Detecting respiration rate (RR) is a promising and practical heat stress diagnostic method for cows, with significant potential benefits for dairy operations in monitoring thermal conditions and managing cooling treatments. Currently, the optical flow method is widely employed for automatic video-based RR estimation. However, the optical flow-based approach for RR estimation can be time-consuming and susceptible to interference from various unrelated cow movements, such as rising, lying down, and body shaking. The aim of this study was to propose a novel optical flow-based algorithm for remotely and rapidly detecting the respiration rate of cows in free stalls. To accomplish this, we initially collected 250 sixty-second video episodes from a commercial dairy farm, which included some episodes with interfering motions. We manually observed the respiration rate for each episode, considering it as the ground truth RR. The analysis revealed that certain cow movements, including posture changes and body shaking, introduced noise that compromises the precision of RR detection. To address this issue, we implemented noise filters, with the Butterworth filter proving highly effective in mitigating noise resulting from cow movements. The selection of the region of interest was found to have a substantial impact on the accuracy of RR detection. Opting for the central region was recommended for optimal results. The comparison between the RR estimated by the modified cow respiration rate (MCRR) algorithm and the ground truth RR showed a good agreement with a mean absolute relative error of 7.6 ± 8.9% and a Pearson correlation coefficient of 0.86. Additionally, the results also indicated that reducing the original frame rate from 25 to 5 frames per second and adjusting the image pixel size from 630 × 450 to 79 × 57 pixels notably reduced computational time from 39.8 to 2.8 s, albeit with a slight increase in mean absolute relative error to 8.0 ± 9.0%.

Monitoring estrus in sows is crucial for enhancing the efficiency of production management in pig farms. Standing reflex, as a clear sign of estrus and the optimal timing indicator for artificial insemination, has lacked an efficient and reliable method for monitoring. This study developed an approach based on machine vision for the automated detection of standing reflex in multiple sows within stalls. Specifically, a detection strategy was proposed based on the analysis of movement patterns by first calculating the Intersection over Union (IoU) sequence for each sow, followed by classification of standing reflex versus non-standing reflex sequences using a Convolutional–BiLSTM–Attention (CBA) network. Additionally, the lying targets were excluded from sequential classification while employing the improved YOLOv8 for segmentation. A total of 1484 images were captured for instance segmentation, and 445 IoU sequences were extracted from videos for temporal classification. Experimental results showed that misclassification rate of the improved YOLOv8 was 3% in distinguishing between lying and standing postures, indicating its efficiency in identifying these two states. Moreover, the mean average precision (mAP) of segmentation reached 98.2%, with a detection latency of 7.8 ms per image, demonstrating the model’s efficient capability in extracting target contours. The CBA model achieved an accuracy of 96.6 ± 2.7%. The proposed method enabled accurate monitoring of standing reflex in sows, facilitating more precise control over breeding times.