Motivation System Design Experiments Coodusic 和京大盛 Fingertip Localization (a)Input frame (b)Binary image (c)Distance transform (d)Fingertips image Light-weight computer vision algorithm to locate the fingertips in 2D Adaptive Skin Segmentation: Otsu's method calculates the optimal threshold o Hand detection Find the centroid of the palm (Distance Transform) Fingertip Detection for tapping gesture Extreme-points-based scheme ·口0,4至·子·2刀00 Ke Sun,et al Mobisys'18 June 3.2018 Depth Aware Finger Tapping on Virtual Display 8/22. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Motivation System Design Experiments Conclusion Fingertip Localization (a) Input frame (b) Binary image (c) Distance transform (d) Fingertips image Light-weight computer vision algorithm to locate the fingertips in 2D Adaptive Skin Segmentation: Otsu’s method calculates the optimal threshold Hand detection Find the centroid of the palm (Distance Transform) Fingertip Detection for tapping gesture Extreme-points-based scheme Ke Sun, et al. Mobisys’18 June 3, 2018 Depth Aware Finger Tapping on Virtual Display 8 / 22