Z Y, Zheng F B. Review on high resolution remote sensing image classification and recognition[J]. Journal of Geo-Information Science, 2015, 17(9):1080-1091. (in Chinese)
[2] Cheng G, Han J. A survey on object detection in optical remote sensing images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 117:11-28.
[3] Isbister E J, Griswold W R. Shore-based radar for harbor surveillance[J]. Electrical Engineering, 2013, 71(12):1072-1077.
[4] 张志龙,张焱,沈振康. 基于特征谱的高分辨率遥感图像港口识别方法[J]. 电子学报,2010, 38(9):2184-2188. Zhang Z L, Zhang Y, Shen Z K. Port recognition in high resolution remote sensing images based on feature spectrum[J]. Acta Electronica Sinica, 2010, 38(9):2184-2188. (in Chinese)
[5] 杨耘,王树根,邱丹丹. 基于规则的高分辨率影像港口识别模型[J]. 测绘信息与工程,2005(5):40-42. Yang Y, Wang S G, Qiu D D. Harbor recognition model from high-resolution images based on rules[J]. Journal of Geomatics, 2005(5):40-42. (in Chinese)
[6] 陈琪,陆军,匡纲要. 基于感知编组的遥感图像港口提取方法[J]. 信号处理,2010(7):1099-1103. Chen Q, Lu J, Kuang G Y. Harbor detection method of remote sensing images based on perceptual organization[J]. Signal Processing, 2010(7):1099-1103. (in Chinese)
[7] 张志龙. 基于遥感图像的重要目标特征提取与识别方法研究[D]. 长沙:国防科学技术大学,2005.
[8] Ye Q, Huo H, Zhu T, Fang T. Harbor detection in large-scale remote sensing images using both deep-learned and topological structure features[C]//International Symposium on Computational Intelligence and Design, Hangzhou, China, 2017:218-222.
[9] Bi F, Chen J, Zhuang Y, Bian M, Zhang Q. A decision mixture model-based method for inshore ship detection using high-resolution remote sensing images[J]. Sensors, 2017, 17(7):1470.
[10] 徐侃,杨文,陈丽君,孙洪. 利用主题模型的遥感图像场景分类[J]. 武汉大学学报(信息科学版),2011, 36(5):540-543. Xu K, Yang W, Chen L J, Sun H. Satellite image scene categorization based on topic models[J]. Geomatics and Information Science of Wuhan University, 2011, 36(5):540-543. (in Chinese)
[11] 王莹. 基于BoW模型的图像分类方法研究[D]. 哈尔滨:哈尔滨工程大学,2012.
[12] 刘春,殷君君,杨健. 基于岸线特征点合并的极化SAR图像小型港口检测[J]. 清华大学学报(自然科学版),2015(8):849-853. Liu C, Yin J J, Yang J. Small harbor detection in polarimetric SAR images based on coastline feature point merging[J]. Journal of Tsinghua University (Natural Science Edition), 2015(8):849-853. (in Chinese)
[13] Alhamdan M, Cruise J, Rickman D, Quattrochi D. Effects of spatial and spectral resolutions on fractal dimensions in forested landscapes[J]. Remote Sensing, 2010, 2(3):611-640.
[14] Mcfeeters S K. The use of the normalized difference water index (NDWI) in the delineation of open water features[J]. International Journal of Remote Sensing, 1996, 17(7):1425-1432.
[15] Bay H, Tuytelaars T, Gool L V. SURF:speeded up robust features[J]. Computer Vision and Image Understanding, 2006, 110(3):404-417.
[16] 郑肇葆, 郑宏. 利用PLSA技术进行图像分割[J]. 武汉大学学报(信息科学版), 2012, 37(2):132-135. Zheng Z B, Zheng H. Image segmentation method based on PLSA technology[J]. Geomatics and Information Science of Wuhan University, 2012, 37(2):132-135. (in Chinese)
[17] Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S. SLIC superpixels compared to state-of-the-art superpixel methods[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11):2274-2282.
[18] Oh K H, Kim S H, Na I S, Kim G B. Object segmentation using mean-shift with grid-mask for grab cut algorithm[J]. International Journal of Software Engineering and Its Applications, 2014, 8(2):409-416.
文章导航

/