摘要
为了准确识别屠宰加工中肉鸡的击晕状态,提出了一种基于快速区域卷积神经网络的肉鸡击晕状态检测方法。对输入图像进行归一化处理,通过卷积神经网络(VGG16)提取肉鸡的卷积特征图,利用区域建议网络提取预测框,在卷积特征图上采用非极大值抑制算法去除重复表述的预测框;将所得的各预测框映射到卷积特征图上,得到预测框在卷积特征图上的候选区域,将其输入感兴趣区域池化层;通过感兴趣区域池化层将大小不一的候选区域进行池化操作、得到统一的输出数据,最后通过全连接层与柔性最大值分类器,输出各击晕类别的概率和预测框的坐标。将2319个样本图像按2∶1的比例随机分为训练集与测试集,对模型进行训练与实验验证。结果表明,本文建立的基于Faster-RCNN的肉鸡击晕状态分类模型对773个测试集肉鸡样本击晕状态分类的总准确率达到96.51%,对肉鸡击晕状态的预测速度可达每小时37000只,基本满足肉鸡屠宰生产线要求。
In order to improve the accuracy of stunning state recognition of broiler chickens,a method of stunning state classification of broilers based on regional convolutional neural network(RCNN)was proposed.The following method was able to detect insufficiently appropriately and excessively stunned conditions of broilers.Initially,the image acquisition platform was utilized to collect the sample images.The data sets of collected samples were made according to the PASCAL visual object classes data set format.The total samples of 2319 images were randomly divided into training set and test set with the ratio of 2∶1.The augmented training sets were obtained through image enhancement technology.A Faster-RCNN was trained by using the augmented training set to detect the stunning states of broilers.The results showed that the recognition accuracy of the Faster-RCNN was 96.51%for 773 sample images in the test set.The accuracy of Faster-RCNN model was significantly higher than that of the established back propagation neural network(BP-NN)model(90.11%).The proposed model could be used to inspect the stunning state of more than 37000 broilers per hour.Deep learning technology was applied to recognize the stunning states of broilers,which can be used to automatically detect the stunning state of broilers and enhance automated slaughtering processes in the poultry industry.
作者
叶长文
康睿
戚超
刘超
赵阳
陈坤杰
YE Changwen;KANG Rui;QI Chao;LIU Chao;ZHAO Yang;CHEN Kunjie(College of Engineering,Nanjing Agricultural University,Nanjing 210031,China)
出处
《农业机械学报》
EI
CAS
CSCD
北大核心
2019年第12期255-259,共5页
Transactions of the Chinese Society for Agricultural Machinery
基金
“十二五”国家科技支撑计划项目(2015BAD19806)
国家肉鸡产业技术体系项目(CARS-42-5)
关键词
肉鸡
电击晕
击晕状态
卷积神经网络
深度学习
broiler chickens
electric stunning
stunning state
convolutional neural network
deep learning
