3D Skeletal Human Action Recognition Using a CNN Fusion Model

Figure 6

Sample frames of the Toyota Smarthome dataset. The red points in each frame were plotted according to the 3D positions of skeletal joints obtained using the method of [18]. (a) Walk. (b) Lay down. (c) Read book. (d) Drink from cup. (e) Stir. (f) Get up.

(a)

(b)

(c)

(d)

(e)

(f)