Objective Image Quality Measures for Disparity Maps Evaluation

Abstract

The evaluation of disparity (range) maps includes the selection of an objective image quality (or error) measure. Among existing measures, the percentage of bad matched pixels is commonly used. However, it requires a disparity error tolerance and ignores the relationship between range and disparity. In this research, twelve error measures are characterized in order to provide the bases to select accurate stereo algorithms during the evaluation process. Adaptations of objective quality measures for disparity maps’ accuracy evaluation are proposed. The adapted objective measures operate in a manner similar to the original objective measures, but allow special handling of missing data. Additionally, the adapted objective measures are sensitive to errors in range and surface structure, which cannot be measured using the bad matched pixels. Their utility was demonstrated by evaluating a set of 50 stereo disparity algorithms known in the literature. Consistency evaluation of the proposed measures was performed using the two conceptually different stereo algorithm evaluation methodologies—ordinary ranking and partition and grouping of the algorithms with comparable accuracy. The evaluation results showed that partition and grouping make a fair judgment about disparity algorithms’ accuracy.

RT-libSGM: FPGA-Oriented Real-Time Stereo Matching System with High Scalability

“…Regarding the system validity evaluation, we evaluate our system using the metric of the invalid disparity rate (error rate), which is calculated through the formulation of [34]. We use uniqueness and L-R consistency checks to avoid mismatching, as introduced in Sect.…”