Stacked Hourglass Networks For Human Pose Estimation
Olivia Luz
Stacked hourglass networks for human pose estimation 5 hands a nal pose estimate requires a coherent understanding of the full body.
We demonstrate the effectiveness of a stacked hourglass network for producing human pose estimates. This work introduces a novel convolutional network architecture for the task of human pose estimation. The person s orientation the arrangement of their limbs and the relationships of adjacent joints are among the many cues that are best recognized at di erent scales in the image. Meth ods based on convolutional neural networks convnets 2 8 9 11.
The network handles a diverse and challenging set of poses with a simple mechanism for reevaluation and assessment of initial predictions. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. Stacked hourglass networks for human pose estimation alejandro newell kaiyu yang jia deng university of michigan ann arbor 1 introduction a key step toward understanding people in images and videos is accurate pose estimation which precisely localizes keypoints of the body. This conventional pipeline however has been greatly reshaped by convolutional neural networks convnets 10 11 12 13 14 a main driver behind an explosive rise in performance across many computer vision tasks.
Human Pose Estimation With Stacked Hourglass Network And Tensorflow In 2020 Human Poses Estimation Deep Learning
Source : pinterest.com
