###
:2019,28(9):239-245
←前一篇   |   后一篇→
本文二维码信息
码上扫一扫!
基于多级特征整合的图像语义分割研究
(河海大学 计算机与信息学院, 南京 211100)
Image Semantic Segmentation Based on Multi-Level Feature Integration
(College of Computer and Information, Hohai University, Nanjing 211100, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 61次   下载 62
投稿时间:2019-03-01    修订日期:2019-03-29
中文摘要: 传统的全卷积神经网络由于不断的池化和下采样操作使得最后的特征热点图分辨率损失严重,导致了分割结果的细节刻画能力的缺失,为了弥补这一缺陷,往往通过跳跃连接融合中层的特征图以恢复空间信息.由于无法充分利用网络的低层特征信息,传统全卷积网络的特征融合阶段存在相当的缺陷,本文对这一现象进行了深入的分析.本文在上采样路径之前采用基于特征金字塔的特征信息增强方法,克服了浅层特征图语义信息匮乏这一缺点,使得整个网络能更充分的利用前向计算产生的特征图,输出的分割结果也更为精确.本文提出的算法在Pascal VOC数据集上取得了75.8%的均像素精度和83.9%的权频交并比,有效的提高了分类精度.
Abstract:Due to continuous pooling and down sampling, the resolution of the final feature hotspot map is seriously lost in the traditional full-convolution neural network, which leads to the loss of detail characterization ability of segmentation results. In order to make up for this defect, the feature map of middle layer is often fused by jumping connection to restore spatial information. Due to the failure to make full use of the low-level feature information of the network, the feature fusion stage of the traditional full-convolution network has some defects. This study makes an in-depth analysis of this phenomenon. The feature information enhancement method based on feature pyramid is adopted before the upper sampling path to overcome the deficiency of semantic information of shallow feature graph, so that the entire network can make full use of the feature graph generated by forward calculation and improve the segmentation result. The algorithm proposed in this study achieves 75.8% average pixel accuracy and 83.9% weight frequency crossover ratio on the Pascal VOC data set, effectively improved the classification accuracy.
文章编号:     中图分类号:    文献标志码:
基金项目:
引用文本:
徐天宇,孟朝晖.基于多级特征整合的图像语义分割研究.计算机系统应用,2019,28(9):239-245
XU Tian-Yu,MENG Zhao-Hui.Image Semantic Segmentation Based on Multi-Level Feature Integration.COMPUTER SYSTEMS APPLICATIONS,2019,28(9):239-245

用微信扫一扫

用微信扫一扫