Paper
15 November 2011 An applied study of human detection in single images
Ren Liu, Xianghua Xie
Author Affiliations +
Proceedings Volume 8335, 2012 International Workshop on Image Processing and Optical Engineering; 83350D (2011) https://doi.org/10.1117/12.917683
Event: 2012 International Workshop on Image Processing and Optical Engineering, 2012, Harbin, China
Abstract
In this paper we perform an applied comparative study of popular HOG based human detection and a state-of-the-art pose adaptive method that uses shape-based model construction. Both methods are implemented with kernel SVM, instead of linear SVM. Detailed performance evaluation is carried out on MIT pedestrian dataset and INRIA person dataset. This study shows that, although pose adaptive method has no significant advantage compared to the HOG based approach on those datasets, the pose adaptive approach is more efficient in detection and it has the capability to segment the human shape from images while carrying out detection which can be advantageous in many applications.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ren Liu and Xianghua Xie "An applied study of human detection in single images", Proc. SPIE 8335, 2012 International Workshop on Image Processing and Optical Engineering, 83350D (15 November 2011); https://doi.org/10.1117/12.917683
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Sensors

Feature extraction

Binary data

Head

Motion models

Error analysis

RELATED CONTENT

Behavioral model of visual perception and recognition
Proceedings of SPIE (September 08 1993)
Identification of simple objects in image sequences
Proceedings of SPIE (August 17 1994)
Object discrimination using neural networks
Proceedings of SPIE (September 16 1992)

Back to Top