基于卷積神經(jīng)網(wǎng)絡(luò)的SAR圖像目標(biāo)檢測(cè)算法

杜蘭; 劉彬; 王燕; 劉宏偉; 代慧

doi:10.11999/JEIT161032

基于卷積神經(jīng)網(wǎng)絡(luò)的SAR圖像目標(biāo)檢測(cè)算法

doi: 10.11999/JEIT161032

杜蘭^1, ,,
劉彬¹,
王燕¹,
劉宏偉¹,
代慧¹

基金項(xiàng)目:

國(guó)家自然科學(xué)基金(61271024, 61322103, 61525105)，高等學(xué)校博士學(xué)科點(diǎn)專項(xiàng)科研基金博導(dǎo)類基金(20130203110013)，陜西省自然科學(xué)基金(2015JZ016)

計(jì)量
- 文章訪問數(shù): 2403
- HTML全文瀏覽量: 312
- PDF下載量: 982
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2016-10-08
- 修回日期: 2016-11-24
- 刊出日期: 2016-12-19

Target Detection Method Based on Convolutional Neural Network for SAR Image

DU Lan^{1
, ,},
LIU Bin¹,
WANG Yan¹,
LIU Hongwei¹,
DAI Hui¹

Funds:

The National Natural Science Foundation of China (61271024, 61322103, 61525105), The Foundation for Doctoral Supervisor of China (20130203110013), The Natural Science Foundation of Shaanxi Province (2015JZ016)

摘要

摘要: 該文研究了訓(xùn)練樣本不足的情況下利用卷積神經(jīng)網(wǎng)絡(luò)(Convolutional Neural Network, CNN)對(duì)合成孔徑雷達(dá)(SAR)圖像實(shí)現(xiàn)目標(biāo)檢測(cè)的問題。利用已有的完備數(shù)據(jù)集來輔助場(chǎng)景復(fù)雜且訓(xùn)練樣本不足的數(shù)據(jù)集進(jìn)行檢測(cè)。首先用已有的完備數(shù)據(jù)集訓(xùn)練得到CNN分類模型，用于對(duì)候選區(qū)域提取網(wǎng)絡(luò)和目標(biāo)檢測(cè)網(wǎng)絡(luò)做參數(shù)初始化；然后利用完備數(shù)據(jù)集對(duì)訓(xùn)練數(shù)據(jù)集做擴(kuò)充；最后通過四步訓(xùn)練法得到候選區(qū)域提取模型和目標(biāo)檢測(cè)模型。實(shí)測(cè)數(shù)據(jù)的實(shí)驗(yàn)結(jié)果證明，所提方法在SAR圖像目標(biāo)檢測(cè)中可以獲得較好的檢測(cè)效果。
- 合成孔徑雷達(dá) /
- 目標(biāo)檢測(cè) /
- 卷積神經(jīng)網(wǎng)絡(luò) /
- 訓(xùn)練數(shù)據(jù)擴(kuò)充
Abstract: This paper studies the issue of SAR target detection with CNN when the training samples are insufficient. The existing complete dataset is employed to assist accomplishing target detection task, where the training samples are not enough and the scene is complicated. Firstly, the existing complete dataset with image-level annotations is used to pre-train a CNN classification model, which is utilized to initialize the region proposal network and detection network. Then, the training dataset is enlarged with the existing complete dataset. Finally, the region proposal model and detection model are obtained through the pragmatic 4-step training algorithm with the augmented training dataset. The experimental results on the measured data demonstrate that the proposed method can improve the detection performance compared with the traditional detection methods.
- SAR /
- Target detection /
- Convolutional Neural Network (CNN) /
- Training data augmentation

HTML全文

參考文獻(xiàn)(17)

XING X W, CHEN Z L, ZOU H X, et al. A fast algorithm based on two-stage CFAR for detecting ships in SAR images [C]. The 2nd Asian-Pacific Conference on Synthetic Aperture Radar, Xian, China, 2009: 506-509.

LENG X, JI K, YANG K, et al. A bilateral CFAR algorithm for ship detection in SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(7): 1536-1540. doi: 10.1109 /LGRS.2015.2412174.

JI Y, ZHANG J, MENG J, et al. A new CFAR ship target detection method in SAR imagery[J]. Acta Oceanologica Sinica, 2010, 29(1): 12-16.

ELDHUSET K. An automatic ship and ship wake detection system for spaceborne SAR images in coastal regions[J]. IEEE Transactions on Geoscience and Remote Sensing, 1996, 34(4): 1010-1019. doi: 10.1109/36.508418.

KRIZHEVSKY A, SUTSKEVER I, and HINTON G E. Imagenet classification with deep convolutional neural networks[C]. Advances in Neural Information Processing Systems, Lake Tahoe, Nevada, USA, 2012: 1097-1105.

SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, Massachusetts, USA, 2015: 1-9.

ZHANG X, ZOU J, MING X, et al. Efficient and accurate approximations of nonlinear convolutional networks[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, Massachusetts, USA, 2015: 1984-1992.

HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]. Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA, 2016: 770-778.

ZEILER M D and FERGUS R. Visualizing and understanding convolutional networks[C]. European Conference on Computer Vision. Springer International Publishing, Zurich, Swizterland, 2014: 818-833.

GOODFELLOW I J, WARDE Farley D, MIRZA M, et al. Maxout networks[J]. International Conference on Machine Learning, 2013, 28(3): 1319-1327.

HE K, ZHANG X, REN S, et al. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification[C]. International Conference on Computer Vision, Santiago, Chile, 2015: 1026-1034.

GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, Ohio, USA, 2014: 580-587.

GIRSHICK R. Fast R-CNN[C]. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 1440-1448.

REN S, HE K, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[C]. Advances in Neural Information Processing Systems, Montral, Canada, 2015: 91-99.

IOFFE S and SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]. International Conference on Machine Learning, Lille, France, 2015: 448-456.

LONG J, SHELHAMER E, and DARRELL T. Fully convolutional networks for semantic segmentation[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, Massachusetts, USA, 2015: 3431-3440.

GAO G, LIU L, ZHAO L, et al. An adaptive and fast CFAR algorithm based on automatic censoring for target detection in high-resolution SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(6): 1685-1697. doi: 10.1109/TGRS.2008.2006504.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)