Apparatus and method for analyzing people flows in image
AssigneeCanon Kabushiki Kaisha
InventorsYasuo Bamba, Kotaro Yano
Life of this patent
Estimating the term…
Abstract
An image processing apparatus includes: an acquisition unit that acquires movement vectors of a crowd for each area of an image; a generation unit that generates people-flow clusters based on the movement vectors acquired by the acquisition unit; a classification unit that classifies the people-flow clusters generated by the generation unit into normal people-flow clusters and abnormal people-flow clusters; and a display unit that displays, in a visually distinguishable manner, the normal people-flow clusters and the abnormal people-flow clusters as superimposed on the image.
Claims20
An image processing apparatus comprising:
- an acquisition unit configured to acquire movement vectors of a crowd for each area of an image;
- a generation unit configured to generate people-flow clusters based on the movement vectors acquired by the acquisition unit;
- a classification unit configured to classify the people-flow clusters generated by the generation unit into normal people-flow clusters and abnormal people-flow clusters;
- and
- a display unit configured to display, in a visually distinguishable manner, the normal people-flow clusters and the abnormal people-flow clusters as superimposed on the image.
An image processing apparatus comprising:
- an acquisition unit configured to acquire movement vectors of a crowd for each area of an image;
- a generation unit configured to generate people-flow clusters based on the movement vectors acquired by the acquisition unit;
- an abnormality degree acquisition unit configured to acquire the degree of abnormality of each people-flow cluster generated by the generation unit;
- and
- a display unit configured to display, in a visually distinguishable manner, the degree of abnormality of the people-flow cluster as superimposed on the image.
An image processing apparatus comprising:
- an acquisition unit configured to acquire movement vectors of a crowd for each area of an image;
- a generation unit configured to generate people-flow clusters based on the movement vectors acquired by the acquisition unit;
- a classification unit configured to classify the people-flow clusters generated by the generation unit into normal people-flow clusters and abnormal people-flow clusters;
- and
- a notification unit configured to provide notification of occurrence of an abnormal people-flow cluster in a case where a people-flow cluster generated by the generation unit is classified as an abnormal people-flow cluster by the classification unit.
A method for image processing, comprising:
- acquiring movement vectors of a crowd for each area of an image;
- generating people-flow clusters based on the acquired movement vectors;
- classifying the generated people-flow clusters into normal people-flow clusters and abnormal people-flow clusters;
- and
- displaying, in a visually distinguishable manner, the normal people-flow clusters and the abnormal people-flow clusters as superimposed on the image.
A method for image processing, comprising:
- acquiring movement vectors of a crowd for each area of an image;
- generating people-flow clusters based on the acquired movement vectors;
- acquiring the degree of abnormality of each generated people-flow cluster;
- and
- displaying, in a visually distinguishable manner, the degree of abnormality of the people-flow cluster as superimposed on the image.
A method for image processing, comprising:
- acquiring movement vectors of a crowd for each area of an image;
- generating people-flow clusters based on the acquired movement vectors;
- classifying the generated people-flow clusters into normal people-flow clusters and abnormal people-flow clusters;
- and
- providing notification of occurrence of an abnormal people-flow cluster in a case where a generated people-flow cluster is classified as an abnormal people-flow cluster.
A non-transitory computer-readable recording medium having stored thereon a program for causing a computer to function, in an image processing apparatus, as:
- an acquisition unit configured to acquire movement vectors of a crowd for each area of an image;
- a generation unit configured to generate people-flow clusters based on the movement vectors acquired by the acquisition unit;
- a classification unit configured to classify the people-flow clusters generated by the generation unit into normal people-flow clusters and abnormal people-flow clusters;
- and
- a display unit configured to display, in a visually distinguishable manner, the normal people-flow clusters and the abnormal people-flow clusters as superimposed on the image.
Dependencies are inferred from the claim text.