Abstract
Drones have found application in many fields ranging from agriculture to defense. With their on-board sensors, they provide useful insights in all the domains. It becomes important to study the abnormal behaviors observed due to the various sensors which hamper the drones’ smooth functioning. From temporally coherent streams of footage obtained, we aim to analyze the image frames, both quantitatively and qualitatively. The pixel level intensity variation was studied to find the patterns in them. Based on the intensity fluctuation distribution, the frames were classified into normal or anomalous. The images were evaluated using machine learning techniques. The best result was yielded by naïve Bayes classification with an accuracy of 92.079%. From the images, semantic inference was established through deep learning architectures through the application of a convolutional neural network. The best result was obtained when using a one-block VGG, yielding a validation accuracy of 92.17% and a test accuracy of 90.435%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Meinen BU, Robinson DT (2020) Mapping erosion and deposition in an agricultural landscape: optimization of UAV image acquisition schemes for sfm-mvs. Remote Sens Environ 239:111666
Zheng H, Zhou X, He J, Yao X, Cheng T, Zhu Y, Cao W, Tian Y (2020) Early season detection of rice plants using rgb, nir-gb and multispectral images from unmanned aerial vehicle (UAV). Comput Electron Agric 169:105223
Radoglou-Grammatikis P, Sarigiannidis P, Lagkas T, Moscholios I (2020) A compilation of UAV applications for precision agriculture. Comput Netw 172:107148
Meng Y, Su J, Song J, Chen WH, Lan Y (2020) Experimental evaluation of UAV spraying for peach trees of different shapes: effects of operational parameters on droplet distribution. Comput Electron Agric 170:105282
Kitjacharoenchai P, Lee S (2019) Vehicle routing problem with drones for last mile delivery. Procedia Manuf 39:314–324
Wiseman AL, Bezombes F, Moore AJ, De Groote I (2020) Non-invasive methods: the applicability of unmanned aerial vehicle (UAV) technology for recording fossilised footprints. Digit Appl Archaeol Cult Heritage 16:e00137
Kansake BA, Kaba FA, Dumakor-Dupey NK, Arthur CK (2019) The future of mining in Ghana: are stakeholders prepared for the adoption of autonomous mining systems? Resour Policy 63:101411
SP Cup (2019) https://2020.ieeeicassp.org/program/sp-cup/. Accessed 15 Sept 2020
Uruma K, Saito K, Takahashi T, Konishi K, Furukawa T (2017) Representative pixels compression algorithm using graph signal processing for colorization-based image coding. In: 2017 IEEE International conference on image processing (ICIP). IEEE, pp 3255–3259
Kamitani T, Fujimoto S, Yoshimura H, Nishiyama M, Iwai Y (2018) Anomaly detection using local regions in road images acquired from a hand-held camera. In: 2018 IEEE 7th Global conference on consumer electronics (GCCE). IEEE, pp. 375–378
Lile C, Yiqun L (2017) Anomaly detection in thermal images using deep neural networks. In: 2017 IEEE International conference on image processing (ICIP). IEEE, pp 2299–2303
Wang R, Nie K, Wang T, Yang Y, Long B (2020) Deep learning for anomaly detection. In: Proceedings of the 13th International conference on web search and data mining. WSDM ’20. Association for Computing Machinery, New York, NY, USA, pp 894–896. https://doi.org/10.1145/3336191.3371876
Chalapathy R, Chawla S (2019) Deep learning for anomaly detection: a survey
Yong D, Yuanpeng Z, Yaqing X, Yu P, Datong L (2017) Unmanned aerial vehicle sensor data anomaly detection using kernel principle component analysis. In: 2017 13th IEEE international conference on electronic measurement instruments (ICEMI), pp. 241–246
Keipour A, Mousaei M, Scherer S (2019) Alfa: a dataset for UAV fault and anomaly detection
Liu G, Zheng Z (2011) Anomaly target detection algorithm based on jpeg images. In: 2011 International conference on multimedia technology, pp 2952–2955
Sindhwani V, Sidahmed H, Choromanski K, Jones B (2020) Unsupervised anomaly detection for self-flying delivery drones. In: International conference on robotics and automation
Haselmann M, Gruber DP, Tabatabai P (2018) Anomaly detection using deep learning based image completion. In: 2018 17th IEEE international conference on machine learning and applications (ICMLA), pp 1237–1242
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Joshi, K. et al. (2022). Anomaly Detection in Drone-Captured Images Using Machine Learning Techniques and Deep Learning Architectures. In: Sivasubramanian, A., Shastry, P.N., Hong, P.C. (eds) Futuristic Communication and Network Technologies. VICFCNT 2020. Lecture Notes in Electrical Engineering, vol 792. Springer, Singapore. https://doi.org/10.1007/978-981-16-4625-6_78
Download citation
DOI: https://doi.org/10.1007/978-981-16-4625-6_78
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-4624-9
Online ISBN: 978-981-16-4625-6
eBook Packages: EngineeringEngineering (R0)