Skip to content
Discussion options

You must be logged in to vote

1.我认为可以用mmpose来检测飞机的关键点。
2. 实际上 2D Body Keypoint 和 2D Animal Keyponit 的网络结构都是通用的,只是数据集不同。2d_kpt_sview_rgb_img里面的模型应该都是可以用的。
3. (1)数据集制作的话,可以试一下 https://github.com/open-mmlab/labelbee-client 工具。但是这个工具目前,无法直接转换成coco格式,还需要手动转换一下格式。(2)不需要mask信息 (3)被遮挡点一种方式是正常脑补坐标[x, y, 1],一种方式是标注为[0,0,0]。两种方式均可。

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by jin-s13
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Ideas
Labels
kind/discussion community discussion
2 participants
Converted from issue

This discussion was converted from issue #1096 on December 28, 2021 06:41.