Vision-based people motion analysis

We have developed a vision-based method for analyzing people motion. The following video is an example of pedestrian motion prediction. The method is based on kriging, which is a statistical spatial interpolation method.

The following video is an example of people flow estimation by kriging. The people flow is visualized with a color-cording technique.

• Ryosuke NAKAISHI, Kazuhiko KAWAMOTO, Data Assimilation for Pedestrian Tracking Using Deep Convolutional Neural Network, In Proc. 5th IWACIII, 5 pages, 2017.
• Kazuhiko Kawamoto, Yoshiyuki Tomura, Kazushi Okamoto, Kriging-based prediction and interpolation for modeling pedestrian dynamics, Proc. IFSA&SCIS , pp.1-4, 2017.
• Kazuhiko Kawamoto, Yoshiyuki Tomura, Kazushi OKAMOTO, Learning pedestrian dynamics with kriging, In Proc. 15th IEEE/ACIS International Conference on Computer and Information Science, pp.39-42, 2016
• Kazuhiko Kawamoto, Yoshiyuki Tomura, Kazushi Okamoto, Pedestrian-movement prediction by kriging, In Proc. 4th IWACIII, pp.94-97, 2015.