MATLAB Answers

Recognition of one upper body gesture

6 views (last 30 days)
Nicolai Denzel
Nicolai Denzel on 6 Jun 2018
Answered: Prajit T R on 12 Jun 2018
Hello everybody,
I want to develop a programm which can recognize pedestrains with a 90 degree arm position.
At the moment I try to solve the problem with a pretrained deep learning network.
I will make one folder with pictures from the correct gesture and one folder with false gestures.
Are there any other suggestions to solve the problem? I am new in image processing and write the programm for a school project.
I would be very pleased about a few tipps.
Best regards
Nicolai Denzel

  0 Comments

Sign in to comment.

Accepted Answer

Prajit T R
Prajit T R on 12 Jun 2018
Hi Nicolai
It would be better if you have a larger training set with both positive and negative categories represented.
Here’s a link that can shed some light about image classification using deep learning: https://www.mathworks.com/help/vision/examples/object-detection-using-deep-learning.html
In the above documentation, it is mentioned as follows: “First a CNN is pretrained using the CIFAR-10 data set, which has 50,000 training images. Then this pretrained CNN is fine-tuned for stop sign detection using just 41 training images. Without pretraining the CNN, training the stop sign detector would require many more images.”
You could try to pretrain the image on the large generic dataset like CIFAR-10 before training it for your specific requirement as mentioned in the documentation example. To obtain a better accuracy for classification, as with other neural networks, you may need more epochs of training.
I suggest the following steps:
1) Pre-train the network on a large dataset first as discussed above.
2) You could try tuning some parameters like 'MiniBatchSize', 'InitialLearnRate', 'MaxEpochs'.
3) Increase the training dataset size.
As the network is being trained, you can observe the accuracy over various epochs. Repeat the above steps until you get a suitable accuracy.
Hope this helps
Prajit

  0 Comments

Sign in to comment.

More Answers (0)

Sign in to answer this question.