I want to use landmark detection for finding specific points of interest in an indoor setting e.g. bedrooms, bathrooms etc. Is it possible to use it? So far I have only seen landmark detection being used for things like faces or human bodies. Any suggestions or ideas?
1
-
2$\begingroup$ I recommend you these great papers: Corners for Layout: End-to-End Layout Recovery from 360 Images and What’s in my Room? Object Recognition on Indoor Panoramic Images $\endgroup$– Javier TGCommented Jun 17, 2021 at 8:54
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
Yes, it is totally possible.
Any suggestions or ideas?
- You will need to train your own model because you might not find any pre-trained models for the same. (but do check if they are available)
- Pick any state of the art model and I will suggest choosing the pose estimation models.
- Collect images and annotate your dataset in the appropriate format using various tools that are available (that the authors of the model used to annotate their dataset).
- Experiment whether the pre-trained weights of the model are helpful or not. For this, you can try to quickly train the model on a small subset of the dataset.
- If you are getting good results, train the model using the whole dataset.
- If you are not getting good results then try increasing data, collecting more images, or changing the model.
