A Two-Stage Approach for Bag Detection in Pedestrian Images

Bag detection in pedestrian images is a very practical visual surveillance problem. It is challenging because bag appearance may vary greatly. In this paper, we propose a novel two-stage approach for bag detection in pedestrian images. Firstly, we utilize two stripe vocabulary forests to check wheth...

Full description

Saved in:
Bibliographic Details
Published inComputer Vision -- ACCV 2014 pp. 507 - 521
Main Authors Du, Yuning, Ai, Haizhou, Lao, Shihong
Format Book Chapter
LanguageEnglish
Published Cham Springer International Publishing
SeriesLecture Notes in Computer Science
Subjects
Classical STRIPS
Convolutional Neural Network (CNN)
Pedestrian Attributes
Pedestrian Images
Proposed Regulation
Online AccessGet full text

Cover

More Information
Summary:Bag detection in pedestrian images is a very practical visual surveillance problem. It is challenging because bag appearance may vary greatly. In this paper, we propose a novel two-stage approach for bag detection in pedestrian images. Firstly, we utilize two stripe vocabulary forests to check whether a pedestrian is with a bag. Secondly, we locate the bag location by ranking the generated bottom-up region proposals. The ranker is learned with a convolutional neural network (CNN). Experiments are performed on a subset of CUHK person re-identification dataset that show the effectiveness of our approach for bag detection in pedestrian images. Although developed for a specific problem, our approach could be applied to detect other carrying objects in pedestrian images.
ISBN:3319168169
9783319168166
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-319-16817-3_33