The Best Model of Convolutional Neural Networks Combined with LSTM for the Detection of Interpersonal Physical Violence in Videos
| Autor: | Hugo David Calderon Vilca, Kent Jhunior Cuadros Ramos, Elmer Y. Diaz Quiroz, Jorge Alexander Angeles Rojas, Rene Alfredo Calderon Vilca, Alejandro Apaza Tarqui |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | Proceedings of the XXth Conference of Open Innovations Association FRUCT, Vol 29, Iss 1, Pp 81-86 (2021) |
| Druh dokumentu: | article |
| ISSN: | 2305-7254 2343-0737 |
| DOI: | 10.23919/FRUCT52173.2021.9435563 |
| Popis: | Citizen insecurity is directly related to interpersonal physical violence, there are algorithms that allow detecting violence in videos, therefore it is necessary to know which is the best model for detecting violence. We compared three convolutional neural network models Xception, InceptionV3 and VGG16 each together with a recurring LSTM network, to find out which of the models is the best for the detection of interpersonal violence in videos. We train the three models using the Real Life Violence Situations data set, then we classify violence and non-violence, as a result, the InceptionV3 model is the best model, managing to classify with an accuracy of 94% compared to the VGG16 and Xception models, which obtained 88% and 93% respectively. Therefore, we recommend the InceptionV3 model for the detection of interpersonal physical violence in citizen security videos. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|