Signal source detection method based on unmanned aerial vehicle vision and wireless signal fusion

• Main Authors: HU HAOJI, WANG XIAO, LIU PENG, HUANG YI, FANG HANGXIANG, XUAN FENG, LIN HUAMING, XU JIAYI, SHAN HANGGUAN, XIAO JIAN
• Format: Patent
• Language: Chinese; English
• Published: 01.07.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS; TRANSMISSION; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

The invention discloses a signal source detection method based on unmanned aerial vehicle vision and wireless signal fusion, which comprises the following steps: (1) an unmanned aerial vehicle solves model parameters of a logarithmic normal model through maximum likelihood estimation by using binocular depth information estimated by vision and received power information obtained by an airborne sensor, and fits received power; and (2) the unmanned aerial vehicle judges a signal source according to a mean square error minimization principle of fitting receiving power and measurement receiving power. The scene that multiple similar objects exist in the flight area of the unmanned aerial vehicle but only a unique signal source exists is considered, binocular depth estimation data and unmanned aerial vehicle airborne sensor receiving power data are used for fusion processing, the situation that binocular depth estimation and sensor measurement receiving power fail is considered, adaptability is high, and the syste