Sample block-based image target counting method

Abstract

The invention provides a sample block-based image target counting method. The method comprises steps: image blocks with a fixed size are sequentially extracted from an input image through a sliding window; and then, according to the simple features and a similarity measurement function, the most similar K candidate image blocks are searched from a training set. Based on the K blocks, sparsity constraints are used, few samples for reconstruction are selected, and reconstruction weights corresponding to the samples are calculated. The weights are applied to a density map corresponding to the samples, an extracted image block corresponding density map is obtained, and the density map is placed at a corresponding position on an input image density map. The above process is repeated until all image blocks are extracted through the sliding window. Finally, all pixel values in the input image density map are accumulated to obtain the number of targets of interest. Compared with a mainstream method, the method of the invention has the advantages that the needed training images are few, the features are simple, the satisfactory accuracy can be achieved, the image resolution is robust, and the good counting accuracy can be kept even if the input image or a video stream has low resolution.

Description

technical field [0001] The invention relates to a method for counting image objects based on sample blocks (approximately sparsity-constrained example-based visual object counting, ASE-VOC), which belongs to the technical field of image processing. Background technique [0002] Image-based object counting methods are used to count the number of objects of interest in a single image or video stream. This is a counting technology that is highly demanded in real life. It can be used to count the number of cells in microscope images, the number of wild organisms, the number of pedestrians in streets or shopping malls, and it can also be used for traffic monitoring and crowd area activity analysis. [0003] The most traditional target counting method is to count the number by detecting the target. This method works poorly when the targets overlap a lot and the targets appear densely, so it is not practical. [0004] The existing mainstream object counting methods are divided in...

AI Technical Summary

Problems solved by technology

[0007] In order to solve the problem of accurate target counting using a small number of labeled samples, the present invention proposes an image target counting method based on sample blocks

Images