Artificial intelligence, sensors, robots, and transportation systems drive an innovative future for poultry broiler and breeder management

CarcassFormer: an end-to-end transformer-based framework for simultaneous localization, segmentation and classification of poultry carcass defect

In the food industry, assessing the quality of poultry carcasses during processing is a crucial step. This study proposes an effective approach for automating the assessment of carcass quality without requiring skilled labor or inspector involvement. The proposed system is based on machine learning (ML) and computer vision (CV) techniques, enabling automated defect detection and carcass quality assessment. To this end, an end-to-end framework called CarcassFormer is introduced. It is built upon a Transformer-based architecture designed to effectively extract visual representations while simultaneously detecting, segmenting, and classifying poultry carcass defects. Our proposed framework is capable of analyzing imperfections resulting from production and transport welfare issues, as well as processing plant stunner, scalder, picker, and other equipment malfunctions. To benchmark the framework, a dataset of 7,321 images was initially acquired, which contained both single and multiple carcasses per image. In this study, the performance of the CarcassFormer system is compared with other state-of-the-art (SOTA) approaches for both classification, detection, and segmentation tasks. Through extensive quantitative experiments, our framework consistently outperforms existing methods, demonstrating re- markable improvements across various evaluation metrics such as AP, AP@50, and AP@75. Furthermore, the qualitative results highlight the strengths of CarcassFormer in capturing fine details, including feathers, and accurately localizing and segmenting carcasses with high precision. To facilitate further research and collaboration, the source code and trained models will be made publicly available upon acceptance.

How Do Escape Distance Behavior of Broiler Chickens Change in Response to a Mobile Robot Moving at Two Different Speeds?

In poultry farming, robots are considered by birds as intruder elements to their environment, because animals escape due to their movement. Their escape is measured using the escape distance (ED) technique. This study analyzes the behavior of animals in relation to their ED through the use of a robot with two speeds: 12 rpm and 26 rpm. The objective is to understand whether the speeds cause variations in ED and their implications for animal stress. A broiler breeding cycle was analyzed (six weeks) through the introduction of the robot weekly. ED analyses were carried out on static images generated from footage of the robot running. The results indicate higher escape distance rates (p < 0.05) peaking midway through the production cycle, notably in the third week. Conversely, the final weeks saw the lowest ED, with the most significant reduction occurring in the last week. This pattern indicates a gradual escalation of ED up to the fourth week, followed by a subsequent decline. Despite RPM12 having shown low ED results, it did not show enough ED to move the animals away from their path of travel, causing bumps and collisions. RPM26 showed higher ED in all breeding phases, but showed ED with no bumps and collisions.

Towards Early Poultry Health Prediction through Non-Invasive and Computer Vision-Based Dropping Classification

The use of artificial intelligence techniques with advanced computer vision techniques offers great potential for non-invasive health assessments in the poultry industry. Evaluating the condition of poultry by monitoring their droppings can be highly valuable as significant changes in consistency and color can be indicators of serious and infectious diseases. While most studies have prioritized the classification of droppings into two categories (normal and abnormal), with some relevant studies dealing with up to five categories, this investigation goes a step further by employing image processing algorithms to categorize droppings into six classes, based on visual information indicating some level of abnormality. To ensure a diverse dataset, data were collected in three different poultry farms in Lithuania by capturing droppings on different types of litter. With the implementation of deep learning, the object detection rate reached 92.41% accuracy. A range of machine learning algorithms, including different deep learning architectures, has been explored and, based on the obtained results, we have proposed a comprehensive solution by combining different models for segmentation and classification purposes. The results revealed that the segmentation task achieved the highest accuracy of 0.88 in terms of the Dice coefficient employing the K-means algorithm. Meanwhile, YOLOv5 demonstrated the highest classification accuracy, achieving an ACC of 91.78%.

Super-resolution fusion optimization for poultry detection: a multi-object chicken detection method

Accurate poultry detection is crucial for studying poultry behavior using computer vision and video surveillance. However, in free-range farming environments, detecting chickens can often be challenging due to their small size and mutual occlusion. The current detection algorithms exhibit a low level of accuracy, with a high probability of false and missed detections. To address this, we proposed a multi-object chicken detection method named Super-resolution Chicken Detection, which utilizes super-resolution fusion optimization. The algorithm employs the residual-residual dense block to extract image features and used a generative adversarial network to compensate for the loss of details during deep convolution, producing high-resolution images for detection. The proposed algorithm was validated with the B1 data set and the MC1 multi-object data set, demonstrating that the reconstructed images possessed richer pixel features compared to original images, specifically it improved detection accuracy and reduced the number of missed detections. The structural similarity of the reconstructed images was 99.9%, and the peak signal-to-noise ratio was above 30. The algorithm improved the Average Precision50:95 of all You Only Look Once Version X (YOLOX) models, with the largest improvement for the B1 data set with YOLOX-Large (+6.3%) and for the MC1 data set with YOLOX-Small (+4.1%). This was the first time a super-resolution reconstruction technique was applied to multi-object poultry detection. Our method will provide a fresh approach for future poultry researchers to improve the accuracy of object detection using computer vision and video surveillance.

Salmonella spp. in Chicken: Prevalence, Antimicrobial Resistance, and Detection Methods

Multidrug-resistant Salmonella spp. is one of the leading causes of worldwide foodborne disease outbreaks. Animal-derived foods, particularly chicken and poultry products, are the most likely source of Salmonella transmission to humans. The increasing demand for chicken meat has raised a global food safety issue. This review aims to determine the prevalence and antimicrobial resistance of Salmonella spp. in chickens from various countries in Asia. The methods for detecting Salmonella will also be discussed in this review. The prevalence of Salmonella spp. in chicken and poultry products is lower in developed countries than in developing countries. In addition, the incidence of Salmonella spp. in chicken and poultry products from fresh markets is higher than those from supermarkets. Furthermore, this review also reported the presence of multidrug-resistant Salmonella strains in various Asian countries. Rapid Salmonella detection based on immunological assays, molecular-based assays, and biosensors can provide more accurate results with high sensitivity and specificity. These methods also require a shorter time than the cultural-based Salmonella detection method. The use of suitable detection methods to determine the presence of Salmonella spp. in chicken and poultry products is important to ensure food safety.