FlowUpdateDelta

Computes one step update of the optical flow based on image data and previous estimate.

Parameters

gamma : float. Defaults to 0.01 The filter gains for the update step.

max_flow : float. Defaults to 1.0 The max magnitude allowed for the optical flow output.

Inputs

in_gray : ImageView {r16f, r32f} image. The input gray-scale image at current time step.

in_gradient : ImageView {rg16f, rg32f} image. The input gray-scale image gradient at current time step.

in_delta_flow : Imageview {rg16f, rg32f} image. The current estimation of the optical flow.

in_gray_old : ImageView {r16f, r32f} image. The input gray-scale image at current time step.

in_flow : SampledImageview {rg16f, rg32f} image. The current estimation of the optical flow from a level above in the pyramid. This image view has half the resolution of the other inputs.

Outputs

out_gray : ImageView {r16f, r32f} image. The image estimate for the next time step. It is a memory copy of in_gray. This image is allocated externally in FlowFilterDelta and bound to this node. This way, the loop between FlowPredictPayload and FlowUpdateDelta can be broken.

out_flow : ImageView {rg16f, rg32f} image. The updated optical flow. The floating point precision of this port depends on the precision of in_flow.

out_delta_flow : ImageView {rg16f, rg32f} image. The updated optical flow. This image is allocated externally in FlowFilterDelta and bound to this node. This way, the loop between FlowPredictPayload and FlowUpdateDelta can be broken.