Parametric classification based on kinematic characteristics of objects for identification of criminals
Year: 2024
Type: article
Abstract: The problem of identifying objects in conditions of their disguise and impossibility of assessment by video images is studied. Potential criminals can be considered as such objects. The task is to assess whether the observed object is a potential criminal element or an ordinary person.It is proposed to use kinematic characteristics of human motion as factors-features for solving the recognition problem, in particular, components of the speed and acceleration vectors of characteristic points of the body in the system of generalized coordinates using Lame functions.It is proposed to use a parametric classification algorithm to solve the identification problem with such a choice of factors-features. The proposed idea, if practically implemented, can create conditions for detecting criminals or identifying suspicious persons for subsequent control checks
Author: Mourad Aouati
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $80
OpenAlex ID: W4405101207