Skip to content

UVA-DSA/error_detection_Siamese

Repository files navigation

Automatic Erroneous Gesture Detection in Robotic Surgery

Motivations

  • Siamese networks have been used in image recognition [1] and eeg-based brain-computer interfaces signal classification [2]. The dual input setup for Siamese networks could help increase the number of training examples that could potentially increase the network performance for smaller datasets. In this work, we used the Siamese network to detect erroneous gestures during robotic surgeries and demonstrated its superiority under certain training setups.
  • Our prior work [3] shows the importance of context in terms of gesture and task. We used the code from this repo to study the how the contexual information affects our neural network performance. image image_context

Environment

python 3.8
pytorch 1.8.0

References

[1] G. R. Koch, “Siamese neural networks for one-shot image recognition,”ICML deep learning workshop, vol. 2. 2015.

[2] S. Shahtalebi, A. Asif, and A. Mohammadi, “Siamese neural networksfor eeg-based brain-computer interfaces.”Annual International Confer-ence of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, vol. 2020, p. 442–446, 2020.

[3] K. Hutchinson, Z. Li, L. A. Cantrell, N. S. Schenkman, and H. Alemzadeh, “Analysis of executional and procedural errors in dry-lab robotic surgery experiments,”arXiv, Jun 2021.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages