论文标题
深层多任务网络，用于封闭的行人姿势估计
Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation
论文作者
论文摘要
关于行人姿势估计的大多数现有作品都不考虑估计被阻塞的行人的姿势，因为相关的汽车数据集中没有遮挡零件的注释。例如，在汽车场景中用于行人检测的众所周知的数据集Citypersons不提供姿势注释，而MS-Coco（非自动驱动数据集）MS-Coco包含人类的姿势估计。在这项工作中，我们提出了一个多任务框架，以通过检测和实例分割任务在这两个分布上执行。此后，编码器使用两个分布的行人实例使用无监督的实例级适应方法来学习姿势特定的特征。提出的框架改善了姿势估计，行人检测和实例分割的最新性能。
Most of the existing works on pedestrian pose estimation do not consider estimating the pose of an occluded pedestrian, as the annotations of the occluded parts are not available in relevant automotive datasets. For example, CityPersons, a well-known dataset for pedestrian detection in automotive scenes does not provide pose annotations, whereas MS-COCO, a non-automotive dataset, contains human pose estimation. In this work, we propose a multi-task framework to extract pedestrian features through detection and instance segmentation tasks performed separately on these two distributions. Thereafter, an encoder learns pose specific features using an unsupervised instance-level domain adaptation method for the pedestrian instances from both distributions. The proposed framework has improved state-of-the-art performances of pose estimation, pedestrian detection, and instance segmentation.
