UAV Landmark Detection Based on Convolutional Neural Network

The extensive use application of visual perception technology in Unmanned Aerial Vehicle (UAV) has brought great changes to the application of UAV in various fields. It is challenge to detect in landmark images for UAV. During UAV flight in different environments, the performance of landmark detection to deteriorate seriously have been caused by the uncertainty of landmark orientation, the diversity of landmark types and the similarities. This paper presents landmark detection of UAV based on Convolutional Neural Network (CNN). Theoretical analysis and experimental results demonstrate landmark recognition with an accuracy of at least 96% to match deployed in UAV, and the proposed CNN can make a correct classification.