Non-contact side-lying cattle respiratory rate detection method and detection system based on RGB-D

By combining RGB-D depth data with computer vision technology and the AMPD algorithm to detect the respiratory rate of lying cattle, the problem of low efficiency in traditional detection methods has been solved, achieving efficient and accurate respiratory rate detection and reducing the impact of stress response and environmental interference.

CN122074949APending Publication Date: 2026-05-26NORTHEAST AGRICULTURAL UNIVERSITY
0 Cites 0 Cited by

Patent Information

Application Number
CN202610065226.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-01-19
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Traditional methods for detecting the respiratory rate of cattle are inefficient and cannot meet the needs of large-scale farms. Furthermore, existing non-contact methods are subject to interference factors in practical applications, resulting in low detection accuracy.

Method used

A non-contact detection method based on RGB-D is adopted. By using RGB-D depth data and computer vision technology, key parts of the side-lying cattle are located. The AMPD algorithm is combined to detect the depth value changes of key target areas in the abdomen, draw respiratory change curves and count peak values ​​to achieve respiratory rate detection.

Benefits of technology

It achieved efficient and accurate detection of cattle respiratory rate, with a determination coefficient R² of 0.94 between the detection results and manual observation, an average detection accuracy of 93.3%, and a root mean square error of 3.75 times/minute, reducing the impact of stress response and environmental interference.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to a non-contact side-lying cattle respiratory rate detection method and system based on RGB-D, and belongs to the technical field of computer vision cattle intelligent breeding. In order to solve the problems of low detection precision, harsh environmental requirements and the like during cattle respiratory rate detection at present, the method comprises the following steps: acquiring RGB-D video stream data of a side-lying cattle in a non-contact manner to obtain an RGB visible light video stream and a depth stream, positioning a key part of the side-lying cattle, and determining the respiratory rate of the side-lying cattle according to the RGB visible light video stream and the depth stream. The method comprises the following steps: acquiring an RGB visible light video stream, framing an abdomen key target area in combination with a key part, performing registration according to a position coordinate corresponding relation of the RGB visible light video stream and a depth video stream, acquiring an average depth value of the abdomen key target area, drawing a breathing change curve according to the change of the average depth value, and detecting and counting a peak value of the breathing change curve to obtain the number of times of breathing. The detection method is effective and reliable, and a new thought is provided for realizing non-contact intelligent cattle respiratory rate detection.
Need to check novelty before this filing date? Find Prior Art