Pregnancy detection method and device based on artificial intelligence, computer equipment and medium

Abstract

The invention relates to a pregnancy detection method and device based on artificial intelligence, computer equipment and a storage medium. By adopting the pregnancy detection method, the livestock pregnancy detection time can be shortened, the pregnancy detection accuracy is improved, and the pregnancy detection efficiency is improved. The pregnancy detection method comprises the following steps:acquiring a to-be-detected video stream of a preset part of livestock, inputting the to-be-detected video stream into a pre-constructed pregnancy state classification model, so that the pregnancy state classification model outputs probability values corresponding to different pregnancy states based on the to-be-detected video stream, wherein the pregnancy state classification model adopts a neural network model based on a time sequence; and determining a pregnancy test result of the livestock according to the relative sizes of the probability values corresponding to the different pregnancy states.

Description

technical field [0001] The present application relates to the technical field of pregnancy image detection, in particular to an artificial intelligence-based pregnancy detection method, device, computer equipment and storage medium. Background technique [0002] In the field of livestock breeding, in order to improve production efficiency and ensure the healthy production of livestock, it is necessary to carry out pregnancy detection on livestock. The current livestock pregnancy inspection requires B-ultrasound images of the gestational sac to be collected after the animal’s pregnancy reaches a certain stage, and then the gestational sac is identified manually. Taking sows as an example, generally sows need to be at least 28 days old after pregnancy. At this time, the B-ultrasound image collected can be recognized by the human eye to identify the shape of the gestational sac. For livestock with a small gestational age, because there is no particularly obvious shape of the g...

AI Technical Summary

Problems solved by technology

For livestock with a small gestational age, because there is no particularly obvious shape of the gestational sac on the B-ultrasound image of the pregnancy test, it is difficult for the human eye to distinguish whether the livestock is pregnant or not as soon as possible, which in turn affects the feeding strategy of the farm and reduces the production efficiency.

Images