Measuring the performance of single image depth estimation methods

Simple item page
dc.contributor.authorCadena, C.
dc.contributor.authorLatif, Y.
dc.contributor.authorReid, I.
dc.contributor.conference2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2016) (9 Oct 2016 - 14 Oct 2016 : Daejeon, South Korea)
dc.date.issued2016
dc.description.abstractWe consider the question of benchmarking the performance of methods used for estimating the depth of a scene from a single image. We describe various measures that have been used in the past, discuss their limitations and demonstrate that each is deficient in one or more ways. We propose a new measure of performance for depth estimation that overcomes these deficiencies, and has a number of desirable properties. We show that in various cases of interest the new measure enables visualisation of the performance of a method that is otherwise obfuscated by existing metrics. Our proposed method is capable of illuminating the relative performance of different algorithms on different kinds of data, such as the difference in efficacy of a method when estimating the depth of the ground plane versus estimating the depth of other generic scene structure. We showcase the method by comparing a number of existing single-view methods against each other and against more traditional depth estimation methods such as binocular stereo.
dc.description.statementofresponsibilityCesar Cadena, Yasir Latif, and Ian D. Reid
dc.identifier.citationProceedings of the ... IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2016, vol.2016-November, pp.4150-4157
dc.identifier.doi10.1109/IROS.2016.7759611
dc.identifier.isbn9781509037629
dc.identifier.issn2153-0858
dc.identifier.issn2153-0866
dc.identifier.orcidLatif, Y. [0000-0002-2529-5322]
dc.identifier.orcidReid, I. [0000-0001-7790-6423]
dc.identifier.urihttp://hdl.handle.net/2440/107953
dc.language.isoen
dc.publisherIEEE
dc.relation.granthttp://purl.org/au-research/grants/arc/DP130104413
dc.relation.granthttp://purl.org/au-research/grants/arc/CE140100016
dc.relation.granthttp://purl.org/au-research/grants/arc/FL130100102
dc.rights© 2016 IEEE
dc.source.urihttps://doi.org/10.1109/iros.2016.7759611
dc.subjectEstimation, measurement, image resolution, three-dimensional displays, cameras, robots, semantics
dc.titleMeasuring the performance of single image depth estimation methods
dc.typeConference paper
pubs.publication-statusPublished

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
RA_hdl_107953.pdf
Size:
2.43 MB
Format:
Adobe Portable Document Format
Description:
Restricted Access
Download

Collections

Computer Science publications