Automatic detection of sow estrus using a lightweight real-time detector and thermal images

Abstract

Determination of ovulation time is one of the most important tasks in sow reproduction management. Temperature variation in the vulva of the sows can be used as a predictor of ovulation time. However, the skin temperatures of sows in existing studies are obtained manually from infrared thermal images, posing an obstacle to the automatic prediction of ovulation time. In this study, an improved YOLO-V5s detector based on feature fusion and dilated convolution (FD-YOLOV5s) was proposed for the automatic extraction of the vulva temperature of sows based on infrared thermal images. For the purpose of reducing the model complexity, the depthwise separable convolution and the modified lightweight ShuffleNet-V2 module were introduced in the backbone. Meanwhile, the feature fusion network structure of the model was simplified for efficiency, and a mixed dilated convolutional module was designed to obtain global features. The experimental results show that FD-YOLOV5s outperformed the other nine methods, with a mean average precision (mAP) of 99.1%, an average frame rate of 156.25 fps, and a model size of only 3.86 MB, indicating that the method effectively simplifies the model while ensuring detection accuracy. Using a linear regression between manual extraction and the results extracted using this method in randomly selected thermal images, the coefficients of determination for maximum and average vulvar temperatures reached 99.5% and 99.3%, respectively. The continuous vulva temperature of sows was obtained by the target detection algorithm, and the sow estrus detection was performed by the temperature trend and compared with the manually detected estrus results. The results showed that the sensitivity, specificity, and error rate of the estrus detection algorithm were 89.3%, 94.5%, and 5.8%, respectively. The method achieves real-time and accurate extraction of sow vulva temperature and can be used for the automatic detection of sow estrus, which could be helpful for the automatic prediction of ovulation time.

Technological Tools and Artificial Intelligence in Estrus Detection of Sows—A Comprehensive Review

“…Jeong et al [92] measured average rectal and vulvar skin temperature and found a non-significant difference (38.8 • C for in-estrus sows vs. 38.7 • C for non-estrus sows). Zheng et al [9] used an infrared thermal imaging technique guided by YOLOV5s detector to monitor and detect sow estrus in real-time. The model detected estrus with 89.3% sensitivity, 94.5% specificity and 5.8% error rate.…”

“…There are great provisions to introduce technological tools in the PLF system. Out of many branches of PLF, breeding pigs in healthy, depression-free conditions and noncontact forms has always been the target worldwide [6,7] as accurate and timely reproduction is essential to the swine business [8][9][10][11][12]. According to several studies, proper detection of estrus in sows plays a crucial role in predicting the correct insemination time and gaining desired production generation after generations [13][14][15].…”

Instance Segmentation and Ensemble Learning for Automatic Temperature Detection in Multiparous Sows

“…Distinguished from the aforementioned methods, the present method employs environmental parameters to counterbalance the temperature losses from environmental disturbances and accurately segments the incomplete thermal window region. Reference [35] introduced a method to extract the vulva region of sows, based on the improved YOLOv5s object detection algorithm [35]. In comparison, the method proposed herein can precisely delineate the sow vulva boundary, accommodate variations of sow vulva across different sizes, and enhance the accuracy and reliability of thermal infrared temperature measurement.…”