Improved AdaBoost Based Infrared Object Detection Algorithm

De Qin Shi; Wei Yang; Shu Ping Wang; Qin Ying Lin

doi:10.4028/www.scientific.net/AMM.490-491.1739

Paper Titles

Oil Supply Characteristic Test and Application of Fuel Injection Pump for Diesel Engine
p.1717

Parameter Identification and Attitude Control of Ducted Fan UAVs
p.1721

Identification of Physical Parameters in a Robotized IPC Device Interacting with Human
p.1729

An Optimized RFID Unidirectional Authentication Method
p.1734

Improved AdaBoost Based Infrared Object Detection Algorithm
p.1739

Modbus/TCP Communication Anomaly Detection Based on PSO-SVM
p.1745

Research of Fuzzy Neural Network in the Fault Diagnosis of Numerically-Controlled Machine Tool
p.1754

Identification of Critical Factors to System Performance Using Availability Modeling and Simulation Analysis
p.1759

Driving Control of a Powered Wheelchair by Voluntary Eye Blinking and with Environment Recognition
p.1764

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 490-491Improved AdaBoost Based Infrared Object Detection...

Improved AdaBoost Based Infrared Object Detection Algorithm

Abstract:

The traditional AdaBoost based object detection algorithm can get perfect performance for visible images, but not for infrared images because of the worse description of Haar features. In this paper, a novel infrared object detection algorithm based on improved AdaBoost with powerful histogram features is proposed. Firstly, HOG histogram with fourth grid area of image gradient is used for the input of classifiers. And then, AdaBoost with weighted FLD as weak classifiers is employed to select the multi-dimension features. Finally, the infrared object detection is realized by multi-scale sliding windows and non-maxima suppression algorithm. The experimental results demonstrate the better performance of the improved AdaBoost detection algorithm which can detect multi-scale infrared targets accurately.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 490-491)

Pages:

1739-1744

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.490-491.1739

Citation:

Cite this paper

Online since:

January 2014

Authors:

De Qin Shi, Wei Yang, Shu Ping Wang, Qin Ying Lin

Keywords:

Adaboost, HOG Features, Infrared Object Detection, Mult-Scale

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] G. R. Bradski, Computer Vision Face Tracking for Use in a Perceptual user Interface [A]. IEEE Workshop on Applications of Computer Vision [C]. Stoughton: 1998, 214-219.

DOI: 10.1109/acv.1998.732882

Google Scholar

[2] F. Pedro, P. Huttenlocher, Efficient Graph-Based Image Segmentation [J]. International Journal of Computer Vision, 2011, 59(2): 167-181.

Google Scholar

[3] A. Ruta, Y. Li and X. Liu, in: Real Time Traffic Sign Recognition from Video by Class-Specific Discriminative Features [J]. Pattern Recognition, 2010. 43(1): 416-430.

DOI: 10.1016/j.patcog.2009.05.018

Google Scholar

[4] F. Mokhatarian and A. K. Mackworth, in: A Theory of Multiscale, Curvature Based Shape Representation for Planar Curves [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(8): 789-805.

DOI: 10.1109/34.149591

Google Scholar

[5] Handoko, Y. Y.Y. Nazaruddin and H. Hu: Using Echo Ultrasound from Schooling Fish to Detect and Classify Fish Types [J]. Journal of Bionic Engineering, 2009. 6(3): 264-269.

DOI: 10.1016/s1672-6529(08)60120-1

Google Scholar

[6] P. Viola, J. C. Platt and C. Zhang: Multiple Instance Boosting for Object Detection[C]. Advances in Neural Information Processing Systems. Cambridge, 2006, XVIII: 1417-1424.

Google Scholar

[7] T. P. Ojala and D. M. Harwood. A Comparative Study of Texture Measures with Classfication based on Feature Distribution [J]. Pattern Recognition, 1996, 29(1): 51-59.

DOI: 10.1016/0031-3203(95)00067-4

Google Scholar

[8] J. Wang, G. Bebis, M. Nicolescu, and R. Miller, in: Improving Target Detection by Coupling It with Tracking [J]. Machine Vision and Applications, 2009, 20(4): 205-223.

DOI: 10.1007/s00138-007-0118-7

Google Scholar

[9] M. Hiromoto, H. Sugano and R. Miyamoto. Partially Parallel Architecture for AdaBoost-Based Detection with Haar-Like Features [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2009, 19(1): 41-52.

DOI: 10.1109/tcsvt.2008.2009253

Google Scholar