YOLOv7-UAV: An Unmanned Aerial Vehicle Image Object Detection Algorithm Based on Improved YOLOv7

Detecting small objects in aerial images captured by unmanned aerial vehicles (UAVs) is challenging due to their complex backgrounds and the presence of densely arranged yet sparsely distributed small targets. In this paper, we propose a real-time small object detection algorithm called YOLOv7-UAV,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Electronics (Basel) 2023-07, Vol.12 (14), p.3141
Hauptverfasser: Zeng, Yalin, Zhang, Tian, He, Weikai, Zhang, Ziheng
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Detecting small objects in aerial images captured by unmanned aerial vehicles (UAVs) is challenging due to their complex backgrounds and the presence of densely arranged yet sparsely distributed small targets. In this paper, we propose a real-time small object detection algorithm called YOLOv7-UAV, which is specifically designed for UAV-captured aerial images. Our approach builds upon the YOLOv7 algorithm and introduces several improvements: (i) removal of the second downsampling layer and the deepest detection head to reduce the model’s receptive field and preserve fine-grained feature information; (ii) introduction of the DpSPPF module, a spatial pyramid network that utilizes concatenated small-sized max-pooling layers and depth-wise separable convolutions to extract feature information across different scales more effectively; (iii) optimization of the K-means algorithm, leading to the development of the binary K-means anchor generation algorithm for anchor allocation; and (iv) utilization of the weighted normalized Gaussian Wasserstein distance (nwd) and intersection over union (IoU) as indicators for positive and negative sample assignments. The experimental results demonstrate that YOLOv7-UAV achieves a real-time detection speed that surpasses YOLOv7 by at least 27% while significantly reducing the number of parameters and GFLOPs to 8.3% and 73.3% of YOLOv7, respectively. Additionally, YOLOv7-UAV outperforms YOLOv7 with improvements in the mean average precision (map (0.5:0.95)) of 2.89% and 4.30% on the VisDrone2019 and TinyPerson datasets, respectively.
ISSN:2079-9292
2079-9292
DOI:10.3390/electronics12143141