Full Text:   <1540>

CLC number: TP75

On-line Access: 2008-01-11

Received: 2007-03-14

Revision Accepted: 2007-07-05

Crosschecked: 0000-00-00

Cited: 0

Clicked: 3622

Citations:  Bibtex RefMan EndNote GB/T7714

-   Go to

Article info.
1. Reference List
Open peer comments

Journal of Zhejiang University SCIENCE A 2008 Vol.9 No.2 P.256~261

http://doi.org/10.1631/jzus.A071131


Boosting multi-features with prior knowledge for mini unmanned helicopter landmark detection


Author(s):  Qin-yuan REN, Ping LI, Bo HAN

Affiliation(s):  The State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China

Corresponding email(s):   qyren@iipc.zju.edu.cn

Key Words:  Boosting, Prior knowledge model, Landmark detection


Qin-yuan REN, Ping LI, Bo HAN. Boosting multi-features with prior knowledge for mini unmanned helicopter landmark detection[J]. Journal of Zhejiang University Science A, 2008, 9(2): 256~261.

@article{title="Boosting multi-features with prior knowledge for mini unmanned helicopter landmark detection",
author="Qin-yuan REN, Ping LI, Bo HAN",
journal="Journal of Zhejiang University Science A",
volume="9",
number="2",
pages="256~261",
year="2008",
publisher="Zhejiang University Press & Springer",
doi="10.1631/jzus.A071131"
}

%0 Journal Article
%T Boosting multi-features with prior knowledge for mini unmanned helicopter landmark detection
%A Qin-yuan REN
%A Ping LI
%A Bo HAN
%J Journal of Zhejiang University SCIENCE A
%V 9
%N 2
%P 256~261
%@ 1673-565X
%D 2008
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.A071131

TY - JOUR
T1 - Boosting multi-features with prior knowledge for mini unmanned helicopter landmark detection
A1 - Qin-yuan REN
A1 - Ping LI
A1 - Bo HAN
J0 - Journal of Zhejiang University Science A
VL - 9
IS - 2
SP - 256
EP - 261
%@ 1673-565X
Y1 - 2008
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.A071131


Abstract: 
Without sufficient real training data, the data driven classification algorithms based on boosting method cannot solely be utilized to applications such as the mini unmanned helicopter landmark image detection. In this paper, we propose an approach which uses a boosting algorithm with the prior knowledge for the mini unmanned helicopter landmark image detection. The stage forward stagewise additive model of boosting is analyzed, and the approach how to combine it with the prior knowledge model is presented. The approach is then applied to landmark image detection, where the multi-features are boosted to solve a series of problems, such as rotation, noises affected, etc. Results of real flight experiments demonstrate that for small training examples the boosted learning system using prior knowledge is dramatically better than the one driven by data only.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1] Amidi, O., Kanade, T., Miller, J.R., 1998. Vision-based Autonomous Helicopter Research at Carnegie Mellon Robotics Institute 1991-1997. American Helicopter Society Int. Conf., p.375-386.

[2] Bühlmann, P., Yu, B., 2003. Boosting with the L2-loss: regression and classification. J. Am. Stat. Assoc., 98:324-338.

[3] Csiszar, I., 1975. I-divergence geometry of probability distributions and minimization problems. Ann. Probab., 3:146-158.

[4] Freund, Y., Schapire, R., 1997. A decision-theoretic generalization of on-line learning and an application to boosting. J. Computer Syst. Sci., 55(1):119-139.

[5] Friedman, J.H., Hastie, T., Tibshirani, R., 2000. Additive logistic regression: a statistical view of boosting. Ann. Stat., 28:337-374.

[6] Harris, D., Corinna, C., 1996. Boosting decision trees. Adv. Neural Inf. Processing Syst., 8:479-485.

[7] Lienhart, R., Maydt, J., 2002. An Extended Set of Haar-like Features for Rapid Object Detection. Proc. IEEE Int. Conf. on Image Processing, 1:900-903.

[8] Saripalli, S., Montgomery, J.F., Sukhatme, G..S., 2002. Vision-based Autonomous Landing of an Unmanned Aerial Vehicle. IEEE Int. Conf. on Robotics and Automation, 3:2799-2804.

[9] Schapire, R.E., 1990. The strength of weak learnability. Matching Learning, 5(2):197-227.

[10] Schapire, F., Freund, Y., Schapire, R., 1996. Experiments with a New Boosting Algorithm. Proc. 13th Int. Conf., p.148-156.

[11] Schapire, R.E., Rochery, M., Rahim, M., Gupta, N., 2005. Boosting with prior knowledge for call classification. IEEE Trans. on Speech and Audio Processing, 13:174-181.

[12] Schwenk, H., Bengio, Y., 2000. Boosting neural networks. Neural Computation, 12(8):1869-1887.

[13] Sharp, C.S., Shakernia, O., Sastry, S.S., 2001. Vision System for Landing an Unmanned Aerial Vehicle, Robotics and Automation. IEEE Int. Conf. on Image Processing, 2:1720-1727.

[14] Viola, P., Jones, M., 2001. Rapid object detection using a boosted cascade of simple features. Computer Vision and Pattern Recognition, 1:511-518.

[15] Zhou, S.K., Georgescu, B., Zhou, X.S., Comaniciu, D., 2005. Image Based Regression Using Boosting Method. Proc. Tenth IEEE Int. Conf. on Computer Vision, 1:541-548.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - Journal of Zhejiang University-SCIENCE