A Computer vision based system for human detection and automatic people counting
| dc.contributor.author | Curiel, Gabriela | eng |
| dc.contributor.author | Guerrero, Kevin | eng |
| dc.contributor.author | Gómez, Diego | eng |
| dc.contributor.author | Charris, Daniela | eng |
| dc.date.accessioned | 2024-12-24 00:00:00 | |
| dc.date.available | 2024-12-24 00:00:00 | |
| dc.date.issued | 2024-12-24 | |
| dc.description.abstract | Occupancy control is a fundamental aspect of managing spaces and services effectively. It aims to ensure safety, compliance with regulations, emergency preparedness, and overall satisfaction for individuals and businesses. To align with the described need, this paper presents a computer vision based system for automatic people counting in gates. The system is divided in five stages: video capture, motion analysis, human detection, human tracking and people counting. An RGB camera captures the top-view image of the gate and analyze the change or movement in the objects in scene. When motion is detected, the frame is sent to the object detector, which is a convolutional neural network. Then, a tracking algorithm analyzes the movement patterns of people. According to the route, it is determined whether the person arrives or leaves and the count is updated. Two test scenarios are analyzed: the entry of a public bus and a building gate. The people detection module is tested, showing a mAP of 95.2% and a mean IoU (50%) of 55.9%. Also, the counting is tested showing an average precision of 96.8%, a recall of 92% and an F1-Score of 94.3%. Finally, the system performance is evaluated, showing an average processing time of 34.2 ms and 29.2 FPS. | eng |
| dc.format.mimetype | application/pdf | eng |
| dc.identifier.doi | 10.32397/tesea.vol5.n2.624 | |
| dc.identifier.eissn | 2745-0120 | |
| dc.identifier.url | https://doi.org/10.32397/tesea.vol5.n2.624 | |
| dc.language.iso | eng | eng |
| dc.publisher | Universidad Tecnológica de Bolívar | eng |
| dc.relation.bitstream | https://revistas.utb.edu.co/tesea/article/download/624/424 | |
| dc.relation.citationedition | Núm. 2 , Año 2024 : Transactions on Energy Systems and Engineering Applications | eng |
| dc.relation.citationendpage | 14 | |
| dc.relation.citationissue | 2 | eng |
| dc.relation.citationstartpage | 1 | |
| dc.relation.citationvolume | 5 | eng |
| dc.relation.ispartofjournal | Transactions on Energy Systems and Engineering Applications | eng |
| dc.relation.references | Xianzhi Li, Qiao Yu, Bander Alzahrani, Ahmed Barnawi, Ahmed Alhindi, Daniyal Alghazzawi, and Yiming Miao. Data fusion for intelligent crowd monitoring and management systems: A survey. IEEE Access, 9:47069–47083, 2021. [2] Ali M. Al-Shaery, Shroug S. Alshehri, Norah S. Farooqi, and Mohamed O. Khozium. In-depth survey to detect, monitor and manage crowd. IEEE Access, 8:209008–209019, 2020. [3] Periódico El Heraldo. ¿a qué se deben los retrasos en las rutas de transmetro?, 2022. [4] Periódico El Universal. ¿por qué se demoran tanto en pasar los buses de transcaribe?, 2021. [5] Revista Semana. Aumentan quejas por falta de buses alimentadores en el portal de suba de transmilenio, 2022. [6] Periódico El País. La increíble cifra de caleños regañados en su trabajo por culpa de los retrasos del mÍo, 2023. [7] Chris Mccarthy, Irene Moser, Prem Prakash Jayaraman, Hadi Ghaderi, Adin Ming Tan, Ali Yavari, Ubaid Mehmood, Matthew Simmons, Yehuda Weizman, Dimitrios Georgakopoulos, Franz Konstantin Fuss, and Hussein Dia. A field study of internet of things-based solutions for automatic passenger counting. IEEE Open Journal of Intelligent Transportation Systems, 2:384–401, 2021. [8] Charlie Kim and Joseph Derisi. Versacount: Customizable manual tally software for cell counting. Source code for biology and medicine, 5:1, 01 2010. [9] Julismah Jani. Using tally counter to count heart rate in physical fitness activity: An innovation approach. IJAEDU International E-Journal of Advances in Education, 1:112, 08 2015. [10] Sylvia T. Kouyoumdjieva, Peter Danielis, and Gunnar Karlsson. Survey of non-image-based approaches for counting people. IEEE Communications Surveys and Tutorials, 22(2):1305–1336, 2020. [11] Navod Suraweera, Alycia Winter, Julian Sorensen, Shenghong Li, Mark Johnson, Iain B. Collings, Stephen V. Hanly, Wei Ni, and Mark Hedley. Passive through-wall counting of people walking using wifi beamforming reports. IEEE Systems Journal, 15(4):5476–5482, 2021. [12] V-COUNT. People counting technologies: A comprehensive guide, 2021 [13] Kamaleswari P and Krishnaraj N. An assessment of object detection in thermal (infrared) image processing. In 2023 Third International Conference on Artificial Intelligence and Smart Energy (ICAIS), pages 1498–1503, 2023. [14] Mertcan Cokbas, Prakash Ishwar, and Janusz Konrad. Low-resolution overhead thermal tripwire for occupancy estimation. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 398–406, 2020. [15] Peng-Rong Tsou, Cheng-En Wu, Yen-Ru Chen, Yun-Ting Ho, Jun-Kai Chang, and Hsiao-Ping Tsai. Counting people by using convolutional neural network and a pir array. In 2020 21st IEEE International Conference on Mobile Data Management (MDM), pages 342–347, 2020. [16] Shijie Sun, Naveed Akhtar, Huansheng Song, Chaoyang Zhang, Jianxin Li, and Ajmal Mian. Benchmark data and method for real-time people counting in cluttered scenes using depth sensors. IEEE Transactions on Intelligent Transportation Systems, 20(10):3599–3612, 2019. [17] José Rodríguez Cadena. Contador automático de pasajeros. B.s. thesis, Universidad del Norte, 2017. [18] Seyed Ali Hosseini Shamoushaki, Mohammad Mostafa Talebi, Amineh Mazandarani, and S. Jafar Hosseini. A high-accuracy, cost-effective people counting solution based on visual depth data. In 2020 International Conference on Machine Vision and Image Processing (MVIP), pages 1–6, 2020. [19] Andes Herviana, Dodi Wisaksono Sudiharto, and Fazmah Arif Yulianto. The prototype of in-store visitor and people passing counters using single shot detector performed by opencv. In 2020 1st International Conference on Information Technology, Advanced Mechanical and Electrical Engineering (ICITAMEE), pages 169–174, 2020. [20] Hayato Nakashima, Ismail Arai, and Kazutoshi Fujikawa. Passenger counter based on random forest regressor using drive recorder and sensors in buses. In 2019 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), pages 561–566, 2019. [21] Muhammad Haris Kaka Khel, Kushsairy Abdul Kadir, Sheroz Khan, Mnmm Noor, Haidawati Nasir, Nawaf Waqas, and Akbar Khan. Realtime crowd monitoring—estimating count, speed and direction of people using hybridized yolov4. IEEE Access, 11:56368–56379, 2023. [22] Immanuel Jose C. Valencia, Marielet A. Guillermo, Elmer P. Dadios, Alexis M. Fillone, Edwin Sybingco, and Robert Kerwin C. Billones. Overhead view bus passenger detection and counter using deepsort and tiny-yolo v4. In 2022 IEEE 14th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), pages 1–6, 2022. [23] Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. You only look once: Unified, real-time object detection. pages 779–788, 06 2016. [24] Farzan Erlik Nowruzi, Wassim A. El Ahmar, Robert Laganiere, and Amir H. Ghods. In-vehicle occupancy detection with convolutional networks on thermal images. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 941–948, 2019. [25] Robert Seidel, Nico Jahn, Sambu Seo, Thomas Goerttler, and Klaus Obermayer. Napc: A neural algorithm for automated passenger counting in public transport on a privacy-friendly dataset. IEEE Open Journal of Intelligent Transportation Systems, 3:33–44, 2022. [26] Nicolai Wojke, Alex Bewley, and Dietrich Paulus. Simple online and realtime tracking with a deep association metric. In 2017 IEEE International Conference on Image Processing (ICIP), pages 3645–3649, 2017. [27] Yifu Zhang, Chunyu Wang, Xinggang Wang, Wenjun Zeng, and Wenyu Liu. Fairmot: On the fairness of detection and re-identification in multiple object tracking. International Journal of Computer Vision, 129(11):3069–3087, sep 2021. [28] Peng Chu, Jiang Wang, Quanzeng You, Haibin Ling, and Zicheng Liu. Transmot: Spatial-temporal graph transformer for multiple object tracking, 2021. [29] Huitong Chen. Comparison of large language and vision models on representative downstream tasks. In 2023 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML), pages 307–311, 2023. [30] Yueting Yang, Xintong Zhang, Jinan Xu, and Wenjuan Han. Empowering vision-language models for reasoning ability through large language models. In ICASSP 2024- 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 10056–10060, 2024. [31] Gabriela Curiel, Kevin Guerrero, Diego Gómez, and Daniela Charris. An improved architecture for automatic people counting in public transport using deep learning. In 2023 1st IEEE Colombian Caribbean Conference (C3), 2023. [32] Z. Zivkovic. Improved adaptive gaussian mixture model for background subtraction. In Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004., volume 2, pages 28–31 Vol.2, 2004. [33] Zoran Zivkovic and Ferdinand van der Heijden. Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recognition Letters, 27(7):773–780, 2006. [34] P. KaewTraKulPong and R. Bowden. An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection, pages 135–144. Springer US, Boston, MA, 2002. [35] Ahmed Elngar, Mohamed Arafa, Abd Naeem, Ahmed Essa, and Zahra shaaban. The viola-jones face detection algorithm analysis: A survey. Journal of Cybersecurity and Information Management, pages 85–95, 01 2021. [36] Seemanthini .K and Manjunath S.S. Human detection and tracking using hog for action recognition. Procedia Computer Science, 132:1317–1326, 01 2018. [37] Songmin Jia, Chentao Diao, Guoliang Zhang, Ao Dun, Yanjun Sun, Xiuzhi Li, and Xiangyin Zhang. Object detection based on the improved single shot multibox detector. Journal of Physics: Conference Series, 1187:042041, 04 2019. [38] Bruce Lucas and Takeo Kanade. An iterative image registration technique with an application to stereo vision (ijcai). volume 81, 04 1981. [39] Humberto Gutiérrez Pulido and Román Salazar. Análisis y Diseño de Experimentos. 05 2012. | eng |
| dc.rights | Gabriela Curiel, Kevin Guerrero, Diego Gómez, Daniela Charris - 2024 | eng |
| dc.rights.accessrights | info:eu-repo/semantics/openAccess | eng |
| dc.rights.coar | http://purl.org/coar/access_right/c_abf2 | eng |
| dc.rights.creativecommons | This work is licensed under a Creative Commons Attribution 4.0 International License. | eng |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0 | eng |
| dc.source | https://revistas.utb.edu.co/tesea/article/view/624 | eng |
| dc.subject | Computer vision | eng |
| dc.subject | Deep learning | eng |
| dc.subject | Human detection | eng |
| dc.subject | Convolutional Neural Network | eng |
| dc.subject | Object Tracking | eng |
| dc.subject | People counting | eng |
| dc.title | A Computer vision based system for human detection and automatic people counting | spa |
| dc.title.translated | A Computer vision based system for human detection and automatic people counting | spa |
| dc.type | Artículo de revista | spa |
| dc.type.coar | http://purl.org/coar/resource_type/c_6501 | eng |
| dc.type.coarversion | http://purl.org/coar/version/c_970fb48d4fbd8a85 | eng |
| dc.type.content | Text | eng |
| dc.type.driver | info:eu-repo/semantics/article | eng |
| dc.type.local | Journal article | eng |
| dc.type.version | info:eu-repo/semantics/publishedVersion | eng |