ArticleOpen Access http://dx.doi.org/10.26855/ea.2026.03.001
Abnormal Behavior Patrol Identification and Localization Research Based on Low-altitude Unmanned Aerial Vehicle
Jintao Li1, Shuifeng Zhang1,*, Hanyu Kong2, Yiqian Cang1, Yuantao Song1, Haokun Yan1
1Nanjing Police University, Nanjing 210023, Jiangsu, China.
2Sichuan University, Chengdu 610065, Sichuan, China.
*Corresponding author: Shuifeng Zhang
This research was funded by the General Innovative Training Project of Jiangsu Province’s College Students’ Innovation and Entrepreneurship Training Program: “Research on Abnormal Behavior Inspection, Recognition and Localization Based on Low-Altitude UAVs” (S202512213017).
Published: January 07, 2026
Abstract
With the acceleration of urbanization, the limitations of traditional fixed monitoring systems in terms of field of view and flexibility are becoming increasingly apparent. Low-altitude Unmanned Aerial Vehicles (UAVs), leveraging their aerial perspective and high mobility, provide a new technological pathway for constructing a dynamic and intelligent security patrol system. This study aims to build an integrated low-altitude UAV intelligent patrol system encompassing perception, identification, localization, and early warning, focusing on solving the key problems of accurate identification and rapid localization of abnormal behaviors in complex scenarios. Methodologically, to address challenges such as significant scale variations of targets and complex backgrounds from the UAV perspective, mainstream object detection algorithms are optimized by introducing attention mechanisms to enhance robustness against small and occluded targets. A multi-modal behavior recognition strategy based on feature-level fusion is designed to improve the system’s adaptability during nighttime and under adverse weather conditions. For localization, a collaborative positioning scheme integrating the Global Positioning System (GPS), Inertial Navigation System (INS), and visual information is proposed to achieve high-precision geographic coordinate calculation and trajectory tracking of identified targets. Through the combined application of deep learning model optimization and multi-source information fusion technology, this study effectively enhances the performance of the UAV patrol system in terms of abnormal behavior recognition accuracy and target localization precision, holding significant theoretical value and practical importance for improving the intelligence level of social security governance.
Keyword
Low-altitude UAV; Abnormal Behavior Recognition; Multi-modal Fusion; Collaborative Localization; Intelligent Patrol
References
[1] Yang Y, Sun P, Lang YB, et al. The current status and future outlook of abnormal event detection in surveillance videos. J China Crim Police Coll. 2025;(03):25-37.
[2] Xu DG, Wang L, Li F. Review of typical object detection algorithms for deep learning. Comput Eng Appl. 2021;57(08):10-25.
[3] Yang F, Ding ZT, Xing MM, et al. Review of object detection algorithm improvement in deep learning. Comput Eng Appl. 2023;59(11):1-15.
[4] He J, Zhang CQ, Li XZ, et al. Survey of research on multimodal fusion technology for deep learning. Comput Eng. 2020;46(5):1-11.
[5] Ren ZY, Wang ZC, Ke ZW, et al. Survey of multimodal data fusion. Comput Eng Appl. 2021;57(18):49-64.
[6] Yu NG, Bai DG. Real-time fall detection algorithm based on pose estimation. Control Decis. 2020;35(11):2761-2766.
[7] Meng QX, Gao ZL, Wang JT, et al. Collaborative detection network for sensitive targets and abnormal human behaviour in public places. Opto-Electron Eng. 2025;52(08):139-161.
[8] Liu H, Gao XY, Su XX, et al. Human pose tracking method based on computer vision technology. Software Guide. 2025;24(04):136-146.
[9] Wang PY, Cheng YF, Xu H, et al. Jamming classification using convolutional neural network-based joint multi-domain feature extraction. J Signal Process. 2022;38(5):915-925.
[10] Chen BF, Li JD, Lu XJ, et al. Survey of deep learning based graph anomaly detection methods. J Comput Res Dev. 2021;58(7):1436-1455.
Copyright
© 2026 by the author(s).
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivatives (CC BY-NC-ND) license, which permits non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited and is not modified or adapted.
https://creativecommons.org/licenses/by-nc-nd/4.0/
How to cite this paper
Abnormal Behavior Patrol Identification and Localization Research Based on Low-altitude Unmanned Aerial Vehicle
How to cite this paper: Jintao Li, Shuifeng Zhang, Hanyu Kong, Yiqian Cang, Yuantao Song, Haokun Yan. (2026). Abnormal Behavior Patrol Identification and Localization Research Based on Low-altitude Unmanned Aerial Vehicle. Engineering Advances, 6(1), 1-6.
DOI: http://dx.doi.org/10.26855/ea.2026.03.001