Share Email Print

Proceedings Paper

Human fixations detection model in video-compressed-domain based on MVE and OBDL
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper deals with the problem of compressed-domain human fixations detection in the video sequences, and presents a fast and efficient algorithm based on Motion Vector Entropy (MVE) and Operational Block Description Length (OBDL). The two features are obtainable from the compressed video bitstream with partial decoding, and generate the feature maps. The two feature maps are processed, and generate MVE map and OBDL map respectively. Then the processed maps are fused. In order to further improve the global saliency detection, the fused map is worked by the Gaussian model whose center is determined by the feature values. The validation and comparison are made by several accuracy metrics on two ground truth datasets. Experimental results show that the proposed saliency detection model obtains superior performances over several state-of-the-art compressed-domain and pixel-domain algorithms on evaluation metrics. Computationally, our algorithm achieves the real-time requirements of the saliency detection.

Paper Details

Date Published: 5 November 2018
PDF: 7 pages
Proc. SPIE 10816, Advanced Optical Imaging Technologies, 108161O (5 November 2018); doi: 10.1117/12.2501852
Show Author Affiliations
Yongjun Li, Henan Univ. (China)
Xuemei Lei, Henan Univ. (China)
Yong Liang, Henan Univ. (China)
Jing Chen, Henan Univ. (China)

Published in SPIE Proceedings Vol. 10816:
Advanced Optical Imaging Technologies
Xiao-Cong Yuan; Kebin Shi; Michael G. Somekh, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?