Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

multi-camera-multi-object-detection with re-identification #94

Open
muhammad-usama-aleem opened this issue Nov 25, 2023 · 3 comments
Open

Comments

@muhammad-usama-aleem
Copy link

how can we track the same person person with different cameras?

For example, if a person is detected by a camera, then this person is labeled with an id number, then this person can keep this id number to the other camera.

@jarvijd
Copy link

jarvijd commented Jan 8, 2024

just wondering - did you ever find an answer to this question?

@muhammad-usama-aleem
Copy link
Author

no, as you can see. I found some repositories which does not work now and even there dataset is not available. let me know if you get any lead.

@rolson24
Copy link

My guess is that you would want to make a model that is similar to the Fast ReID model (but more powerful and accurate) to get the embedding vectors for each detection box, and then match the detections from one camera to the next based on how close they are in the embedding space. Honestly it sounds like you would need some sort of facial recognition or something depending on if the cameras are looking at the same area or not, and how long you want the tracker to remember a person.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants