基于深度学习的人体动作草图到三维骨骼模型重建方法的研究  

Research of deep learning based 3D skeleton model reconstruction method from human motion sketch

作　　者：马昊 李淑琴[1,2] 丁濛 Ma Hao;Li Shuqin;Ding Meng(School of Computer,Beijing Information Science&Technology University,Beijing 100101,China;Joint Laboratory of Sensing&Computational Intelligence,Beijing Information Science&Technology University,Beijing 100101,China)

机构地区：[1]北京信息科技大学计算机学院,北京100101 [2]北京信息科技大学感知与计算智能联合实验室,北京100101

出　　处：《计算机应用研究》2020年第6期1867-1870,共4页Application Research of Computers

基　　金：国家自然科学基金资助项目(61502039);2017年度教育教学改革研究专项招标课题(2017JGZB08)。

摘　　要：为了提高三维人体骨骼模型的建模效率并简化交互规则,提出了一种基于深度学习的手绘人体动作草图到三维骨骼模型的重建方法。首先将三维骨骼模型渲染为二维图像来建立维度映射关系,进而使用图像分类方法识别手绘草图动作并根据维度映射实现三维骨骼模型重建。在实验中使用基于深度卷积神经网络对图像分类模型进行构建,使用浅层卷积网络作为训练单元,并使用逐级分类与分块训练策略加速网络收敛速度来提高训练效率。最后实验结果验证了该方法的可行性与有效性。In order to improve the modeling efficiency of 3 D human skeleton model and simplify the interaction rules,this paper presented a deep learning based 3 D skeleton model reconstruction method from human motion sketch. Firstly,this method rendered the 3 D skeleton models into 2 D images to establish the dimension mapping and then used the image classification method to recognize motion from sketch and further to realize 3 D skeleton model reconstruction according to the dimension mapping between 2 D and 3 D. This method built the image classification model base on CNN and used a shallow convolutional network as the training unit in the experiment. This method also used hierarchical classification and blocking training scheme to accelerate the convergence time of network to improve training efficiency. Finally,the experiment results verify the feasibility and effectiveness of this method.

关 键 词：深度学习 卷积神经网络 三维重建 图像分类 草图建模技术 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]