Detail publikace

Centroid based person detection using pixelwise prediction of the position

DOLEŽEL, P. ŠKRABÁNEK, P. ŠTURSA, D. BARUQUE ZANON, B. COGOLLOS ADRIAN, H. KRÝDA, P.

Originální název

Centroid based person detection using pixelwise prediction of the position

Typ

článek v časopise ve Web of Science, Jimp

Jazyk

angličtina

Originální abstrakt

Implementations of person detection in tracking and counting systems tend towards processing of orthogonally captured images on edge computing devices. The ellipse-like shape of heads in orthogonally captured images inspired us to predict head centroids to determine positions of persons in images. We predict the centroids using a fully convolutional network (FCN). We combine the FCN with simple image processing operations to ensure fast inference of the detector. We experiment with the size of the FCN output to further decrease the inference time. We compare the proposed centroid-based detector with bounding box-based detectors on head detection task in terms of the inference time and the detection performance. We propose a performance measure which allows quantitative comparison of the two detection approaches. For the training and evaluation of the detectors, we form original datasets of 8000 annotated images, which are characterized by high variability in terms of lighting conditions, background, image quality, and elevation profile of scenes. We propose an approach which allows simultaneous annotation of the images for both bounding box-based and centroid-based detection. The centroid-based detector shows the best detection performance while keeping edge computing standards.

Klíčová slova

Persondetection; Fullyconvolutionalnetworks; Performancemeasure; Edgecomputing; Computervision

Autoři

DOLEŽEL, P.; ŠKRABÁNEK, P.; ŠTURSA, D.; BARUQUE ZANON, B.; COGOLLOS ADRIAN, H.; KRÝDA, P.

Vydáno

6. 7. 2022

Nakladatel

ELSEVIER

Místo

AMSTERDAM

ISSN

1877-7503

Periodikum

Journal of Computational Science

Ročník

63

Číslo

1

Stát

Nizozemsko

Strany od

1

Strany do

12

Strany počet

12

URL

https://www.sciencedirect.com/science/article/pii/S1877750322001442

Plný text v Digitální knihovně

http://hdl.handle.net/11012/208207

BibTex

@article{BUT178514,
  author="Petr {Doležel} and Pavel {Škrabánek} and Dominik {Štursa} and Bruno {Baruque Zanon} and Hector {Cogollos Adrian} and Pavel {Krýda}",
  title="Centroid based person detection using pixelwise prediction of the position",
  journal="Journal of Computational Science",
  year="2022",
  volume="63",
  number="1",
  pages="1--12",
  doi="10.1016/j.jocs.2022.101760",
  issn="1877-7503",
  url="https://www.sciencedirect.com/science/article/pii/S1877750322001442"
}