基于并联自适应残差网络与CBAM的ECT图像重建

马敏; 吴环

doi:10.3969/j.issn.1000-1158.2024.02.11

PDF(633 KB)

计量学报 ›› 2024, Vol. 45 ›› Issue (2) : 214-221. DOI: 10.3969/j.issn.1000-1158.2024.02.11

流量计量

基于并联自适应残差网络与CBAM的ECT图像重建

马敏,吴环

作者信息 +

ECT Image Reconstruction Based on Parallel Adaptive Residual Network with CBAM

MA Min,WU Huan

Author information +

文章历史 +

摘要

为解决电容层析成像中软场效应导致重建图像精度低的问题,提出了一种基于并联自适应残差网络与卷积注意力机制的图像重建算法。通过引入并联自适应残差模块提取丰富的特征层信息,再利用压缩激励网络调整各通道的权重系数,达到过滤冗余信息的效果,引入卷积注意力机制学习浅层特征的通道和空间信息,将卷积注意力机制通道与并联自适应残差网络进行特征融合以补偿损失的浅层特征和空间信息。仿真结果表明,相比LBP算法、Landweber迭代算法、1D CNN算法,改进算法有效提高了重建质量。

Abstract

In order to solve the problem that soft effect in capacitance tomography should lead to low accuracy of reconstructed image, a parallel adaptive residual network with convolutional attention mechanism image reconstruction algorithm is proposed. The parallel adaptive residual module is used to extract the rich feature layer information. The weight coefficients of each channel are adjusted by the squeeze and excitation networks to filter the redundant information. The convolutional attention mechanism is used to learn the channel and space information of the shallow feature. The feature fusion between the convolutional attention mechanism channel and the parallel adaptive residual network is proposed to compensate the lost shallow features and spatial information. Simulation results show that compared with LBP algorithm, Landweber iterative algorithm and 1DCNN algorithm, the improved algorithm can guarantee real-time performance and improve reconstruction quality effectively.

导出引用

马敏,吴环. 基于并联自适应残差网络与CBAM的ECT图像重建[J]. 计量学报. 2024, 45(2): 214-221 https://doi.org/10.3969/j.issn.1000-1158.2024.02.11

MA Min,WU Huan. ECT Image Reconstruction Based on Parallel Adaptive Residual Network with CBAM[J]. Acta Metrologica Sinica. 2024, 45(2): 214-221 https://doi.org/10.3969/j.issn.1000-1158.2024.02.11

中图分类号： TB937

参考文献

［1］王化祥, 杨五强. 电容过程成像技术的进展［J］. 仪器仪表学报, 2000, 21(1): 4-7, 11.
WANG H X, YANG W Q. Advances in electrical capacitive process imaging techniques ［J］. Journal of Instrumentation, 2000, 21(1): 4-7+11.
［2］马敏, 张彩霞, 陆成超, 等. 基于小波变换的ECT图像处理［J］. 中南大学学报, 2016, 47 (6): 1947-1952.
MA M, ZHANG C X, LU C C, et al, ECT image processing based on wavelet transform ［J］. Journal of Central South University, 2016, 47 (6): 1947-1952.
［3］张立峰, 王化祥. 基于小波神经网络的电容层析成像图像重建算法［J］. 中国电机工程学报, 2008, 28 (35): 39-43.
ZHANG L F, WANG H X. Electrical capacitive tomography image reconstruction algorithm based on wavelet neural network ［J］. Proceedings of the CSEE, 2008, 28 (35): 39-43.
［4］LEI J, LIU Q B. Self-paced learning assisted regularization reconstruction method with data-adaptive prior for electrical capacitance tomography［J］. Expert Systems with Applications, 2022, 191: 116296-.
［5］MARASHDEH Q, WARSITO W, FAN L S, et al. Nonlinear forward problem solution for electrical capacitance tomography using feed-forward neural network ［J］. IEEE Sensors Journal, 2006, 6 (2): 441-449.
［6］LEI J, LIU Q B, WANG X Y. Computational inverse imaging method by machine learning-informed physical model for electrical capacitance tomography ［J］. Journal of Computational Science, 2022,:57
［7］GAMIO J C, ORTIZ-ALEMAN C, MARTIN R. Electrical capacitance tomography two-phase oil-gas pipe flow imaging by the linear back-projection algorithm ［J］. Geofísica Internacional, 2005, 44 (3): 265.
［8］YANG W Q, SPINK D M, YORK T A, et al. An image reconstruction algorithm based on Landweber's iteration method for electrical capacitance tomography ［J］. Measure-ment Science and Technology, 1999, 10 (11): 1065-1069.
［9］TONG G W, LIU SH, CHEN H Y, et al. Regularization iteration imaging algorithm for electrical capacitance tomography ［J］. Measurement Science and Technology, 2018, 29 (3): 035403-035403.
［10］ZHENG J, PENG L H. An Autoencoder-Based Image Reconstruction for Electrical Capacitance Tomography ［J］. IEEE Sensors Journal, 2018, 18 (13): 5464-5474.
［11］WANG H M, HU H L, WANG L J, et al. Image reconstruction for an Electrical Capacitance Tomography (ECT) system based on a least squares support vector machine and bacterial colony chemotaxis algorithm ［J］. Flow Measurement and Instrumentation, 2012, 27: 59-66.
［12］马敏, 孙颖, 范广永. 基于深度信念网络的ECT图像重建算法［J］. 计量学报, 2021, 42 (4): 476-482.
MA M, SUN Y, FAN G Y. Electrical capacitance tomography image reconstruction algorithm based on deep belief network ［J］. Acta Metrologica Sinica, 2021, 42 (4): 476-482.
［13］张立峰, 王会忍. 基于卷积神经网络及有限元仿真的电容层析成像图像重建［J］. 系统仿真学报, 2022, 34 (4): 712-718.
ZHANG L F, WANG H R. Electrical capacitive tomography image reconstruction based on convolutional neural network and finite element simulation ［J］. Journal of System Simulation, 2022, 34 (4): 712-718.
［14］ZHENG J, LI J K, LI Y, et al. A benchmark dataset and deep learning-based image reconstruction for electrical capacitance tomography ［J］. Sensors, 2018, 18 (11): 3701-3701.
［15］严春满, 穆哲. 一种改进的梯度加速Landweber算法及其在ECT图像重建中的应用［J］. 电子测量与仪器学报, 2021, 35 (6): 169-175.
YAN C M, MU Z, An improved gadient acceleration Landweber algorithm and its application in ECT image reconstruction ［J］. Journal of Electronic Measurement and Instrumentation, 2021, 35 (6): 169-175.
［16］CUI Z Q, WANG Q, XUE Q, et al. A review on image reconstruction algorithms for electrical capacitance/resistance tomography ［J］. Sensor Review, 2016, 36 (4): 429-445.
［17］张立峰, 戴力. 基于极限学习机求解正问题的ECT图像重建［J］. 仪器仪表学报, 2021, 42 (10): 64-71.
ZHANG L F, DAI L. ECT image reconstruction based on extreme learning machine to solve positive problems ［J］. Journal of Instrumentation, 2021, 42 (10): 64-71.
［18］马敏, 刘一斐, 王力. 基于改进半阈值算法的电容层析成像滑油监测方法研究［J］. 推进技术, 2021, 42 (11): 2590-2599.
MA M, LIU Y F, WANG L. Research on capacitive tomography lubrication oil monitoring method based on improved semi-threshold algorithm ［J］. Propulsion technology, 2021, 42 (11): 2590-2599.
［19］WAN G, FANG H B, WANG D C, et al. Ceramic tile surface defect detection based on deep learning ［J］. Ceramics International, 2022, 48 (8): 11085-11093.