Utilization of deep learning in PTZ (pan-tilt-zoom) camera control systems for geospatial-based intelligence surveillance
DOI:
https://doi.org/10.61511/rstde.v2i2.2025.2249Keywords:
geospatial intelligence, intelligent surveillance, PTZ camerasAbstract
Background: The rising complexity of threats to public safety and critical infrastructure has highlighted the limitations of conventional human-operated surveillance systems, creating the need for adaptive, intelligent, and real-time monitoring solutions. Advances in artificial intelligence (AI), computer vision, and geospatial technologies provide opportunities to enhance surveillance through automated detection, analysis, and response. This article examines the integration of pan-tilt-zoom (PTZ) cameras with deep learning models, geospatial data, and distributed computing frameworks as the foundation for next-generation intelligent surveillance systems. Methods: The study employs a narrative review approach, synthesizing recent developments in PTZ camera calibration, convolutional neural networks (CNN), reinforcement learning for autonomous control, and fog computing for distributed video analysis. Research spanning dual-mode fisheye-PTZ systems, lightweight CNN architectures, geospatial data integration, and Internet of Robotic Things (IoRT) frameworks is analyzed to demonstrate practical applications in smart city, industrial, and defense contexts. Findings: Findings reveal that PTZ cameras, when coupled with deep learning and geospatial intelligence, achieve high accuracy in real-time object tracking, small-object recognition, and anomaly detection, with minimal latency under dynamic conditions. Experimental evidence shows error margins below 2% in calibration models and near-perfect accuracy in long-range facial recognition. Integration with fog computing and IoRT enhances responsiveness, scalability, and contextual awareness, while reinforcement learning enables autonomous decision-making for robots and camera networks. Conclusion: The article concludes that combining PTZ hardware precision, AI-based visual analysis, and spatial data intelligence transforms surveillance systems from passive observers into proactive, adaptive, and collaborative agents. However, challenges remain in ensuring robustness under real-world conditions, minimizing latency, and addressing operational usability. Novelty/Originality of this article: This work presents a holistic synthesis of AI-driven vision, PTZ camera control, geospatial intelligence, and distributed architectures, offering an integrated framework for developing adaptive and context-aware surveillance systems in the digital era.
References
-Yadumi, S., Xion, T. E., Wei, S. G. W., & Boursier, P. (2021). Review on integrating geospatial big datasets and open research issues. IEEE Access, 9, 10604–10620. https://doi.org/10.1109/ACCESS.2021.3051084
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021). Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, 8(1). https://doi.org/10.1186/s40537-021-00444-8
Andronie, M., Lăzăroiu, G., Iatagan, M., Hurloiu, I., Ștefănescu, R., Dijmărescu, A., & Dijmărescu, I. (2023). Big data management algorithms, deep learning-based object detection technologies, and geospatial simulation and sensor fusion tools in the Internet of Robotic Things. ISPRS International Journal of Geo-Information, 12(2). https://doi.org/10.3390/ijgi12020035
Arroyo, S., Garcia, L., Safar, F., & Oliva, D. (2021). Urban dual mode video detection system based on fisheye and PTZ cameras. IEEE Latin America Transactions, 19(9), 1537-1545. https://doi.org/10.1109/TLA.2021.9468447
Arshad, M. H., Bilal, M., & Gani, A. (2022). Human activity recognition: Review, taxonomy and open challenges. Sensors, 22(17). https://doi.org/10.3390/s22176463
Bazargani, J.S., Zafari, M., Sadeghi-Niaraki, A., & Choi, S. M. (2022). A survey of GIS and AR integration: Applications. Sustainability (Switzerland), 14(16). https://doi.org/10.3390/su141610134
Choi, Y. (2023). GeoAI: Integration of artificial intelligence, machine learning, and deep learning with GIS. Applied Sciences, 13(6). https://doi.org/10.3390/app13063895
Church, J. S., Gegout, M., & Adams, P. J. (2024). Effectiveness of optical, digital, and hybrid zoom equipped drones for use in reading livestock ear tags for individual animal identification. Drone Systems and Applications, 12, 1–7. https://doi.org/10.1139/dsa-2023-0041
Fahim, A., Papalexakis, E., Krishnamurthy, S. V., Roy Chowdhury, A. K., Kaplan, L., & Abdelzaher, T. (2023). AcTrak: Controlling a steerable surveillance camera using reinforcement learning. ACM Transactions on Cyber-Physical Systems, 7(2). https://doi.org/10.1145/3585316
Fan, J., Lu, R., Yang, X., Gao, F., Li, Q., & Zeng, J. (2021). Design and implementation of intelligent EOD system based on six-rotor UAV. Drones, 5(4). https://doi.org/10.3390/drones5040146
Fathy, C., & Saleh, S. N. (2022). Integrating deep learning-based IoT and fog computing with software-defined networking for detecting weapons in video surveillance systems. Sensors, 22(14). https://doi.org/10.3390/s22145075
Fuertes, D., del-Blanco, C. R., Carballeira, P., Jaureguizar, F., & García, N. (2022). People detection with omnidirectional cameras using a spatial grid of deep learning foveatic classifiers. Digital Signal Processing, 126. https://doi.org/10.1016/j.dsp.2022.103473
García-Segura, T., Montalbán-Domingo, L., Llopis-Castelló, D., Sanz-Benlloch, A., & Pellicer, E. (2023). Integration of deep learning techniques and sustainability-based concepts into an urban pavement management system. Expert Systems with Applications, 231. https://doi.org/10.1016/j.eswa.2023.120851
Giordano, J., Lazzaretto, M., Michieletto, G., & Cenedese, A. (2022). Visual sensor networks for indoor real-time surveillance and tracking of multiple targets. Sensors, 22(7). https://doi.org/10.3390/s22072661
Gohil, M., Mehta, D., & Shaikh, M. (2024). An integration of geospatial and fuzzy-logic techniques for multi-hazard mapping. Results in Engineering, 21. https://doi.org/10.1016/j.rineng.2024.101758
Grilli, E., Daniele, A., Bassier, M., Remondino, F., & Serafini, L. (2023). Knowledge enhanced neural networks for point cloud semantic segmentation. Remote Sensing, 15(10). https://doi.org/10.3390/rs15102590
Huillca, J. L., & Fernandes, L. A. F. (2022). Using conventional cameras as sensors for estimating confidence intervals for the speed of vessels from single images. Sensors, 22(11). https://doi.org/10.3390/s22114213
Jing, B., & Xue, H. (2024). IoT fog computing optimization method based on improved convolutional neural network. IEEE Access, 12. https://doi.org/10.1109/ACCESS.2023.3348133
Junos, M. H., Mohd Khairuddin, A. S., & Dahari, M. (2022). Automated object detection on aerial images for limited capacity embedded device using a lightweight CNN model. Alexandria Engineering Journal, 61(8). https://doi.org/10.1016/j.aej.2021.11.027
Kattenborn, T., Schiefer, F., Frey, J., Feilhauer, H., Mahecha, M. D., & Dormann, C. F. (2022). Spatially autocorrelated training and validation samples inflate performance assessment of convolutional neural networks. ISPRS Open Journal of Photogrammetry and Remote Sensing, 5. https://doi.org/10.1016/j.ophoto.2022.100018
Khan, S., Khan, M. A., Alhaisoni, M., Tariq, U., Yong, H. S., Armghan, A., & Alenezi, F. (2021). Human action recognition: A paradigm of best deep learning features selection and serial based extended fusion. Sensors, 21(23). https://doi.org/10.3390/s21237941
Li, J., Hong, D., Gao, L., Yao, J., Zheng, K., Zhang, B., & Chanussot, J. (2022). Deep learning in multimodal remote sensing data fusion: A comprehensive review. International Journal of Applied Earth Observation and Geoinformation, 112. https://doi.org/10.1016/j.jag.2022.102926
Llauradó, J. M., Pujol, F. A., Tomás, D., Visvizi, A., & Pujol, M. (2023). Study of image sensors for enhanced face recognition at a distance in the smart city context. Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023-40110-y
Lou, H., Duan, X., Guo, J., Liu, H., Gu, J., Bi, L., & Chen, H. (2023). DC-YOLOv8: Small-size object detection algorithm based on camera sensor. Electronics (Switzerland), 12(10). https://doi.org/10.3390/electronics12102323
Mao, K., Xu, Y., Wang, R., & Pan, S. (2022). A general calibration method for dual-PTZ cameras based on feedback parameters. Applied Sciences (Switzerland), 12(18). https://doi.org/10.3390/app12189148
Nepal, U., & Eslamiat, H. (2022). Comparing YOLOv3, YOLOv4 and YOLOv5 for autonomous landing spot detection in faulty UAVs. Sensors, 22(2). https://doi.org/10.3390/s22020464
Puttinaovarat, S., & Horkaew, P. (2022). A geospatial platform for crowdsourcing green space area management using GIS and deep learning classification. ISPRS International Journal of Geo-Information, 11(3). https://doi.org/10.3390/ijgi11030208
Ren, S., Malof, J., Fetter, R., Beach, R., Rineer, J., & Bradbury, K. (2022). Utilizing geospatial data for assessing energy security: Mapping small solar home systems using unmanned aerial vehicles and deep learning. ISPRS International Journal of Geo-Information, 11(4). https://doi.org/10.3390/ijgi11040222
Reuschling, F., & Jakobi, J. (2022). Remote AFIS: Development and validation of low-cost remote tower concepts for uncontrolled aerodromes. CEAS Aeronautical Journal, 13(4), 1067–1083. https://doi.org/10.1007/s13272-022-00613-2
Shi, Q., Chen, Y., & Liang, H. (2023). Real-time risk assessment of road vehicles based on inverse perspective mapping. Array, 20. https://doi.org/10.1016/j.array.2023.100325
Shivappriya, S. N., Priyadarsini, M. J. P., Stateczny, A., Puttamadappa, C., & Parameshachari, B. D. (2021). Cascade object detection and remote sensing object detection method based on trainable activation function. Remote Sensing, 13(2). https://doi.org/10.3390/rs13020200
Sun, Y. T. A., Lin, H. C., Wu, P. Y., & Huang, J. T. (2022). Learning by watching via keypoint extraction and imitation learning. Machines, 10(11). https://doi.org/10.3390/machines10111049
Ullah, W., Ullah, A., Hussain, T., Khan, Z. A., & Baik, S. W. (2021). An efficient anomaly recognition framework using an attention residual LSTM in surveillance videos. Sensors, 21(8). https://doi.org/10.3390/s21082811
Vijeikis, R., Raudonis, V., & Dervinis, G. (2022). Efficient violence detection in surveillance. Sensors, 22(6). https://doi.org/10.3390/s22062216
Villegas-Ch, W., & García-Ortiz, J. (2023). Authentication, access, and monitoring system for critical areas with the use of artificial intelligence integrated into perimeter security in a data center. Frontiers in Big Data, 6. https://doi.org/10.3389/fdata.2023.1200390
Whitehurst, D., Friedman, B., Kochersberger, K., Sridhar, V., & Weeks, J. (2021). Drone-based community assessment, planning, and disaster risk management for sustainable development. Remote Sensing, 13(9). https://doi.org/10.3390/rs13091739
Yang, L., Driscol, J., Sarigai, S., Wu, Q., Chen, H., & Lippitt, C. D. (2022). Google Earth Engine and artificial intelligence (AI): A comprehensive review. Remote Sensing, 14(14). https://doi.org/10.3390/rs14143253
You, J., Hu, Z., Xiao, H., & Xu, C. (2022). Cell-based target localization and tracking with an active camera. Applied Sciences (Switzerland), 12(6). https://doi.org/10.3390/app12062771
Zhai, H., & Zhang, Y. (2022). Target detection of low-altitude UAV based on improved YOLOv3 network. Journal of Robotics, 2022. https://doi.org/10.1155/2022/4065734
Zheng, J., Mao, S., Wu, Z., Kong, P., & Qiang, H. (2022). Improved path planning for indoor patrol robot based on deep reinforcement learning. Symmetry, 14(1). https://doi.org/10.3390/sym14010132
Downloads
Published
Issue
Section
Citation Check
License
Copyright (c) 2025 Farhat Bashir, Syachrul Arief
This work is licensed under a Creative Commons Attribution 4.0 International License.
