This paper presents an augmented reality-based method for geo-registering videos from low-cost multi-rotor Unmanned Aerial Vehicles (UAVs). The goal of the proposed method is to conduct an accurate geo-registration and target localization on a UAV video stream. The geo-registration of video stream requires accurate attitude data. However, the Inertial Measurement Unit (IMU) sensors on most low-cost UAVs are not capable of being directly used for geo-registering the video. The magnetic compasses on UAVs are more vulnerable to the interferences in the working environment than the accelerometers. Thus the camera yaw error is the main sources of the registration error. In this research, to enhance the low accuracy attitude data from the onboard IMU, an extended Kalman Filter (EKF) model is used to merge Real Time Kinematic Global Positioning System (RTK GPS) data with the IMU data. In the merge process, the high accuracy RTK GPS data can be used to promote the accuracy and stability of the 3-axis body attitude data. A method of target localization based on the geo-registration model is proposed to determine the coordinates of the ground targets in the video. The proposed method uses a modified extended Kalman Filter to combine the data from RTK GPS and the IMU to improve the accuracy of the geo-registration and the localization result of the ground targets. The localization results are compared to the reference point coordinates from satellite image. The comparison indicates that the proposed method can provide practical geo-registration and target localization results.
impact on road safety and efficiency. It is a big challenge to accurately and efficiently monitor and manage road assets. This paper proposes a mobile surveying system that is cost efficient and robust to acquire and manage road assets information in highly dynamic environments like highways and urban streets, where the data collection has previously been laborious and even dangerous for the staff performing the survey. Equipped with laser measurement systems, camera, proprioceptive sensors and novel sensor fusion algorithms; the proposed system can survey and manage road assets expeditiously. Laser sensors measure surroundings with range and remission data. Range data is processed to build up 3D model of surveyed objectives with position and attitude information from proprioceptive sensors. Remission data is used for extracting traffic lanes and signs on the road and tunnels, is calculated and marked on the 3D model, and compared with the signs captured by the camera. Road surface condition is measured by both inertial and laser sensors. Any abnormal circumstance detected is reported automatically. The surveying results are presented in a user friendly interface and saved as videos for convenient data management. Experimental results of a prototype system demonstrate its performance for road assets monitoring and management.
In emergency response and disaster rescue, unmanned aerial vehicles (UAVs) onboard thermal infrared (TIR) sensors are an essential means of acquiring ground information in the nighttime working environment. To enable field personnel to make better decisions based on TIR video streams returned from a UAV, the geographic information enhancement of TIR video streams is required. At present, it is difficult for low-cost UAVs to carry high-precision attitude sensors and thus obtain high-precision camera attitude information to meet the enhanced processing requirements of UAV TIR video streams. To this end, this paper proposes an improved Kalman filter algorithm to improve the geographic registration (geo-registration) accuracy by fusing the positioning and heading data from the dual-antenna real-time kinematic global positioning system (RTK-GPS) with onboard internal measurement unit (IMU) data. This method can yield high-precision position and attitude data in real time based on low-cost UAV hardware, based on which high-precision geo-registration results can be obtained. The computational complexity can be reduced compared with video stream feature tracking algorithms. Furthermore, the problem of unstable matching due to the low resolution and texture level of TIR video streams can be avoided. The experimental results prove that the proposed method can reduce the registration error by 66.15%, and significantly improve the geo-registration accuracy of UAV TIR video streams. Thus, it can strongly support the popularization and practicality of the application of augmented reality (AR) technology to low-cost UAV platforms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.