arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1807.04067cs.CV
收藏

MultiPoseNet:基于位姿残差网络的快速多人位姿估计

MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network

Middle East Technical University(中东技术大学)

Muhammed Kocabas, Salih Karagoz, Emre Akbas

摘要:

在本文中,我们提出了MultiPoseNet,一种新的自下而上的多人姿态估计架构,它结合了多任务模型和一种新的分配方法。MultiPoseNet可以联合处理人物检测、关键点检测、人物分割和姿势估计问题。新的分配方法是由姿态残差网络(PRN)实现的,该网络接收关键点和人物检测,并通过将关键点分配给人物实例来产生准确的姿态。在COCO关键点数据集上,我们的姿势估计方法在准确性(比之前的最佳结果高出4点mAP)和速度方面都优于所有之前的自下而上方法;它的性能也与最好的自上而下方法相当,同时至少快4倍。我们的方法是最快的实时的系统与23帧/秒。源代码可从以下网址获得:https://github.com/mkocabas/pose-residual-network

英文摘要:

In this paper, we present MultiPoseNet, a novel bottom-up multi-person pose estimation architecture that combines a multi-task model with a novel assignment method. MultiPoseNet can jointly handle person detection, keypoint detection, person segmentation and pose estimation problems. The novel assignment method is implemented by the Pose Residual Network (PRN) which receives keypoint and person detections, and produces accurate poses by assigning keypoints to person instances. On the COCO keypoints dataset, our pose estimation method outperforms all previous bottom-up methods both in accuracy (+4-point mAP over previous best result) and speed; it also performs on par with the best top-down methods while being at least 4x faster. Our method is the fastest real time system with 23 frames/sec. Source code is available at: https://github.com/mkocabas/pose-residual-network

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。

↑