Signal processing for people detection in crowded areas
Procesamiento de señales para detección de personas en aglomeraciones
Article Sidebar
Main Article Content
This paper addresses the development and implementation of a signal processing system for detecting and counting people in open spaces, using background subtraction techniques with a Raspberry Pi 3B+ embedded board and the Python programming language. The methodology employed includes image conversion to grayscale, background segmentation using the Background Subtractor MOG2 algorithm, Gaussian smoothing filtering, and adaptive thresholding with the Otsu method, along with morphological techniques to enhance detection quality and contour detection for identifying objects. In the image capture phase, factors such as height, tilt angle, and environmental luminosity are considered to ensure the quality of the collected data. Grayscale conversion assigns values between 0 and 255 to pixels, and background subtraction uses Gaussian distributions to differentiate between moving objects and the background. Gaussian smoothing filters are applied to reduce noise, while Otsu's thresholding adapts the threshold to the specific characteristics of each image. Finally, morphological operations refine segmentation, and the simple approximation method is used for contour detection. The system was evaluated with videos captured from four buildings at the Universidad Francisco de Paula Santander and two public areas in Cúcuta, showing detection rates between 87.14% and 93.33% at the university and between 88.89% and 90.51% in public areas.
Downloads
Article Details
M. Leo, G. Medioni, M. Trivedi, T. Kanade, and G. M. Farinella, “Computer vision for assistive technologies,” Computer Vision and Image Understanding, vol. 154, pp. 1–15, 2017, doi: 10.1016/j.cviu.2016.09.001. DOI: https://doi.org/10.1016/j.cviu.2016.09.001
X. Li and Y. Shi, “Computer vision imaging based on artificial intelligence,” in Proceedings - 2018 International Conference on Virtual Reality and Intelligent Systems, ICVRIS 2018, IEEE, 2018, pp. 22–25. doi: 10.1109/ICVRIS.2018.00014. DOI: https://doi.org/10.1109/ICVRIS.2018.00014
N. S. Sakpal and M. Sabnis, “Adaptive Background Subtraction in Images,” in 2018 International Conference On Advances in Communication and Computing Technology, ICACCT 2018, IEEE, 2018, pp. 439–444. doi: 10.1109/ICACCT.2018.8529323. DOI: https://doi.org/10.1109/ICACCT.2018.8529323
S. A. Korkmaz, A. Akcicek, H. Binol, and M. F. Korkmaz, “Recognition of the stomach cancer images with probabilistic HOG feature vector histograms by using HOG features,” in SISY 2017 - IEEE 15th International Symposium on Intelligent Systems and Informatics, Proceedings, 2017, pp. 339–342. doi: 10.1109/SISY.2017.8080578. DOI: https://doi.org/10.1109/SISY.2017.8080578
J. Hernández Santiago, J. S. Ruiz Castilla, C. H. Moreno Montiel, and B. Hernández Santiago, “Segmentación de placas vehiculares usando Haar-AdaBoost y Clustering,” Research in Computing Science, vol. 147, no. 5, pp. 269–279, 2018, doi: 10.13053/rcs-147-5-20. DOI: https://doi.org/10.13053/rcs-147-5-20
A. J. A. Barreto and C. P. A. Barreto, “Some commercial customs in the footwear industry of the municipality of San José de Cúcuta (Colombia),” Revista de Derecho Privado, no. 36, pp. 319–331, 2019, doi: 10.18601/01234366.n36.12. DOI: https://doi.org/10.18601/01234366.n36.12
Diario La Opinión, “Cifras del censo no les cuadran a alcaldes del área metropolitana de Cúcuta,” Actualidad. Accessed: Jun. 29, 2020. [Online]. Available: https://www.laopinion.com.co/economia/cifras-del-censo-no-les-cuadran-alcaldes-del-area-metropolitana-de-cucuta-182061#OP
V. Fremont, M. T. Bui, D. Boukerroui, and P. Letort, “Vision-based people detection system for heavy machine applications,” Sensors (Switzerland), vol. 16, no. 1, pp. 1–30, 2016, doi: 10.3390/s16010128. DOI: https://doi.org/10.3390/s16010128
E. N. Kajabad and S. V. Ivanov, “People Detection and Finding Attractive Areas by the use of Movement Detection Analysis and Deep Learning Approach,” Procedia Comput Sci, vol. 156, pp. 327–337, 2019, doi: 10.1016/j.procs.2019.08.209. DOI: https://doi.org/10.1016/j.procs.2019.08.209
A. Gavriilidis, J. Velten, S. Tilgner, and A. Kummert, “Machine learning for people detection in guidance functionality of enabling health applications by means of cascaded SVM classifiers,” J Franklin Inst, vol. 355, no. 4, pp. 2009–2021, 2018, doi: 10.1016/j.jfranklin.2017.10.008. DOI: https://doi.org/10.1016/j.jfranklin.2017.10.008
C. H. Setjo, B. Achmad, and Faridah, “Thermal image human detection using Haar-cascade classifier,” in Proceedings - 2017 7th International Annual Engineering Seminar, InAES 2017, 2017. doi: 10.1109/INAES.2017.8068554.
H. A. M. Alhamzawi, “Faces and eyes Detection in Digital Images Using Cascade Classifiers,” Computer Engineering and Applications Journal, vol. 7, no. 1, pp. 57–66, 2018, doi: 10.18495/comengapp.v7i1.222.
H. A. M. Alhamzawi, “Faces and eyes Detection in Digital Images Using Cascade Classifiers,” Computer Engineering and Applications Journal, vol. 7, no. 1, pp. 57–66, 2018, doi: 10.18495/comengapp.v7i1.222. DOI: https://doi.org/10.18495/comengapp.v7i1.222
M. S. Fuentes, N. A. L. Zelaya, and J. L. O. Avila, “Coffee Fruit Recognition Using Artificial Vision and neural NETWORKS,” in 2020 5th International Conference on Control and Robotics Engineering, ICCRE 2020, 2020, pp. 224–228. doi: 10.1109/ICCRE49379.2020.9096441. DOI: https://doi.org/10.1109/ICCRE49379.2020.9096441
P. Constante, O. Chang, E. Pruna, and I. Escobar, “Artificial Vision Techniques for Strawberry ’ s Industrial Classification,” Ieee Latin America Transactions, vol. 14, no. 6, pp. 2576–2581, 2016, doi: 10.1158/1078-0432.CCR-12-2618. DOI: https://doi.org/10.1109/TLA.2016.7555221
C. H. Setjo, B. Achmad, and Faridah, “Thermal image human detection using Haar-cascade classifier,” Proceedings - 2017 7th International Annual Engineering Seminar, InAES 2017, no. January 2020, 2017, doi: 10.1109/INAES.2017.8068554. DOI: https://doi.org/10.1109/INAES.2017.8068554
R. A. Maulana Budiman, B. Achmad, Faridah, A. Arif, Nopriadi, and L. Zharif, “Localization of white blood cell images using Haar Cascade classifiers,” in Proceedings of 2016 1st International Conference on Biomedical Engineering: Empowering Biomedical Technology for Better Future, IBIOMED 2016, 2017. doi: 10.1109/IBIOMED.2016.7869822. DOI: https://doi.org/10.1109/IBIOMED.2016.7869822
C. Li, Z. Qi, N. Jia, and J. Wu, “Human face detection algorithm via Haar cascade classifier combined with three additional classifiers,” in ICEMI 2017 - Proceedings of IEEE 13th International Conference on Electronic Measurement and Instruments, Institute of Electrical and Electronics Engineers Inc., Jul. 2017, pp. 483–487. doi: 10.1109/ICEMI.2017.8265863. DOI: https://doi.org/10.1109/ICEMI.2017.8265863
J. J. Soto Espinoza, “Desarrollo de un sistema embebido para detectar en tiempo real la presencia de personas en ambientes controlados,” Universidad de las Fuerzas Armadas, 2018.
D. M. López Mena, “Diseño E Implementación De Un Sistema De Visión Artificial Para Determinar Condiciones De Fatiga En Una Persona Mediante El Índice Perclos, Utilizando Open Cv Y Una Tarjeta Raspberry Pi 3,” Escuela Politécnica Nacional, 2017. [Online]. Available: https://bibdigital.epn.edu.ec/bitstream/15000/17531/1/CD-8036.pdf
A. M. García Piragua and W. A. Moreno Gómez, “Sistema de conteo automático de flujo de personas por medio de visión artificial,” Universidad Distrital Francisco José de Caldas, 2016. doi: 10.1017/CBO9781107415324.004. DOI: https://doi.org/10.1017/CBO9781107415324.004
M. G. Jiménez Ochoa, “Desarrollo de un sistema de visión artificial para la detección de aglomerción de personas en un semáforo,” Universidad Nacional de Loja, 2015. [Online]. Available: http://dspace.unl.edu.ec/jspui/bitstream/123456789/11225/1/Jiménez Ochoa%2C Magaly Gabriela.pdf
B. Rodríguez-Cuenca, S. García-Cortés, C. Ordóñez, and M. C. Alonso, “Morphological operations to extract urban curbs in 3d mls point clouds,” ISPRS Int J Geoinf, vol. 5, no. 6, 2016, doi: 10.3390/ijgi5060093. DOI: https://doi.org/10.3390/ijgi5060093
