Live animal health detection method and system based on infrared temperature measurement and image recognition

Abstract

The invention provides a live animal health detection method and system based on infrared temperature measurement and image recognition, equipment and a medium. The method comprises: delimiting a detection area, and erecting a camera and an infrared temperature sensing tester in the detection area; collecting healthy and sick fur images of the live livestock, marking to obtain a hair data set, and training the hair data set to obtain a hair health condition detection model; collecting images of normal raising and abnormal sagging of a cattle head, marking to obtain a head sagging data set, and training the head sagging data set to obtain a head sagging condition detection model; calling a hair health condition detection model and a head sagging condition detection model to detect the position coordinates, the hair health condition and the head sagging condition of the live livestock in the current detection area in real time; and using an infrared temperature sensing tester for detecting the temperature in the position coordinate area of the live livestock, and then combining the temperature with the hair health condition and the head sagging condition to comprehensively judge the health state of the live livestock. According to the invention, the health degree of the live livestock can be efficiently and stably detected in real time.

Description

technical field [0001] The present invention relates to the fields of animal husbandry, image processing and recognition, in particular to a live animal health detection method, system, equipment and medium based on infrared temperature measurement and image recognition. Background technique [0002] The livestock breeding industry is a labor-intensive industry. In the existing technology, when the health of live animals needs to be tested, manual testing is generally used, and manual testing is time-consuming and laborious. Not only is the detection efficiency low, but it is also not easy to Find out all livestock with abnormal health. In addition, when manual inspection is used, it needs to rely on the personal experience of the operator, which leads to strong randomness in the health inspection of live animals, and it is impossible to guarantee that each live animal can achieve the same inspection level. Therefore, there is a need to provide a solution that can stably mo...

AI Technical Summary

Problems solved by technology

[0003] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide a live animal health detection method, system, equipment and medium based on infrared temperature measurement and image recognition, which is used to solve the problem of live animal health detection in the prior art. The problem of low manual detection efficiency and strong randomness

Images