Generative detect for occlusion object based on occlusion generation and feature completing

Simple item page
dc.contributor.authorXu, Can
dc.contributor.authorYuen, Peter W. T.
dc.contributor.authorLang, Wenxi
dc.contributor.authorXin, Rui
dc.contributor.authorMao, Kaichen
dc.contributor.authorJiang, Haiyan
dc.date.accessioned2021-06-25T09:26:38Z
dc.date.available2021-06-25T09:26:38Z
dc.date.issued2021-06-17
dc.description.abstractDetecting the object with external occlusion has always been a hot topic in computer version, while its accuracy is always limited due to the loss of original object information and increase of new occlusion noise. In this paper, we propose a occluded object detection algorithm named GC-FRCN (Generative feature completing Faster RCNN), which consists of the OSGM (Occlusion Sample Generation Module) and OSIM (Occlusion Sample Inpainting Module). Specifically, the OSGM mines and discards the feature points with high category response on the feature map to enhance the richness of occlusion scenes in the training data set. OSIM learns an implicit mapping relationship from occluded feature map to real feature map adversarially, which aims at improving feature quality by repair the noisy object feature. Extensive experiments and ablation studies have been conducted on four different datasets. All the experiments demonstrate the GC-FRCN can effectively detect objects with local external occlusion and has good robustness for occlusion at different scales.en_UK
dc.identifier.citationXu C, Yuen P, Lang W, et al., (2021) Generative detect for occlusion object based on occlusion generation and feature completing. Journal of Visual Communication and Image Representation, Volume 78, July 2021, Article number 103189en_UK
dc.identifier.issn1047-3203
dc.identifier.urihttps://doi.org/10.1016/j.jvcir.2021.103189
dc.identifier.urihttp://dspace.lib.cranfield.ac.uk/handle/1826/16810
dc.language.isoenen_UK
dc.publisherElsevieren_UK
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectOcclusionen_UK
dc.subjectObject detectionen_UK
dc.subjectFeature completingen_UK
dc.subjectGenerative adversarial networksen_UK
dc.titleGenerative detect for occlusion object based on occlusion generation and feature completingen_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Generative_detect_for_occlusion_object_based-2021.pdf
Size:
2.35 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (CDS)