基于多特征融合詞包模型的SAR目標(biāo)鑒別算法

宋文青; 王英華; 時(shí)荔蕙; 劉宏偉; 保錚

doi:10.11999/JEIT170086

基于多特征融合詞包模型的SAR目標(biāo)鑒別算法

doi: 10.11999/JEIT170086

基金項(xiàng)目:

國(guó)家自然科學(xué)基金(61671354, 61701379)，國(guó)家杰出青年科學(xué)基金(61525105)，中央高?；究蒲袠I(yè)務(wù)費(fèi)專項(xiàng)資金，陜西省自然科學(xué)基礎(chǔ)研究計(jì)劃(2016JQ6048)

計(jì)量
- 文章訪問數(shù): 1312
- HTML全文瀏覽量: 155
- PDF下載量: 228
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2017-01-23
- 修回日期: 2017-08-25
- 刊出日期: 2017-11-19

SAR Target Discrimination Algorithm Based on Bag-of-words Model with Multi-feature Fusion

Funds:

The National Natural Science Foundation of China (61671354, 61701379), The National Science Fund for Distinguished Young Scholars of China (61525105), The Fundamental Research Funds for the Central Universities, The Natural Science Basic Research Plan in Shaanxi Province of China (2016JQ6048)

摘要

摘要: 針對(duì)復(fù)雜場(chǎng)景中的SAR目標(biāo)鑒別問題，該文提出一種基于多特征融合詞包(Bag-of-Words, BoW)模型的SAR目標(biāo)鑒別算法。在BoW模型底層特征提取階段，算法采用SAR-SIFT特征描述局部區(qū)域的形狀信息；同時(shí)，采用該文基于傳統(tǒng)鑒別特征提出的一組新的SAR圖像局部特征描述局部區(qū)域的對(duì)比度信息和紋理信息。對(duì)于BoW模型中多個(gè)底層特征的融合，算法采用圖像層的特征融合方式生成圖像的全局鑒別特征，其中各單底層特征BoW模型特征的權(quán)系數(shù)通過L2范數(shù)約束的多核學(xué)習(xí)方法訓(xùn)練得到。在MiniSAR實(shí)測(cè)SAR圖像數(shù)據(jù)上的目標(biāo)鑒別實(shí)驗(yàn)表明，與基于傳統(tǒng)鑒別特征以及單底層特征BoW模型特征的鑒別算法相比較，該文基于多特征融合BoW模型SAR目標(biāo)鑒別算法具有更好的鑒別性能。
- SAR /
- 目標(biāo)鑒別 /
- 詞包模型 /
- 底層特征 /
- 多核學(xué)習(xí)
Abstract: In order to solve the SAR target discrimination problem in the real complex scenes, a SAR target discrimination method is proposed based on Bag-of-Words (BoW) model with multiple low-level features fusion. In the low-level feature extraction stage of BoW model, the SAR-SIFT feature is utilized to describe the shape information of local regions of an image sample. And also, a set of new local descriptors is used to capture the contrast information and the texture information of the local regions, which is extracted based on the traditional target discrimination features. For the fusion of different low-level features in BoW model, the image-level feature fusion strategy is implemented to generate the image global feature, which is realized by the Multiple Kernel Learning (MKL) method with L2-norm regularization. Experimental results with the MiniSAR real SAR dataset show that the proposed SAR target discrimination algorithm based on BoW model with multi-feature fusion achieves better discrimination performance compared with methods based on the traditional discrimination features and the BoW model features using single low-level descriptor.
- SAR /
- Target discrimination /
- Bag-of-Words (BoW) model /
- Low-level descriptor /
- Multiple Kernel Learning (MKL)

HTML全文

參考文獻(xiàn)(36)

VERBOUT S M, WEAVER A L, and NOVAK L M. New image features for discriminating targets from clutter[C]. Defense Sensing and Controls. International Society for Optics and Photonics, Aerospace, 1998: 120-137. doi: 10.1117 /12.319439.

KREITHEN D E, HALVERSEN S D, and OWIRKA G J. Discriminating targets from clutter[J]. The Lincoln Laboratory Journal, 1993, 6(1): 25-52.

GAO Gui. An improved scheme for target discrimination in high-resolution SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(1): 277-294. doi: 10.1109/TGRS.2010.2052623.

WANG Yinghua and LIU Hongwei. A hierarchical ship detection scheme for high-resolution SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(10): 4173-4184. doi: 10.1109/TGRS.2012.2189011.

張小強(qiáng), 熊博蒞, 匡綱要. 一種基于變化檢測(cè)技術(shù)的SAR圖像艦船目標(biāo)鑒別方法[J]. 電子與信息學(xué)報(bào), 2015, 37(1): 63-70. doi: 10.11999/JEIT140143.

ZHANG Xiaoqiang, XIONG Boli, and KUANG Gangyao. A ship target discrimination method based on change detection in SAR imagery[J]. Journal of Electronics Information Technology, 2015, 37(1): 63-70. doi: 10.11999/JEIT140143.

PARK J I, PARK S H, and KIM K T. New discrimination features for SAR automatic target recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(3): 476-480. doi: 10.1109/LGRS.2012.2210385.

高貴. SAR圖像目標(biāo)鑒別研究綜述[J]. 信號(hào)處理, 2009(9): 1421-1432. doi: 10.3969/j.issn.1003-0530.2009.09.018.

GAO Gui. Study on target discrimination in SAR images: A survey[J]. Signal Processing, 2009, 25(9): 1421-1432. doi: 10.3969/j.issn.1003-0530.2009.09.018.

WANG Yinghua and LIU Hongwei. SAR target discrimination based on BOW model with sample-reweighted category-specific and shared dictionary learning[J]. IEEE Geoscience and Remote Sesnsing Letters, 2017 in revision.

CSURKA G, DANCE C R, FAN L, et al. Visual categorization with bags of keypoints[C]. European Conference on Computer Vision, Prague, 2004: 1-22.

YANG Jianchao, YU Kai, GONG Yihong, et al. Linear spatial pyramid matching using sparse coding for image classification[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Miami, Florida, 2009: 1794-1801. doi: 10.1109/CVPR.2009.5206757.

王瑞霞, 彭國(guó)華. N-words 模型下Hesse 稀疏表示的圖像檢索算法[J]. 電子與信息學(xué)報(bào), 2016, 38(5): 1115-1122. doi: 10.11999/JEIT150617.

WANG Ruixia and PENG Guohua. Hesse sparse representation under n-word model for image retrieval[J]. Journal of Electronics Information Technology, 2016, 38(5): 1115-1122. doi: 10.11999/JEIT150617.

FAROOQ J. Object detection and identification using SURF and BoW model[C]. International Conference on Computing, Electronic and Electrical Engineering, Quetta, Pakistan, 2016: 318-323.

GEMERT J C, GEUSEBROEK J M, VEENMAN C J, et al. Kernel codebooks for scene categorization[C]. European Conference on Computer Vision, Marseille, France, 2008: 696-709. doi: 10.1007/978-3-540-88690-7_52.

BAHMANYAR R, CUI S, and DATCU M. A comparative study of Bag-of-Words and Bag-of-Topics models of EO image patches[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(6): 1357-1361. doi: 10.1109/LGRS.2015. 2402391.

YAO W, LOFFELD O, and DATCU M. Application and evaluation of a hierarchical patch clustering method for remote sensing images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(6): 2279-2289. doi: 10.1109/JSTARS.2016.2536143.

GLEICH D and SIPOS D. Categorization based on sparse coding for SAR patch categorization[C]. European Conference on Synthetic Aperture Radar, Hamburg, 2016: 1-4.

CUI S, SCHWARZ G, and DATCU M. Remote sensing image classification: no features, no clustering[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(11): 5158-5170. doi: 10.1109/ JSTARS.2015.2495267.

黃凱奇, 任偉強(qiáng), 譚鐵牛. 圖像物體分類與檢測(cè)算法綜述[J]. 計(jì)算機(jī)學(xué)報(bào), 2014, 37(6): 1225-1240. doi: 10.3724/SP.J.1016. 2014.01225.

HUANG Kaiqi, REN Weiqiang, and TAN Tieniu. A review on image classification and detection[J]. Chinese Journal of Computers, 2014, 37(6): 1225-1240. doi: 10.3724/SP.J.1016. 2014.01225.

LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110. doi: 10.1023/B:VISI.0000029664.99615.94.

DELLINGER F, DELON J, GOUSSEAU Y, et al. SAR-SIFT: A SIFT-like algorithm for SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(1): 453-466. doi: 10.1109/TGRS.2014.2323552.

Fernando B, MUSELET D, FROMONT E, et al. Discriminative feature fusion for image classification[C]. IEEE Conference on Computer Vision and Pattern Recognition, Providence, Rhode Island, 2012: 3434-3441. doi: 10.1109/CVPR.2012.6248084.

LUO Wei, YANG Jian, XU Wei, et al. Higher-level feature combination via multiple kernel learning for image classification[J]. Neurocomputing, 2015, 167(C): 209-217. doi: 10.1016/j.neucom.2015.04.075.

LAZEBNIK S, SCHMID C, and PONCE J. Beyond bags of features: spatial pyramid matching for recognizing natural scene categories[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, USA, 2006: 2169-2178. doi: 10.1109/CVPR.2006.68.

BUCAK S S, JIN R, and JAIN A K. Multiple kernel learning for visual object recognition: a review[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(7): 1354-1369. doi: 10.1109/TPAMI.2013.212.

LI F F and PERONA P. A bayesian hierarchical model for learning natural scene categories[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, USA, 2005(2): 524-531. doi: 10.1109/CVPR.2005. 16.

MIKOLAJCZYK K and SCHMID C. A performance evaluation of local descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630. doi: 10.1109/TPAMI.2005.188.

FJORTOFT R, LOPES A, and MARTHON P. An optimal multiedge detector for SAR image segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing, 1998, 36(3): 793-802. doi: 10.1109/36.673672.

SMITH M E and VARSHNEY P K. Intelligent CFAR processor based on data variability[J]. IEEE Transactions on Aerospace and Electronic Systems, 2000, 36(3): 837-847. doi: 10.1109/7.869503.

ELDARYMLI K, MCGUIRE P, POWER D, et al. Target detection in synthetic aperture radar imagery: A state- of-the-art survey[J]. Journal of Applied Remote Sensing, 2013, 7(1): 1-35. doi: 10.1117/1.JRS.7.071598.

YU Wenyi, WANG Yinghua, and LIU Hongwei. Superpixel- based CFAR target detection for high-resolution SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(5): 730-734. doi: 10.1109/LGRS.2016.2540809.

HE H and GARCIA E A. Learning from imbalanced data[J]. IEEE Transactions on Knowledge and Data Engineering, 2009, 21(9): 1263-1284. doi: 1263-1284.10.1109/TKDE.2008. 239.

DING Jun, LIU Hongwei, CHEN Bo, et al. Convolutional neural network with data augmentation for SAR Target recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(3): 1-5. doi: 10.1109/LGRS.2015.2513754.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)