A method of counting the number of fry using video data

Abstract

The invention relates to a method for counting the number of fish fry using video data, comprising the following steps: acquiring the image of the fry passing through the fishway through an image acquisition device; performing grayscale processing on each frame of the acquired image, and reducing the resolution; Binarize each frame of image so that there are only black pixels and white pixels on the image; extract the same N columns of pixel data from each frame of image; process the black pixels on each column of pixel data , determine the statistical pixels; compare the N column pixel data of the next frame image with the N column pixel data of the previous frame image row by row, if the pixel is changed from a white pixel to a black pixel, the statistical value of the fish fry will increase by 1, After comparing all images to get the final statistical value. The invention can quickly count the number of fry.

Description

technical field [0001] The invention relates to the application of image processing and analysis technology in the field of aquaculture, in particular to a method for counting the number of fry by using video data. Background technique [0002] The large-scale statistics of the number of fish fry in a certain water body is a problem often encountered in the aquatic industry. The statistics of the number and specification of fish fry will be involved in the aquatic application links such as feed delivery, transportation and sales, survival rate statistics, and breeding density control. Traditional fish fry testing methods include statistical methods such as reckoning method, bowl measurement method, and bay method, but these methods are not only complicated to operate, but also due to the uneven distribution of fry, the count value of these methods is often far from the actual number of fry, and there is an efficiency. Low, large error and other obvious shortcomings. Since t...

AI Technical Summary

Problems solved by technology

Traditional fish fry testing methods include statistical methods such as reckoning method, bowl measurement method, and bay method, but these methods are not only complicated to operate, but also due to the uneven distribution of fry, the count value of these methods is often far from the actual number of fry, and there is an efficiency. Obvious shortcomings such as low and large errors

Since the 1980s, some aquatic workers have begun to develop modern fry counting tools such as photoelectric fish counters and bridge fish counters, but these tools are not only expensive, but also easily affected by various factors such as the size of fish fry

Images