Invention Grant
- Patent Title: Methods and systems for predicting flow of crowds from limited observations
-
Application No.: US15404296Application Date: 2017-01-12
-
Publication No.: US10210398B2Publication Date: 2019-02-19
- Inventor: Hassan Mansour , Mouhacine Benosman , Vahan Huroyan
- Applicant: Mitsubishi Electric Research Laboratories, Inc.
- Applicant Address: US MA Cambridge
- Assignee: Mitsubishi Electric Research Laboratories, Inc.
- Current Assignee: Mitsubishi Electric Research Laboratories, Inc.
- Current Assignee Address: US MA Cambridge
- Agent Gene Vinokur; James McAleenan; Hironori Tsukamoto
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G06T7/215 ; G06K9/62

Abstract:
Systems and methods for determining flows by acquiring a video of the flows with a camera, wherein the flows are pedestrians in a scene. The video includes a set of frames, wherein motion vectors are extracted from each frame in the set, and a data matrix is constructed from the motion vectors in the set of frames. A low rank Koopman operator can be determined from the data matrix and a spectrum of the low rank Koopman operator can be analyzed to determine a set of Koopman modes. Then, the frames are segmented into independent flows according to a clustering of the Koopman modes.
Public/Granted literature
- US20180197017A1 Methods and Systems for Predicting Flow of Crowds from Limited Observations Public/Granted day:2018-07-12
Information query