Abstract

One of the most common and financially detrimental conditions affecting dairy cows is mastitis, which is often identified by visual inspection or somatic cell count (SCC) testing, both of which are labor-intensive, subjective, and time-consuming. Existing deep learning (DL)-based approaches, including CLE-UNet, DCYOLO, FS-YOLOv4, and YOLOv7-SVM, have improved detection accuracy but still face challenges in capturing temporal dynamics, handling noisy thermal data, and optimizing model parameters effectively. To address these limitations, this work proposes a novel YOLOv8 integrated with Probabilistic Spiking Network and Secretary Bird Optimization (YOLOv8PSN-SBO) framework for automated mastitis detection using thermal imaging. The system begins with thermal video acquisition and manual annotation of key anatomical regions, followed by adaptive iterative guided filtering (AIGF) to enhance image clarity. Multi-scale feature extraction is achieved using a Cascading Residual Graph Convolutional Network (CRGCN), while YOLOv8 performs precise spatial localization of cow eyes, udders, and head postures. These spatial outputs are then temporally processed using a Probabilistic Spiking Neural Network (PSNN) that leverages biological spiking behavior to infer thermal anomalies. The Secretary Bird Optimization Algorithm (SBOA) is employed to fine-tune parameters such as confidence thresholds, anchor box sizes, loss weights, and spiking neuron dynamics for optimal performance. The proposed YOLOv8PSN-SBO model, implemented in PyTorch and validated on 1200 labeled thermal images, significantly outperforms baseline methods, achieving a detection accuracy of 91.75%, recall of 92.31%, F1-score of 91.55%, and an mAP@0.5 of 94.60%, with a real-time processing speed of 65 FPS, establishing it as a robust and efficient solution for automated mastitis detection in dairy farming.