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. 26 - 29 Sep 2010. , pp. 1841-1844.

Download

[img] PDF c_middleton_icip2010.pdf - Accepted Manuscript
Download (5MB)

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 (Other)
Additional Information: Event Dates: September 26-29, 2010
Venue - Dates: 17th IEEE International Conference on Image Processing, 2010-09-26 - 2010-09-29
Keywords: Image analysis, Image classification, Object detection, Identification of persons, Image segmentation
Organisations: Electronics & Computer Science, IT Innovation
ePrint ID: 272040
Date :
Date Event
September 2010Published
Date Deposited: 17 Feb 2011 11:32
Last Modified: 17 Apr 2017 18:01
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/272040

Actions (login required)

View Item View Item