publication . Conference object . Preprint . 2018

Crowd Counting via Scale-Adaptive Convolutional Neural Network

Zhang, Lu; Shi, Miaojing; Chen, Qiaobo;
Open Access English
  • Published: 12 Mar 2018
  • Publisher: IEEE
Abstract
International audience; The task of crowd counting is to automatically estimate the pedestrian number in crowd images. To cope with the scale and perspective changes that commonly exist in crowd images, state-of-the-art approaches employ multi-column CNN architectures to regress density maps of crowd images. Multiple columns have different receptive fields corresponding to pedestrians (heads) of different scales. We instead propose a scale-adaptive CNN (SaCNN) architecture with a backbone of fixed small receptive fields. We extract feature maps from multiple layers and adapt them to have the same output size; we combine them to produce the final density map. The...
Subjects
free text keywords: [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Computer Science - Computer Vision and Pattern Recognition
35 references, page 1 of 3

[1] L. Boominathan, S. S. Kruthiventi, and R. V. Babu. Crowdnet: a deep convolutional network for dense crowd counting. In ACM MM, 2016. 1, 2, 3, 4, 5, 6, 7

[2] G. J. Brostow and R. Cipolla. Unsupervised bayesian detection of independent motion in crowds. In CVPR, 2006. 2

[3] A. B. Chan, Z.-S. J. Liang, and N. Vasconcelos. Privacy preserving crowd monitoring: Counting people without people models or tracking. In CVPR, 2008. 1, 2

[4] A. B. Chan and N. Vasconcelos. Bayesian poisson regression for crowd counting. In ICCV, 2009. 1, 2

[5] K. Chen, C. C. Loy, S. Gong, and T. Xiang. Feature mining for localised crowd counting. In BMVC, 2012. 2

[6] D. Ciregan, U. Meier, and J. Schmidhuber. Multi-column deep neural networks for image classification. In CVPR, 2012. 2

[7] W. Ge and R. T. Collins. Marked point processes for crowd counting. In CVPR, 2009. 1

[8] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In CVPR, pages 770-778, 2016.

[9] H. Idrees, I. Saleemi, C. Seibert, and M. Shah. Multi-source multi-scale counting in extremely dense crowd images. In CVPR, 2013. 1, 2, 4, 6, 7

[10] H. Idrees, K. Soomro, and M. Shah. Detecting humans in dense crowds using locally-consistent scale prior and global occlusion reasoning. TPAMI, 37(10):1986-1998, 2015. 1

[11] D. Kong, D. Gray, and H. Tao. Counting pedestrians in crowds using viewpoint invariant training. In BMVC, 2005. 2

[12] V. Lempitsky and A. Zisserman. Learning to count objects in images. In NIPS, 2010. 2, 6, 7

[13] M. Li, Z. Zhang, K. Huang, and T. Tan. Estimating the number of people in crowded scenes by mid based foreground segmentation and head-shoulder detection. In ICPR, 2008. 1

[14] T.-Y. Lin, P. Dolla´r, R. Girshick, K. He, B. Hariharan, and S. Belongie. Feature pyramid networks for object detection. 2017. 2

[15] T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dolla´r, and C. L. Zitnick. Microsoft coco: Common objects in context. In ECCV. 7

35 references, page 1 of 3
Abstract
International audience; The task of crowd counting is to automatically estimate the pedestrian number in crowd images. To cope with the scale and perspective changes that commonly exist in crowd images, state-of-the-art approaches employ multi-column CNN architectures to regress density maps of crowd images. Multiple columns have different receptive fields corresponding to pedestrians (heads) of different scales. We instead propose a scale-adaptive CNN (SaCNN) architecture with a backbone of fixed small receptive fields. We extract feature maps from multiple layers and adapt them to have the same output size; we combine them to produce the final density map. The...
Subjects
free text keywords: [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Computer Science - Computer Vision and Pattern Recognition
35 references, page 1 of 3

[1] L. Boominathan, S. S. Kruthiventi, and R. V. Babu. Crowdnet: a deep convolutional network for dense crowd counting. In ACM MM, 2016. 1, 2, 3, 4, 5, 6, 7

[2] G. J. Brostow and R. Cipolla. Unsupervised bayesian detection of independent motion in crowds. In CVPR, 2006. 2

[3] A. B. Chan, Z.-S. J. Liang, and N. Vasconcelos. Privacy preserving crowd monitoring: Counting people without people models or tracking. In CVPR, 2008. 1, 2

[4] A. B. Chan and N. Vasconcelos. Bayesian poisson regression for crowd counting. In ICCV, 2009. 1, 2

[5] K. Chen, C. C. Loy, S. Gong, and T. Xiang. Feature mining for localised crowd counting. In BMVC, 2012. 2

[6] D. Ciregan, U. Meier, and J. Schmidhuber. Multi-column deep neural networks for image classification. In CVPR, 2012. 2

[7] W. Ge and R. T. Collins. Marked point processes for crowd counting. In CVPR, 2009. 1

[8] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In CVPR, pages 770-778, 2016.

[9] H. Idrees, I. Saleemi, C. Seibert, and M. Shah. Multi-source multi-scale counting in extremely dense crowd images. In CVPR, 2013. 1, 2, 4, 6, 7

[10] H. Idrees, K. Soomro, and M. Shah. Detecting humans in dense crowds using locally-consistent scale prior and global occlusion reasoning. TPAMI, 37(10):1986-1998, 2015. 1

[11] D. Kong, D. Gray, and H. Tao. Counting pedestrians in crowds using viewpoint invariant training. In BMVC, 2005. 2

[12] V. Lempitsky and A. Zisserman. Learning to count objects in images. In NIPS, 2010. 2, 6, 7

[13] M. Li, Z. Zhang, K. Huang, and T. Tan. Estimating the number of people in crowded scenes by mid based foreground segmentation and head-shoulder detection. In ICPR, 2008. 1

[14] T.-Y. Lin, P. Dolla´r, R. Girshick, K. He, B. Hariharan, and S. Belongie. Feature pyramid networks for object detection. 2017. 2

[15] T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dolla´r, and C. L. Zitnick. Microsoft coco: Common objects in context. In ECCV. 7

35 references, page 1 of 3
Powered by OpenAIRE Open Research Graph
Any information missing or wrong?Report an Issue
publication . Conference object . Preprint . 2018

Crowd Counting via Scale-Adaptive Convolutional Neural Network

Zhang, Lu; Shi, Miaojing; Chen, Qiaobo;