An Auto-adaptive CNN for Crowd Counting in Monitor Image

The crowd computing in video surveillance has been a challenging task in the field of computer vision because of such problems as extreme overlap of objects, scale changes, case size, scene view and so on. Many works have focused on the issue of the scale variation, and have achieved great progress. To solve this issue, this paper presents an auto-adaptive deep convolutional neural network for crowd counting based on density: 1) a classifier is used to judge the density of image patches which are divided by image; 2) a regressor is used to predict the number of persons in high-density image patches, and a detector is used to predict the number of crowd in low-density image patches; and 3) we get the crowd counting of an image by adding up all the image patches of different level density. To achieve further improvement from more and better data, we introduce PlayGround Crowd Dataset, a new set of person annotations on top of the playground dataset.

[1]  Shaogang Gong,et al.  Crowd Counting and Profiling: Methodology and Evaluation , 2013, Modeling, Simulation and Visual Analysis of Crowds.

[2]  Xiaogang Wang,et al.  Cross-scene crowd counting via deep convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Andrew Y. Ng,et al.  End-to-End People Detection in Crowded Scenes , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Alan Fern,et al.  Person count localization in videos from noisy foreground and detections , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Liang Lin,et al.  Is Faster R-CNN Doing Well for Pedestrian Detection? , 2016, ECCV.

[7]  Bingbing Ni,et al.  Crowded Scene Analysis: A Survey , 2015, IEEE Transactions on Circuits and Systems for Video Technology.

[8]  Vishal M. Patel,et al.  A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation , 2017, Pattern Recognit. Lett..

[9]  Shenghua Gao,et al.  Single-Image Crowd Counting via Multi-Column Convolutional Neural Network , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Shiv Surya,et al.  Switching Convolutional Neural Network for Crowd Counting , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[12]  Daniel Oñoro-Rubio,et al.  Towards Perspective-Free Object Counting with Deep Learning , 2016, ECCV.

[13]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.