Objective Image Quality Measures for Disparity Maps Evaluation
| Autor: | Dimitrije Bujakovic, Milenko Andric, Saad Merrouche, Boban Bondžulić |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
stereo correspondence algorithms
Computer Networks and Communications Computer science Image quality lcsh:TK7800-8360 02 engineering and technology error measures Set (abstract data type) Consistency (database systems) 0202 electrical engineering electronic engineering information engineering Electrical and Electronic Engineering disparity maps Pixel business.industry lcsh:Electronics 020206 networking & telecommunications Pattern recognition quantitative evaluation Partition (database) image quality analysis Range (mathematics) Hardware and Architecture Control and Systems Engineering Signal Processing 020201 artificial intelligence & image processing Artificial intelligence business |
| Zdroj: | Electronics, Vol 9, Iss 1625, p 1625 (2020) Electronics Volume 9 Issue 10 |
| ISSN: | 2079-9292 |
| Popis: | 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&rsquo 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&mdash 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&rsquo accuracy. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|