Comparison of FairMOT-VGG16 and MCMOT Implementation for Multi-Object Tracking and Gender Detection on Mall CCTV
Dublin Core
Title
Comparison of FairMOT-VGG16 and MCMOT Implementation for Multi-Object Tracking and Gender Detection on Mall CCTV
Subject
CCTV, Detection, Gender, Tracking
Description
The crowd detection system on CCTV has proven to be useful for retail owners in mall areas where data can be used as a guide by owners to find out the number of visitors who enter at a certain time.
However, such information was still insufficient. The necessity for richer data has led to the development of specific person detection which involves gender. Gender detection can provide specific details about men and women visiting a particular location. However, gender detection alone does not provide an identity label for every detection that occurs, so it needs to be combined with a multi-person tracking system. This study compares two methods, method that are tracks person using one-class FairMOT and classify detected person based on gender and method that track multi-class object where the class is male and
female at the same time simultaneously called MCMOT which is extended version of FairMOT. The first method produces MOTA, MOTP, IDS, and FPS of 78.56, 79.57, 19, and 24.4, while the second method makes 69.84, 81.94, 147, and 30.5. Besides, evaluation of gender was also carried out where the first method resulted in a gender accuracy of 65% while the second method was 62.35%
However, such information was still insufficient. The necessity for richer data has led to the development of specific person detection which involves gender. Gender detection can provide specific details about men and women visiting a particular location. However, gender detection alone does not provide an identity label for every detection that occurs, so it needs to be combined with a multi-person tracking system. This study compares two methods, method that are tracks person using one-class FairMOT and classify detected person based on gender and method that track multi-class object where the class is male and
female at the same time simultaneously called MCMOT which is extended version of FairMOT. The first method produces MOTA, MOTP, IDS, and FPS of 78.56, 79.57, 19, and 24.4, while the second method makes 69.84, 81.94, 147, and 30.5. Besides, evaluation of gender was also carried out where the first method resulted in a gender accuracy of 65% while the second method was 62.35%
Creator
Pray Somaldo, Dina Chahyati
Source
http://dx.doi.org/10.21609/jiki.v14i1.958
Publisher
Faculty of Computer Science Universitas Indonesia
Date
2021-02-28
Contributor
Sri Wahyuni
Rights
e-ISSN : 2502-9274 printed ISSN : 2088-7051
Format
PDF
Language
English
Type
Text
Coverage
Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Information)
Files
Collection
Citation
Pray Somaldo, Dina Chahyati, “Comparison of FairMOT-VGG16 and MCMOT Implementation for Multi-Object Tracking and Gender Detection on Mall CCTV,” Repository Horizon University Indonesia, accessed May 22, 2025, https://repository.horizon.ac.id/items/show/8817.