0
$\begingroup$

I have a bunch of images and I need recognise some objects on them:

  • Analyse the type of vehicle (car, truck, tanker), make, model, colour.
  • Check if there are persons on the image.

I would like to build this using Keras.

I have some questions on this:

  • Could I use some pretrained models for this?
  • Can I avoid labelling my images?
  • How can I, on the one hand, analyse the cars and, on the other hand, recognise whether or not there are people?
Improve this question
$\endgroup$
1
  • $\begingroup$ By reading your problem statement, I feel that solving this problem using Object Detection will be ideal. But I don't know the exact details of the dataset. Are you sure you want to perform image classification? What if an image contains person and car both? $\endgroup$
    – Devashish Prasad
    Commented Jun 1, 2021 at 5:03

1 Answer 1

Reset to default
0
$\begingroup$

You can for instance tackle that as an Object Recognition task.

Then, one possible solution is to use YOLO for object detection; Such networks split input images into many cells, and for each cell they predict a set of bounding boxes (and the corresponding object label, if any).

You can for instance configure your network to recognize as much classes as there are unique objects' settings; In your case for example it could be: N = 3*#make*#model#color + 1 classes, and you'd probably need to prepare (label) a dataset specifically for that! which is not your objective. The +1 is to make sure we included Person.

Or, you can leverage pre-trained YOLO on some dataset so that it's able to recognize: Person, Truck, Car, Tanker (I guess you should be able to find such weights easily, https://cocodataset.org/#explore) and manage to use that in prediction mode on your images. If you got more specific training examples from your specific distribution, then consider fine tuning on top of that. But you should be able to get reliable predictions even without retraining (and thus, without the need for tagged data). But following this approach, you still have to label things for make, model, colour detection ..

Improve this answer
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.