ScholarGate
Asistent
Machine learningDeep learning / NLP / CV

Detekcija objekata

Detekcija objekata je zadatak kompjuterskog vida u kojem duboka neuralna mreža istovremeno locira i klasifikuje svaku instancu jedne ili više kategorija objekata unutar slike, proizvodeći bounding box i oznaku klase za svaki detektovani objekat. Moderni detektori — od porodice R-CNN do YOLO i DETR — postižu skoro ljudsku tačnost pri brzinama u realnom vremenu na standardnim repernim skupovima podataka.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte celu metodu

Samo za članove

Prijavite se besplatnim nalogom da biste pročitali ovaj odeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

+6 more

Izvori

  1. Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 580–587. DOI: 10.1109/CVPR.2014.81
  2. Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 779–788. DOI: 10.1109/CVPR.2016.91

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Object Detection (Region-Based and Anchor-Free Deep Neural Network Models). ScholarGate. https://scholargate.app/sr/deep-learning/object-detection

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Citirana u

ScholarGateObject Detection (Object Detection (Region-Based and Anchor-Free Deep Neural Network Models)). Preuzeto 2026-06-15 sa https://scholargate.app/sr/deep-learning/object-detection · Skup podataka: https://doi.org/10.5281/zenodo.20539026