Robust Long-Term Aerial Video Mosaicking by Weighted Feature-Based Global Motion Estimation

Aerial video images can be stitched together into a common panoramic image. For that, the global motion between images can be estimated by detecting Harris corner features which are linked to correspondences by a feature tracker. Assuming a planar ground, a homography can be estimated after an appropriate outlier removal. Since Harris features tend to occur clustered at highly structured 3D objects, these features are located in various different planes leading to an inaccurate global motion estimation (gme). Moreover, if only a small number of features is detected or features are located at moving objects, the accuracy of the gme is also negatively affected, leading to severe stitching errors in the panorama.

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

[2]  B. Silverman.  Density estimation for statistics and data analysis , 1986 .

[3]  Barnabás Póczos,et al.  On the Decreasing Power of Kernel and Distance Based Nonparametric Hypothesis Tests in High Dimensions , 2014, AAAI.

[4]  Bodo Rosenhahn,et al.  Temporally Consistent Superpixels , 2013, 2013 IEEE International Conference on Computer Vision.

[5]  Joern Ostermann,et al.  Mesh-based piecewise planar motion compensation and optical flow clustering for ROI coding , 2015, APSIPA Transactions on Signal and Information Processing.

[6]  Motoaki Kawanabe,et al.  Direct Importance Estimation with Model Selection and Its Application to Covariate Shift Adaptation , 2007, NIPS.

[7]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[8]  Jörn Ostermann,et al.  Region of Interest Coding for Aerial Video Sequences Using Landscape Models , 2013 .

[9]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..

[10]  Yongil Kim,et al.  Parameter Optimization for the Extraction of Matching Points Between High-Resolution Multisensor Images in Urban Areas , 2014, IEEE Transactions on Geoscience and Remote Sensing.

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

[12]  Yuanyuan Xu,et al.  Automatic panorama mosaicing with high distorted fisheye images , 2010, 2010 Sixth International Conference on Natural Computation.

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

[14]  Jörn Ostermann,et al.  Illumination change robust, codec independent lowbit rate coding of stereo from singleview aerial video , 2016, 2016 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON).

[15]  Jörn Ostermann,et al.  Mesh-based global motion compensation for robust mosaicking and detection of moving objects in aerial surveillance , 2011, CVPR 2011 WORKSHOPS.

[16]  Xiangyang Xu,et al.  SIFT Feature Point Matching Based on Improved RANSAC Algorithm , 2013, 2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics.

[17]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[19]  C. D. Kemp,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[20]  H. Shimodaira,et al.  Improving predictive inference under covariate shift by weighting the log-likelihood function , 2000 .

[21]  Jörn Ostermann,et al.  Low bit rate ROI based video coding for HDTV aerial surveillance video sequences , 2011, CVPR 2011 WORKSHOPS.