Fast and Precise Binary Instance Segmentation of 2D Objects for Automotive Applications

Show simple item record
dc.contributor.authorGanganna Ravindra, Darshan
dc.contributor.authorDinges, Laslo
dc.contributor.authorAl-Hamadi, Ayoub
dc.contributor.authorBaranau, Vasili
dc.contributor.editorSkala, Václav
dc.date.accessioned2022-09-02T10:29:16Z
dc.date.available2022-09-02T10:29:16Z
dc.date.issued2022
dc.description.abstract-translatedIn this paper, we focus on improving binary 2D instance segmentation to assist humans in labeling ground truth datasets with polygons. Humans labeler just have to draw boxes around objects, and polygons are generated automatically. To be useful, our system has to run on CPUs in real-time. The most usual approach for binary instance segmentation involves encoder-decoder networks. This report evaluates state-of-the-art encoder-decoder networks and proposes a method for improving instance segmentation quality using these networks. Alongside network architecture improvements, our proposed method relies upon providing extra information to the network input, so-called “extreme points”, i.e. the outermost points on the object silhouette. The user can label them instead of a bounding box almost as quickly. The bounding box can be deduced from the extreme points as well. This method produces better IoU compared to other state-of-the-art encoder-decoder networks and also runs fast enough when it is deployed on a CPU.en
dc.format4 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationWSCG 2022: full papers proceedings: 30. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 302-305.en
dc.identifier.doihttps://www.doi.org/10.24132/CSRN.3201.38
dc.identifier.isbn978-80-86943-33-6
dc.identifier.issn2464-4617
dc.identifier.urihttp://hdl.handle.net/11025/49609
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencyen
dc.rights© Václav Skala - UNION Agencyen
dc.rights.accessopenAccessen
dc.subjectextrémní bodycs
dc.subjectIoUcs
dc.subjectkodér-dekodércs
dc.subjectinstance binární segmentacecs
dc.subject.translatedextreme pointsen
dc.subject.translatedIoUen
dc.subject.translatedencoder-decoderen
dc.subject.translatedinstance binary segmentationen
dc.titleFast and Precise Binary Instance Segmentation of 2D Objects for Automotive Applicationsen
dc.typeconferenceObjecten
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
B61-full.pdf
Size:
2.71 MB
Format:
Adobe Portable Document Format
Description:
Plný text
Download
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

WSCG 2022: Full Papers Proceedings