Counting Pedestrian with Mixed Features and Extreme Learning Machine

An approach for estimating the number of pedestrians is presented in this paper. The proposed counting framework combines two main pedestrian counting strategies—direct approach and indirect approach—by the use of mixed features and extreme learning machine (ELM). ELM is used to map mixed features to the number of pedestrians. Mixed features consist of holistic low-level features and rectangular local binary pattern (rLBP) features, and rLBP features are new features designed to describe the statistical and structural information of explicit pedestrian detection rectangles. Through mixed features, the information from both direct approach (rLBP features) and indirect approach (low-level features) is used in our algorithm, so we can take full advantage of two counting strategies. The detection rectangles are obtained by the use of the pedestrian detector described in paper “the fastest pedestrian detector in the west" (FPDW) by Dollár et al. Based on integral channel features and soft cascade classifier, FPDW is able to provide outstanding detection results at rapid speed. Experimental results on PETS 2009 datasets show that the proposed counting framework can improve counting accuracy significantly by the combination of two counting strategies. rLBP features are effective to describe the useful information of detection rectangles for regression models, and mixed features are more effective than either of both.

[1]  Visvanathan Ramesh,et al.  Fast Crowd Segmentation Using Shape Indexing , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[2]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[3]  Victor C. M. Leung,et al.  Extreme Learning Machines [Trends & Controversies] , 2013, IEEE Intelligent Systems.

[4]  Ramakant Nevatia,et al.  Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[5]  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).

[6]  Leslie G. Valiant,et al.  Cognitive computation , 1995, Proceedings of IEEE 36th Annual Foundations of Computer Science.

[7]  Nuno Vasconcelos,et al.  Analysis of Crowded Scenes using Holistic Properties , 2009 .

[8]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[9]  E. Cambria,et al.  Sentic Computing , 2015, Cognitive Computation.

[10]  Hongming Zhou,et al.  Extreme Learning Machines [Trends & Controversies] , 2013 .

[11]  Björn W. Schuller,et al.  Bidirectional LSTM Networks for Context-Sensitive Keyword Detection in a Cognitive Virtual Agent Framework , 2010, Cognitive Computation.

[12]  Hai Tao,et al.  Counting Pedestrians in Crowds Using Viewpoint Invariant Training , 2005, BMVC.

[13]  Pietro Perona,et al.  Integral Channel Features , 2009, BMVC.

[14]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[15]  Erik Cambria,et al.  Common Sense Knowledge for Handwritten Chinese Text Recognition , 2013, Cognitive Computation.

[16]  David A. McAllester,et al.  A discriminatively trained, multiscale, deformable part model , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  John M. Henderson,et al.  Clustering of Gaze During Dynamic Scene Viewing is Predicted by Motion , 2011, Cognitive Computation.

[18]  Ramakant Nevatia,et al.  Segmentation and Tracking of Multiple Humans in Crowded Environments , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Serge J. Belongie,et al.  Counting Crowded Moving Objects , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[20]  Pietro Perona,et al.  The Fastest Pedestrian Detector in the West , 2010, BMVC.

[21]  Jianming Zhao,et al.  Detect and Count Pedestrians in Real Time , 2014 .

[22]  Erik Cambria,et al.  Sentic Computing: Techniques, Tools, and Applications , 2012 .

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

[24]  Luc Van Gool,et al.  Coupled Detection and Trajectory Estimation for Multi-Object Tracking , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[25]  Bernt Schiele,et al.  Pedestrian detection in crowded scenes , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[26]  Ramakant Nevatia,et al.  Bayesian human segmentation in crowded situations , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[27]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..

[28]  Sheng-Fuu Lin,et al.  Estimation of number of people in crowded scenes using perspective transformation , 2001, IEEE Trans. Syst. Man Cybern. Part A.

[29]  Nuno Vasconcelos,et al.  Privacy preserving crowd monitoring: Counting people without people models or tracking , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[30]  Amaury Lendasse,et al.  Fast Face Recognition Via Sparse Coding and Extreme Learning Machine , 2013, Cognitive Computation.

[31]  Roberto Cipolla,et al.  Unsupervised Bayesian Detection of Independent Motion in Crowds , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[32]  Nikos Paragios,et al.  A MRF-based approach for real-time subway monitoring , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.