An effective approach to pedestrian detection in thermal imagery

In this paper, an integrated algorithm to detect humans in thermal imagery was introduced. In recent years, histogram of oriented gradient (HOG) is a quite popular algorithm for person detection in visible imagery. We implement the pedestrian detection in infrared imagery with this algorithm by adjusting the parameters. Simultaneously, we have increased some other geometric characteristics, such as mean contrast, which is used as features for the detection. After analyzing the property of the infrared imagery, which is designed to meet the shortfall of the HOG in infrared imagery, the combined vectors are fed to a linear SVM for object/non-object classification and we get the detector at the same time. After that, the detection window is scanned across the image at multiple positions and scales, which is followed by the combination of the overlapping detections. At last, a pedestrian is described by a final detection, and we have detected the pedestrians in the thermal imagery. Experimental results with OSU Thermal Pedestrian Database are reported to demonstrate the excellent performance of our algorithms.

[1]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[2]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[3]  Bruce N. Nelson,et al.  Automatic vehicle detection in infrared imagery using a fuzzy inference-based classification system , 2001, IEEE Trans. Fuzzy Syst..

[4]  Tomaso A. Poggio,et al.  Pedestrian detection using wavelet templates , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Hironobu Fujiyoshi,et al.  Moving target classification and tracking from real-time video , 1998, Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201).

[6]  Qing Jun Wang,et al.  LPP-HOG: A New Local Image Descriptor for Fast Human Detection , 2008, 2008 IEEE International Symposium on Knowledge Acquisition and Modeling Workshop.

[7]  Curt H. Davis,et al.  Vector-guided vehicle detection from high-resolution satellite imagery , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[8]  Cordelia Schmid,et al.  Human Detection Based on a Probabilistic Assembly of Robust Part Detectors , 2004, ECCV.

[9]  Pietro Perona,et al.  Pedestrian detection: A benchmark , 2009, CVPR.

[10]  Paul A. Viola,et al.  Detecting Pedestrians Using Patterns of Motion and Appearance , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[11]  Alexei A. Efros,et al.  Unbiased look at dataset bias , 2011, CVPR 2011.

[12]  James W. Davis,et al.  A Two-Stage Template Approach to Person Detection in Thermal Imagery , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.

[13]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[14]  Mei-Chen Yeh,et al.  Fast Human Detection Using a Cascade of Histograms of Oriented Gradients , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).