ETH Zurich, Computer Vision Laboratory, Zurich, Switzerland.
IEEE Trans Pattern Anal Mach Intell. 2012 Nov;34(11):2282-8. doi: 10.1109/TPAMI.2012.85.
Most existing techniques for articulated Human Pose Estimation (HPE)consider each person independently. Here we tackle the problem in a new setting,coined Human Pose Coestimation (PCE), where multiple people are in a common,but unknown pose. The task of PCE is to estimate their poses jointly and toproduce prototypes characterizing the shared pose. Since the poses of the individual people should be similar to the prototype, PCE has less freedom compared to estimating each pose independently, which simplifies the problem.We demonstrate our PCE technique on two applications. The first is estimating the pose of people performing the same activity synchronously, such as during aerobics, cheerleading, and dancing in a group. We show that PCE improves pose estimation accuracy over estimating each person independently. The second application is learning prototype poses characterizing a pose class directly from an image search engine queried by the class name (e.g., “lotus pose”). We show that PCE leads to better pose estimation in such images, and it learns meaningful prototypes which can be used as priors for pose estimation in novel images.
大多数现有的人形关节姿态估计（HPE）技术都独立考虑每个人。在这里，我们在一个新的环境中处理这个问题，称为人体姿态协同估计（PCE），其中多个人处于一个共同的，但未知的姿势。PCE 的任务是共同估计他们的姿势，并生成表示共享姿势的原型。由于每个人的姿势应该与原型相似，因此与独立估计每个姿势相比，PCE 的自由度更小，从而简化了问题。我们在两个应用程序上展示了我们的 PCE 技术。第一个应用是估计同时进行相同活动的人的姿势，例如在有氧运动、啦啦队和团体舞蹈中。我们表明，与独立估计每个人的姿势相比，PCE 可以提高姿势估计的准确性。第二个应用是直接从通过类名（例如，“莲花姿势”）查询的图像搜索引擎学习表示姿势类的原型姿势。我们表明，PCE 可以提高此类图像中的姿势估计准确性，并且它可以学习到有意义的原型，这些原型可以用作新颖图像中姿势估计的先验知识。
