Open AccessReal‐time object entity detection system for smart surveillance application
Author(s) -
Ko K.E.,
Sim K.B.
Publication year - 2017
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
ISSN - 1350-911X
DOI - 10.1049/el.2017.1532
Subject(s) - benchmark (surveying) , object (grammar) , computer science , object detection , set (abstract data type) , process (computing) , scheme (mathematics) , class (philosophy) , artificial intelligence , real time computing , state (computer science) , computer vision , method , data mining , pattern recognition (psychology) , object oriented programming , mathematics , algorithm , mathematical analysis , geodesy , programming language , geography , operating system
A real‐time scheme for detecting object entities in real‐time among a set of objects contained in the same class category is proposed. Building a unified framework for real‐time object entity detection system without an additional training process to distinguish the object entities while minimising the loss of accuracy is focused. The experimental results on a benchmark dataset demonstrate that the method shows outstanding precision performance while achieving state‐of‐the‐art object detection speed.