中文

Journal of Shanghai University >

2022 , Vol. 28 >Issue 2: 314 - 323

DOI: https://doi.org/10.12066/j.issn.1007-2861.2352

Research Articles

Improved approach to detect small sample target based on remote sensing image

Expand
  • 1. Key Laboratory for Digital Land and Resources of Jiangxi Province, East China University of Technology, Nanchang 330013, Jiangxi, China
    2. School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China

Received date: 2021-09-22

  Online published: 2022-04-28

Fold

Abstract

In this study, an improved convolutional neural network (CNN)approach is proposed to detect small sample targets from remotesensing images. The approach is designed to address the two issuesof small target samples and the unbalanced distribution of groundobject samples with respect to target detection of small samples byremote sensors. In the proposed method, first, $K$-nearest neighbor(kNN) regression is adopted to extract the features of each pointand convolution layer to construct the local neighborhood. Second,all local features are aggregated by maximum pooling layer in CNN torepresent global features. Subsequently, the full connection layerand scaled exponential linear unit (SELU) activation function areapplied to calculate the probability corresponding to each categoryfor classification. Finally, the proposed approach is tested andevaluated on hyperspectral imager remote sensing images datasets.Experimental results show that the proposed improvements to the CNNmodel fuse fully local features and result in the effectiverecognition and detection of small sample targets from remotesensing image with high accuracy while maintaining thenonlocal diffusion capabilities of information.

Key words： convolutional neural network (CNN); small sample; deep learning

Cite this article

LI Chengfan, ZHAO Junjuan . Improved approach to detect small sample target based on remote sensing image[J]. Journal of Shanghai University, 2022 , 28(2) : 314 -323 . DOI: 10.12066/j.issn.1007-2861.2352

References

[1] Reese D C, O'Malley R T, Brodeur R D, et al. Epipelagic fish distributions in relation to thermal fronts in a coastal upwelling system high-resolution remote-sensing techniques[J]. ICES Journal of Marine Science, 2019, 68(9): 1865-1874.
[2] Lei F, Yu Y, Zhang D J, et al. Water remote sensing eutrophication inversion algorithm based on multilayer convolutional neural network[J]. Journal of Intelligent and Fuzzy System, 2020, 39(4): 5319-5227.
[3] Dong Y N, Liang T Y, Zhang Y X, et al. Spectral-spatial weighted kernel manifold embedded distribution alignment for remote sensing image classification[J]. IEEE Transactions on Cybernetics, 2021, 51(6): 3185-3197.
[4] Ding L, Tang H, Bruzzone L. LANet: local attention embedding to improve the semantic segmentation on remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(1): 426-435.
[5] Di L P, Zhong Y F, Yao Y Y, et al. Spark-based adaptive mapreduce data processing method for remote sensing imagery[J]. International Journal of Remote Sensing, 2021, 42(1): 171-187.
[6] Xiao Q T, Zhong X, Zhong C H. Application research of KNN algorithm based on clustering in big data talent demand information classification[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2020, 34(6): 2050015.
[7] Altunkaynak A, Jalilzadnezamabad A. Extended lead time accurate forecasting of plamer drought severity index using hybid wavelet-fuzzy and machine learning techniques[J]. Journal of Hydrology, 2021, 601(3): 126619.
[8] 仉文岗, 李红蕊, 巫崇智, 等. 基于 RF 和 KNN 的地下采场开挖稳定性评估[J]. 湖南大学学报(自然科学版), 2021, 48(3): 164-172.
[9] 叶利华, 王磊, 张文文, 等. 高分辨率光学遥感场景分类的深度度量学习方法[J]. 测绘学报, 2019, 48(6): 698-707.
[10] 于挺, 杨军. 基于 $K$ 近邻卷积神经网络的点云模型识别与分类[J]. 激光与光电子学进展, 2020, 57(10): 101510.
[11] Borgi A, Akdag H. Knowledge based supervised fuzzy-classification: an application to image processing[J]. Annals of Mathematics and Artificial Intelligence, 2018, (32): 67-86.
[12] Maulik U, Chakraborty D. A self-trained ensemble with semisupervised SVM: an application to pixel classification of remote sensing imagery[J]. Pattern Recognition, 2019, 44(3): 615-623.
[13] Mountrakis G, Irn J, Ogole C. Support vector machines in remote sensing: a review[J]. ISPRS Journal of Photogremmetry and Remote Sensing, 2018, 66(3): 247-259.
[14] LI F F. A Bayesian approach to unsupervised one-shot learning of object categories[C]// 2003 IEEE International Conference on Computer Vision. 2003: 1134-1141.
[15] Li F F, Fergus R, Perona P. One-shot learning of object categories[J]. IEEE Transaction on Pattern Analysis & Machine Intelligence, 2006, 28(4): 594-611.
[16] Ake B M, Salakhutdinov R, Tenenbaum J B. Human-level concept learning through probabilistic program induction[J]. Science, 2015, 350(6266): 1332-1338.
[17] Koch G, Zemel R, Salakhutdinov R. Siamese neural networks for one-shot image recog- nition[C]// 32nd International Conference on Machine Learning. 2015: 2-15.
[18] Vinyale O, Blundell C, Lillicrap T, et al. Matching networks for one shot learning[C]// 30nd International Conference on Neural Information Processing System. 2016: 3630-3638.
[19] Snell J, Swersky K, Zemel R. Prototypical networks for few-shot learning[C]// 31nd International Conference on Neural Information Processing System. 2017: 4077-4087.
[20] Li W, Xu J, Huo J, et al. Distribution consistency based covariance metric networks for few-shot learning[C]// 33th AAAI Conference on Artificial Intelligence. 2019: 458-472.
[21] Finn C, Abbeel P, Levine S. Model-agnostic meta-learning for fast adaptation of deep networks[C]// 34th International Conference on Machine Learning. 2017: 1126-1135.
[22] Ravichandran A, Bhotika R, Soatto S. Few-shot learning with embedded class models and shot-free meta training[C]// 2019 International Conference on Computer Vision. 2019: 331-339.
[23] Sun Q, Liu Y, Chua T, et al. Meta-transfer learning for few-shot learning[C]// 32th IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 403-412.
[24] Chen H, Wang Y, Wang G, et al. LSTD: a low-shot transfer detector for object detection[C]// 32th AAAI Conference on Artificial Intelligence. 2018: 258-274.
[25] Wang T, Zhang X, Yuan L, et al. Few-shot adaptive faster R-CNN[C]// 32th IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 7173-7182.
[26] Chen W, Liu Y, Kira Z, et al. A Closer look at few-shot classification[C]// International Conference on Learning Representation. 2019: 542-551.
Options
Outlines

/

〈 〉