Rapid Pedestrian Detection Based On Movement Trend

DOI

10.2991/icamcs-16.2016.73How to use a DOI?

Keywords

Pedestrian detection, Kalman filter, Prediction, Verification

Abstract

This paper presents a movement trends based approach for pedestrian detection aiming at reducing the consumption of feature calculation caused by sliding windows. A new approach to predict the location of pedestrian is proposed by combining the movement trend of objects, extracted by improved background segmentation algorithm, with Kalman filter. The keypoint descriptor BRISK (Binary Robust Invariant Scalable Keypoints) is presented to verify the predicted location and make it reliable. Experiment results on PETS dataset report that the algorithm is 10.9 times faster than SVM+HOG method and keep a better accuracy at the same time.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Ruohua Li
AU  - Taihong Wang
PY  - 2016/06
DA  - 2016/06
TI  - Rapid Pedestrian Detection Based On Movement Trend
BT  - Proceedings of the 2016 5th International Conference on Advanced Materials and Computer Science
PB  - Atlantis Press
SP  - 345
EP  - 349
SN  - 2352-5401
UR  - https://doi.org/10.2991/icamcs-16.2016.73
DO  - 10.2991/icamcs-16.2016.73
ID  - Li2016/06
ER  -