How do you deal with incomplete person appeared in image？network can not return right pose!

leoxiaobin / deep-high-resolution-net.pytorch

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

https://jingdongwang2017.github.io/Projects/HRNet/PoseEstimation.html

MIT License

4.33k stars 912 forks source link

How do you deal with incomplete person appeared in image？network can not return right pose! #6

Open oujieww opened 5 years ago

oujieww commented 5 years ago

Sorry , something wrong,i can not process image. For example,the whole image，only have one person upper body！So ，the detector will give a box [0,0,w,h]. in this project , the network use input image with " center of image == person center,in mpii"! but in this kind of image,we only have upper body,we can not build this kind of input in inference time.

So, anyone can help me to deal with this kind of problem?^_^

leoxiaobin commented 5 years ago

you can try our pre-trained models on COCO dataset, and it can handle the kind of image that only having upper body.

oujieww commented 5 years ago

@leoxiaobin thank you for your reply. Is that because the 'center' of COCO is from bbox? For mpii is only default by person body?