Histogram of Confidences for Person Detection


Middleton, Lee and Snowdon, James R. (2010) Histogram of Confidences for Person Detection. At 17th IEEE International Conference on Image Processing, Hong Kong, 26 - 29 Sep 2010. , 1841-1844.

Download

[img] PDF (ICIP 2010 paper) - Accepted Version
Download (4Mb)

Description/Abstract

This paper focuses on the problem of person detection in harsh industrial environments. Different image regions often have different requirements for the person to be detected. Additionally, as the environment can change on a frame to frame basis even previously detected people can fail to be found. In our work we adapt a previously trained classifier to improve its performance in the industrial environment. The classifier output is initially used an image descriptor. Structure from the descriptor history is learned using semi-supervised learning to boost overall performance. In comparison with two state of the art person detectors we see gains of 10%. Our approach is generally applicable to pretrained classifiers which can then be specialised for a specific scene.

Item Type: Conference or Workshop Item (Speech)
Additional Information: Event Dates: September 26-29, 2010
ISBNs: 9781424479931
ISSNs: 1522-4880
Keywords: Image analysis, Image classification, Object detection, Identification of persons, Image segmentation
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science
Faculty of Physical Sciences and Engineering > Electronics and Computer Science > IT Innovation Centre
ePrint ID: 272040
Date Deposited: 17 Feb 2011 11:32
Last Modified: 27 Mar 2014 20:17
Contact Email Address: ljm@ecs.soton.ac.uk
Further Information:Google Scholar
ISI Citation Count:0
URI: http://eprints.soton.ac.uk/id/eprint/272040

Actions (login required)

View Item View Item