Fry counting device and method based on machine vision detection and tracking

Abstract

The invention relates to the technology of fishery breeding equipment, and aims to provide a fry counting device and method based on machine vision detection and tracking. The device comprises a camera device used for collecting and analyzing pictures or video data and a computer terminal, and a lens of the camera device is aligned with an observation cabin through which fries pass; the fry separation module, the observation cabin and the fish collection container are sequentially connected through water pipes, and the space between a conical funnel and an angle adjusting valve is divided into continuous spiral channels through an annular partition plate in the fry separation module. The device can automatically disperse fish fries, effectively avoids accumulation and adhesion of the fish fries, reduces the fish fry detection and tracking difficulty, and effectively guarantees the counting precision; meanwhile, the observation cabin isolates external light source interference, the bottom of the square tube is white, continuous shooting, detection, tracking and counting are achieved, and the counting efficiency is improved; by continuously detecting and tracking the fry, the influence of fry migration on the counting precision is eliminated, and the counting precision is effectively improved.

Description

technical field [0001] The invention relates to the technical field of fish farming equipment, in particular to a fry counting device and method based on machine vision detection and tracking. Background technique [0002] With the proposal of "smart fishery", my country's fish farming will also pay more attention to the level of mechanization, intelligence and informatization. Accurately estimating the number of fry is an important topic in mechanized and intelligent fish farming, and it is the basic guarantee for scientific baiting, fry survival rate assessment, breeding density control, fry sales and purchase, and other standardized and scientific management. Traditional counting methods mostly use manual estimation, such as weighing estimation, which is not only time-consuming, laborious, and has an error of 15-25%, but also easily causes physical damage and survival pressure to fry, reducing the survival rate of fry. Fishery and metering professionals at home and abroa...

AI Technical Summary

Problems solved by technology

[0004] The application publication number CN110766123A discloses a fry counting system and a fry counting method. An output port is provided at the bottom of the fry water tank to be tested for a plurality of fry to enter the one-way waterway, and images are collected and counted in the one-way waterway, but in actual During the operation, the fish fry swim randomly and like countercurrent, and they may not necessarily enter the one-way channel, which will affect the counting efficiency

Moreover, the size of the one-way waterway is fixed, and the size of the adapted fry is limited

[0005] Application publication number CN110973036A discloses a machine vision-based fry counting device and method, which counts fry in batches through a revolving door, but does not consider the problems of sticking and accumulation of fry in the counting area, making the number of counts smaller than the real number

Images