arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.01460cs.CV
收藏

使用综合训练的深度卷积网络学习分割人体部位

Learning to Segment Human Body Parts with Synthetically Trained Deep Convolutional Networks

FlexSight Srl(FlexSight有限公司);University of Padova(帕多瓦大学);PlayCast Srl(PlayCast有限公司)

Alessandro Saviolo, Matteo Bonotto, Daniele Evangelista, Marco Imperoli, Jacopo Lazzaro, Emanuele Menegatti, Alberto Pretto

摘要:

本文提出了一种新的框架,用于人体部位分割的基础上,深度卷积神经网络训练,只用合成数据。所提出的方法实现了尖端的结果,而不需要训练的模型与真实的注释数据的人体部位。我们的贡献包括一个数据生成管道,利用游戏引擎创建用于训练网络的合成数据,以及一个新的预处理模块,结合边缘响应图和自适应直方图均衡来引导网络学习人体部位的形状,确保对光照条件变化的鲁棒性。为了选择最佳的候选架构,我们进行详尽的测试,手动注释的图像真实的人体四肢。我们进一步将我们的方法与身体部位分割任务中的几种高端商业分割工具进行比较。结果表明,我们的方法优于其他模型的显着保证金。最后,我们提出了一个消融研究,以验证我们的预处理模块。在本文中,我们发布了所提出的方法的实现以及获得的数据集。

英文摘要:

This paper presents a new framework for human body part segmentation based on Deep Convolutional Neural Networks trained using only synthetic data. The proposed approach achieves cutting-edge results without the need of training the models with real annotated data of human body parts. Our contributions include a data generation pipeline, that exploits a game engine for the creation of the synthetic data used for training the network, and a novel pre-processing module, that combines edge response maps and adaptive histogram equalization to guide the network to learn the shape of the human body parts ensuring robustness to changes in the illumination conditions. For selecting the best candidate architecture, we perform exhaustive tests on manually annotated images of real human body limbs. We further compare our method against several high-end commercial segmentation tools on the body parts segmentation task. The results show that our method outperforms the other models by a significant margin. Finally, we present an ablation study to validate our pre-processing module. With this paper, we release an implementation of the proposed approach along with the acquired datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑