Results

The dynamic skeleton model currently includes the upper body and arms. Figure 2.2 shows the real-time response to various target postures. The model interpolates those portions of the body state that are not measured directly, such as the upper body and elbow orientation, by use of the model's intrinsic dynamics and the behavior (control) model. The model also rejects noise that is inconsistent with the dynamic model. Table 2.4 compares noise in the physics+behavior tracker with the physics-only tracker noise. It can be seen that there is a significant increase in performance.

Figure 2.4: Sum Square Error of a Physics-only tracker (triangles) vs. error from a Physics+Behavior Tracker

[width=120mm]figs/sse

Figure 2.5: Tracking performance on a sequence with significant occlusion. Top: A diagram of the sequence and a single camera's view of the motion Left: A graph of tracking results without feedback. Right: Correct tracking when feedback is enabled.

[width=26mm]figs/rumbaD [width=26mm]figs/rumba0 [width=26mm]figs/rumba1 [width=26mm]figs/rumba2 [width=26mm]figs/rumba3

[width=130mm]figs/helix_shadow

Figure 2.5 illustrates another advantage of feedback from higher-level models to the low-level vision system. Without feedback, the 2-D tracker fails if there is even partial self-occlusion, or occlusion of an object with similar appearance (such as another person), from a single camera's perspective. With feedback, information from the dynamic model can be used to resolve ambiguity during 2-D tracking. With models of behavior, longer occlusions can be tolerated.