Open Access Open Access  Restricted Access Subscription Access

Visual Estimation of UAV Landing Attitude Based on Adaboost

Mei Wu, Chuangwei Wang


In the process of UAV autonomous landing, with reference to the independent designed landmark, visual navigation system using Adaboost classifier based on Haar features can recognize the landmarks in a wide variety of complex environments. A method for estimating the attitude of UAV in autonomous landing is put forward according to the camera imaging principle, and then the derivation is given in the following. In the end of this paper, the effectiveness of the proposed algorithm is verified by simulation examples.

Full Text:



Al-Jarrah M, Adiiansyah S, Marji Z K, et al. Autonomous aerial vehicles, guidance, control and signal processing platform[C]//Systems, Signals and Devices (SSD), 2011 8th International Multi-Conference on. IEEE, 2011: 1-17.

Jang J S, Liccardo D. Automation of small UAVs using a low cost MEMS sensor and embedded computing platform[C]//25th Digital Avionics Systems Conference, 2006 IEEE/AIAA. IEEE, 2006: 1-9.

Campoy P, Correa J F, Mondragón I, et al. Computer vision onboard UAVs for civilian tasks[M]//Unmanned Aircraft Systems. Springer Netherlands, 2009: 105-135.

Liwei Qiu, Zishan Song. Computer vision algorithm for unmanned helicopter of autonomous in ship [J]. Journal of Beijing University of Aeronautics and Astronautics, 2003, 29(2): 99-102.

Ning Gao. Moving human detection based on Haar features [D]. Jilin University, 2013.

Li X, Wang L, Sung E. AdaBoost with SVM-based component classifiers[J]. Engineering Applications of Artificial Intelligence, 2008, 21(5): 785-795.



  • There are currently no refbacks.