Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation. (arXiv:2206.07510v1 [cs.CV])

Web: http://arxiv.org/abs/2206.07510

Most of the existing works on pedestrian pose estimation do not consider
estimating the pose of an occluded pedestrians, 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 …

arxiv cv deep networks