Publikationer från Malmö universitet
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Specialized Indoor and Outdoor Scene-specific Object Detection Models
Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT). Malmö universitet, Internet of Things and People (IOTAP).ORCID-id: 0000-0002-9464-7010
Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT). Malmö universitet, Internet of Things and People (IOTAP).ORCID-id: 0000-0003-0998-6585
Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT). Malmö universitet, Internet of Things and People (IOTAP).ORCID-id: 0000-0002-3797-4605
Axis Communications AB, Lund, Sweden.
Vise andre og tillknytning
2023 (engelsk)Inngår i: Sixteenth International Conference on Machine Vision (ICMV 2023) / [ed] Osten, Wolfgang, 2023Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Object detection is a critical task in computer vision with applications across various domains, ranging from autonomous driving to surveillance systems. Despite extensive research on improving the performance of object detection systems, identifying all objects in different places remains a challenge. The traditional object detection approaches focus primarily on extracting and analyzing visual features without considering the contextual information about the places of objects. However, entities in many real-world scenarios closely relate to their surrounding environment, providing crucial contextual cues for accurate detection. This study investigates the importance and impact of places of images (indoor and outdoor) on object detection accuracy. To this purpose, we propose an approach that first categorizes images into two distinct categories: indoor and outdoor. We then train and evaluate three object detection models (indoor, outdoor, and general models) based on YOLOv5 and 19 classes of the PASCAL VOC dataset and 79 classes of COCO dataset that consider places. The experimental evaluations show that the specialized indoor and outdoor models have higher mAP (mean Average Precision) to detect objects in specific environments compared to the general model that detects objects found both indoors and outdoors. Indeed, the network can detect objects more accurately in similar places with common characteristics due to semantic relationships between objects and their surroundings, and the network’s misdetection is diminished. All the results were analyzed statistically with t-tests.

sted, utgiver, år, opplag, sider
2023.
Serie
Proceedings of SPIE, ISSN 0277-786X, E-ISSN 1996-756X ; 13072
Emneord [en]
object detection, YOLOv5, indoor object detection, outdoor object detection, scene classification
HSV kategori
Identifikatorer
URN: urn:nbn:se:mau:diva-66441DOI: 10.1117/12.3023479ISI: 001208308300024Scopus ID: 2-s2.0-85191658757ISBN: 9781510674622 (tryckt)ISBN: 9781510674639 (digital)OAI: oai:DiVA.org:mau-66441DiVA, id: diva2:1846539
Konferanse
International Conference on Machine Vision (ICMV 2023), Nov. 15-18, 2023, Yerevan, Armenia
Tilgjengelig fra: 2024-03-22 Laget: 2024-03-22 Sist oppdatert: 2024-05-20bibliografisk kontrollert

Open Access i DiVA

fulltext(871 kB)9 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 871 kBChecksum SHA-512
1863a296e9721bdae1fc83cc681ceda2e370c5786fdb1e869d5df98fe51859ec8cdd35fd0d3c22938aa43fa3c4daacce5a6f41f34410aed003826652bfeb8dc0
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstScopus

Person

Jamali, MahtabDavidsson, PaulKhoshkangini, RezaMihailescu, Radu-Casian

Søk i DiVA

Av forfatter/redaktør
Jamali, MahtabDavidsson, PaulKhoshkangini, RezaMihailescu, Radu-Casian
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 9 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 370 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf