Automatic Selection of Machine Learning Models for Armed People Identification

This research aims to improve the automatic identification of armed people in surveillance videos. We focus on people armed with pistols and revolvers. Furthermore, we use the YOLOv4 to detect people and weapons in each video frame. We developed a series of algorithms to create a dataset with the in...

Full description

Saved in:
Bibliographic Details
Main Authors: Alonso Javier Amado-Garfias, Santiago Enrique Conant-Pablos, Jose Carlos Ortiz-Bayliss, Hugo Terashima-Marin
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10763529/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846141951511887872
author Alonso Javier Amado-Garfias
Santiago Enrique Conant-Pablos
Jose Carlos Ortiz-Bayliss
Hugo Terashima-Marin
author_facet Alonso Javier Amado-Garfias
Santiago Enrique Conant-Pablos
Jose Carlos Ortiz-Bayliss
Hugo Terashima-Marin
author_sort Alonso Javier Amado-Garfias
collection DOAJ
description This research aims to improve the automatic identification of armed people in surveillance videos. We focus on people armed with pistols and revolvers. Furthermore, we use the YOLOv4 to detect people and weapons in each video frame. We developed a series of algorithms to create a dataset with the information extracted from the bounding boxes generated by YOLOv4 in real-time. Thereby, we initially developed six-armed people detectors (APD) based on six machine learning models: Random Forest Classifier (RFC-APD), Multilayer Perceptron (MLP-APD), Support Vector Machine (SVM-APD), Logistic Regression (LR-APD), Naive Bayes (NB-APD), and Gradient Boosting Classifier (GBC-APD). These models use 20 predictors to make their predictions. These predictors are computed from the bounding box coordinates of the detected people and weapons, their distances, and areas of intersection. Based on our results, the RFC-APD was the best-performing detector, with an accuracy of 95.59%, a recall of 94.51%, and an F1-score of 95.65%. In this work, we propose to create selectors for deciding which APD to use in each video frame (APD4F) to improve the detection results. Besides, we implemented two types of APD4Fs, one based on a Random Forest Classifier (RFC-APD4F) and another in a Multilayer Perceptron (MLP-APD4F). We developed 44 APD4Fs combining subsets of the six APDs. Both APD4F types outperformed most of the independent use of all six APDs. A multilayer perceptron-based APD4F, which combines an MLP-APD, a NB-APD, and a LR-APD, presented the best performance, achieving an accuracy of 95.84%, a recall of 99.28% and an F1 score of 96.07%.
format Article
id doaj-art-2311ccf26cd648b89f510d1804c78b27
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-2311ccf26cd648b89f510d1804c78b272024-12-04T00:01:43ZengIEEEIEEE Access2169-35362024-01-011217595217596810.1109/ACCESS.2024.350448310763529Automatic Selection of Machine Learning Models for Armed People IdentificationAlonso Javier Amado-Garfias0https://orcid.org/0000-0001-8447-3355Santiago Enrique Conant-Pablos1https://orcid.org/0000-0001-6270-3164Jose Carlos Ortiz-Bayliss2https://orcid.org/0000-0003-3408-2166Hugo Terashima-Marin3https://orcid.org/0000-0002-5320-0773School of Engineering and Sciences, Tecnológico de Monterrey, Monterrey, Nuevo Leon, MexicoSchool of Engineering and Sciences, Tecnológico de Monterrey, Monterrey, Nuevo Leon, MexicoSchool of Engineering and Sciences, Tecnológico de Monterrey, Monterrey, Nuevo Leon, MexicoSchool of Engineering and Sciences, Tecnológico de Monterrey, Monterrey, Nuevo Leon, MexicoThis research aims to improve the automatic identification of armed people in surveillance videos. We focus on people armed with pistols and revolvers. Furthermore, we use the YOLOv4 to detect people and weapons in each video frame. We developed a series of algorithms to create a dataset with the information extracted from the bounding boxes generated by YOLOv4 in real-time. Thereby, we initially developed six-armed people detectors (APD) based on six machine learning models: Random Forest Classifier (RFC-APD), Multilayer Perceptron (MLP-APD), Support Vector Machine (SVM-APD), Logistic Regression (LR-APD), Naive Bayes (NB-APD), and Gradient Boosting Classifier (GBC-APD). These models use 20 predictors to make their predictions. These predictors are computed from the bounding box coordinates of the detected people and weapons, their distances, and areas of intersection. Based on our results, the RFC-APD was the best-performing detector, with an accuracy of 95.59%, a recall of 94.51%, and an F1-score of 95.65%. In this work, we propose to create selectors for deciding which APD to use in each video frame (APD4F) to improve the detection results. Besides, we implemented two types of APD4Fs, one based on a Random Forest Classifier (RFC-APD4F) and another in a Multilayer Perceptron (MLP-APD4F). We developed 44 APD4Fs combining subsets of the six APDs. Both APD4F types outperformed most of the independent use of all six APDs. A multilayer perceptron-based APD4F, which combines an MLP-APD, a NB-APD, and a LR-APD, presented the best performance, achieving an accuracy of 95.84%, a recall of 99.28% and an F1 score of 96.07%.https://ieeexplore.ieee.org/document/10763529/Machine learningarmed people detectioncomputer visionobject detectionYOLO
spellingShingle Alonso Javier Amado-Garfias
Santiago Enrique Conant-Pablos
Jose Carlos Ortiz-Bayliss
Hugo Terashima-Marin
Automatic Selection of Machine Learning Models for Armed People Identification
IEEE Access
Machine learning
armed people detection
computer vision
object detection
YOLO
title Automatic Selection of Machine Learning Models for Armed People Identification
title_full Automatic Selection of Machine Learning Models for Armed People Identification
title_fullStr Automatic Selection of Machine Learning Models for Armed People Identification
title_full_unstemmed Automatic Selection of Machine Learning Models for Armed People Identification
title_short Automatic Selection of Machine Learning Models for Armed People Identification
title_sort automatic selection of machine learning models for armed people identification
topic Machine learning
armed people detection
computer vision
object detection
YOLO
url https://ieeexplore.ieee.org/document/10763529/
work_keys_str_mv AT alonsojavieramadogarfias automaticselectionofmachinelearningmodelsforarmedpeopleidentification
AT santiagoenriqueconantpablos automaticselectionofmachinelearningmodelsforarmedpeopleidentification
AT josecarlosortizbayliss automaticselectionofmachinelearningmodelsforarmedpeopleidentification
AT hugoterashimamarin automaticselectionofmachinelearningmodelsforarmedpeopleidentification