The poultry industry plays a pivotal role in global agriculture, with poultry serving as a major source of protein and contributing significantly to economic growth. However, the sector faces challenges associated with labor-intensive tasks that are repetitive and physically demanding. Automation has emerged as a critical solution to enhance operational efficiency and improve working conditions. Specifically, robotic manipulation and handling of objects is becoming ubiquitous in factories. However, challenges exist to precisely identify and guide a robot to handle a pile of objects with similar textures and colors. This paper focuses on the development of a vision system for a robotic solution aimed at automating the chicken rehanging process, a fundamental yet physically strenuous activity in poultry processing. To address the limitation of the generic instance segmentation model in identifying overlapped objects, a cost-effective, dual-active laser scanning system was developed to generate precise depth data on objects. The well-registered depth data generated were integrated with the RGB images and sent to the instance segmentation model for individual chicken detection and identification. This enhanced approach significantly improved the model’s performance in handling complex scenarios involving overlapping chickens. Specifically, the integration of RGB-D data increased the model’s mean average precision (mAP) detection accuracy by 4.9% and significantly improved the center offset—a customized metric introduced in this study to quantify the distance between the ground truth mask center and the predicted mask center. Precise center detection is crucial for the development of future robotic control solutions, as it ensures accurate grasping during the chicken rehanging process. The center offset was reduced from 22.09 pixels (7.30 mm) to 8.09 pixels (2.65 mm), demonstrating the approach’s effectiveness in mitigating occlusion challenges and enhancing the reliability of the vision system.
Effective environmental monitoring is critical for preventing microbial and allergenic cross-contamination. However, manual swabbing methods, commonly used to verify hygienic conditions, are prone to inconsistent results because of variability in pressure, coverage, and techniques. Two novel solutions will be explored to address these challenges: a robotic swabbing system with tactile sensing control, and a fluorescence/absorbance spectrometer for non-contact, protein-based residue detection. The robotic system was evaluated against trained and untrained humans, measuring water pickup, surface coverage, and pressure consistency. Concurrently, the fluorescence system analyzed model poultry protein soil to correlate spectral patterns with contamination levels. The robotic system demonstrated statistically superior performance, achieving consistent force application and near-complete surface coverage, overcoming key limitations of manual sampling. The fluorescence system distinguished contamination with high sensitivity, validating its use as a rapid, non-contact assessment tool. Together, the robotic sample acquisition and the spectrometer’s sensitive analysis provide a dual-modality framework for enhancing hygiene monitoring in manufacturing facilities.
The poultry industry has been driven by broiler chicken production and has grown into the world's largest animal protein sector. Automated detection of chicken carcasses on processing lines is vital for quality control, food safety, and operational efficiency in slaughterhouses and poultry processing plants. However, developing robust deep learning models for tasks like instance segmentation in these fast-paced industrial environments is often hampered by the need for laborious acquisition and annotation of large-scale real-world image datasets. We present the first pipeline generating photo-realistic, automatically labeled synthetic images of chicken carcasses. We also introduce a new benchmark dataset containing 300 annotated real-world images, curated specifically for poultry segmentation research. Using these datasets, this study investigates the efficacy of synthetic data and automatic data annotation to enhance the instance segmentation of chicken carcasses, particularly when real annotated data from the processing line is scarce. A small real dataset with varying proportions of synthetic images was evaluated in prominent instance segmentation models. Results show that synthetic data significantly boosts segmentation performance for chicken carcasses across all models. This research underscores the value of synthetic data augmentation as a viable and effective strategy to mitigate data scarcity, reduce manual annotation efforts, and advance the development of robust AI-driven automated detection systems for chicken carcasses in the poultry processing industry.
The poultry industry plays a pivotal role in global agriculture, serving as a major source of protein and contributing significantly to economic growth. However, the sector faces challenges associated with labor-intensive tasks that are repetitive and physically demanding. Automation has emerged as a critical solution to enhance operational efficiency and improve working conditions. Specifically, robot manipulation and handling of objects is becoming ubiquitous in factories. However, challenges exist to precisely identify and guide the robot to handle a pile of objects with similar textures and colors. This paper focuses on the development of a vision system for a robotic solution aimed at automating the chicken rehanging process, a fundamental yet physically strenuous activity in poultry processing. To address the limitation of the generic instance segmentation model in identifying overlapped objects, a cost-effective dual-active laser scanning system was developed to generate precise depth data of objects. The generated well-registered depth data integrated with the RGB images were sent into the instance segmentation model for individual chicken detection and identification. This enhanced approach significantly improved the model’s performance in handling complex scenarios involving overlapping chickens. Specifically, the integration of RGB-D data increased the model’s mean Average Precision (mAP) detection accuracy by 4.9% and significantly improved the center offset—a customized metric introduced in this study to quantify the distance between the ground truth mask center and the predicted mask center. Precise center detection is crucial for the development of future robotic control solutions, as it ensures accurate grasping during the chicken rehanging process. The center offset was reduced from 22.09 pixels (7.30 mm) to 8.09 pixels (2.65 mm), demonstrating the approach’s effectiveness in mitigating occlusion challenges and enhancing the reliability of the vision system.