Digitální knihovna UPCE přechází na novou verzi. Omluvte prosím případné komplikace. / The UPCE Digital Library is migrating to a new version. We apologize for any inconvenience.

Publikace:
On possibilities of human head detection for person flow monitoring system

Konferenční objektopen accesspeer-reviewedpostprint
Načítá se...
Náhled

Datum

Autoři

Doležel, Petr
Štursa, Dominik
Škrabánek, Pavel

Název časopisu

ISSN časopisu

Název svazku

Nakladatel

Springer Nature Switzerland AG

Výzkumné projekty

Organizační jednotky

Číslo časopisu

Abstrakt

Along with the development of human society, economy, industry and engineering, as well as with growing population in the world's biggest cities, various approaches to person detection have become the subject of great interest. One approach to developing a person detection system is proposed in this paper. A high-angle video sequence is considered as the input to the system. Then, three classification algorithms are considered: support vector machines, pattern recognition neural networks and convolutional neural networks. The results showed very little difference between the classifiers, with the overall accuracy more than 95% over a testing set.

Popis

Klíčová slova

Person flow monitoring, Support vector machines, Pattern recognition neural network, Convolutional neural network, Histograms of oriented gradients, Systém monitorování pohybu osob, metoda podpůrných vektorů, umělá neuronová síť, konvoluční síť, histogramy orientovaných gradientů

Citace

Permanentní identifikátor

Endorsement

Review

Supplemented By

Referenced By