English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Head pose estimation plays a vital role in various applications, e.g.,driverassistance systems, human-computer interaction, virtual realitytechnology, and so on. We propose a novel geometry based algorithm foraccurately estimating the head pose from a single 2D face image at a very lowcomputational cost. Specifically, the rectangular coordinates of only fournon-coplanar feature points from a predefined 3D facial model as well as thecorresponding ones automatically/ manually extracted from a 2D face image arefirst normalized to exclude the effect of external factors (i.e., scale factorand translation parameters). Then, the four normalized 3D feature points arerepresented in spherical coordinates with reference to the uniquely determinedsphere by themselves. Due to the spherical parameterization, the coordinates offeature points can then be morphed along all the three directions in therectangular coordinates effectively. Finally, the rotation matrix indicatingthe head pose is obtained by minimizing the Euclidean distance between thenormalized 2D feature points and the 2D re-projections of morphed 3D featurepoints. Comprehensive experimental results over two popular databases, i.e.,Pointing'04 and Biwi Kinect, demonstrate that the proposed algorithm canestimate head poses with higher accuracy and lower run time thanstate-of-the-art geometry based methods. Even compared with start-of-the-artlearning based methods or geometry based methods with additional depthinformation, our algorithm still produces comparable performance.

Single Image based Head Pose Estimation with Spherical Parameterization and 3D Morphing