Improve pose estimation for small-scale persons using head and body centers with Cheng
Improve pose estimation for small-scale persons using head and body centers with Cheng
Bottom-Up 2D Pose Estimation via Dual Anatomical Centers for Small-Scale Persons
arXiv paper abstract https://arxiv.org/abs/2208.11975v1
arXiv PDF paper https://arxiv.org/pdf/2208.11975v1.pdf
In multi-person 2D pose estimation, the bottom-up methods simultaneously predict poses for all persons, and unlike the top-down methods, do not rely on human detection.
However, the SOTA bottom-up methods' accuracy is still inferior compared to the existing top-down methods.
... propose multi-scale training to enhance the network to handle scale variation with single-scale testing, particularly for small-scale persons.
... introduce dual anatomical centers (i.e., head and body) ... can predict the human poses more accurately and reliably, especially for small-scale persons.
... method achieves 38.4% improvement on bounding box precision and 39.1% improvement on bounding box recall over the state of the art (SOTA) on the challenging small-scale persons subset of COCO.
For the human pose AP evaluation, ... achieve a new SOTA (71.0 AP) on the COCO test-dev set with the single-scale testing ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Commenti