Bookmark and Share

Computer Vision Metrics: Chapter Six (Part C)

Register or sign in to access the Embedded Vision Academy's free technical training content.

The training materials provided by the Embedded Vision Academy are offered free of charge to everyone. All we ask in return is that you register, and tell us a little about yourself so that we can understand a bit about our audience. As detailed in our Privacy Policy, we will not share your registration information, nor contact you, except with your consent.

Registration is free and takes less than one minute. Click here to register, and get full access to the Embedded Vision Academy's unique technical training content.

If you've already registered, click here to sign in.

See a sample of this page's content below:

For Part B of Chapter Six, please click here.

Bibliography references are set off with brackets, i.e. "[XXX]". For the corresponding bibliography entries, please click here.

Dynamic Texture Metric Using 3D LBPs

Dynamic textures are visual features that morph and change as they move from frame to frame; examples include waves, clouds, wind, smoke, foliage, and ripples. Two extensions of the basic LBP used for tracking such dynamic textures are discussed here: VLBP and LBP-TOP.

Volume LBP (VLBP)

To create the VLBP [175] descriptor, first an image volume is created by stacking together at least three consecutive video frames into a volume 3D dataset. Next, three LBPs are taken centered on the selected interest point, one LBP from each parallel plane in the volume, into a summary volume LBP or VLBP, and the histogram of each orthogonal LBP is concatenated into a single dynamic descriptor vector, the VLBP. The VLPB can then be tracked from frame to frame and recalculated to account for dynamic changes in the texture from frame to frame. See Figure 6-12.

Figure 6-12. (Top) VLBP method [175] of calculating LBPs from parallel planes. (Bottom) LBP-TOP method [176] of calculating LBPs from orthogonal planes. (Image used by permission, © Intel Press, from Building Intelligent Systems)


The LBP-TOP [176] is created like the VLBP, except that instead of calculating the three individual LBPs from parallel planes, they are calculated from orthogonal planes in the volume (x,y,z) intersecting the interest point, as shown in Figure 6-12. The 3D composite descriptor is the same size as the VLBP and contains three planes’ worth of data. The histograms for each LBP plane are also concatenated for the LBP-TOP like the VLBP.

Other LBP Variants

As shown in Table 6-1, there are many variants of the LBP [173]. Note that the LBP has been successfully used as a replacement for SIFT, SURF, and also as a texture metric.

Table 6-1. LBP Variants (from reference [173])