Small Object Detection Algorithm for Aerial Photography Based on Improved YOLOv3

This study presents an improved You Only Look Once version 3 (YOLOv3) algorithm for small object detection, to address problems such as low detection precision for small objects, missed detection, and false detection in the detection process. First, in terms of network structure, the feature extract...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Ji suan ji gong cheng Jg. 51; H. 6; S. 184 - 192
1. Verfasser: XI Qi, WANG Mingjie, WEI Jinghe, ZHAO Wei
Format: Journal Article
Sprache:Chinesisch
Englisch
Veröffentlicht: Editorial Office of Computer Engineering 15.06.2025
Schlagworte:
small object detection|you only look once version 3 (yolov3)|densely connected network (densenet)|loss function|generalized intersection over union (giou)
ISSN:1000-3428
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This study presents an improved You Only Look Once version 3 (YOLOv3) algorithm for small object detection, to address problems such as low detection precision for small objects, missed detection, and false detection in the detection process. First, in terms of network structure, the feature extraction capability of the backbone network is improved by using DenseNet-121, with a Densely Connected Network (DenseNet), to replace the original Darknet-53 network as its basic network. Simultaneously, the convolution kernel size is modified to further reduce the loss of feature map information, to enhance the robustness of the detection model against small objects. A fourth feature detection layer with a size of 104×104 pixel is added. Second, the bilinear interpolation method is used to replace the original nearest neighbor interpolation method for upsampling operations, to solve the serious feature loss problem in most detection algorithms. Finally, in terms of the loss function, Generalized Intersection over Union (GIoU) is used instead of Intersection over Union (IoU) to calculate the loss value of the boundary frame, and the Focal Loss function is introduced as the confidence loss function of the boundary frame. Experimental results show that the mean Average Precision (mAP) of the improved algorithm on the VisDrone2019 dataset is 63.3%, which is 13.2 percentage points higher than that of the original YOLOv3 detection model, and 52 frame/s on a GTX 1080 Ti device. The improved algorithm has good detection performance for small objects.
ISSN:1000-3428
DOI:10.19678/j.issn.1000-3428.0068698