Anomaly detection in cropland monitoring using multiple view vision transformer

被引：0

作者：

Xuesong Liu ^{[1
]}

Yansong Liu ^{[2
]}

He Sui ^{[3
]}

Chuan Qin ^{[4
]}

Yuanxi Che ^{[5
]}

Zhaobo Guo ^{[1
]}

机构：

[1] James Watt School of Engineering, University of Glasgow, Glasgow

[2] School of Intelligence Engineering, Shandong Management University, Jinan

[3] College of Aeronautical Engineering, Civil Aviation University of China, Tianjin

[4] Department of Infrastructure Engineering, University of Melbourne, Melbourne, 3010, VIC

[5] Department of Computer Science, Xidian University, Xi’an

来源：

Scientific Reports | / 15卷 / 1期

关键词：

Anomaly detection; Attention mechanism; Cropland; Low altitude; Machine vision; Vision transformer;

D O I：

10.1038/s41598-025-98405-1

中图分类号：

学科分类号：

摘要：

In recent times, the importance of low-altitude security, especially in agricultural surveillance, has seen a remarkable upswing. This paper puts forward a novel Internet of Drones framework tailored for low-altitude operations. Anomaly detection, which is pivotal for ensuring the integrity of the entire system, poses a substantial challenge. Such anomalies can range from unpredictable weather patterns in farmlands to unauthorized intrusions. To surmount this, a comprehensive deep learning pipeline is proposed in this study. It deploys a vision transformer model featuring a unique attention mechanism. The pipeline includes the meticulous collection of a vast array of normal and abnormal farmland images, followed by preprocessing to standardize data. Anomaly detection is then carried out, and the model’s performance is evaluated using metrics like sensitivity (92.8%), specificity (93.1%), accuracy (93.5%), and F1 score (94.1%). Comparative analysis with state-of-the-art algorithms reveals the superiority of the proposed model. In the future, this study plans to explore integrating data from thermal, infrared, or LIDAR sensors, enhance the interpretability of the vision transformer model, and optimize the deep learning pipeline to reduce computational complexity. © The Author(s) 2025.

引用

共 34 条

[1]

Henrio J., Nakashima T., Anomaly detection in videos recorded by drones in a surveillance context, In 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), (2018)

[2]

Sindhwani V., Sidahmed H., Choromanski K., Jones B., Unsupervised anomaly detection for self-flying delivery drones, 2020 IEEE International Conference on Robotics and Automation (ICRA), (2020)

[3]

Avola D., Et al., Low-altitude aerial video surveillance via one-class SVM anomaly detection from textural features in UAV images, Information, 13, (2022)

[4]

Avola D., Et al., A novel gan-based anomaly detection and localization method for aerial video surveillance at low altitude, Remote Sens, 14, (2022)

[5]

Yang H., Kuang B., Mouazen A.M., Wireless sensor network for orchard management, 2011 Third International Conference on Measuring Technology and Mechatronics Automation, 3, pp. 1162-1165, (2011)

[6]

Feng C., Wu H.R., Zhu H.J., Sun X., The design and realization of apple orchard intelligent monitoring system based on internet of things technology, Adv. Mater. Res, 546, pp. 898-902, (2012)

[7]

Bietresato M., Et al., A tracked mobile robotic lab for monitoring the plants volume and health, 2016 12Th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA), pp. 1-6, (2016)

[8]

Meng X., Cong W., Liang H., Li J., Design and implementation of apple orchard monitoring system based on wireless sensor network, 2018 IEEE International Conference on Mechatronics and Automation (ICMA), pp. 200-204, (2018)

[9]

Srivastava G., Et al., Connotation of unconventional drones for agricultural applications with node arrangements using neural networks, In 2022 IEEE 96Th Vehicular Technology Conference (Vtc2022-Fall), pp. 1-6, (2022)

[10]

Mohammad G.B., Shitharth S., Dileep P., Classification of Normal and Anomalous Activities in a Network by Cascading C4.5 Decision Tree and K-Means Clustering Algorithms, chap., 7, pp. 109-131, (2022)

← 1 2 3 4 →