当前位置: X-MOL 学术Comput. Vis. Image Underst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
High-speed multi-person pose estimation with deep feature transfer
Computer Vision and Image Understanding ( IF 4.3 ) Pub Date : 2020-06-09 , DOI: 10.1016/j.cviu.2020.103010
Ying Huang , Hubert P.H. Shum , Edmond S.L. Ho , Nauman Aslam

Recent advancements in deep learning have significantly improved the accuracy of multi-person pose estimation from RGB images. However, these deep learning methods typically rely on a large number of deep refinement modules to refine the features of body joints and limbs, which hugely reduce the run-time speed and therefore limit the application domain. In this paper, we propose a feature transfer framework to capture the concurrent correlations between body joint and limb features. The concurrent correlations of these features form a complementary structural relationship, which mutually strengthens the network’s inferences and reduces the needs of refinement modules. The transfer sub-network is implemented with multiple convolutional layers, and is merged with the body part detection network to form an end-to-end system. The transfer relationship is automatically learned from ground-truth data instead of being manually encoded, resulting in a more general and efficient design. The proposed framework is validated on the multiple popular multi-person pose estimation benchmarks - MPII, COCO 2018 and PoseTrack 2017 and 2018. Experimental results show that our method not only significantly increases the inference speed to 73.8 frame per second (FPS), but also attains comparable state-of-the-art performance.



中文翻译:

具有深度特征转移的高速多人姿势估计

深度学习的最新进展显着提高了根据RGB图像进行多人姿势估计的准确性。但是,这些深度学习方法通​​常依赖于大量的深度细化模块来细化人体关节和四肢的特征,这极大地降低了运行时速度,因此限制了应用领域。在本文中,我们提出了一个特征转移框架来捕获身体关节和四肢特征之间的并发关联。这些功能的并发关联形成了互补的结构关系,从而相互加强了网络的推论并减少了优化模块的需求。传输子网由多个卷积层实现,并与身体部位检测网络合并以形成端到端系统。传递关系是从真实数据中自动学习的,而不是手动编码的,从而实现了更通用,更有效的设计。所提出的框架已通过多种流行的多人姿势估计基准进行了验证-MPII,COCO 2018和PoseTrack 2017和2018。实验结果表明,我们的方法不仅将推理速度显着提高到了每秒73.8帧(FPS),而且达到可比的最新性能。

更新日期:2020-06-09
down
wechat
bug