Video segmentation andkeyframe extraction are the basis of Content-based Video Retrieval (CBVR), inwhich keyframe selection is at the very core of CBVR. At shot level, key-frameextraction provides sufficient indexing and browsing of large video databases.In this paper, we proposed two improved approaches of key-frame extraction forvideo summarization. In our first synthesis method based on histogram-basedmethod and pixel-based method, videos were firstly segmented into shotsaccording to video content, by our improved histogram-based method, with theuse of histogram intersection and nonuniform partitioning and weighting. Then,the obtained results are secondly detected to optimize the results. On theother hand, we realized an improved clustering algorithm for video shotsegmentation, in consideration of video characteristics. Within each shot,key-frames were determined with the calculation of image entropy of every framein HSV colour space. Our simulation results in section 4 prove that extractedkey frames with our method are compact and faithful to the original video.Moreover, according to the types of test videos, different methods for shotsegmentation are highly recommended
Downloaded From: http://opticalengineering.spiedigitallibrary.org/ on 08/24/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx Scale-unambiguous relative pose estimation of space uncooperative targets based on the fusion of three-dimensional time-of-flight camera and monocular cameraAbstract. An approach of scale-unambiguous relative pose estimation for space uncooperative targets based on the fusion of low resolution three-dimensional time-of-flight camera and monocular camera is proposed. No a priori knowledge about the targets is assumed. First, a modified range-intensity Markov random field model is presented to quickly reconstruct the range value for each feature point. Second, the scale-ambiguous relative pose estimation algorithm based on extended Kalman filter-unscented Kalman filter-particle filter combination filter is designed in vision simultaneous localization and mapping framework. Third, the overall scale factor estimation approach based on range-intensity fusion image, which takes the feature points' range reconstruction uncertainty as measurement noise, is proposed for the final scale-unambiguous pose estimation. Finally, some simulations demonstrate the validity and capability of the proposed approach.
The optimal selection of multi-temporal differential interferogram series is an important step to monitor ground subsidence using the Stanford method for persistent scatterers (StaMPS)based small baseline subset (SBAS) interferometric synthetic aperture radar (InSAR). Using a deformation model and its two solution methods, least squares and singular value decomposition, we present the composing mode and optimal selection of multi-temporal differential interferogram series and show that their quality and quantity affect the accuracy of monitored deformation information of SBAS InSAR. Using 29 ENVISAT ASAR images covering urban areas of Beijing, China, a different number of optimal multi-temporal differential interferogram series are formed to monitor urban ground subsidence by the StaMPS-based SBAS method. The comparison and verification of test results indicate that the quality and quantity of multi-temporal differential interferogram series substantially impact the singularity and degree of ill condition of the deformation model, locations of the selected slowly decorrelating filtered phase (SDFP) pixels, and monitored annual mean subsidence velocities. The suitable number of multi-temporal differential interferogram series under the optimal quality is 1-2 for a month in urban ground subsidence monitoring using StaMPS-based SBAS InSAR, a higher quantity of differential interferograms of the optimal quality is not always better.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.