Computer Vision System for Landing Platform State Assessment Onboard of Unmanned Aerial Vehicle in Case of Input Visual Information Distortion

The paper describes a computer vision system for organizing a safe landing of an unmanned aerial vehicle in conditions of potential distortions of the input video information. A sequence of methods for image preprocessing was proposed. Firstly, it is necessary to conduct a contrast enhancement using histogram equalization. After that, a Gaussian filter should be applied to remove an extra noise. Neural network YOLOv3-tiny was trained to recognize the state of the landing platform - open or closed. The achieved recognition accuracy on the test sample was 0.96. The algorithm was implemented in Jetson Nano and the achieved frame processing time is equal to 0.5 seconds.

[1]  Yu Li,et al.  The recognition of rice images by UAV based on capsule network , 2018, Cluster Computing.

[2]  B. K. Shreyamsha Kumar,et al.  Image denoising based on gaussian/bilateral filter and its method noise thresholding , 2013, Signal Image Video Process..

[3]  Brijendra Kumar Joshi,et al.  Image denoising using wavelet transform and median filtering , 2013, 2013 Nirma University International Conference on Engineering (NUiCONE).

[4]  Vidya Sudevan,et al.  Vision based autonomous landing of an Unmanned Aerial Vehicle on a stationary target , 2017, 2017 17th International Conference on Control, Automation and Systems (ICCAS).

[5]  Gonzalo Pajares,et al.  Recognition of a landing platform for unmanned aerial vehicles by using computer vision-based techniques , 2017, Expert Syst. Appl..

[6]  Hyoungkwan Kim,et al.  UAV-based automatic generation of high-resolution panorama at a construction site with a focus on preprocessing for image stitching , 2017 .

[7]  K. Nam,et al.  Autonomous Vision-based Target Detection and Safe Landing for UAV , 2018, International Journal of Control, Automation and Systems.

[8]  Salvatore Livatino.  CVonline : the Evolving, Distributed, Non-Proprietary, On-Line Compendium of Computer Vision , 2003 .

[9]  Hamid Hassanpour,et al.  A Preprocessing Approach For Image Analysis Using Gamma Correction , 2012 .

[10]  M. Yukawa,et al.  SSIM image quality metric for denoised images , 2010 .

[11]  David Hyunchul Shim,et al.  Vision-based UAV landing on the moving vehicle , 2016, 2016 International Conference on Unmanned Aircraft Systems (ICUAS).

[12]  Yuliya Gerasimova,et al.  On Binarization of Images at the Pavement Defects Recognition , 2018, 2018 IEEE International Conference on Electrical Engineering and Photonics (EExPolytech).

[13]  Manpreet Kaur,et al.  Survey of Contrast Enhancement Techniques based on Histogram Equalization , 2011 .

[14]  Nabil Aouf,et al.  Vision Based Autonomous Landing of Multirotor UAV on Moving Platform , 2017, J. Intell. Robotic Syst..

[15]  Pascual Campoy Cervera,et al.  An Approach Toward Visual Autonomous Ship Board Landing of a VTOL UAV , 2014, 2013 International Conference on Unmanned Aircraft Systems (ICUAS).