StereoPipeline

This class provides a framework for constructing stereo matching pipelines that conform to the taxonomy laid out in Scharstein and Szeliski (2002).

According to this taxonomy, stereo matching can be divided into four steps:

- Matching cost computation - Cost aggregation - Disparity computation - Disparity refinement

Implementations of various algorithms that conform to requirements of these components can be found in this module, as well as several helper functions that will create commonly used pipelines out of these building blocks.

class StereoPipeline : StereoMatcher {
CostVolume mCost;
StereoPipelineProperties mProperties;
StereoCostFunction mCostFunction;
StereoCostAggregator mCostAggregator;
DisparityMethod mDisparityMethod;
DisparityRefiner mDisparityRefiner;
}

Inherited Members

From StereoMatcher

evaluate
DisparityMap evaluate(inout Image left, inout Image right, DisparityMap prealloc = emptyDisparityMap())

Compute a disparity map using the method defined by the subclass.

Meta