PERIAPT: Joint Person Detection, Re-Identification and Pose Tracking in Video

对于许多应用，如机器人、自动驾驶或智能工厂，机器必须意识到人类在他们附近。这需要知道现在人类的位置和姿势，并持续跟踪他们。虽然人物检测、人物重新识别和姿态跟踪是高度相关的，但这三个任务以前都是独立研究的。例如，被检测人员的包围盒的对准质量影响重新识别的准确性。如果一个人被遮挡了很长时间，或者离开现场后再次出现，需要重新识别。此外，人体探测器很难检测到部分被遮挡的人，而即使人体的其他部位被遮挡，也可以检测到可见的关节。因此，我们将研究这三项任务如何相互协助，我们的目标是通过在联合框架内共同解决这三项任务来提高这三项任务的准确性。

For many applications like robotics, autonomous driving, or smart factories, machines have to be aware of humans in their vicinity. This requires to know the location and pose of the present humans and track them continuously. Although person detection, person reidentification and pose tracking are highly correlated, the three tasks have been previously studied independently. For instance, the alignment quality of the bounding boxes of detected persons affects the re-identification accuracy. If a person is occluded for a long time or re-appears after leaving the scene, it needs to be re-identified. Furthermore, person detectors struggle to detect partially occluded persons whereas visible joints can be detected even if other parts of the human body are occluded. We will therefore investigate how the three tasks can assist each other and we aim to improve the accuracy for all three tasks by solving them together in a joint framework.