Multi-UAV UWA video surveillance system

In this work, an autonomous surveillance system providing ultra wide angle (UWA) video information is presented using multi-UAV platform. Towards this end, a fleet of UAVs are initially deployed into appropriate formation (such as triangle, diamond, or line) with cameras pointing outwards to cover the region of interest (ROI). In aid of image processing technique, the UAVs formation will be further optimized using temporal as well as spatial information to achieve a decent overlap (20% is defined in this work from both information adequacy and utilization efficiency perspective) between any two adjacent video sources. Thereafter, videos separately captured will be stitched together forming an UWA video by extracting and matching feature points in the base station. Notably, a vision-feedback-formation-control (VFFC) closed-loop framework is proposed for better performance. In the end, an experiment is elaborated to illustrate the UWA video generated by the proposed system.

[1]  Cordelia Schmid,et al.  A Performance Evaluation of Local Descriptors , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[3]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[4]  Lei Yan,et al.  Parallel-perspective stereo mosaics of video images from unmanned aerial vehicle remote sensing system , 2005, Proceedings. 2005 IEEE International Geoscience and Remote Sensing Symposium, 2005. IGARSS '05..

[5]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[6]  Sunglok Choi,et al.  Performance Evaluation of RANSAC Family , 2009, BMVC.

[7]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[8]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  David Salesin,et al.  Interactive digital photomontage , 2004, SIGGRAPH 2004.

[10]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[11]  Hideki Koike,et al.  Human-centric panoramic imaging stitching , 2012, AH '12.

[12]  Valerio Pascucci,et al.  Panorama weaving , 2012, ACM Trans. Graph..

[13]  Zhaoyang Lu,et al.  Fast Aerial Video Stitching , 2014 .

[14]  Steven Mills,et al.  New Conditional Sampling Strategies for Speeded-Up RANSAC , 2009, BMVC.

[15]  Michal Irani,et al.  Video indexing based on mosaic representations , 1998, Proc. IEEE.

[16]  Jinhai Cai,et al.  The stitching of aerial videos from UAVs , 2013, 2013 28th International Conference on Image and Vision Computing New Zealand (IVCNZ 2013).

[17]  Mohammad H. Mahoor,et al.  Fast image blending using watersheds and graph cuts , 2009, Image Vis. Comput..

[18]  Yi Wang,et al.  Super-resolution mosaicking of UAV surveillance video , 2008, 2008 15th IEEE International Conference on Image Processing.

[19]  Chen Yu,et al.  Feedback-control-aided image stitching using multi-UAV platform , 2016, 2016 12th World Congress on Intelligent Control and Automation (WCICA).