Open AccessA Research on Dynamic Target Tracking with Camera Based on Kalman Filter
Author(s) -
Yimeng Ma
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1453/1/012106
Subject(s) - kalman filter , frame (networking) , computer science , set (abstract data type) , tracking (education) , computer vision , relation (database) , function (biology) , artificial intelligence , filter (signal processing) , matrix (chemical analysis) , real time computing , data mining , telecommunications , psychology , pedagogy , evolutionary biology , biology , programming language , materials science , composite material
With the popularization of the camera, all kinds of video network communication technologies have developed towards civil use and become increasingly popular. For household application, a common PC is used to obtain the frame data from the home network, while the constant frame is set as the background. The update function is used to update background in real time, and thereby forming an inter-frame relation matrix. Based on the matrix, Kalman filter can match and track targets. This method can effectively complete the calculation on the PC, perform precise detection and deal with the complexity of the household application. Finally, with the test results, this paper further proves that the method is feasible and can be used in actual situations.