投审稿平台
投稿指南
下载专区
地  址:北京市海淀区中关村科学院
南路6号中国科学院计算所342号 [地图]
《计算机辅助设计与图形学学报》编辑部
邮政编码:100190
电  话:010-62562491
     010-62600342
订阅信息
ISSN   1003-9775
CN    11-2925/TP
邮发代号:82-456
单  价:80.00元
全年订价:960.00元
订阅电话:010-64017032
在线期刊

结合边缘轮廓和姿态特征的人体精确解析模型

甘霖1), 刘骊1,2)*, 刘利军1,2), 付晓东1,2), 黄青松1,2)
1) (昆明理工大学信息工程与自动化学院 昆明 650500) 2) (云南省计算机技术应用重点实验室 昆明 650500)
分类号: TP391.41 DOI: 10.3724/SP.J.1089.2021.18683
出版年,卷(期):页码: 2021 , 33 ( 9 ): 1428-1439 甘霖
摘要: 针对着装场景中由于人体姿态、边缘轮廓、服装配饰的复杂性以及着装部位关节点被遮挡等因素导致人体解析精度较低的问题, 提出一种结合边缘轮廓和姿态特征的人体精确解析模型. 首先采用残差网络ResNet-101作为主干网络表征输入人体图像进行初步人体解析, 得到粗解析特征; 然后构建边缘轮廓模块, 结合上采样后的全局和局部特征得到人体边缘轮廓; 再基于着装姿态定义着装姿态损失函数, 通过姿态估计模块提取人体姿态特征; 最后联合粗解析特征、边缘轮廓和姿态特征, 并定义结构损失和人体解析损失的组合函数输出精确的解析结果. 在多个数据集上的实验结果表明, 该模型的mIoU评测指标提高了1.96%, 在人体的着装姿态和部位遮挡等方面获得了更准确的语义分割结果, 能有效地提高着装人体解析的精度.
关键词: 人体解析; 着装场景; 姿态估计; 边缘轮廓; 语义分割
Accurate Human Parsing Model by Edge Contour and Pose Feature
Gan Lin1), Liu Li1,2)*, Liu Lijun1,2), Fu Xiaodong1,2), and Huang Qingsong1,2)
1) (Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500)2) (Computer Technology Application Key Laboratory of Yunnan Province, Kunming 650500)
abstract: To address the problem of low accuracy and precision of human parsing due to human pose, edge contour, complexity of clothing accessories and occlusions of human pose joints in dressing scenes, an accurate human parsing model with edge contour and pose features is proposed for dressed human. Firstly, the backbone network based on ResNet-101 is used to represent input human body images and extract the coarse parsing features. Secondly, the edge contour module combining the global and local features after upsampling is constructed to obtain the edge contour of human body. Then, the defined human pose loss function based on human pose is added into pose estimation module to acquire pose features. Finally, coarse parsing feature, edge contour and pose features are integrated into accuracy parsing module, and the accurate human parsing results are output by the combined function of structure loss function and human parsing loss function. The experimental results show that the proposed model can effectively improve 1.96% of mIoU and accuracy on human datasets with more accurate segmentation results for different poses and occlusions of the human body parts.
keyword: human parsing; dressing scene; pose estimation; edge contour; semantic segmentation
 
Copyright © 2004《计算机辅助设计与图形学学报》版权所有
电话:010-62600342 传真:010-62562491
E_mail:jcad@ict.ac.cn