Ansatte – Københavns Universitet

Object classfication from RGB-D images using depth context kernel descriptors

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Hong Pan, Søren Ingvor Olsen, Yaping Zhu

Context cue is important in object classification. By embedding the depth context cue of image attributes into kernel descriptors, we propose a new set of depth image descriptors called depth context kernel descriptors (DCKD) for RGB-D based object classification. The motivation of DCKD is to use the depth consistency of image attributes defined within a neighboring region to improve the robustness of descriptor matching in the kernel space. Moreover, a novel joint spatial-depth pooling (JSDP) scheme, which further partitions image sub-regions using the depth cue and pools features in both 2D image plane and the depth direction, is developed to take full advantage of the available depth information. By embedding DCKD and JSDP into the standard object classification pipeline, we achieve superior performance to state-of-the-art methods on RGB-D benchmarks for object classification and scene recognition.
OriginalsprogEngelsk
Titel2015 IEEE International Conference on Image Processing (ICIP 2015)
Antal sider5
ForlagIEEE
Publikationsdato2015
Sider512-516
ISBN (Elektronisk)978-1-4799-8339-1
DOI
StatusUdgivet - 2015
BegivenhedInternational Conference on Image Processing 2015 - Quebec City, Canada
Varighed: 27 sep. 201530 sep. 2015

Konference

KonferenceInternational Conference on Image Processing 2015
LandCanada
ByQuebec City
Periode27/09/201530/09/2015

ID: 160890096