Animal weight measuring method and device based on image detection, equipment and medium

Abstract

The invention relates to artificial intelligence, and discloses an animal weight measurement method, device, equipment and medium based on image detection, and the method comprises the steps: selecting a checkerboard with a set specification as a calibration object; placing a calibration object in the middle of the position under the animal to be measured, and obtaining an image of the animal to be measured and the calibration object as a whole; detecting a to-be-detected animal in the image, and correcting the scale of the to-be-detected animal according to the checkerboard to obtain an imageonly comprising the to-be-detected animal; and inputting the image only including the to-be-detected animal into the weight estimation model, classifying the to-be-detected animal according to the weight categories through the weight estimation model, obtaining the probability that the to-be-detected animal belongs to each weight category, and calculating the weight of the to-be-detected animal according to the probability that the to-be-detected animal belongs to each weight category. The method is convenient to operate, does not depend on equipment, is controllable in error, and can improvethe efficiency of animal weight measurement.

Description

technical field [0001] The invention relates to artificial intelligence, in particular to a method, device, electronic equipment and computer-readable storage medium for measuring animal body weight based on image detection. Background technique [0002] With the growth of population and the continuous improvement of living standards, the demand for pork from urban and rural residents is increasing, and the market size of the pig breeding industry exceeds one trillion yuan. In recent years, with the rapid development of deep learning technology, more and more companies have applied AI technology to the pig breeding industry. At present, the weight of live pigs is mainly measured in the following ways: first, the empirical formula is used to measure the weight, which needs to measure many indicators of the pig, such as body height, chest depth, side body length, etc., and then use the formula to calculate the weight. Obviously, it is difficult to obtain this information in a...

AI Technical Summary

Problems solved by technology

Obviously, it is difficult to obtain this information in actual production, the operation is inconvenient, and the accuracy is not high; second, most vision-based projection ranging solutions need to calibrate the camera, fix the camera position, and collect multiple photos, which is not user-friendly; 3. Use sensors that obtain depth information to calculate point cloud data, obtain volume information, and calculate body weight. This solution requires additional expensive equipment

What is more critical is that the pigs that are paid for by insurance are generally dead pigs. It is difficult to move the pigs, and it is difficult to obtain the three-dimensional information of the pigs.

Images