Page 231 -
P. 231

210                                                          4 Feature detection and matching



















                          (a)                   (b)                    (c)                    (d)
                Figure 4.30 Performance-driven, hand-drawn animation (Buck, Finkelstein, Jacobs et al. 2000) c   2000 ACM:
                (a) eye and mouth portions of hand-drawn sketch with their overlaid control lines; (b) an input video frame
                with the tracked features overlaid; (c) a different input video frame along with its (d) corresponding hand-drawn
                animation.


                                which input images to morph based on nearest neighbor feature appearance matching and
                                triangular barycentric interpolation. It also computes the global location and orientation of
                                the head from the tracked features. The resulting morphed eye and mouth regions are then
                                composited back into the overall head model to yield a frame of hand-drawn animation (Fig-
                                ure 4.30d).
                                   In more recent work, Barnes, Jacobs, Sanders et al. (2008) watch users animate paper
                                cutouts on a desk and then turn the resulting motions and drawings into seamless 2D anima-
                                tions.



                                4.2 Edges


                                While interest points are useful for finding image locations that can be accurately matched
                                in 2D, edge points are far more plentiful and often carry important semantic associations.
                                For example, the boundaries of objects, which also correspond to occlusion events in 3D, are
                                usually delineated by visible contours. Other kinds of edges correspond to shadow boundaries
                                or crease edges, where surface orientation changes rapidly. Isolated edge points can also be
                                grouped into longer curves or contours, as well as straight line segments (Section 4.3). It
                                is interesting that even young children have no difficulty in recognizing familiar objects or
                                animals from such simple line drawings.


                                4.2.1 Edge detection

                                Given an image, how can we find the salient edges? Consider the color images in Figure 4.31.
                                If someone asked you to point out the most “salient” or “strongest” edges or the object bound-
                                aries (Martin, Fowlkes, and Malik 2004; Arbel´ aez, Maire, Fowlkes et al. 2010), which ones
                                would you trace? How closely do your perceptions match the edge images shown in Fig-
                                ure 4.31?
   226   227   228   229   230   231   232   233   234   235   236