Super-Resolution Mosaicing of Unmanned Aircraft System (UAS) Surveillance Video Frames

Unmanned Aircraft Systems have been used in many military and civil applications, particularly surveillance. However, video frames are often blurry, noisy, and exhibit insufficient spatial resolution. This project aims to develop a vision-based algorithm to improve the quality of UAS video frames. This algorithm will be able to generate high resolution mosaic output through a combination of image mosaicing and super-resolution (SR) reconstruction techniques. The mosaicing algorithm is based on the Scale Invariant Feature Transform, Best Bins First, Random Sample Consensus, reprojection, and stitching algorithms. A regularized spatial domain-based SR algorithm is used to super resolve a mosaic input. The performance of the proposed system is evaluated using three metrics: Mean Square Error, Peak Signal-to-Noise Ratio, and Singular Value Decomposition-based measure. Evaluation has been performed using 36 test sequences from three categories: images of 2D surfaces, images of outdoor 3D scenes, and airborne images from an Unmanned Aerial Vehicle. Exhaustive testing has shown that the proposed SR mosaicing algorithm is effective in UAS applications because of its relative computational simplicity and robustness.

[1]  Naima Kaabouch,et al.  Scene Classification and Landmark Spotting in Multilayer Image Mosaic for UAVs in GPS-denied Situations , 2012, Infotech@Aerospace.

[2]  J. Flusser,et al.  Superresolution imaging: a survey of current techniques , 2008, Optical Engineering + Applications.

[3]  Kai-Kuang Ma,et al.  Edge-adaptive super-resolution image reconstruction using a Markov chain Monte Carlo approach , 2007, 2007 6th International Conference on Information, Communications & Signal Processing.

[4]  Moon Gi Kang,et al.  Regularized adaptive high-resolution image reconstruction considering inaccurate subpixel registration , 2003, IEEE Trans. Image Process..

[5]  Nelson D. A. Mascarenhas,et al.  Super-Resolution Image Reconstruction using the ICM Algorithm , 2007, 2007 IEEE International Conference on Image Processing.

[6]  Jing Yu,et al.  Projection onto convex sets super-resolution image reconstruction based on wavelet bi-cubic interpolation , 2011, Proceedings of 2011 International Conference on Electronic & Mechanical Engineering and Information Technology.

[7]  Youn Jin Kim,et al.  Evaluating super resolution algorithms , 2011, Electronic Imaging.

[8]  Li Tian,et al.  Task-Oriented Evaluation of Super-Resolution Techniques , 2010, 2010 20th International Conference on Pattern Recognition.

[9]  Mark R. Pickering,et al.  A transform-domain approach to super-resolution mosaicing of compressed images , 2008 .

[10]  Jeffrey K. Uhlmann,et al.  New extension of the Kalman filter to nonlinear systems , 1997, Defense, Security, and Sensing.

[11]  Hui Cheng,et al.  Super-resolution image reconstruction based on MWSVR estimation , 2008, 2008 7th World Congress on Intelligent Control and Automation.

[12]  Naima Kaabouch,et al.  Hierarchical multi-level image mosaicing for autonomous navigation of UAV , 2012, Electronic Imaging.

[13]  Bruce H. Pillman.  Super-Resolution Imaging , 2013, J. Electronic Imaging.

[14]  M. Hadhoud,et al.  A new super-resolution image reconstruction algorithm based on wavelet fusion , 2005, Proceedings of the Twenty-Second National Radio Science Conference, 2005. NRSC 2005..

[15]  Xunxiang Li,et al.  Research on fast super-resolution image reconstruction base on image sequence , 2008, 2008 9th International Conference on Computer-Aided Industrial Design and Conceptual Design.

[16]  Yupin Luo,et al.  Self-adaptive blind super-resolution image reconstruction , 2010, 2010 3rd International Congress on Image and Signal Processing.

[17]  Jian-hua Yuan.  Super-Resolution Image Reconstruction Based on the Minimal Surface Constraint on the Manifold , 2009, 2009 Chinese Conference on Pattern Recognition.

[18]  Ahmet M. Eskicioglu,et al.  Multidimensional image quality measure using singular value decomposition , 2003, IS&T/SPIE Electronic Imaging.

[19]  Naima Kaabouch,et al.  Quantitative evaluation of image mosaicing in multiple scene categories , 2012, 2012 IEEE International Conference on Electro/Information Technology.

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

[21]  Moon Gi Kang,et al.  Super-resolution image reconstruction: a technical overview , 2003, IEEE Signal Process. Mag..

[22]  Li Chen,et al.  Blind Super-Resolution Image Reconstruction using a Maximum a Posteriori Estimation , 2006, 2006 International Conference on Image Processing.