School of Computer Science, South-Central Minzu University, Wuhan 430074, China
Show less
文章历史+
Received
Published
Revised
2025-01-31
2026-02-18
2025-10-28
Online Date
2026-05-27
PDF (11530K)
摘要
为提升全二维气相色谱数据中复杂化合物分析的准确性,基于U-net语义分割模型研究了streak噪声的精准分割问题,提出了一种AP-U-net改进模型。streak噪声具有低对比度、尺度多变等特点,在复杂背景中分割该目标具有一定挑战性。针对经典U-net模型存在的特征传递效率低、池化操作导致信息丢失以及全局信息捕捉困难等问题,分别采用残差连接优化梯度流动、Haar小波分解(Haar wavelet decomposition,HWD)替代下采样以及引入SK注意力机制(selective kernel attention)进行改进。结果表明:改进后的AP-U-net模型在GC×GC数据集上的平均交并比(mean intersection over union,MIoU)、精确度(accuracy,Acc)、类别像素准确率(class precision average,Cpa)和Dice系数分别达到81.44%、98.69%、83.22%和78.21%。与原始U-net模型相比,改进模型MIoU指标提升3.83%,Dice系数提升5.7%,与部分主流分割模型相比也展现出一定优势,具有良好的应用价值。
Abstract
In order to improve the accuracy of complex compound analysis in comprehensive two-dimensional gas chromatography (GC×GC) data, an improved model named AP-U-net was proposed based on the U-net semantic segmentation framework to investigate the precise segmentation of streak noise. Streak noise was characterized by low contrast and multi-scale variations, which makes it challenging to segment this target in complex backgrounds. To address the issues of low feature propagation efficiency, information loss caused by pooling operations, and difficulty in capturing global context in the original U-net, residual connections were introduced to enhance gradient flow, Haar wavelet decomposition (HWD) was used to replace downsampling, and a selective kernel (SK) attention mechanism was incorporated to improve global information modeling. The results show that the improved AP-U-net model achieved a mean intersection over union (MIoU) of 81.44%, accuracy (Acc) of 98.69%, class pixel accuracy (Cpa) of 83.22%, and a Dice coefficient of 78.21% on the GC×GC dataset. Compared with the original U-net model, the MIoU increases by 3.83%, and the Dice coefficient increases by 5.7%. It is concluded that the AP-U-net model effectively segments streak noise and shows certain advantages over some mainstream segmentation models, indicating good application potential.
MEI Le, LI Bo.
Streak Noise Segmentation of Comprehensive Two-dimensional Gas Chromatography Images Based on AP-U-net[J].
Science Technology and Engineering, 2026, 26(5): 2076-2083 DOI:10.12404/j.issn.1671-1815.2500658
ChenWenting. Research progress on the application of comprehensive two-dimensional gas chromatography[J]. Chemical Analysis and Meterage, 2022, 31(8): 82-89.
[3]
LathaI, ReichenbachS E, TaoQ. Comparative analysis of peak-detection techniques for comprehensive two-dimensional chromatography[J]. Journal of Chromatography A, 2011, 1218(38): 6792-6798.
[4]
WangX, ChenZ, DongC, et al. Pre-segmentation of point cloud based on centroid matrix of streak tube imaging LiDAR[J]. IEEE Geoscience and Remote Sensing Letters, 2024, 22: 1-4.
[5]
ChangY, ChenM, YuC, et al. Direction and residual awareness curriculum learning network for rain streaks removal[J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(6): 8414-8428.
[6]
JiangZ, LiuR, YangS, et al. DRNet: learning a dynamic recursion network for chaotic rain streak removal[J]. Pattern Recognition, 2025, 158: 111004.
[7]
QureshiM H, TienW H. Novel streak-resolving algorithm for particle streak velocimetry[J]. Flow Measurement and Instrumentation, 2022, 87: 102208.
DongHongyue, ZhangXingzhong, ZhaoJielun. Industrial crack segmentation based on reversible pyramid and balanced attention[J]. Computer Engineering and Applications, 2022, 58(12): 234-242.
WangNanyang, ShenJianghai. Image segmentation method of rock core hole based on MSHAM-UNet[J]. Science Technology and Engineering, 2024, 24(24): 10362-10369.
CaoZhan, YuPeng, ChenHua. An automatic identification method of outcrop crack based on attention U-Net model[J]. Science Technology and Engineering, 2023, 23(10): 4149-4156.
LiXin, LiBo, WuPeide, et al. Streak target segmentation of comprehensive two-dimensional gas chromatography based on CBAM-U-Net[J]. Information Technology and Informatization, 2023(11): 45-48.
[18]
RonnebergerO, FischerP, BroxT. U-net: convolutional networks for biomedical image segmentation[C]// Medical Image Computing and Computer-assisted Intervention-MICCAI 2015: 18th International Conference. Munich: Springer International Publishing, 2015: 234-241.
[19]
XuG, LiaoW, ZhangX, et al. Haar wavelet downsampling: a simple but effective downsampling module for semantic segmentation[J]. Pattern Recognition, 2023, 143: 109819.
[20]
LiX, WangW, HuX, et al. Selective kernel networks[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 510-519.
[21]
HeK, ZhangX, RenS, et al. Deep residual learning for image recognition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
[22]
CazenaveT. Cosine annealing, mixnet and swish activation for computer Go[M]//Advances in Computer Games. Cham: Springer International Publishing, 2021: 53-60.
[23]
ChenL C, ZhuY, PapandreouG, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]// Proceedings of the European Conference on Computer Vision (ECCV). Berlin: Springer, Cham, 2018: 833-851.
[24]
XieE, WangW, YuZ, et al. SegFormer: simple and efficient design for semantic segmentation with transformers[J]. Advances in Neural Information Processing Systems, 2021, 34: 12077-12090.
[25]
SunK, XiaoB, LiuD, et al. Deep high-resolution representation learning for human pose estimation[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 5693-5703.
[26]
NguyenN H T, PerryS, BoneD, et al. Two-stage convolutional neural network for road crack detection and segmentation[J]. Expert Systems with Applications, 2021, 186: 115718.