Fine-grained detection of caged-hen head states using adaptive Brightness Adjustment in combination with Convolutional Neural Networks

Timely identification and tracking of abnormal hens in stacked cages are of great significance for precision treatment and the elimination of sick individuals.The head features of the caged-hens are used to overcome observation difficulties caused by the cage and feathers blocking,but it is still hard to identify similar head states.To solve this problem,the fine-grained detection of caged-hens head states was developed using adaptive Brightness Adjustment in combination with Convolutional Neural Networks(FBA-CNN).Grid Region-based CNN(R-CNN),a convolution neural network(CNN),was optimized with the Squeeze-and-Excitation(SE)and Depthwise Over-parameterized Convolutional(DO-Conv)to detect layer heads from cages and to accurately cut them as single-head images.The brightness of each single-head image was adjusted adaptively and classified through the deep convolution neural network based on SE-Resnet50.Finally,we returned to the original image to realize multi-target detection with coordinate mapping.The results showed that the AP@0.5 of layer head detection using the optimized Grid R-CNN was 0.947,the accuracy of classification with SE-Resnet50 was 0.749,the F1 score was 0.637,and the mAP@0.5 of FBA-CNN was 0.846.In summary,this automated method can accurately identify different layer head states in layer cages to provide a basis for follow-up studies of abnormal behavior including dyspnea and cachexia.

A review on computer vision systems in monitoring of poultry: A welfare perspective

Monitoring of poultry welfare-related bio-processes and bio-responses is vital in welfare assessment and management of welfare-related factors.With the current development in information technologies,computer vision has become a promising tool in the real-time automation of poultry monitoring systems due to its non-intrusive and non-invasive properties,and its ability to present a wide range of information.Hence,it can be applied to monitor several bio-processes and bio-responses.This review summarizes the current advances in poultrymonitoring techniques based on computer vision systems,i.e.,conventional machine learning-based and deep learning-based systems.A detailed presentation on the machine learning-based system was presented,i.e.,pre-processing,segmentation,feature extraction,feature selection,and dimension reduction,and modeling.Similarly,deep learning approaches in poultry monitoring were also presented.Lastly,the challenges and possible solutions presented by researches in poultry monitoring,such as variable illumination conditions,occlusion problems,and lack of augmented and labeled poultry datasets,were discussed.

Short-term feeding behaviour sound classification method for sheep using LSTM networks

A deep learning approach using long-short term memory(LSTM)networks was implemented in this study to classify the sound of short-term feeding behaviour of sheep,including biting,chewing,bolus regurgitation,and rumination chewing.The original acoustic signal was split into sound episodes using an endpoint detection method,where the thresholds of short-term energy and average zero-crossing rate were utilized.A discrete wavelet transform(DWT),Mel-frequency cepstral,and principal-component analysis(PCA)were integrated to extract the dimensionally reduced DWT based Mel-frequency cepstral coefficients(denoted by PW_MFCC)for each sound episode.Then,LSTM networks were employed to train classifiers for sound episode category classification.The performances of the LSTM classifiers with original Mel-frequency cepstral coefficients(MFCC),DWT based MFCC(denoted by W_MFCC),and PW_MFCC as the input feature coefficients were compared.Comparison results demonstrated that the introduction of DWT improved the classifier performance effectively,and PCA reduced the computational overhead without degrading classifier performance.The overall accuracy and comprehensive F1-score of the PW_MFCC based LSTM classifier were 94.97%and 97.41%,respectively.The classifier established in this study provided a foundation for an automatic identification system for sick sheep with abnormal feeding and rumination behaviour pattern.

Optimization of tracer coating parameters and their effects on the mechanical properties and quality of food-grade tracers for grain traceability

The purpose of this study was to optimize the coating process of food-grade tracers to manufacture tracers with good physical,mechanical and practical properties and an excellent appearance.The effects of the coating weight gain(1.00%-5.00%),coating solution spray rate(1.50-7.50 g/min)and tablet bed temperature(30℃-40℃)on the coating appearance quality,moisture absorption rate,friction coefficient,peak shear force,breaking rate,barcode recognition rate,transport wear rate and transport recognition rate were analysed using a Box-Behnken design(BBD)of response surface methodology(RSM).The experimental data were fitted to quadratic polynomial models by multiple regression analysis.The mathematical models of the barcode recognition rate,transport wear rate and transport recognition rate exhibited no statistically significant difference in these data.The optimum coating parameters were as follows:a 5.00%coating weight gain,spray rate of 5.47 g/min and tablet bed temperature of 35.42℃.Under the optimized conditions,the tracers had a good appearance(coating appearance quality),moisture resistance(moisture absorption rate),and frictional(friction coefficient),compression(peak shear force),and impact characteristics(breaking rate).