Research on wideband electromagnetic image striping noise removal method based on BiGRU-CNN
-
摘要: 电磁探测成像系统能够对电磁干扰源进行大范围、宽频带且快速的定位，系统主要由抛物反射面和多通道超宽频带信号采集系统组成。由于各个通道器件参数受限于制造工艺的影响不可能完全一致，探测不同频率干扰源的响应特性也不相同，导致获得的电磁图像中存在的条带噪声随干扰源的频率变化而呈现出不同的特征，严重地影响定位的精度。构建了双向门控循环单元（BiGRU）-卷积神经网络（CNN）模型，根据实测数据构建数据集作为模型的输入，BiGRU和CNN利用图像相邻行间的强相关性，从过去和未来的输入中广泛收集冗余信息，对条带噪声进行提取并对空间信息进行整合处理，利用数据之间的差值对这个过程进行循环迭代。通过大量的实验对模型进行验证，BiGRU-CNN方法与测试的经典方法相比更优，在垂直梯度能量方面降低了15.2%，在残差非均匀性方面降低了21.9%。Abstract: The electromagnetic detection and imaging system enables wide-range, wideband, and fast localization of electromagnetic interference sources. The system primarily consists of a parabolic reflector and a multi-channel ultra-wideband signal acquisition system. Due to variations in device parameters across channels caused by manufacturing processes, it is impossible to achieve complete consistency, resulting in stripe noise in the obtained electromagnetic images that significantly affects localization accuracy. A bidirectional gated recurrent unit (BiGRU)-convolutional neural network (CNN) model was constructed, which constructs a dataset based on the measured data as the input. The BiGRU and the CNN utilize the strong correlation between neighboring rows of the image to extensively collect redundant information from the past and future inputs, to extract the stripe noise and to integrate the spatial information, and to utilize the difference between the data for loop iteration of this process. The model is validated through a large number of experiments and the BiGRU-CNN method outperforms other tested (classical) methods by reducing the vertical gradient energy by 15.2% and the residual nonuniformity by 21.9%.
-
图 4 不同方法在1 GHz、3 GHz和4 GHz下的去条带结果
Figure 4. De-striping results of various methods for 1 GHz, 3 GHz and 4 GHz
-
[1] Xie Shuguo, Wang Tianheng, Hao Xuchun, et al. Localization and frequency identification of large-range wide-band electromagnetic interference sources in electromagnetic imaging system[J]. Electronics, 2019, 8: 499. doi: 10.3390/electronics8050499 [2] Luan Shenshen, Xie Shuguo, Wang Tianheng, et al. A space-variant deblur method for focal-plane microwave imaging[J]. Applied Sciences, 2018, 8: 2166. doi: 10.3390/app8112166 [3] Goswami A, Sharma D, Mathuku H, et al. Change detection in remote sensing image data comparing algebraic and machine learning methods[J]. Electronics, 2022, 11: 431. doi: 10.3390/electronics11030431 [4] Lai Rui, Guan Juntao, Yang Yintang, et al. Spatiotemporal adaptive nonuniformity correction based on BTV regularization[J]. IEEE Access, 2019, 7: 753-762. doi: 10.1109/ACCESS.2018.2885803 [5] Liang Kun, Yang Cailan, Peng Li, et al. Nonuniformity correction based on focal plane array temperature in uncooled long-wave infrared cameras without a shutter[J]. Applied Optics, 2017, 56(4): 884-889. doi: 10.1364/AO.56.000884 [6] 高浩博, 卜桐, 李欣, 等. 基于深度学习的高分辨率卫星遥感影像条带噪声去除[J]. 遥感学报, 2023, 27(3):610-622 doi: 10.11834/jrs.20221054Gao Haobo, Bu Tong, Li Xin, et al. Stripe noise removal in high resolution satellite remote sensing images based on deep learning[J]. National Remote Sensing Bulletin, 2023, 27(3): 610-622 doi: 10.11834/jrs.20221054 [7] 邵晓鹏, 靳振华, 王阳. 去除红外图像条带噪声改进算法研究[J]. 电子科技, 2013, 26(10):83-87Shao Xiaopeng, Jin Zhenhua, Wang Yang. Improved algorithm for removing stripe noise of infrared images[J]. Electronic Science and Technology, 2013, 26(10): 83-87 [8] 罗佩言. 大动态阵列信号接收与处理技术研究[D]. 武汉: 华中科技大学, 2022Luo Peiyan. Research on large dynamic array signal receiving and processing technology[D]. Wuhan: Huazhong University of Science and Technology, 2022 [9] Lai Rui, Yue Gaoyu, Zhang Gangxuan. Total variation based neural network regression for nonuniformity correction of infrared images[J]. Symmetry, 2018, 10: 157. doi: 10.3390/sym10050157 [10] Chang Yi, Yan Luxin, Wu Tao, et al. Remote sensing image stripe noise removal: from image decomposition perspective[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(12): 7018-7031. doi: 10.1109/TGRS.2016.2594080 [11] Li Hongjun, Suen C Y. A novel non-local means image denoising method based on grey theory[J]. Pattern Recognition, 2016, 49: 237-248. doi: 10.1016/j.patcog.2015.05.028 [12] He Kaiming, Sun Jian, Tang Xiaoou. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397-1409. doi: 10.1109/TPAMI.2012.213 [13] Münch B, Trtik P, Marone F, et al. Stripe and ring artifact removal with combined wavelet-Fourier filtering[J]. Optics Express, 2009, 17(10): 8567-8591. doi: 10.1364/OE.17.008567 [14] Tendero Y, Landeau S, Gilles J. Non-uniformity correction of infrared images by midway equalization[J]. Image Processing On Line, 2012, 2: 134-146. doi: 10.5201/ipol.2012.glmt-mire [15] 张亚涛, 吉书鹏, 王强锋, 等. 基于区域对比度的图像清晰度评价算法[J]. 应用光学, 2012, 33(2):293-299Zhang Yatao, Ji Shupeng, Wang Qiangfeng, et al. Definition evaluation algorithm based on regional contrast[J]. Journal of Applied Optics, 2012, 33(2): 293-299 [16] Guan Juntao, Lai Rui, Xiong Ai. Wavelet deep neural network for stripe noise removal[J]. IEEE Access, 2019, 7: 44544. doi: 10.1109/ACCESS.2019.2908720 [17] Guan Juntao, Lai Rui, Xiong Ai. Learning spatiotemporal features for single image stripe noise removal[J]. IEEE Access, 2019, 7: 144489-144499. doi: 10.1109/ACCESS.2019.2944239 [18] Fayyaz Z, Platnick D, Fayyaz H, et al. Deep unfolding for iterative stripe noise removal[C]//Proceedings of 2022 International Joint Conference on Neural Networks (IJCNN). 2022: 1-7. [19] Yin Xing, Liu Changhui, Fang Xiaodong. Sentiment analysis based on BiGRU information enhancement[J]. Journal of Physics:Conference Series, 2021, 1748: 032054. doi: 10.1088/1742-6596/1748/3/032054 [20] Zhao Jufeng, Zhou Qiang, Chen Yueting, et al. Single image stripe nonuniformity correction with gradient-constrained optimization model for infrared focal plane arrays[J]. Optics Communications, 2013, 296: 47-52. doi: 10.1016/j.optcom.2013.01.038 [21] Lai Rui, Yang Yintang, Li Qing, et al. Improvement in adaptive nonuniformity correction method with nonlinear model for infrared focal plane arrays[J]. Optics Communications, 2009, 282(17): 3444-3447. doi: 10.1016/j.optcom.2009.05.046 -
下载:
点击查看大图
图(5)
计量
- 文章访问数: 221
- HTML全文浏览量: 113
- PDF下载量: 62
- 被引次数: 0
