Matches in SemOpenAlex for { <https://semopenalex.org/work/W2016524789> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W2016524789 abstract "This paper describes a fast and robust artificial neural network algorithm for solving the stereo correspondence problem in binocular vision. In this algorithm, the stereo correspondence problem is modelled as a cost minimization problem where the cost is the value of the matching function between the edge pixels along the same epipolar line. A multiple-constraint energy minimization neural network is implemented for this matching process. This algorithm differs from previous works in that it integrates ordering and geometry constraints in addition to uniqueness, continuity, and epipolar line constraint into a neural network implementation. The processing procedures are similar to that of the human vision processes. The edge pixels are divided into different clusters according to their orientation and contrast polarity. The matching is performed only between the edge pixels in the same clusters and at the same epipolar line. By following the epipolar line, the ordering constraint (the left-right relation between pixels) can be specified easily without building extra relational graphs as in the earlier works. The algorithm thus assigns artificial neurons which follow the same order of the pixels along an epipolar line to represent the matching candidate pairs. The algorithm is discussed in detail and experimental results using real images are presented." @default.
- W2016524789 created "2016-06-24" @default.
- W2016524789 creator A5025516499 @default.
- W2016524789 creator A5065020885 @default.
- W2016524789 date "1993-03-11" @default.
- W2016524789 modified "2023-09-23" @default.
- W2016524789 title "<title>Multiple-constraints neural network solution for edge-pixel-based stereo correspondence problem</title>" @default.
- W2016524789 cites W1492899472 @default.
- W2016524789 doi "https://doi.org/10.1117/12.141761" @default.
- W2016524789 hasPublicationYear "1993" @default.
- W2016524789 type Work @default.
- W2016524789 sameAs 2016524789 @default.
- W2016524789 citedByCount "0" @default.
- W2016524789 crossrefType "proceedings-article" @default.
- W2016524789 hasAuthorship W2016524789A5025516499 @default.
- W2016524789 hasAuthorship W2016524789A5065020885 @default.
- W2016524789 hasConcept C105795698 @default.
- W2016524789 hasConcept C11413529 @default.
- W2016524789 hasConcept C115961682 @default.
- W2016524789 hasConcept C154945302 @default.
- W2016524789 hasConcept C160633673 @default.
- W2016524789 hasConcept C165064840 @default.
- W2016524789 hasConcept C23379248 @default.
- W2016524789 hasConcept C3004257 @default.
- W2016524789 hasConcept C31972630 @default.
- W2016524789 hasConcept C33923547 @default.
- W2016524789 hasConcept C41008148 @default.
- W2016524789 hasConcept C50644808 @default.
- W2016524789 hasConceptScore W2016524789C105795698 @default.
- W2016524789 hasConceptScore W2016524789C11413529 @default.
- W2016524789 hasConceptScore W2016524789C115961682 @default.
- W2016524789 hasConceptScore W2016524789C154945302 @default.
- W2016524789 hasConceptScore W2016524789C160633673 @default.
- W2016524789 hasConceptScore W2016524789C165064840 @default.
- W2016524789 hasConceptScore W2016524789C23379248 @default.
- W2016524789 hasConceptScore W2016524789C3004257 @default.
- W2016524789 hasConceptScore W2016524789C31972630 @default.
- W2016524789 hasConceptScore W2016524789C33923547 @default.
- W2016524789 hasConceptScore W2016524789C41008148 @default.
- W2016524789 hasConceptScore W2016524789C50644808 @default.
- W2016524789 hasLocation W20165247891 @default.
- W2016524789 hasOpenAccess W2016524789 @default.
- W2016524789 hasPrimaryLocation W20165247891 @default.
- W2016524789 hasRelatedWork W1606809182 @default.
- W2016524789 hasRelatedWork W1841847813 @default.
- W2016524789 hasRelatedWork W2006151313 @default.
- W2016524789 hasRelatedWork W2008515079 @default.
- W2016524789 hasRelatedWork W2038886224 @default.
- W2016524789 hasRelatedWork W2154631645 @default.
- W2016524789 hasRelatedWork W2373807803 @default.
- W2016524789 hasRelatedWork W2996602101 @default.
- W2016524789 hasRelatedWork W3152085117 @default.
- W2016524789 hasRelatedWork W4321273231 @default.
- W2016524789 isParatext "false" @default.
- W2016524789 isRetracted "false" @default.
- W2016524789 magId "2016524789" @default.
- W2016524789 workType "article" @default.