相似性約束的深度置信網(wǎng)絡(luò)在SAR圖像目標(biāo)識(shí)別的應(yīng)用
doi: 10.11999/JEIT150366
基金項(xiàng)目:
國家自然科學(xué)基金(61372132, 61201292)，新世紀(jì)優(yōu)秀人才支持計(jì)劃(NCET-13-0945)，青年千人計(jì)劃
Similarity Constrained Deep Belief Networks with Application to SAR Image Target Recognition
Funds:
The National Natural Science Foundation of China (61372132, 61201292), The Program for New Century Excellent Talents (NCET-13-0945), The Program for Young Thousand Talent by Chinese Central Government
-
摘要: 特征提取是合成孔徑雷達(dá)(SAR)圖像目標(biāo)識(shí)別的關(guān)鍵環(huán)節(jié)。SAR圖像中存在的相干斑點(diǎn)和非光滑特性使得傳統(tǒng)針對(duì)光學(xué)圖像的特征提取方法變得很難應(yīng)用。雖然可以采用深度置信網(wǎng)絡(luò)(DBN)自動(dòng)地進(jìn)行特征學(xué)習(xí)，但是該方法屬于無監(jiān)督學(xué)習(xí)方法，這使得學(xué)習(xí)到的特征與具體的任務(wù)是無關(guān)的。該文提出一種叫做相似性約束的受限玻爾茲曼機(jī)模型。該模型在學(xué)習(xí)過程中通過約束特征向量之間的相似性達(dá)到引入監(jiān)督信息的目的。另外，可以將多個(gè)相似性約束的受限玻爾茲曼機(jī)堆疊成一種新的深度模型，稱其為相似性約束的深度置信網(wǎng)絡(luò)模型。實(shí)驗(yàn)結(jié)果表明在SAR圖像目標(biāo)識(shí)別應(yīng)用中，該方法相比主成分分析(PCA)以及原始DBN具有更好的識(shí)別性能。
-
關(guān)鍵詞:
- SAR圖像目標(biāo)識(shí)別 /
- 特征提取 /
- 深度置信網(wǎng)絡(luò) /
- 相似性約束的深度置信網(wǎng)絡(luò)
Abstract: Feature extraction is a key step in SAR image target recognition. The existence of speckle and discontinuity makes the conventional methods for natural images difficult to apply. Although Deep Belief Networks (DBNs) can be used to learn feature representations automatically, they work essentially in an unsupervised way, and hence the learned features are task-irrelevant. A new Boltzmann machine called Similarity constrained Restricted Boltzmann Machines (SRBMs) is proposed, which injects the supervised information into learning process through constraint on the similarity of feature vectors. Furthermore, a deep architecture named Similarity constrained DBNs (SDBNs) is constructed by layer-wise stacking of SRBMs. Experimental results show the proposed SDBN is superior to DBN and PCA in SAR image target recognition. -
ZHAO Qun, PRINCIPE J C, et al. Support vector machines for SAR automatic target recognition[J]. IEEE Transactions on Aerospace and Electronic Systems, 2001, 37(2): 643-655. SUN Yijun, LIU Zhipeng, TODOROVIC S, et al. Adaptive boosting for synthetic aperture radar automatic target recognition[J]. IEEE Transactions on Aerospace and Electronic Systems, 2007, 43(1): 112-125. ZHOU Jianxiong, SHI Zhiguang, CHENG Xiao, et al. Automatic target recognition of SAR images based on global scattering center model[J]. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(10): 3713-3729. PARK Jong-II, PARK Sang-hong, and KIM Kyung-tae. New discrimination features for SAR automatic target recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(3): 476-480. ABDEL-RAHMAN M, GEORGE D, and GEOFFREY H. Acoustic modeling using deep belief networks [J]. IEEE Transactions on Audio, Speech, and Language Processing, 2012, 20(1): 14-22. NAVDEEP J and GEOFFREY H. Learning a better representation of speech soundwaves using restricted Boltzmann machines[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Prague, 2011: 5884-5887. WU Yue, WANG Zuoguan, and JI Qiang. Facial feature tracking under varying facial expressions and face poses based on RBM[C]. IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, 2013: 3452-3459. HUGO L and YOSHUA B. Classification using discriminative restricted Boltzmann machines[C]. International Conference on Machine Learning, New York, NY, USA, 2008: 536-543. UMAMAHESH S, VISHAL M, and RAJ Raghu G. SAR automatic target recognition using discriminative graphical models[J]. IEEE Transactions on Aerospace and Electronic Systems, 2014, 50(1): 591-606. LIU M, WU Y, ZHANG P, et al. SAR target configuration recognition using locality preserving property and Gaussian mixture distribution[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(2): 268-272. YOSHUA B, AARON C, and PASCAL V. Representation learning: A review and new perspectives[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8): 1798-1828. FISCHER A and IGEL C. Training restricted Boltzmann machines: An introduction[J]. Pattern Recognition, 2014, 47(1): 25-39. YOSHUA B, LAMBLIN P, POPOVICI D, et al. Greedy layer-wise training of deep networks[C]. Proceedings of Advances in Neural Information Processing Systems, Vancouver, British Columbia, Canada, 2007: 153-160. GEOFFREY H. Training products of experts by minimizing contrastive divergence[J]. Neural Computation, 2002, 14(8): 1771-1800. HE Xiaofei, YAN Shuicheng, HU Yuxiao, et al. Face recognition using laplacianfaces[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(3): 328-340. -
計(jì)量
- 文章訪問數(shù): 1634
- HTML全文瀏覽量: 157
- PDF下載量: 740
- 被引次數(shù): 0
下載:
