Kasani Payam Hosseinzadeh, Oh Seung Min, Choi Yo Han, Ha Sang Hun, Jun Hyungmin, Park Kyu Hyun, Ko Han Seo, Kim Jo Eun, Choi Jung Woo, Cho Eun Seok, Kim Jin Soo
College of Animal Life Sciences, Kangwon National University, Chuncheon 24341, Korea.
Gyeongbuk Livestock Research Institute, Yeongju, 63052, Korea.
J Anim Sci Technol. 2021 Mar;63(2):367-379. doi: 10.5187/jast.2021.e35. Epub 2021 Mar 31.
The objectives of this study were to evaluate convolutional neural network models and computer vision techniques for the classification of swine posture with high accuracy and to use the derived result in the investigation of the effect of dietary fiber level on the behavioral characteristics of the pregnant sow under low and high ambient temperatures during the last stage of gestation. A total of 27 crossbred sows (Yorkshire × Landrace; average body weight, 192.2 ± 4.8 kg) were assigned to three treatments in a randomized complete block design during the last stage of gestation (days 90 to 114). The sows in group 1 were fed a 3% fiber diet under neutral ambient temperature; the sows in group 2 were fed a diet with 3% fiber under high ambient temperature (HT); the sows in group 3 were fed a 6% fiber diet under HT. Eight popular deep learning-based feature extraction frameworks (DenseNet121, DenseNet201, InceptionResNetV2, InceptionV3, MobileNet, VGG16, VGG19, and Xception) used for automatic swine posture classification were selected and compared using the swine posture image dataset that was constructed under real swine farm conditions. The neural network models showed excellent performance on previously unseen data (ability to generalize). The DenseNet121 feature extractor achieved the best performance with 99.83% accuracy, and both DenseNet201 and MobileNet showed an accuracy of 99.77% for the classification of the image dataset. The behavior of sows classified by the DenseNet121 feature extractor showed that the HT in our study reduced ( < 0.05) the standing behavior of sows and also has a tendency to increase ( = 0.082) lying behavior. High dietary fiber treatment tended to increase ( = 0.064) lying and decrease ( < 0.05) the standing behavior of sows, but there was no change in sitting under HT conditions.
本研究的目的是评估卷积神经网络模型和计算机视觉技术，以高精度对猪的姿势进行分类，并将所得结果用于研究妊娠后期在低温和高温环境下膳食纤维水平对妊娠母猪行为特征的影响。在妊娠后期（第90至114天），采用随机完全区组设计，将总共27头杂交母猪（约克夏×长白；平均体重192.2±4.8千克）分配到三种处理中。第1组母猪在中性环境温度下饲喂3%纤维日粮；第2组母猪在高温环境下饲喂含3%纤维的日粮；第3组母猪在高温环境下饲喂6%纤维日粮。选择了8种流行的基于深度学习的特征提取框架（DenseNet121、DenseNet201、InceptionResNetV2、InceptionV3、MobileNet、VGG16、VGG19和Xception）用于猪姿势自动分类，并使用在实际猪场条件下构建的猪姿势图像数据集进行比较。神经网络模型在未见数据上表现出优异的性能（泛化能力）。DenseNet121特征提取器在图像数据集分类中以99.83%的准确率取得了最佳性能，DenseNet201和MobileNet的准确率均为99.77%。由DenseNet121特征提取器分类的母猪行为表明，本研究中的高温降低了（<0.05）母猪的站立行为，并且有增加躺卧行为的趋势（=0.082）。高膳食纤维处理倾向于增加（=0.064）母猪的躺卧行为并减少（<0.05）站立行为，但在高温条件下坐卧行为没有变化。
