[1]李顺新,陈飞飞.基于比例池化的RGB图像语义分割网络[J].计算机技术与发展,2024,34(08):101-107.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0129]
　LI Shun-xin,CHEN Fei-fei.RGB Image Semantic Segmentation Net Based on Proportional Pooling[J].,2024,34(08):101-107.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0129]
点击复制

基于比例池化的RGB图像语义分割网络

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
34
期数:
2024年08期
页码:
101-107
栏目:
人工智能
出版日期:
2024-08-10

文章信息/Info

Title:
RGB Image Semantic Segmentation Net Based on Proportional Pooling
文章编号:
1673-629X(2024)08-0101-07
作者:
李顺新1; 2; 3; 陈飞飞1; 2
1. 武汉科技大学 计算机科学与技术学院,湖北 武汉 430065; 2. 湖北智能信息处理与实时工业系统重点实验室,湖北 武汉 430065; 3. 武汉科技大学 大数据科学与工程研究院,湖北 武汉 430065
Author(s):
LI Shun-xin1; 2; 3; CHEN Fei-fei1; 2
1. School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,China; 2. Hubei Province Key Laboratory of Intelligent Information Procession and Real-time Industrial,Wuhan 430065,China; 3. Big Data Science and Enginee
关键词:
语义分割; 比例池化; 金字塔结构; 多尺度特征融合; 特征降噪
Keywords:
semantic segmentation; proportional pooling; pyramid structure; multi-scale feature fusion; feature denoising
分类号:
TP391.4
DOI:
10.20165/j.cnki.ISSN1673-629X.2024.0129
摘要:
针对传统的金字塔多级特征融合算法进行语义分割时存在的特征图有效信息弱和噪声叠加效应等问题,提出一 种基于比例池化的混合注意力机制。 首先在主干网络特征输出处引入比例池化注意力模块对输入特征图进行不同程度的语义信息抽取和特征降噪,突出特征图有效特征信息占比,随后将不同内核的池化结果作为级联金字塔结构的输入特征,对降噪后的多尺度特征进行融合,平滑图像噪声实现特征二次降噪和小目标物体语义信息增强。 实验在 Pascal VOC 2012 数据集上验证了该方法在分割领域上的有效性,并采用平均像素准确率(mPA)和平均交并比(mIoU)作为模型的性能评估指标。 实验结果表明,基于比例池化的金字塔网络在 mPA 和 mIoU 上达到了 90. 19% 和 79. 92% ,优于对比的语义分割方法。
Abstract:
Aiming at the problems of weak effective information of feature map and noise superposition effect of feature map noise when the traditional pyramid feature fusion segmentation algorithm performs semantic segmentation,a hybrid attention mechanisms based on proportional pooling is proposed. Firstly,the proportional pooling attention module is introduced at the feature output of the backbone network to extract the semantic information and denoise the input feature map to different degrees,and the proportion of effective feature information of the feature map is highlighted,and then the pooling results of different kernels are used as the input features of the cascade pyramid structure, and the multi-scale features after noise reduction are fused to realize the secondary feature reduction and the semantic information enhancement of small target objects. The effectiveness of the proposed method in the segmentation domain is verified on the Pascal VOC 2012 dataset, and the average pixel accuracy ( mPA) and average intersection union ratio ( mIoU) are used as the performance evaluation indicators of the model. Experimental results show that the pyramid network based on proportional pooling reaches 90. 19% and 79. 92% on mPA and mIoU,which is better than that of the comparative semantic segmentation methods.

相似文献/References:

[1]张泽宇,郭 斌,张太红*.基于 DCNN 的马匹图像分割算法研究[J].计算机技术与发展,2020,30(10):210.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 037]
　ZHANG Ze-yu,GUO Bin,ZHANG Tai-hong.Research on Horse Image Segmentation Algorithm Based on DCNN[J].,2020,30(08):210.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 037]
[2]龚 安,赵 莉,姚鑫杰.基于改进的 U-Net 网络模型的气胸分割算法[J].计算机技术与发展,2021,31(10):173.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 029]
　GONG An,ZHAO Li,YAO Xin-jie.Pneumothorax Segmentation Algorithm Based on Improved U-Net Network Model[J].,2021,31(08):173.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 029]
[3]宋 宇,王小瑀,梁 超,等.基于多级特征图联合上采样的实时语义分割[J].计算机技术与发展,2022,32(02):82.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 013]
　SONG Yu,WANG Xiao-yu,LIANG Chao,et al.Real-time Semantic Segmentation Based on Multi-scale Feature Map Joint Pyramid Upsamping[J].,2022,32(08):82.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 013]
[4]姚芷馨,张太红,赵昀杰.基于卷积神经网络的多模型交通场景识别研究[J].计算机技术与发展,2022,32(07):93.[doi:10. 3969 / j. issn. 1673-629X. 2022. 07. 016]
　YAO Zhi-xin,ZHANG Tai-hong,ZHAO Yun-jie.Research on Multi-model Traffic Scene Recognition Based on Convolution Neural Network[J].,2022,32(08):93.[doi:10. 3969 / j. issn. 1673-629X. 2022. 07. 016]
[5]张 鑫,陈 黎.基于多尺度特征融合的消防车通道占用检测[J].计算机技术与发展,2022,32(10):51.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 009]
　ZHANG Xin,CHEN Li.Fire Truck Passages Occupancy Detection Based on Multi-scale Feature Fusion[J].,2022,32(08):51.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 009]
[6]李松宇.基于 HED—UNet 遥感图像建筑物语义分割[J].计算机技术与发展,2022,32(S2):58.[doi:10. 3969 / j. issn. 1673-629X. 2022. S2. 010]
　LI Song-yu.Semantic Segmentation of Buildings in Remote Sensing Images Based on HED-UNet[J].,2022,32(08):58.[doi:10. 3969 / j. issn. 1673-629X. 2022. S2. 010]
[7]杜睿山,宋健辉,孟令东.基于注意力机制的岩石铸体薄片轻量化分割[J].计算机技术与发展,2023,33(10):128.[doi:10. 3969 / j. issn. 1673-629X. 2023. 10. 020]
　DU Rui-shan,SONG Jian-hui,MENG Ling-dong.Lightweight Segmentation of Rock Casting Sheet Based on Attention Mechanism[J].,2023,33(08):128.[doi:10. 3969 / j. issn. 1673-629X. 2023. 10. 020]
[8]刘贤梅,刘鹏飞,贾 迪,等.基于多特征融合的城市场景三维点云语义分割[J].计算机技术与发展,2023,33(11):78.[doi:10. 3969 / j. issn. 1673-629X. 2023. 11. 012]
　LIU Xian-mei,LIU Peng-fei,JIA Di,et al.3D Point Cloud Semantic Segmentation of Urban Scene Based on Multi-feature Fusion[J].,2023,33(08):78.[doi:10. 3969 / j. issn. 1673-629X. 2023. 11. 012]
[9]陈世婕,王卫星*,彭 莉.基于多尺度网络的苗绣绣片纹样分割算法研究[J].计算机技术与发展,2023,33(11):149.[doi:10. 3969 / j. issn. 1673-629X. 2023. 11. 022]
　CHEN Shi-jie,WANG Wei-xing*,PENG Li.Research on Miao Embroidery Pattern Segmentation Algorithm Based on Multi-scale Network[J].,2023,33(08):149.[doi:10. 3969 / j. issn. 1673-629X. 2023. 11. 022]
[10]曾碧卿,杨 睿,李一娴,等.基于卷积神经网络的零件圆检测方法[J].计算机技术与发展,2023,33(11):64.[doi:10. 3969 / j. issn. 1673-629X. 2023. 11. 010]
　ZENG Bi-qing,YANG Rui,LI Yi-xian,et al.Part Circle Detection Method Based on Convolutional Neural Network[J].,2023,33(08):64.[doi:10. 3969 / j. issn. 1673-629X. 2023. 11. 010]

更新日期/Last Update: 2024-08-10