SwePub
Sök i LIBRIS databas

  Utökad sökning

id:"swepub:oai:DiVA.org:liu-179288"
 

Sökning: id:"swepub:oai:DiVA.org:liu-179288" > Predicting Signed D...

  • Brissman, EmilLinköpings universitet,Datorseende,Tekniska fakulteten (författare)

Predicting Signed Distance Functions for Visual Instance Segmentation

  • Artikel/kapitelEngelska2021

Förlag, utgivningsår, omfång ...

  • Institute of Electrical and Electronics Engineers (IEEE),2021
  • electronicrdacarrier

Nummerbeteckningar

  • LIBRIS-ID:oai:DiVA.org:liu-179288
  • https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-179288URI
  • https://doi.org/10.1109/SAIS53221.2021.9484039DOI

Kompletterande språkuppgifter

  • Språk:engelska
  • Sammanfattning på:engelska

Ingår i deldatabas

Klassifikation

  • Ämneskategori:ref swepub-contenttype
  • Ämneskategori:kon swepub-publicationtype

Anmärkningar

  • Funding: Wallenberg AI, Autonomous Systems, and Software Program (WASP) - Knut and Alice Wallenberg Foundation
  • Visual instance segmentation is a challenging problem and becomes even more difficult if objects of interest varies unconstrained in shape. Some objects are well described by a rectangle, however, this is hardly always the case. Consider for instance long, slender objects such as ropes. Anchor-based approaches classify predefined bounding boxes as either negative or positive and thus provide a limited set of shapes that can be handled. Defining anchor-boxes that fit well to all possible shapes leads to an infeasible number of prior boxes. We explore a different approach and propose to train a neural network to compute distance maps along different directions. The network is trained at each pixel to predict the distance to the closest object contour in a given direction. By pooling the distance maps we obtain an approximation to the signed distance function (SDF). The SDF may then be thresholded in order to obtain a foreground-background segmentation. We compare this segmentation to foreground segmentations obtained from the state-of-the-art instance segmentation method YOLACT. On the COCO dataset, our segmentation yields a higher performance in terms of foreground intersection over union (IoU). However, while the distance maps contain information on the individual instances, it is not straightforward to map them to the full instance segmentation. We still believe that this idea is a promising research direction for instance segmentation, as it better captures the different shapes found in the real world.

Ämnesord och genrebeteckningar

Biuppslag (personer, institutioner, konferenser, titlar ...)

  • Johnander, JoakimLinköpings universitet,Datorseende,Tekniska fakulteten(Swepub:liu)joajo88 (författare)
  • Felsberg, Michael,1974-Linköpings universitet,Datorseende,Tekniska fakulteten(Swepub:liu)micfe03 (författare)
  • Linköpings universitetDatorseende (creator_code:org_t)

Sammanhörande titlar

  • Ingår i:33rd Annual Workshop of the Swedish-Artificial-Intelligence-Society (SAIS): Institute of Electrical and Electronics Engineers (IEEE), s. 5-1097816654423679781665442374

Internetlänk

Hitta via bibliotek

Till lärosätets databas

Sök utanför SwePub

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy