Method and device for calculating number and moving direction of pedestrians

摘要

A method for calculating the number and moving direction of pedestrians is provided. in which feature points of a current frame image are extracted; the feature points of the current frame image are compared with those of a selected historical frame image, to obtain moving feature points of the current frame image; directional weighted counting is performed on the moving feature points of the current frame image to obtain the moving direction of the pedestrians; and edge points of pedestrian images are extracted from a foreground image of the current frame image, and performing joint weighted counting on the edge points of the pedestrian images and the moving feature points of the current frame image according to correction coefficients of locations of the respective points, to obtain the number of the pedestrians. A device for calculating the number and moving direction of pedestrians is also provided.

主权项

1. A method for calculating a number and moving direction of pedestrians, comprising:
step A: extracting feature points of a current frame image; step B: comparing the feature points of the current frame image with those of a selected historical frame image, to obtain moving feature points of the current frame image; and step C: performing directional weighted counting on the moving feature points of the current frame image to obtain the moving direction of the pedestrians, wherein the step of comparing the feature points of the current frame image with those of the selected historical frame image to obtain the moving feature points of the current frame image comprises: step a: extracting each of the feature points of the current frame image; step b: selecting, around the feature points, template images; step c: selecting, from the selected historical frame image around locations corresponding to the feature points of the current frame image, search images; step d: searching the search images by virtue of the template images for points matched with the feature points; step e: judging a location relation between each feature point and its matched point; and step f: when a distance between the feature point and the matched point is greater than a set threshold, determining that the feature point of the current frame image is a moving feature point; and repeating the steps e and f until all the moving feature points in the current frame image and their moving directions are obtained.