Fast and Accurate Detection of UAV Objects Based on Mobile-Yolo Network
Jun Wang, Wang Hongjun, Jian Liu, Rui Zhou, Chun-Hao Chen, Chuang Liu
Abstract
With the development and popularization of unmanned aerial vehicle (UAV) technology, the UAV devices have been widely used in practice. Aiming at the problems of low accuracy and slow speed in detecting UAV objects, this paper constructs a UAV object dataset and proposes an efficient UAV object detection method based on Mobile-YOLO Network (MYN). Firstly, a UAV data set was constructed, including 3,698 UAV images, in which the proportion of large, medium and small-scale objects was about 3:1:1, providing a data basis for algorithm research and experimental verification. Secondly, we construct a Mobile-YOLO network model for UAV object detection based on YOLOv4, enhancing the detection speed to 51FPS under the premise of high precision. The results show that the Mobile-YOLO network has fewer parameters, faster operation speed and better comprehensive performance.