CAD (computer-aided design) people counting method based on FAST (features from accelerated segment test)

Abstract

The invention discloses a CAD (computer-aided design) people counting method based on FAST (features from accelerated segment test), and belongs to the field of computer vision-based people counting. The method is characterized in that after a crowd surveillance video image is subjected to filtering preprocessing, an FAST corner feature vector of a current image is obtained through a corner detection algorithm; a low-density crowd image and a high-density crowd image is divided according to the ratio of the number of feature points and the sum of pixels of the current crowd image, and foreground images of the low-density crowd image and the high-density crowd image are extracted; as for the foreground image of the low-density crowd image, the connected domain area T obtained through an erosion algorithm is taken as an FAST point, and as for the foreground image of the high-density crowd image, a neighbor domain is established for the core point of each pixel through an OPTiCS algorithm, then, the minimum reach distance from the core point of each neighbor domain to each pixel is taken as the minimum reach distance in each neighbor domain, and an FAST point vector X of the high-density crowd is constructed accordingly; a crowd evaluation model is constructed according to T, X and the distance D between a camera and the crowd; and a set training sample is taken as a test vector for performing SVM (support vector machine) training, so that the counting speed and the accuracy rate are increased.

Description

technical field [0001] The invention relates to people counting in the field of computer vision. Background technique [0002] Current people counting methods can be divided into three main categories: [0003] Type 1 methods use a statistical method to estimate the number of people in an area. This type of method usually associates the pixels or other features of the motion area with the specific number of people in the area, and then trains a function to estimate the number of people in the motion area. For example, Kim et al. and Lee et al. used the underlying features - foreground pixel accumulation and motion vectors to count the number of people, the pixel accumulation sum is associated with the number of people, and the motion vector is used to distinguish two directions, using simpler features to count kernel function. And Chan et al. further use multiple features to train the regression function. The features used can be divided into two categories: region-relat...

AI Technical Summary

Problems solved by technology

The advantage of this segmentation method is that it is simple and fast, but its disadvantages are also obvious. In the case of relatively dense crowds, the reliability of the results obtained is not high; methods based on template matching, such as hierarchical matching based on contours by Gavrila et al. Algorithm, in order to solve the problem of pedestrian posture, construct nearly 2500 contour templates to match pedestrians, adopt the matching strategy from coarse to fine to improve the speed; the method based on statistical classification obtains a classifier by learning the training data, and detects into a classification problem

Images