Please use this identifier to cite or link to this item:
https://doi.org/10.1587/transinf.E96.D.993
Title: | Human attribute analysis using a top-view camera based on two-stage classification | Authors: | Yamasaki T. Matsunami T. Chen T. |
Keywords: | Human attributes Surveillance Top-view camera |
Issue Date: | 2013 | Publisher: | Institute of Electronics, Information and Communication, Engineers, IEICE | Citation: | Yamasaki T., Matsunami T., Chen T. (2013). Human attribute analysis using a top-view camera based on two-stage classification. IEICE Transactions on Information and Systems E96-D (4) : 993-996. ScholarBank@NUS Repository. https://doi.org/10.1587/transinf.E96.D.993 | Abstract: | This paper presents a technique that analyzes pedestrians' attributes such as gender and bag-possession status from surveillance video. One of the technically challenging issues is that we use only topview camera images to protect privacy. The shape features over the frames are extracted by bag-of-features (BoF) using histogram of oriented gradients (HoG) vectors. In order to enhance the classification accuracy, a two-staged classification framework is presented. Multiple classifiers are trained by changing the parameters in the first stage. The outputs from the first stage is further trained and classified in the second stage classifier. The experiments using 60-minute video captured at Haneda Airport, Japan, show that the accuracies for the gender classification and the bagpossession classification were 95.8% and 97.2%, respectively, which is a significant improvement from our previous work. Copyright | Source Title: | IEICE Transactions on Information and Systems | URI: | http://scholarbank.nus.edu.sg/handle/10635/146113 | ISSN: | 09168532 | DOI: | 10.1587/transinf.E96.D.993 |
Appears in Collections: | Staff Publications |
Show full item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.