Within the last year
Within the past 3 years
1 - 10 of 10 articles
Highlights ► Multi-camera active-vision system used to improve human action sensing performance. ► Environment may be cluttered with multiple, dynamic obstacles. ► Selects near-optimal camera poses to maximize visibility of a human subject. ► Generalized framework can be customized to...
Highlights ► A scalable human body model can better explain noisy data. ► The HS-APF algorithm can efficiently explore a high dimensional state space. ► Combination of structural and likelihood annealing yield to accurate estimations. ► Adaptive resampling can efficiently combine state...
Highlights ► Pose clustering from dense range data without correspondences is studied. ► Variants with sampling point triples and point-with-normal pairs from the data. ► Variants with clustering in canonical parameter space and consistent parameter space. ► At sufficient data quality,...
Highlights ► Multi-scale dual-tree complex wavelet transform is adopted for variable lighting face recognition. ► The context model technique is employed for devising the discontinuity measure. ► A conduction function is presented which can smooth the high-frequency illumination...
Highlights ► Challenging outdoor computer vision application. ► Improved particle filter tracker using partition sampling and auxiliary variables. ► Accurate road tracking results suitable for real world applications.
Highlights ► A probabilistic framework for user-assisted semi-automatic segmentation of elongated structures in 3D images. ► Utilize both image intensities and registration results between slices. ► Bezier curve interpolation for path regularization. ► GPU utilization for efficiency both...
Highlights ► Compared two sets of corresponding six degree of freedom (6DoF) data by creating the best homogeneous matrix (rotation and translation) that transforms one data set to the other. ► Created an error metric to analyze the 6DoF data. ► Formulated a statistical method to identify...
Highlights ► Fast method to detect humans from stationary surveillance videos. ► Joint appearance and foreground feature correlation learning. ► Feature subset covariance descriptor leading to same accuracy at reduced computation. ► Vertical slant image rectification increasing integral...
Highlights ► We estimate the uncertainty of optical flow computation from the input images only. ► Bootstrap resampling calculates the OF repeatedly for different pixel subsets. ► We use the combined local–global OF method but the technique is general. ► The bootstrap method performs...
Read and print from thousands of top scholarly journals.
Sign up with Facebook
Sign up with Google
Already have an account? Log in
Save this article to read later. You can see your Read Later on your DeepDyve homepage.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Sign Up Log In
To subscribe to email alerts, please log in first, or sign up for a DeepDyve account if you don’t already have one.
To get new article updates from a journal on your personalized homepage, please log in first, or sign up for a DeepDyve account if you don’t already have one.