Automatic Selection of Machine Learning Models for Armed People Identification

被引:0
作者
Javier Amado-Garfias, Alonso [1 ]
Conant-Pablos, Santiago Enrique [1 ]
Ortiz-Bayliss, Jose Carlos [1 ]
Terashima-Marin, Hugo [1 ]
机构
[1] Tecnol Monterrey, Sch Engn & Sci, Monterrey 64849, Nuevo Leon, Mexico
关键词
Weapons; YOLO; Videos; Detectors; Cameras; Object recognition; Computational modeling; Accuracy; Video surveillance; Real-time systems; Machine learning; armed people detection; computer vision; object detection; CLASSIFICATION;
D O I
10.1109/ACCESS.2024.3504483
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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%.
引用
收藏
页码:175952 / 175968
页数:17
相关论文
共 50 条
[41]   Machine learning in thermoelectric materials identification: Feature selection and analysis [J].
Xu, Yijing ;
Jiang, Lu ;
Qi, Xiang .
COMPUTATIONAL MATERIALS SCIENCE, 2021, 197
[42]   Landslide susceptibility assessment using feature selection-based machine learning models [J].
Liu, Lei-Lei ;
Yang, Can ;
Wang, Xiao-Mi .
GEOMECHANICS AND ENGINEERING, 2021, 25 (01) :1-16
[43]   Prediction of intrapartum fetal hypoxia considering feature selection algorithms and machine learning models [J].
Zafer Cömert ;
Abdulkadir Şengür ;
Ümit Budak ;
Adnan Fatih Kocamaz .
Health Information Science and Systems, 7
[44]   Machine Learning Models for Cultural Heritage Image Classification: Comparison Based on Attribute Selection [J].
Jankovic, Radmila .
INFORMATION, 2020, 11 (01)
[45]   Prediction of intrapartum fetal hypoxia considering feature selection algorithms and machine learning models [J].
Comert, Zafer ;
Sengur, Abdulkadir ;
Budak, Umit ;
Kocamaz, Adnan Fatih .
HEALTH INFORMATION SCIENCE AND SYSTEMS, 2019, 7 (01)
[46]   Automatic Digital Modulation Recognition Based on Genetic-Algorithm-Optimized Machine Learning Models [J].
Ansari, Sam ;
Alnajjar, Khawla A. ;
Saad, Mohamed ;
Abdallah, Saeed ;
El-Moursy, Ali A. .
IEEE ACCESS, 2022, 10 :50265-50277
[47]   Bilinear Models for Machine Learning [J].
Doghri, Tayssir ;
Szczecinski, Leszek ;
Benesty, Jacob ;
Mitiche, Amar .
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2020, PT I, 2020, 12396 :687-698
[48]   Automatic identification of residential building features using machine learning techniques [J].
Pietro, Carpanese ;
Marco, Dona ;
Francesca, da Porto .
XIX ANIDIS CONFERENCE, SEISMIC ENGINEERING IN ITALY, 2023, 44 :1980-1987
[49]   Automatic Identification of Individual Nanoplastics by Raman Spectroscopy Based on Machine Learning [J].
Xie, Lifang ;
Luo, Siheng ;
Liu, Yangyang ;
Ruan, Xuejun ;
Gong, Kedong ;
Ge, Qiuyue ;
Li, Kejian ;
Valev, Ventsislav Kolev ;
Liu, Guokun ;
Zhang, Liwu .
ENVIRONMENTAL SCIENCE & TECHNOLOGY, 2023, 57 (46) :18203-18214
[50]   Detecting Plant Diseases Using Machine Learning Models [J].
Kohut, Nazar ;
Basystiuk, Oleh ;
Shakhovska, Nataliya ;
Melnykova, Nataliia .
SUSTAINABILITY, 2025, 17 (01)