Pedestrian Detection Based on Multi-Stage Unsupervised Learning

Yuan Yin; Min Jiang Liao; Xiao Lin Li

doi:10.4028/www.scientific.net/AMM.687-691.957

Paper Titles

Monitoring the Travel Characteristics of High Voltage Circuit Breaker Based on TLD
p.938

Design and Application of the Serial Port Communication Module Based on New LED Solar Cell Testing System
p.942

Measurement of Cr(VI) Based on Absorption Spectrum through Plastic Fiber
p.948

The Method Based on BP Neural Network of Pile Foundation Defect Detection
p.952

Pedestrian Detection Based on Multi-Stage Unsupervised Learning
p.957

Algorithm Design of 3D Measurement System Based on FPGA
p.961

Multi-Threaded Technology Apply in Real Time Measurement System of Dual-Camera
p.966

A Real-Time Monitoring and Certification System for Logistics
p.970

Measuring Real-Time Physiological Changes by near Infrared Spectroscopy
p.974

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 687-691Pedestrian Detection Based on Multi-Stage...

Pedestrian Detection Based on Multi-Stage Unsupervised Learning

Abstract:

In order to implement effective detection and utilize large numbers of unlabeled samples,a pedestrian detection method based on Unsupervised learning was presented.We apply deep learning to human detection to acquire pedestrian features with unlabeled data set.The detection method uses unsupervised convolution sparse auto-encoders to train features at all levels from the data set,then trains classifier with end-to-end supervised method.Additionally,we fine-tune the features in a supervised way.Experiments show that the method approach an state-of-art result on all data set.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 687-691)

Pages:

957-960

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.687-691.957

Citation:

Cite this paper

Online since:

November 2014

Authors:

Yuan Yin*, Min Jiang Liao, Xiao Lin Li

Keywords:

Nonlinear Transform, Non-Maximum Suppression, Pedestrian Detection, Sparse Coding, Unsupervised Learning

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Enzweiler M, Gavrila D M. Monocular pedestrian detection: Survey and experiments[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2009, 31(12): 2179-2195.

DOI: 10.1109/tpami.2008.260

Google Scholar

[2] Vázquez D, López A M, Ponsa D. Unsupervised domain adaptation of virtual and real worlds for pedestrian detection[C]/Pattern Recognition (ICPR), 2012 21st International Conference on. IEEE, 2012: 3492-3495.

Google Scholar

[3] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.

DOI: 10.1126/science.1127647

Google Scholar

[4] Kavukcuoglu K, Sermanet P, Boureau Y L, et al. Learning convolutional feature hierarchies for visual recognition[C]/Advances in neural information processing systems. 2010: 1090-1098.

Google Scholar

[5] Lee H, Battle A, Raina R, et al. Efficient sparse coding algorithms[C]/Advances in neural information processing systems. 2006: 801-808.

DOI: 10.7551/mitpress/7503.003.0105

Google Scholar

[6] Beck A, Teboulle M. A fast iterative shrinkage-thresholding algorithm for linear inverse problems[J]. SIAM Journal on Imaging Sciences, 2009, 2(1): 183-202.

DOI: 10.1137/080716542

Google Scholar

[7] Lee H, Grosse R, Ranganath R, et al. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations[C]/Proceedings of the 26th Annual International Conference on Machine Learning. ACM, 2009: 609-616.

DOI: 10.1145/1553374.1553453

Google Scholar