This website is organized as follows:
- Handgun Dataset for the sliding window approach
- Handgun Dataset for the region proposals approach
This project focuses on the detection of handguns in videos Deep CNN (Convolutional Neural Networks).
The trainning dataset, appropriate for the classification task, consists of 102 classes with a total of 9261 images. The pistol class has 200.
The trainning dataset, appropriate for the detection task, contains 3000 images of guns with rich context.
Test dataset for both classification and detection. A total of 608 images of which 304 are images of pistols.
Olmos, R., Tabik, S., & Herrera, F. (2018).
Automatic handgun detection alarm in videos using deep learning.
Neurocomputing, 275, 66-72.
Link to the pdf