DocumentCode
1672269
Title
Human detection in compressed domain
Author
Ozer, I. Burak ; Wolf, Wayne
Author_Institution
Dept. of Electr. Eng., Princeton Univ., NJ, USA
Volume
3
fYear
2001
fDate
6/23/1905 12:00:00 AM
Firstpage
274
Abstract
We propose an algorithm for human detection in JPEG compressed still images and MPEG I-frames. In this new algorithm, the overall shape of a standing or walking person is detected by using an eigenspace representation of human silhouettes obtained from AC-DCT coefficients. Our approach is invariant to changes in intensity, color and textures and has the advantage of using the available data in the standard compression algorithms. The algorithm achieves a correct detection rate of 80% for frontal and rear views of human bodies in cluttered scenes
Keywords
data compression; discrete cosine transforms; eigenvalues and eigenfunctions; image coding; image recognition; object detection; video coding; AC-DCT coefficients; JPEG compressed still images; MPEG I-frames; eigenspace representation; human activity recognition; human detection; human silhouettes; standing person; walking person; Decoding; Discrete cosine transforms; Face detection; Humans; Image coding; Legged locomotion; Object detection; Shape; Transform coding; Video compression;
fLanguage
English
Publisher
ieee
Conference_Titel
Image Processing, 2001. Proceedings. 2001 International Conference on
Conference_Location
Thessaloniki
Print_ISBN
0-7803-6725-1
Type
conf
DOI
10.1109/ICIP.2001.958104
Filename
958104
Link To Document