DOI : https://doi.org/10.18517/ijaseit.15.1.20327

Human Detection System Using Machine Learning to Calculate Crowd Potential

Eni Dwi Wardihani (1), Rindang Ayu Oktaviani (2), Ricky Sambora (3), Eko Supriyono (4), Amin Suharjono (5), Rizkha Ajeng Rochmatika (6), Catur Budi Waluyo (7), Muhlasah Novitasari Mara (8), Ari Sriyanto Nugroho (9), Aminuddin Rizal (10), Suko Tyas Pernanda (11)
(1) Department of Telecommunication Engineering, Politeknik Negeri Semarang, Tembalang, Semarang, Indonesia
(2) Department of Telecommunication Engineering, Politeknik Negeri Semarang, Tembalang, Semarang, Indonesia
(3) Department of Telecommunication Engineering, Politeknik Negeri Semarang, Tembalang, Semarang, Indonesia
(4) Department of Telecommunication Engineering, Politeknik Negeri Semarang, Tembalang, Semarang, Indonesia
(5) Department of Telecommunication Engineering, Politeknik Negeri Semarang, Tembalang, Semarang, Indonesia
(6) Department of Telecommunication Engineering, Politeknik Negeri Semarang, Tembalang, Semarang, Indonesia
(7) Department of Telecommunication Engineering, Politeknik Negeri Semarang, Tembalang, Semarang, Indonesia
(8) Department of Telecommunication Engineering, Politeknik Negeri Semarang, Tembalang, Semarang, Indonesia
(9) Department of Telecommunication Engineering, Politeknik Negeri Semarang, Tembalang, Semarang, Indonesia
(10) Department of Electronics Engineering, Politeknik Negeri Semarang, Tembalang, Semarang, Indonesia
(11) Department of Electronics Engineering, Politeknik Negeri Semarang, Tembalang, Semarang, Indonesia
Fulltext View | Download
How to cite (IJASEIT) :
[1]
E. D. Wardihani, “Human Detection System Using Machine Learning to Calculate Crowd Potential”, Int. J. Adv. Sci. Eng. Inf. Technol., vol. 15, no. 1, pp. 60–66, Feb. 2025.
Citation Format :
Crowds are a common social phenomenon occurring in various settings such as large gatherings, public transportation, and popular tourist attractions. Crowding poses significant risks as it can lead to scenarios known as human stampedes. In incidents such as those at Kanjuruhan and Itaewon, the presence of large crowds caused individuals to lose their footing, resulting in falls, trampling, and respiratory complications. This issue is further exacerbated by current crowd detection techniques, which still rely on manual observation. To address this problem, a machine learning-based system was developed for human detection by counting the number of detected heads to evaluate crowd capacity. This study employs a combination of Convolutional Neural Network (CNN) architecture and the YOLOv8 algorithm, trained on a custom dataset and implemented on Jetson Nano for real-time monitoring via a website hosted on localhost. The dataset was created by collecting images of crowded locations, such as bus stops during peak commuting hours and shopping malls on weekends. Testing was conducted at Kantik Kolam Berkah in Politeknik Negeri Semarang during lunch hours on weekdays. Density estimation was performed by calculating the number of detected heads divided by the area being observed, yielding a density figure for the area. The findings reveal that the developed system can identify individuals and measure density with an average precision of 0.965 and an average recall of 0.765, with an average inference time of 283.73 milliseconds (ms).

S. A. H. Al-Gadhi, “A Review Study of Crowd Behavior and Movement,” J. King Saud Univ. - Eng. Sci., vol. 8, no. 1, pp. 77–107, 1996, doi: 10.1016/S1018-3639(18)30641-X.

A. Fadlil and D. Prayogi, “Face Recognition Using Machine Learning Algorithm Based on Raspberry Pi 4b,” Int. J. Artif. Intell. Res., vol. ISSN, no. 1, pp. 2579–7298, 2022, doi: 10.29099/ijair.v7i1.321.

M. Luqman Bukhori and E. E. Prasetiyo. (2023). “Sistem Deteksi Masker Berbasis Jetson Nano dengan Deep Learning Framework TensorFlow”. Jurnal Nasional Teknik Elektro Dan Teknologi Informasi, 12(1), 15-21. doi: 10.22146/jnteti.v12i1.5472

L. Ezzeddini et al., “Analysis of the performance of Faster R-CNN and YOLOv8 in detecting fishing vessels and fishes in real time,” PeerJ Comput. Sci., vol. 10, p. e2033, 2024, doi: 10.7717/peerj-cs.2033.

I. Karamouzas, N. Sohre, R. Hu, and S. J. Guy, “Crowd space: A predictive crowd analysis technique,” SIGGRAPH Asia 2018 Tech. Pap. SIGGRAPH Asia 2018, vol. 37, no. 6, 2018, doi:10.1145/3272127.3275079.

R. Bai, F. Shen, M. Wang, J. Lu, and Z. Zhang, “Improving Detection Capabilities of YOLOv8-n for Small Objects in Remote Sensing Imagery: Towards Better Precision with Simpliied Model Complexity Improving Detection Capabilities of YOLOv8-n for Small Objects in Remote Sensing Imagery: Towards Better Pre,” Res. Sq., pp. 0–9, 2023. doi: 10.21203/rs.3.rs-3085871/v1

R. Iyer, P. Shashikant Ringe, R. Varadharajan Iyer, and K. Prabhulal Bhensdadiya, “Comparison of YOLOv3, YOLOv5s and MobileNet-SSD V2 for Real-Time Mask Detection,” Artic. Int. J. Res. Eng. Technol., vol. 8, no. 7, pp. 1156–1160, 2021.

I. P. Sary, S. Andromeda, and E. U. Armin, “Performance Comparison of YOLOv5 and YOLOv8 Architectures in Human Detection using Aerial Images,” Ultim. Comput. J. Sist. Komput., vol. 15, no. 1, pp. 8–13, 2023, doi: 10.31937/sk.v15i1.3204.

M. Wirz, T. Franke, D. Roggen, E. Mitleton-Kelly, P. Lukowicz, and G. Tröster, “Probing crowd density through smartphones in city-scale mass gatherings,” EPJ Data Sci., vol. 2, no. 1, pp. 1–24, 2013, doi:10.1140/epjds17.

N. N. Amir Sjarif, S. M. Shamsuddin, S. Z. Mohd Hashim, and S. S. Yuhaniz, “Crowd analysis and its applications,” Commun. Comput. Inf. Sci., vol. 179 CCIS, no. PART 1, pp. 687–697, 2011, doi:10.1007/978-3-642-22170-5_59.

J. C. S. Jacques, S. R. Mussef, and C. R. Jung, “Crowd analysis using computer vision techniques,” IEEE Signal Process. Mag., vol. 27, no. 5, pp. 66–77, 2010, doi: 10.1109/MSP.2010.937394.

H. Yan, “Deadly crowd surges have happened for decades. Safety standards exist, but they’re not required nationwide,” CNN, Nov. 12, 2021. https://edition.cnn.com/2021/11/11/us/safety-standards-requirements-crowd-surges/index.html

Abdulkadir Gozuoglu, Okan Ozgonenel, and Cenk Gezegin, “CNN-LSTM Based Deep Learning Application on Jetson Nano: Estimating Electrical Energy Consumption for Future Smart Homes,” Internet of things, vol. 26, pp. 101148–101148, Jul. 2024, doi:10.1016/j.iot.2024.101148.

V. Gonzalez-Huitron, J. A. León-Borges, A. E. Rodriguez-Mata, L. E. Amabilis-Sosa, B. Ramírez-Pereda, and H. Rodriguez, “Disease detection in tomato leaves via CNN with lightweight architectures implemented in Raspberry Pi 4,” Computers and Electronics in Agriculture, vol. 181, p. 105951, Feb. 2021, doi:10.1016/j.compag.2020.105951.

Y. Chen, Y.-F. Li, C. Cheng, and H. Ying, “Neural network based cognitive approaches from face perception with human performance benchmark,” Pattern recognition letters, Jun. 2024, doi:10.1016/j.patrec.2024.06.024.

J. Yan et al., “Enhanced object detection in pediatric bronchoscopy images using YOLO-based algorithms with CBAM attention mechanism,” Heliyon, vol. 10, no. 12, pp. e32678–e32678, Jun. 2024, doi: 10.1016/j.heliyon.2024.e32678.

Sushila Palwe, A. Gunjal, S. Jindal, A. Shrivastava, A. Deshmukh, and Mehul Navalakha, “An Intelligent and Deep Learning Approach for Pothole Surveillance Smart Application,” Procedia computer science, vol. 235, pp. 3271–3282, Jan. 2024, doi: 10.1016/j.procs.2024.04.309.

E. Casas, L. Ramos, C. Romero, and Francklin Rivas-Echeverría, “A comparative study of YOLOv5 and YOLOv8 for corrosion segmentation tasks in metal surfaces,” Array, vol. 22, pp. 100351–100351, Jul. 2024, doi: 10.1016/j.array.2024.100351.

F. Hou, W. Lei, S. Li, J. Xi, M. Xu, and J. Luo, “Improved Mask R-CNN with distance guided intersection over union for GPR signature detection and segmentation,” Automation in Construction, vol. 121, p. 103414, Jan. 2021, doi: 10.1016/j.autcon.2020.103414.

X. Zhang et al., “Area in circle: A novel evaluation metric for object detection,” Knowledge-based systems, vol. 293, pp. 111684–111684, Jun. 2024, doi: 10.1016/j.knosys.2024.111684.

Mohd Nazuan Wagimin et al., “Classification model for chlorophyll content using CNN and aerial images,” Computers and electronics in agriculture, vol. 221, pp. 109006–109006, Jun. 2024, doi:10.1016/j.compag.2024.109006.

X. Yang, Y. Liu, A. Majumdar, E. Grass, and W. Ochieng, “Characteristics of crowd disaster: database construction and pattern identification,” International journal of disaster risk reduction, pp. 104653–104653, Jul. 2024, doi: 10.1016/j.ijdrr.2024.104653.

Z. Zhu and Y. Cheng, “Application of attitude tracking algorithm for face recognition based on OpenCV in the intelligent door lock,” Computer Communications, vol. 154, pp. 390–397, Mar. 2020, doi: 10.1016/j.comcom.2020.02.003.

D. Syrlybayev, N. Nauryz, A. Seisekulova, K. Yerzhanov, and Md. H. Ali, “Smart Door for COVID Restricted Areas,” Procedia Computer Science, vol. 201, pp. 478–486, Jan. 2022, doi:10.1016/j.procs.2022.03.062.

T. Peng-o and P. Chaikan, “High performance and energy efficient sobel edge detection,” Microprocessors and Microsystems, vol. 87, p. 104368, Nov. 2021, doi: 10.1016/j.micpro.2021.104368.

J. Lee, M. Yu, Y. Kwon, and T. Kim, “Quantune: Post-training quantization of convolutional neural networks using extreme gradient boosting for fast deployment,” Future Generation Computer Systems, vol. 132, pp. 124–135, Jul. 2022, doi: 10.1016/j.future.2022.02.005.

Islomjon Shukhratov, Andrey Pimenov, A. Stepanov, Nadezhda Mikhailova, A. Baldycheva, and Andrey Somov, “Optical Detection of Plastic Waste Through Computer Vision,” Intelligent systems with applications, pp. 200341–200341, Feb. 2024, doi:10.1016/j.iswa.2024.200341.

J. Amin, Irum Shazadi, M. Sharif, M. Yasmin, Nouf Abdullah Almujally, and Y. Nam, “Localization and Grading of NPDR Lesions Using ResNet-18-YOLOv8 Model and Informative Features Selection for DR Classification based on Transfer Learning,” Heliyon, pp. e30954–e30954, May 2024, doi: 10.1016/j.heliyon.2024.e30954.

B. Ganga, Lata B.T, and Venugopal K.R, “Object detection and crowd analysis using deep learning techniques: Comprehensive review and future directions,” Neurocomputing, pp. 127932–127932, May 2024, doi: 10.1016/j.neucom.2024.127932.

Y. C. Putra and A. W. Wijayanto, “Automatic detection and counting of oil palm trees using remote sensing and object-based deep learning,” Remote Sensing Applications: Society and Environment, vol. 29, p. 100914, Jan. 2023, doi: 10.1016/j.rsase.2022.100914.

A. Deshpande and K. Warhade, “SADY: Student Activity Detection Using YOLO-based Deep Learning Approach,” International Journal on Advanced Science, Engineering and Information Technology/International journal of advanced science, engineering and information technology, vol. 13, no. 4, pp. 1501–1501, Jul. 2023, doi: 10.18517/ijaseit.13.4.18393.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).