Optimized Belief Propagation (CPU and GPU)
DisparityMapEvaluation.h File Reference

Declares class to store disparity map evaluation results. More...

#include <map>
#include <iostream>
#include <numeric>
#include <array>
#include <vector>
#include "RunEval/RunData.h"
Include dependency graph for DisparityMapEvaluation.h:
This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes

struct  beliefprop::DisparityMapEvaluationParams
 Struct to store parameters for evaluation of disparity map from stereo processing. More...
 
class  DisparityMapEvaluation
 Class to store disparity map evaluation results. Specifically comparison between two disparity maps such as output disparity map from bp processing and ground truth disparity map. More...
 

Namespaces

 beliefprop
 Namespace for enums, constants, structures, and functions specific to belief propagation processing.
 

Variables

constexpr std::string_view beliefprop::kAvgRMSErrorHeader {"Average RMS error"}
 Constant string view for header of average RMS error in evaluation. More...
 
constexpr std::array< float, 4 > beliefprop::kDisparityDiffThresholds
 Difference thresholds in output disparity for a computed disparity at a pixel to be considered a "bad pixel" when compared to the ground truth in the evaluation. More...
 
constexpr float beliefprop::kMaxDiffCap
 Max difference in disparity for evaluation where disparity difference for each pixel is capped to minimize influence of outliers in the average difference across all pixels. More...
 

Detailed Description

Declares class to store disparity map evaluation results.

Author
Scott Grauer-Gray

Definition in file DisparityMapEvaluation.h.