AIRBORNE VISION-AIDED LANDING NAVIGATION SYSTEM FOR FIXED-WING UAV

In order to achieve accurate automatic recovery of fixed-wing UAV at the known landing site, an airborne aided landing navigation system based on machine vision is designed and realized, and the key algorithms of the system are investigated. First, according to the need of automatic landing, such as high precision, real-time and strong anti-interference ability, a scheme of vision-aided landing navigation system is proposed based on guidance illuminant with fixed waveband. Then, aiming at the characteristics of the system, the primary algorithms are designed and realized including camera system calibration with optical filter, fast and accurate blob location, and pose estimation for quasisingular case. Finally, the system is established in DSP, and verified by the experiment. Feasibility experimental results indicate the tendency of the location data between GPS and the system is consistent. Precision experimental results show the extraction precision of blob centroid in the image coordinates is better than 0 1 subpixel, and the localization precisions of UAV along the runway, vertical to the runway and the height orientation are 0.234m, 0.025m and 0.009m when UAV is at about 100m away from the ideal landing point. Efficiency experimental results illustrate the processing frequency is 100Hz similar to 15Hz. It can satisfy the requirements of automatic landing which are real-time, high precision as well as strong anti-interference ability.