Abstract
In recent years, unmanned aerial vehicles (UAVs) have developed rapidly. Because of their small size, low cost, and strong maneuverability, they have been widely used in several fields such as aerial photography, rescue, transportation, and agriculture. Object recognition requires a large amount of data, but in real application scenarios, due to factors such as privacy and high data labeling costs, it is impossible to obtain sufficient label training samples. This paper proposes an unmanned aerial vehicle (UAV) image object recognition model based on small sample learning (IORS). Based on data enhancement and improved feature fusion capabilities, the YOLOv4_Tiny model is improved to make it more applicable to UAV images. This solves the problem of identifying dense small targets in UAV images when dealing with a small number of samples. The experimental results showed that in UAV images, the proposed method has a good target recognition effect without reducing the speed, while the overall accuracy is increased by approximately 4.5%.
Similar content being viewed by others
Data availability
The datasets analysed during the current study are available in the [VisDrone] repository, [http://aiskyeye.com/].
References
Bochkovskiy A, Wang C, Liao H (2020) YOLOv4: optimal speed and accuracy of object detection. https://arxiv.org/abs/2004.10934
Dai J, Li Y, He K, Sun J (2016) R-FCN: object detection via region-based fully convolutional networks. Proc. NIPS 379–387
He Z, Zhang L (2019) Multi-adversarial faster-RCNN for unrestricted object detection. Proc. ICCV 6667–6676
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. Proc. CVPR 770–778
Jin R, Lin D (2020) Adaptive Anchor for fast object detection in aerial image. IEEE Geosci Remote Sens Lett 17(5):839–843. https://doi.org/10.1109/LGRS.2019.2936173
Liu W, Angueliv D, Erhan D, Szegedy C, Reed S et al (2016) SSD: single shot multiBox detector. Proc. ECCV 21–37. https://doi.org/10.1007/978-3-319-46448-0_2
Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. Proc. CVPR 8759–8768. https://doi.org/10.1109/CVPR.2018.00913
Liu Y, Zhao T, Shen Z (2021) Small target detection for UAV aerial images based on improved YOLOv3. Proc. RCAE 12–16
Lu H, Li Y, Mu S, Wang D, Kim H (2017) Motor anomaly detection for unmanned aerial vehicles using reinforcement learning. IEEE Internet Things 5(4):2315–2322. https://doi.org/10.1109/JIOT.2017.2737479
Lu H, Li Y, Uemura T, Kim H, Serikawa S (2018) Low illumination underwater light field images reconstruction using deep convolutional neural networks. Future Gener Comput Syst 82:142–148. https://doi.org/10.1016/j.future.2018.01.001
Luo K, Luo R, Zhou Y (2021) UAV Detection based on rainy environment. Proc. IMCEC 1207–1210
Niu R, Qu Y, Wang Z (2021) UAV Detection based on improved YOLOv4 object detection model. Proc. ICBASE 25–29
Peng B, Cai X, Zhang Y, Li S (2017) Automatic vehicle detection from UAV videos based on symmetrical frame difference and background block modeling. Southeast Univ J Nat Sci 47(4):685–690
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. Proc. CVPR 779–788. https://doi.org/10.1109/CVPR.2016.91
Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031
Waleed E, Arslan A, Aliza M, Mohamed I (2020) Energy-efficient task scheduling and physiological assessment in disaster management using UAV-assisted networks. Comput Commun 155:150–157. https://doi.org/10.1016/j.comcom.2020.03.019
Wang J, Jiang S, Song W et al (2019) A comparative study of small object detection algorithms. Proc. CCC 8507–8512
Xia G, Bai X, Ding J, Zhu Z, Belongie S et al (2018) DOTA: a large-scale dataset for object detection in aerial images. Proc. CVPR 3974–3983. https://doi.org/10.1109/CVPR.2018.00418
Xu Z (2021) Application research of tethered UAV platform in marine emergency communication network. J Web Eng 20(2):491–511
Xu Y, Gu H, Dai Q et al (2019) Motion tracking detection and tracking technology based on aerial video. Proc. IHMSC 122–125
Zhang H, Wang J (2019) Towards adversarially robust object detection. Proc. ICCV 421–430. https://doi.org/10.1109/ICCV.2019.00051
Zhang M, Wang C, Yang J et al (2021) Research on engineering vehicle target detection in aerial photography environment based on YOLOX. Proc. ISCID 254–256
Zhu H, Qi Y, Shi H et al (2018) Human detection under UAV: an improved faster R-CNN approach. Proc. ICSAI 367–372
Zhu P, Wen L, Bian X, Ling H, Hu Q (2018) Vision meets drones: a challenge. https://arxiv.org/abs/1804.07437
Zhu D, Xu G, Zhou J, Di E, Li M (2021) Object detection in complex road scenarios: improved YOLOv4-Tiny algorithm. Proc. ICTC 75–80
Acknowledgements
This research was funded by the Natural Science Foundation of Chongqing (CSTB2022NSCQ-MSX1415) and the National Natural Science Foundation of China (61702020).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Tan, L., Lv, X., Wang, G. et al. UAV image object recognition method based on small sample learning. Multimed Tools Appl 82, 26631–26642 (2023). https://doi.org/10.1007/s11042-023-14985-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-14985-y