首页|基于改进的IIE-SegNet的快速图像语义分割方法

基于改进的IIE-SegNet的快速图像语义分割方法

扫码查看
原文链接
  • 万方数据
  • 维普
针对IIE-SegNet计算复杂度高、计算量大等问题,本文提出一种基于IIE-SegNet的改进方法.编码结构中引入经ImageNet训练过的VGG16 和多尺度空洞卷积空间金字塔池化来获得丰富的编码信息;解码结构中,设计全局加平均模块来解决IIE-SegNet计算量大的问题;研究Focal损失函数来解决正、负采样不平衡的问题.实验结果表明:与IIE-SegNet相比,本方法在PASCAL VOC 2012 数据集上的语义分割速度更快,平均每次迭代快0.6 s左右,测试单张图像的时间平均减少了 0.94 s;分割精度更高,MIoU提升了 2.1%.在扩展的PASCAL VOC 2012(Exp-PASCAL VOC 2012)数据集上的语义分割速度更快,平均每次迭代快 0.4 s左右,测试单张图像的时间平均减少了0.92 s;分割精度更高,MPA和MIoU分别提升了 2.6%和 2.8%,特别是对于小尺度目标分割边界更清晰,性能得到了很大的提升.
Fast image semantic segmentation method based on improved IIE-SegNet
To address the high computational complexity and large computational load of IIE-SegNet,this paper proposes an improved method based on IIE-SegNet.VGG16 trained in ImageNet and multiscale atrous spatial pyra-mid pooling(MASPP)module are introduced into the encoding module to obtain abundant coding information.In the decoding structure,the global add average(GAA)module is designed to solve the problem of heavy computa-tion of IIE-SegNet.Focal loss function is analyzed to solve the problem of positive and negative sampling imbal-ance.The experimental result shows that compared with IIE-SegNet,on the PASCAL VOC 2012 dataset,our net-work achieves faster segmentation,with an average of 0.6 s faster per iteration,a reduction in the average time to test a single image by 0.94 s,and an increase in MIoU 2.1%.On the expanded PASCAL VOC 2012(Exp-PAS-CAL VOC 2012)data set,the semantic segmentation speed is faster,an average of 0.4 s faster per iteration,and the average time to test a single image is reduced by 0.92 s;furthermore,our network exhibits higher accuracy and improvements in the MPA and MIoU by 2.6%and 2.8%,respectively.In particular,for small-scale target seg-mentation,the boundary is clearer,and the performance is greatly improved.

semantic segmentationdeep learningmultiscale atrous spatial pyramid pooling(MASPP)image in-formation entropy(IIE)global add average(GAA)VGG16IIE-SegNet

李庆、王宏健、李本银、肖瑶、迟志康

展开 >

哈尔滨工程大学 智能科学与工程学院,黑龙江 哈尔滨 150001

烟台南山学院 智能科学与工程学院,山东 烟台 264000

语义分割 深度学习 多尺度空洞卷积空间金字塔池化 图像信息熵 全局加平均 VGG16 IIE-SegNet

GF科技创新特区项目水下机器人重点实验室基金项目哈尔滨工程大学高水平科研引导专项

21-163-05-ZT-002-005-03JCKYS2022SXJQR-093072022QBZ0403

2024

10.11990/jheu.202212015

哈尔滨工程大学学报
哈尔滨工程大学

哈尔滨工程大学学报

CSTPCD北大核心
影响因子：0.655
ISSN：1006-7043
年,卷(期)：2024.45(2)
  • 5