An efficient segmentation model for abnormal chicken droppings recognition based on improved deep dual-resolution network.

The characteristics of chicken droppings are closely linked to their health status. In prior studies, chicken droppings recognition is treated as an object detection task, leading to challenges in labeling and missed detection due to the diverse shapes, overlapping boundaries, and dense distribution of chicken droppings. Additionally, the use of intelligent monitoring equipment equipped with edge devices in farms can significantly reduce manual labor. However, the limited computational power of edge devices presents challenges in deploying real-time segmentation algorithms for field applications. Therefore, this study redefines the task as a segmentation task, with the main objective being the development of a lightweight segmentation model for the automated monitoring of abnormal chicken droppings. A total of 60 Arbor Acres broilers were housed in 5 specific pathogen-free cages for over 3 wk, and 1650 RGB images of chicken droppings were randomly divided into training and testing sets in an 8:2 ratio to develop and test the model. Firstly, by incorporating the attention mechanism, multi-loss function, and auxiliary segmentation head, the segmentation accuracy of the DDRNet was enhanced. Then, by employing the group convolution and an advanced knowledge-distillation algorithm, a lightweight segmentation model named DDRNet-s-KD was obtained, which achieved a mean Dice coefficient (mDice) of 79.43% and an inference speed of 86.10 frames per second (FPS), showing a 2.91% and 61.2% increase in mDice and FPS compared to the benchmark model. Furthermore, the DDRNet-s-KD model was quantized from 32-bit floating-point values to 8-bit integers and then converted to TensorRT format. Impressively, the weight size of the quantized model was only 13.7 MB, representing an 82.96% reduction compared to the benchmark model. This makes it well-suited for deployment on the edge device, achieving an inference speed of 137.51 FPS on Jetson Xavier NX. In conclusion, the methods proposed in this study show significant potential in monitoring abnormal chicken droppings and can provide an effective reference for the implementation of other agricultural embedded systems.

The characteristics of chicken droppings are closely related to their health. In this study, we developed a lightweight segmentation model for chicken droppings and evaluated its inference speed on the edge device with limited computational power. The results showed that the proposed model exhibits significant potential in the early warning of abnormal chicken droppings, which can help producers implement interventions before disease outbreaks, thereby avoiding great economic losses. Additionally, the model optimization and compression processes proposed in this study can provide an effective reference for the implementation of other embedded systems.

Eggshell biometrics for individual egg identification based on convolutional neural networks.

Individual egg identification technology has potential applications in breeding, product tracking/tracing, and anti-counterfeit. This study developed a novel method for individual egg identification based on eggshell images. A convolutional neural network-based model, named Eggshell Biometric Identification (EBI) model, was proposed and evaluated. The main workflow included eggshell biometric feature extraction, egg information registration, and egg identification. The image dataset of individual eggshell was collected from the blunt-end region of 770 chicken eggs using an image acquisition platform. The ResNeXt network was then trained as a texture feature extraction module to obtain sufficient eggshell texture features. The EBI model was applied to a test set of 1,540 images. The testing results showed that when an appropriate Euclidean distance threshold for classification was set (17.18), the correct recognition rate and the equal error rate reached 99.96% and 0.02%. This new method provides an efficient and accurate solution for individual chicken egg identification, and can be extended to eggs of other poultry species for product tracking/tracing and anti-counterfeit.

A reliable and low-cost deep learning model integrating convolutional neural network and transformer structure for fine-grained classification of chicken Eimeria species.

Chicken coccidiosis is a disease caused by Eimeria spp. and costs the broiler industry more than 14 billion dollars per year globally. Different chicken Eimeria species vary significantly in pathogenicity and virulence, so the classification of different chicken Eimeria species is of great significance for the epidemiological survey and related prevention and control. The microscopic morphological examination for their classification was widely used in clinical applications, but it is a time-consuming task and needs expertise. To increase the classification efficiency and accuracy, a novel model integrating transformer and convolutional neural network (CNN), named Residual-Transformer-Fine-Grained (ResTFG), was proposed and evaluated for fine-grained classification of microscopic images of seven chicken Eimeria species. The results showed that ResTFG achieved the best performance with high accuracy and low cost compared with traditional models. Specifically, the parameters, inference speed and overall accuracy of ResTFG are 1.95M, 256 FPS and 96.9%, respectively, which are 10.9 times lighter, 1.5 times faster and 2.7% higher in accuracy than the benchmark model. In addition, ResTFG showed better performance on the classification of the more virulent species. The results of ablation experiments showed that CNN or Transformer alone had model accuracies of only 89.8% and 87.0%, which proved that the improved performance of ResTFG was benefit from the complementary effect of CNN's local feature extraction and transformer's global receptive field. This study invented a reliable, low-cost, and promising deep learning model for the automatic fine-grain classification of chicken Eimeria species, which could potentially be embedded in microscopic devices to improve the work efficiency of researchers and extended to other parasite ova, and applied to other agricultural tasks as a backbone.

In vivo prediction of abdominal fat and breast muscle in broiler chicken using live body measurements based on machine learning.

The purpose of this study was to predict the carcass characteristics of broilers using support vector regression (SVR) and artificial neural network (ANN) model methods. Data were obtained from 176 yellow feather broilers aged 100-day-old (90 males and 86 females). The input variables were live body measurements, including external measurements and B-ultrasound measurements. The predictors of the model were the weight of abdominal fat and breast muscle in male and female broilers, respectively. After descriptive statistics and correlation analysis, the datasets were randomly divided into train set and test set according to the ratio of 7:3 to establish the model. The results of this study demonstrated that it is feasible to use machine learning methods to predict carcass characteristics of broilers based on live body measurements. Compared with the ANN method, the SVR method achieved better prediction results, for predicting breast muscle (male: R2 = 0.950; female: R2 = 0.955) and abdominal fat (male: R2 = 0.802; female: R2 = 0.944) in the test set. Consequently, the SVR method can be considered to predict breast muscle and abdominal fat of broiler chickens, except for abdominal fat in male broilers. However, further revaluation of the SVR method is suggested.

Effects of light color and intensity on discrimination of red objects in broilers.

Poultry are sensitive to red objects, such as comb and blood on the body surface, likely inducing injurious pecking in flocks. Light is an important factor that affects the pecking behavior of poultry. A wooden box was built to investigate the effects of Light Emitting Diode (LED) light color (warm white and cold white) and intensity (5 and 50 lux) of background light on the discrimination of red objects in broilers. A piece of red photographic paper (Paper 1) was used to simulate a red object and paired with another piece of paper (Paper 2 to 8) with a different color. Bigger number of the paired paper indicated greater color difference. The experiment consisted of three phases: adaptation, training, and test. In the adaptation phase, birds were selected for the adaptation to reduce the stress from the box. In the training phase, birds were trained to discriminate and peck at Paper 1 when paired with Paper 8 under one type of background light. Twenty-three birds were tested when the paired paper was changed from Paper 7 to 2. Each pair of paper included 12 trials for every bird, and response time to peck and proportion of choices of Paper 1 in the last 10 trials were collected. The results showed that broilers tested under 5 lux light had longer response times than broilers tested under 50 lux light (P < 0.05). When Paper 1 was paired with paper 7, broilers tested under warm white light had lower proportion of choices of Paper 1 than those tested under cold white light (P < 0.05). Color difference had a significant effect on response time of broilers (P < 0.05). Moreover, the proportion of choices of Paper 1 decreased to 50% (chance-level performance) when color of the paired paper was gradually similar to Paper 1. Conclusively, rearing broilers in warm white rather than cold white light with appropriate light intensity should be recommended to reduce damaging pecking behavior in broiler production.

Poultry are sensitive to red objects, such as comb and blood on the body surface, likely inducing injurious pecking in flocks. We built a wooden box to investigate the effects of light color (reddish and bluish) and intensity (5 and 50 lux) of background light on the discrimination of red objects in broilers. A piece of red photographic paper (Paper 1) was used and paired with another piece of paper (Paper 2 to 8) with a different color. Every bird was trained to discriminate and peck at Paper 1 when paired with Paper 8 under one type of background light. Then, Paper 8 was changed from Paper 7 to 2. Response time to peck and proportion of choices of Paper 1 were collected. We found that broilers under 5 lux light had longer response times than under 50 lux light. Broilers under reddish light had lower proportion of choices than under bluish light. Moreover, color difference had a significant effect on the response time and the proportion of choices. Conclusively, rearing broilers under reddish rather than bluish light with appropriate intensity should be recommended to reduce damaging pecking behavior in broiler production.