Full metadata record
DC pole | Hodnota | Jazyk |
---|---|---|
dc.contributor.author | Ganganna Ravindra, Darshan | |
dc.contributor.author | Dinges, Laslo | |
dc.contributor.author | Al-Hamadi, Ayoub | |
dc.contributor.author | Baranau, Vasili | |
dc.contributor.editor | Skala, Václav | |
dc.date.accessioned | 2022-09-02T10:29:16Z | |
dc.date.available | 2022-09-02T10:29:16Z | |
dc.date.issued | 2022 | |
dc.identifier.citation | WSCG 2022: full papers proceedings: 30. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 302-305. | en |
dc.identifier.isbn | 978-80-86943-33-6 | |
dc.identifier.issn | 2464-4617 | |
dc.identifier.uri | http://hdl.handle.net/11025/49609 | |
dc.format | 4 s. | cs |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | en |
dc.publisher | Václav Skala - UNION Agency | en |
dc.rights | © Václav Skala - UNION Agency | en |
dc.subject | extrémní body | cs |
dc.subject | IoU | cs |
dc.subject | kodér-dekodér | cs |
dc.subject | instance binární segmentace | cs |
dc.title | Fast and Precise Binary Instance Segmentation of 2D Objects for Automotive Applications | en |
dc.type | conferenceObject | en |
dc.rights.access | openAccess | en |
dc.type.version | publishedVersion | en |
dc.description.abstract-translated | In 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.subject.translated | extreme points | en |
dc.subject.translated | IoU | en |
dc.subject.translated | encoder-decoder | en |
dc.subject.translated | instance binary segmentation | en |
dc.identifier.doi | https://www.doi.org/10.24132/CSRN.3201.38 | |
dc.type.status | Peer-reviewed | en |
Vyskytuje se v kolekcích: | WSCG 2022: Full Papers Proceedings |
Soubory připojené k záznamu:
Soubor | Popis | Velikost | Formát | |
---|---|---|---|---|
B61-full.pdf | Plný text | 2,78 MB | Adobe PDF | Zobrazit/otevřít |
Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam:
http://hdl.handle.net/11025/49609
Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.