Malmö University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Segment Anything Model (SAM) Meets Object Detected Box Prompts
Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT). Malmö University, Internet of Things and People (IOTAP). Computer Engineering Department, Bitlis Eren University, Bitlis, Turkiye.ORCID iD: 0000-0002-2223-3927
Ericsson AB, Ericsson Research, Lund, Sweden.
Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT). Malmö University, Internet of Things and People (IOTAP).ORCID iD: 0000-0002-0155-7949
Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT). Malmö University, Internet of Things and People (IOTAP).ORCID iD: 0000-0002-2763-8085
Show others and affiliations
2024 (English)In: 2024 IEEE International Conference on Industrial Technology (ICIT), Institute of Electrical and Electronics Engineers (IEEE), 2024Conference paper, Published paper (Refereed)
Abstract [en]

Segmenting images is an intricate and exceptionally demanding field within computer vision. Instance Segmentation is one of the subfields of image segmentation that segments objects on a given image or video. It categorizes the class labels according to individual instances, ensuring that distinct instance markers are assigned to each occurrence of the same object class, even if multiple instances exist. With the development of computer systems, segmentation studies have increased very rapidly. One of the state-of-the-art algorithms recently published by Meta AI, which segments everything on a given image, is called the Segment Anything Model (SAM). Its impressive zero-shot performance encourages us to use it for diverse tasks. Therefore, we would like to leverage the SAM for an effective instance segmentation model. Accordingly, in this paper, we propose a hybrid instance segmentation method in which Object Detection algorithms extract bounding boxes of detected objects and load SAM to produce segmentation, called Box Prompted SAM (BP-SAM). Experimental evaluation of the COCO2017 Validation dataset provided us with promising performance.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2024.
Series
IEEE International Conference on Industrial Technology, ISSN 2641-0184, E-ISSN 2643-2978
Keywords [en]
SAM, Segment Anything Model, Object Detection, Instance Segmentation, Computer Vision
National Category
Computer graphics and computer vision
Identifiers
URN: urn:nbn:se:mau:diva-70258DOI: 10.1109/icit58233.2024.10541006Scopus ID: 2-s2.0-85195782363ISBN: 979-8-3503-4026-6 (electronic)ISBN: 979-8-3503-4027-3 (print)OAI: oai:DiVA.org:mau-70258DiVA, id: diva2:1889549
Conference
2024 IEEE International Conference on Industrial Technology (ICIT), Bristol, United Kingdom, 25-27 March 2024
Funder
Knowledge Foundation, 20220087-H-01Available from: 2024-08-15 Created: 2024-08-15 Last updated: 2025-02-07Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Akin, ErdalAdewole, Kayode SakariyahMalekian, RezaPersson, Jan A.

Search in DiVA

By author/editor
Akin, ErdalAdewole, Kayode SakariyahMalekian, RezaPersson, Jan A.
By organisation
Department of Computer Science and Media Technology (DVMT)Internet of Things and People (IOTAP)
Computer graphics and computer vision

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 402 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf