Synthetic Data Generation for Deep Learning in Counting Pedestrians

One of the main limitations of the application of Deep Learning (DL) algorithms is when dealing with problems with small data. One workaround to this issue is the use of synthetic data generators. In this framework, we explore the benefits of synthetic data generation as a surrogate for the lack of large data when applying DL algorithms. In this paper, we propose a problem of learning to count the number of pedestrians using synthetic images as a substitute for real images. To this end, we introduce an algorithm to create synthetic images for being fed to a designed Deep Convolutional Neural Network (DCNN) to learn from. The model is capable of accurately counting the number of individuals in a real scene.

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

[2]  S. Subramanian,et al.  Height of Nations: A Socioeconomic Analysis of Cohort Differences and Patterns among Women in 54 Low- to Middle-Income Countries , 2011, PloS one.

[3]  Hyun Ah Song,et al.  Hierarchical Representation Using NMF , 2013, ICONIP.

[4]  Dario Maio,et al.  Synthetic fingerprint-image generation , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[5]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

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

[7]  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.

[8]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  A. Marana,et al.  On the efficacy of texture analysis for crowd monitoring , 1998, Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237).

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

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

[13]  Kate Smith-Miles,et al.  A Comprehensive Survey of Data Mining-based Fraud Detection Research , 2010, ArXiv.

[14]  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.

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  Nuno Vasconcelos,et al.  Anomaly detection in crowded scenes , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  G. Griffin,et al.  Caltech-256 Object Category Dataset , 2007 .

[18]  Jordi Vitrià,et al.  Learning to count with deep object features , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[19]  Christian Eggert,et al.  On the Benefit of Synthetic Data for Company Logo Detection , 2015, ACM Multimedia.

[20]  姚雯,et al.  Synthetic healthcare data generation , 2013 .