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

Abstract

Object detection methods of UAV (Unmanned Aerial Vehicle) images are greatly improved with the development of UAV technology. In comparison, the existing object detection methods of UAV images lack outstanding performance in the face of challenges such as small targets, dense scenes, sparse distribution, occlusion, and complex background, especially prominent in the task of vehicle detection. This paper proposed an improved YOLOv5s method to perform vehicle detection of UAV images. The CA (Coordinate Attention) is first applied to the neck of YOLOv5s to generate direction-aware and position-sensitive feature maps, respectively, to improve the detection accuracy of sparsely distributed vehicle targets in complex backgrounds. Then, an improved PAFPN (Path Aggregation Feature Pyramid Network) at the neck of YOLOv5s is proposed for more efficient detection of small and dense vehicle targets. Finally, the CIoU (Complete Intersection Over Union) loss function was used to calculate the bounding box regression to obtain a more comprehensive overlap measure to accommodate different shapes of vehicle targets. We conducted extensive experiments on the self-built UAV-OP (Unmanned Aerial Vehicle from Orthographic Perspective) dataset. The experimental results show that our method achieves the best detection accuracy with a small quantity of calculation increase compared with YOLOv5s. The mAP50 improved by 3%, and the mAP50:95 improved by 1.7% with a 0.3 GFlops increase.

Comprehensive Investigation of Unmanned Aerial Vehicles (UAVs): An In-Depth Analysis of Avionics Systems

“…Such a procedure begins with data capturing (i.e., images of the surroundings) [159] through the embedded cameras. Obtained data can then be pre-processed in order to ameliorate its quality, therefore rendering the target tracking algorithm more accurate [160]. The target tracking algorithm afterward identifies objects of interest in the processed data, thus providing class The global reference map in Figure 2 is constructed from a mosaic of georeferenced images, such that an "sRt" model (i.e., accounts for the 3D motions) is produced for usage after an assumption of a planar ground and a UAV image that is parallel to it, defined as in (1).…”

“…Such a procedure begins with data capturing (i.e., images of the surroundings) [159] through the embedded cameras. Obtained data can then be pre-processed in order to ameliorate its quality, therefore rendering the target tracking algorithm more accurate [160]. The target tracking algorithm afterward identifies objects of interest in the processed data, thus providing class probabilities and bounding box coordinates [161].…”