Authors

Abstract

Individual pig recognition is an essential step for accurate breeding and intelligent management of pigs. To realize individual pig identification, applicable dataset of pigs needs to be built. For pigs’ behavior is difficult to control, the data acquisition is of great difficulty and low efficiency. In addition, few reports on pig face detection are there at home and abroad, thus, face data acquisition faces more difficulty. In this study, double open mv3 digital cameras were adopted, and the approach of starting the pig face acquisition program by acquiring pig figure with a vertical camera to calculate the slope of their back before sending a signal to the horizontal camera was adopted. The image brightness was calculated based on RGB function: when the value was less than 90, the supplementary light system would be started by L298 module, and when the value was more than 120, the acquisition system would be restarted. This study provides a reference for solving the key problem of automatic acquisition of pig face data for pig face detection.

Abstract in Chinese

生猪个体识别是生猪的精准养殖与智能管理的必要步骤，为实现生猪个体识别需构建适用的生猪数据集，由于生猪行为难于控制，数据采集难度大、效率低且关于生猪脸部检测的国内外研究鲜有报道，脸部数据的采集难度更大，本研究中采用双open mv3数字摄像头，提出由垂直摄像头采集到生猪身影计算背部区域斜率并发送信号给水平摄像头启动猪脸采集程序的方法，并基于RGB函数计算图像亮度，当值低于90时由L298模块启动补光系统，当值大于120时重新启动采集系统，为解决猪脸数据自动采集的关键问题猪脸检测提供了参考。