A high-level image sequence fusion algorithm for human detection

Author

Wang Meng ; Dai Yaping ; Liu Yan

Author_Institution

Sch. of Autom., Beijing Inst. of Technol. Univ., Beijing, China

fYear

2010

fDate

29-31 July 2010

Firstpage

2755

Lastpage

2759

Abstract

For detecting a human from background more clearly, we try to fuse two video image sequences captured from visible and thermal sensors respectively into one by a high-level image sequence fusion (HISF) algorithm. The HISF algorithm combined the Histogram of Oriented Gradient (HOG) descriptor and linear Support Vector Machine (SVM) aiming at high quality of human detection. Comparing with several multi-resolution image fusion algorithms, it is shown by the Detection Error Tradeoff (DET) curves that the proposed algorithm increases system robust performance and achieves an excellent classification rate.

Keywords

image classification; image fusion; image resolution; image sequences; object detection; support vector machines; DET curves; HISF algorithm; SVM; detection error tradeoff curve; high-level image sequence fusion algorithm; histogram of oriented gradient descriptor; human detection; linear support vector machine; multiresolution image fusion algorithms; thermal sensors; video image sequences; Classification algorithms; Humans; Image fusion; Image sequences; Pixel; Support vector machines; Transforms; Histogram of Oriented Gradient (HOG); Image Sequence Fusion; Object Detection; SVM;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Conference (CCC), 2010 29th Chinese

Conference_Location

Beijing

Print_ISBN

978-1-4244-6263-6

Type

conf

Filename

5573348