The real-time human detection and counting system leverages deep learning and computer vision to detect individuals, classify gender, and estimate age from live video feeds or CCTV footage. Implemented using flask as a lightweight web framework, the system manages user authentication, detection control, and real-time result display. A Python-based detection script operates asynchronously, ensuring smooth execution, while results – including counts of males, females, and total individuals – are stored in a JSON file for persistence and retrieval. Our project addresses the growing demand for accurate crowd monitoring solutions, particularly in high-traffic environments like shopping malls and public spaces. Using the YOLO V8 model for human detection and Deep SORT for object tracking, the system maintains precise tracking and counting of individuals. TensorFlow optimizes performance on GPU, enabling real-time processing with enhanced speed and accuracy. To ensure adaptability, the system tackles environmental challenges such as varying lighting conditions, camera angles, and low-resolution imagery. Advanced techniques, like frame differencing and histogram of oriented gradients, improve detection accuracy, while an expectation–maximization model enhances people’s localization in minimal-movement scenarios. Beyond security and surveillance, this project has significant applications in retail analytics and crowd management, aiding businesses in optimizing space utilization and improving operational efficiency. Extensive testing demonstrates the system’s high accuracy under diverse conditions, establishing it as a reliable tool for modern automation and real-time monitoring needs. By integrating state-of-the-art deep learning techniques, our system presents a scalable and robust solution for intelligent human detection and analytics in dynamic environments.

People counting, human detection, real-time tracking, deep learning, YOLOv3, computer vision, TensorFlow, crowd management

🔒 This is a subscription article

Full text is available to subscribers and institutional members. Please choose an option below to access it.

1. Cho SI, Kang SJ. Real-time people counting system for customer movement analysis. IEEE Access. 2018;6:55264–72.
2. Hou YL, Pang GK. People counting and human detection in a challenging situation. IEEE Trans Syst Man Cybern A Syst Hum. Sep 20;41(1):24–33.
3. Senthilkumar S, Brindha K, Kryvinska N, Bhattacharya S, Reddy Bojja G. SCB-HC-ECC–based privacy safeguard protocol for secure cloud storage of smart card–based health care system. Front Public Health. 2021;9:688399.
4. Al-Rawashdeh M, Keikhosrokiani P, Belaton B, Alawida M, Zwiri A. IoT adoption and application for smart healthcare: A systematic review. Sensors (Basel). 2022;22(14):5377.
5. Abdulmalek S, Nasir A, Jabbar WA, Almuhaya MA, Bairagi AK, Khan MA, Kee SH. IoT-based healthcare-monitoring system towards improving quality of life: A review. Healthcare (Basel). 2022;10(10):1993.
6. Abdulbaqi AS, Obaid AJ, Alazawi SA. A smart system for health caregiver based on IoMT: Toward tele-health caregiving. Int J Online Biomed Eng. 2021;17(7).
7. Yuanbing W, Wanrong L, Bin L. An improved authentication protocol for smart healthcare system using wireless medical sensor network. IEEE Access. 2021;9:105101–17.
8. Wu TY, Yang L, Luo JN, Wu JM. A provably secure authentication and key agreement protocol in cloud‐based smart healthcare environments. Secur Commun Netw. 2021;2021:2299632.
9. Amintoosi H, Nikooghadam M, Shojafar M, Kumari S, Alazab M. Slight: A lightweight authentication scheme for smart healthcare services. Comput Electr Eng. 2022;99:107803.
10. Abdullah S, Arshad J, Khan MM, Alazab M, Salah K. PRISED tangle: A privacy-aware framework for smart healthcare data sharing using IOTA tangle. Complex Intell Syst. 2023;9(3):3023–41.
11. Lin TW, Hsu CL, Le TV, Lu CF, Huang BY. A smartcard-based user-controlled single sign-on for privacy preservation in 5G-IoT telemedicine systems. Sensors (Basel). 2021;21(8):2880.
12. Peralta-Ochoa AM, Chaca-Asmal PA, Guerrero-Vásquez LF, Ordoñez-Ordoñez JO, Coronel-González EJ. Smart healthcare applications over 5G networks: A systematic review. Appl Sci (Basel). 2023;13(3):1469.
13. Al Omar A, Jamil AK, Khandakar A, Uzzal AR, Bosri R, Mansoor N, et al. A transparent and privacy-preserving healthcare platform with novel smart contract for smart cities. IEEE Access. 2021;9:90738–49.
14. Wu TY, Yang L, Luo JN, Wu JM. A provably secure authentication and key agreement protocol in cloud‐based smart healthcare environments. Secur Commun Netw. 2021;2021:2299632.

The real-time human detection and counting system leverages deep learning and computer vision to detect individuals, classify gender, and estimate age from live video feeds or CCTV footage. Implemented using flask as a lightweight web framework, the system manages user authentication, detection control, and real-time result display. A Python-based detection script operates asynchronously, ensuring smooth execution, while results – including counts of males, females, and total individuals – are stored in a JSON file for persistence and retrieval. Our project addresses the growing demand for accurate crowd monitoring solutions, particularly in high-traffic environments like shopping malls and public spaces. Using the YOLO V8 model for human detection and Deep SORT for object tracking, the system maintains precise tracking and counting of individuals. TensorFlow optimizes performance on GPU, enabling real-time processing with enhanced speed and accuracy. To ensure adaptability, the system tackles environmental challenges such as varying lighting conditions, camera angles, and low-resolution imagery. Advanced techniques, like frame differencing and histogram of oriented gradients, improve detection accuracy, while an expectation–maximization model enhances people’s localization in minimal-movement scenarios. Beyond security and surveillance, this project has significant applications in retail analytics and crowd management, aiding businesses in optimizing space utilization and improving operational efficiency. Extensive testing demonstrates the system’s high accuracy under diverse conditions, establishing it as a reliable tool for modern automation and real-time monitoring needs. By integrating state-of-the-art deep learning techniques, our system presents a scalable and robust solution for intelligent human detection and analytics in dynamic environments.

People counting, human detection, real-time tracking, deep learning, YOLOv3, computer vision, TensorFlow, crowd management

🔒 This is a subscription article

Full text is available to subscribers and institutional members. Please choose an option below to access it.

1. Cho SI, Kang SJ. Real-time people counting system for customer movement analysis. IEEE Access. 2018;6:55264–72.
2. Hou YL, Pang GK. People counting and human detection in a challenging situation. IEEE Trans Syst Man Cybern A Syst Hum. Sep 20;41(1):24–33.
3. Senthilkumar S, Brindha K, Kryvinska N, Bhattacharya S, Reddy Bojja G. SCB-HC-ECC–based privacy safeguard protocol for secure cloud storage of smart card–based health care system. Front Public Health. 2021;9:688399.
4. Al-Rawashdeh M, Keikhosrokiani P, Belaton B, Alawida M, Zwiri A. IoT adoption and application for smart healthcare: A systematic review. Sensors (Basel). 2022;22(14):5377.
5. Abdulmalek S, Nasir A, Jabbar WA, Almuhaya MA, Bairagi AK, Khan MA, Kee SH. IoT-based healthcare-monitoring system towards improving quality of life: A review. Healthcare (Basel). 2022;10(10):1993.
6. Abdulbaqi AS, Obaid AJ, Alazawi SA. A smart system for health caregiver based on IoMT: Toward tele-health caregiving. Int J Online Biomed Eng. 2021;17(7).
7. Yuanbing W, Wanrong L, Bin L. An improved authentication protocol for smart healthcare system using wireless medical sensor network. IEEE Access. 2021;9:105101–17.
8. Wu TY, Yang L, Luo JN, Wu JM. A provably secure authentication and key agreement protocol in cloud‐based smart healthcare environments. Secur Commun Netw. 2021;2021:2299632.
9. Amintoosi H, Nikooghadam M, Shojafar M, Kumari S, Alazab M. Slight: A lightweight authentication scheme for smart healthcare services. Comput Electr Eng. 2022;99:107803.
10. Abdullah S, Arshad J, Khan MM, Alazab M, Salah K. PRISED tangle: A privacy-aware framework for smart healthcare data sharing using IOTA tangle. Complex Intell Syst. 2023;9(3):3023–41.
11. Lin TW, Hsu CL, Le TV, Lu CF, Huang BY. A smartcard-based user-controlled single sign-on for privacy preservation in 5G-IoT telemedicine systems. Sensors (Basel). 2021;21(8):2880.
12. Peralta-Ochoa AM, Chaca-Asmal PA, Guerrero-Vásquez LF, Ordoñez-Ordoñez JO, Coronel-González EJ. Smart healthcare applications over 5G networks: A systematic review. Appl Sci (Basel). 2023;13(3):1469.
13. Al Omar A, Jamil AK, Khandakar A, Uzzal AR, Bosri R, Mansoor N, et al. A transparent and privacy-preserving healthcare platform with novel smart contract for smart cities. IEEE Access. 2021;9:90738–49.
14. Wu TY, Yang L, Luo JN, Wu JM. A provably secure authentication and key agreement protocol in cloud‐based smart healthcare environments. Secur Commun Netw. 2021;2021:2299632.