Accurate detection method of pig's temperature based on non‐point source thermal infrared image

Abstract

Body temperature measurement is a very important task in the sow breeding process. The authors used an infrared camera to detect the temperature of the body surface of the sows, relying on calculating the average of the infrared image temperature in the ear root region. Based on the grayscale value of the target image of the infrared image and the corresponding temperature value of 180 infrared images, a G‐T (Gray‐Temperature) model was established by linear least squares method, which achieved temperature inversion of each pixel of the target pig. For the different growth stages and different breeds of sows, the R‐square of the all established models is greater than 0.95. The average relative error of the model inversion of the body temperature was only 0.076977%. This means that the body temperature of the sows could be detected without relying on the software. Based on the G‐T model, the authors design a kind of sow's ear root recognition and body surface temperature detection algorithm for different sow population scenarios.

Assessment of Rectal Temperature using Infrared Thermal Camera in Pigs

“…Stukelj et al (4) , however, established three anatomical regions in healthy pigs: the ear canal, the outer ear, and the perianal region, for predicting the body temperature. Zhang et al (28) , observed high association between rectal temperature and the base of the ear. Similar, Schmitt & O'Driscoll (22) in their study, rectal temperature was correlated with all infrared thermography (IRT) data and found correlations were strongest with the ear base, and weakest with the ear tip and minimum back temperature.…”

Non-contact evaluation of pigs’ body temperature under various infrared sources

“…In recent years, a large number of researches have been conducted to detect the temperature of the pig-body, which is an important physiological indicator in many applications such as the early diagnosis and treatment diseases [7], [11], [14], [17]. To date, pig body temperature measurement techniques can be classified into two group, namely: i) contact; and ii) non-contact [5].…”

“…However, this technique still has some limitations, such as high initial investment cost, does not tend to work well underwater, can not detect radiation through glass, and especially the accurate temperature measurements are hindered by surrounding infrared sources. In order to improve the performance of the IRT method and to eliminate the influence of ambient temperature on temperature detection, some studies have focused on using infrared image processing techniques to detect target objects [17], [20]- [22]. In the context of various illumination conditions, Sa et al by their work [20] represented a pig monitoring strategy, in which the complementary information from depth and infrared images is exploited for pig detection.…”

“…It is observed that in the mentioned articles, there are two fundamental issues associated with a high accuracy rate in body temperature measurement of the IRT method: i) the segmentation of pig-body shape based on infrared images, which helps to recognize the features of the pig-body exactly, is quite consistent with the IRT method; and ii) by comparing pixel by pixel technique, the temperature of each pixel in infrared images is extracted effectively and in short time consuming. In extracting the pig-body temperature from infrared images, Zhang et al in [17] proposed a gray-temperature (G-T) model, which was established by linear least squares method. They found that the correlation between the gray (G) and the temperature (T) values based on their Fotric-225 infrared camera image is: T = 0.040428G + 30.01546.…”

The Application of Cameras in Precision Pig Farming: An Overview for Swine-Keeping Professionals

“…In addition, noninvasive data collection or monitoring is the safest method for humans since the interaction between humans and animals can cause infection to pass from animals to humans or humans to animals. Generally, any infection causes weakness [ 114 ], fever [ 9 , 116 ], and progressive deceleration of diurnal activities [ 67 ]. Monitoring activities such as drinking, eating, lying, and walking is significant, and changes in activities are a way to track animal health.…”