Home > Uncategorized > Measuring Crowd Collectiveness

Measuring Crowd Collectiveness

As we know that crowds in nature have a variety of scales, shapes, and dynamics. To quantitatively analyze the dynamic properties of crowd, we need to have a general descriptor that could measure the level of collective motions in crowd.

The simple and naive measure is the average velocity of the whole crowd, but we found that this measure is sensitive to noise and the global shapes of the crowd movement. Like these crowds in the following Figure, if the crowd move globally in a C shape, the average velocity would be very small, but in fact the ‘collectiveness’ of the crowd is high.


In recent work of Zhou et al (CVPR2013 oral, TPAMI2014) , a new descriptor of crowd called Collectiveness is proposed. This descriptor utilizes the graph connectivity of individuals in the neighborhood to build a global indicator to measure the collective level of crowd motions. As shown below,  crowd movement could be accurately estimated and quantified into different dynamic categories.

crowd_img1Besides, there are a lot of applications based on this general descriptor, such as monitoring crowd dynamics in videos, detecting collective motions in time-series data, and generating collective map of scenes. Just check the TPAMI journal paper of this work.



  • Bolei Zhou, Xiaoou Tang, and Xiaogang Wang. “Measuring Crowd Collectiveness.” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2013, oral paper)
  • Bolei Zhou, Xiaoou Tang, Hepeng Zhang, and Xiaogang Wang. “Measuring Crowd Collectiveness.” The IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI, regular paper)


Categories: Uncategorized
  1. January 17, 2014 at 12:37 pm

    Interesting. I wonder what level of density human crowds need to have before this can be used. Anything too low and people can just keep coordinated by speaking. Maybe at a hundred or so the motion effects would take over and Collectiveness would become a useful tool.

    • January 17, 2014 at 4:00 pm

      Hi Greg, thanks for the comments. Yes, this descriptor works when the density of crowd is high enough. BTW, I checked your work on tiltor, it is interesting and related to this blog. Would like to write a introduction article about your idea and work on crowd behavior so that I could publish it in this blog?

  2. January 29, 2014 at 7:25 pm

    Hi Bolei! So sorry for the long overdue reply. I would love to talk with you about Tiltor and anything else you are writing about. Please email whenever is most convenient for you. Thanks,

  1. No trackbacks yet.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: