Research on Object Detection and Recognition Method for UAV Aerial Images Based on Improved YOLOv5

Abstract

In this paper, an object detection and recognition method based on improved YOLOv5 is proposed for application on unmanned aerial vehicle (UAV) aerial images. Firstly, we improved the traditional Gabor function to obtain Gabor convolutional kernels with better edge enhancement properties. We used eight Gabor convolutional kernels to enhance the object edges from eight directions, and the enhanced image has obvious edge features, thus providing the best object area for subsequent deep feature extraction work. Secondly, we added a coordinate attention (CA) mechanism to the backbone of YOLOv5. The plug-and-play lightweight CA mechanism considers information of both the spatial location and channel of features and can accurately capture the long-range dependencies of positions. CA is like the eyes of YOLOv5, making it easier for the network to find the region of interest (ROI). Once again, we replaced the Path Aggregation Network (PANet) with a Bidirectional Feature Pyramid Network (BiFPN) at the neck of YOLOv5. BiFPN performs weighting operations on different input feature layers, which helps to balance the contribution of each layer. In addition, BiFPN adds horizontally connected feature branches across nodes on a bidirectional feature fusion structure to fuse more in-depth feature information. Finally, we trained the overall improved YOLOv5 model on our integrated dataset LSDUVD and compared it with other models on multiple datasets. The results show that our method has the best convergence effect and mAP value, which demonstrates that our method has unique advantages in processing detection tasks of UAV aerial images.

Artemisia Frigida Distribution Mapping in Grassland with Unmanned Aerial Vehicle Imagery and Deep Learning

“…Firstly, it is necessary to obtain a sufficient amount of high-quality data. UAV can easily and quickly obtain images of the target area, but the resolution of the sensors and the environmental conditions during image acquisition may lead to some images not meeting the requirements for object detection data, ultimately affecting the detection performance [30,31]. Secondly, the quality of data annotation also affects the performance of the detection model.…”

Improved drone image small target detection based on YOLOv7

“…In order to solve the problems of target detection in drone aerial images, scholars at home and abroad have proposed many solutions, Zhang Z et al [1] created a new drone-yolo network to improve the detection accuracy of drone aerial images to solve the problem of large scene size and small detection objects. Zhang H et al [2] used discrete quantisation to improve the traditional Gabor filter, while using multiple filters to pre-process the image edges to achieve the image edge enhancement effect.. Zhang Y et al [3] proposed a new lightweight detection model for YOLO called CURI-YOLOv7. The backbone structure based on MobileOne block reduces the number of parameters of the model, and the use of SPPF structure to improve the inference speed, as well as the modification of the neck structure by using GSConv, improves the accuracy and speed of detection.…”

Object Detection of UAV Images from Orthographic Perspective Based on Improved YOLOv5s

“…Jawaharlalnehru A et al [31] proposed an improved YOLO algorithm, employing methods such as object box dimension clustering, classification of the pre-trained network, multi-scale detection training, and modification of candidate box filtering rules, which have the potential to better adapt to localization tasks and improve detection results. Zhang H et al [32] proposed an improved YOLOv5-based object detection algorithm. Firstly, they utilized multiple improved Gabor convolutional kernels (filters) to enhance the edges of preprocessed objects from various directions.…”