Are bounding boxes required when using keypoints? #8904
Replies: 2 comments
-
It does not really important. You may use both. CVAT will export results with images.
Labeling specification depends on your requirements. It may be several points meaning corners, a bounding box (rotated or not), a polygon, a mask. CVAT supports all these cases.
I am not sure I understand this question. |
Beta Was this translation helpful? Give feedback.
0 replies
-
Thank you for your help. I'm new at this. I found another way of doing it
which works perfectly.
…On Fri, 17 Jan 2025, 20:00 Boris Sekachev, ***@***.***> wrote:
Should I be using individual images or mp4 ?
It does not really important. You may use both. CVAT will export results
with images.
Does it need a bounding box?
Labeling specification depends on your requirements. It may be several
points meaning corners, a bounding box (rotated or not), a polygon, a mask.
CVAT supports all these cases.
How many images should I annotate as a trial?
I am not sure I understand this question.
—
Reply to this email directly, view it on GitHub
<#8904 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AE66ZFGQV7IEHZSF7MR4UU32LDBCJAVCNFSM6AAAAABUYVXT32VHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTCOBWGQ2DAMY>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
|
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hi all, probably a newbie question, but I'm going around in circles.
So, I run a large excavator and I'm trying to track the bucket size reasonably accurately, as it moves up & down, nearer and further away.
It's basically a moving rectangular box.
I successfully added bounding boxes to 800 images using Labelimg and trained a model to track my custom object. However the box sizes change and not very stable. I need more accurate sizes.
I found CVAT to do the annotating and am trying to setup 4 key points to define the buckets' shape.
Thanks

Brent
Beta Was this translation helpful? Give feedback.
All reactions