Pedestrian Counting System Based on Multiple Object Detection and Tracking

With the increasing demands on video surveillance and business promotion, effective pedestrian counting in surveillance environments has become a hot research topic in computer vision. In this paper, we implement a pedestrian counting system based on multiple object detection and tracking. Region proposal network (RPN) and Real Adaboost classifier are employed to train a head-shoulder detector with high accuracy. We utilize the DSST algorithm to track the position transformations and the size changes of pedestrians. By combining human detection with object tracking together and using detection results to optimize the tracking algorithm, the pedestrian counting system is developed with high robustness against occlusions. We evaluated the system on the videos recorded in the subway station. The results showed that our system achieves a high accuracy and can be used for pedestrian counting in crowded public places.

[1]  Xiaogang Wang,et al.  Visual Tracking with Fully Convolutional Networks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[2]  Michael Felsberg,et al.  Accurate Scale Estimation for Robust Visual Tracking , 2014, BMVC.

[3]  Dorin Comaniciu,et al.  Real-time tracking of non-rigid objects using mean shift , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[4]  Joon Hee Han,et al.  Local Decorrelation For Improved Pedestrian Detection , 2014, NIPS.

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

[6]  Bernt Schiele,et al.  Ten Years of Pedestrian Detection, What Have We Learned? , 2014, ECCV Workshops.

[7]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[8]  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.

[9]  Bernt Schiele,et al.  Filtered channel features for pedestrian detection , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Pietro Perona,et al.  Fast Feature Pyramids for Object Detection , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Liqing Zhang,et al.  Real Time Crowd Counting with Human Detection and Human Tracking , 2014, ICONIP.

[12]  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).

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

[14]  Bruce A. Draper,et al.  Visual object tracking using adaptive correlation filters , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.