Selection of Image Texture Analysis and Color Model in the Advanced Image Processing of Thermal Images of Horses following Exercise

Simple Summary

Detecting horse state after exercise is critical for maximizing athletic performance. The horse’s response to fatigue includes exercise termination or exercise continuation at a lower intensity, which significantly limit the results achieved in races and equestrian competition. As conventional methods of detecting and quantifying exercise effort have shown some limitations, infrared thermography was proposed as a method of contactless detection of exercise effect. The promising correlation between body surface temperature and exercise-dependent blood biomarkers has been demonstrated. As the application of conventional thermography is limited by low specificity, advanced thermal image analysis was proposed here to visualize the link between blood biomarkers and texture of thermal images. Twelve horses underwent standardized exercise tests for six consecutive days, and both thermal images and blood samples were collected before and after each test. The images were analyzed using four color models (RGB, red-green-blue; YUV, brightness-UV-components; YIQ, brightness-IQ-components; HSB, hue-saturation-brightness) and eight texture-features approaches, including 88 features in total. In contrast to conventional temperature measures, as many as twelve texture features in two color models (RGB, YIQ) were linked with blood biomarker levels as part of the horse’s response to exercise.

Abstract

As the detection of horse state after exercise is constantly developing, a link between blood biomarkers and infrared thermography (IRT) was investigated using advanced image texture analysis. The aim of the study was to determine which combinations of RGB (red-green-blue), YUI (brightness-UV-components), YIQ (brightness-IQ-components), and HSB (hue-saturation-brightness) color models, components, and texture features are related to the blood biomarkers of exercise effect. Twelve Polish warmblood horses underwent standardized exercise tests for six consecutive days. Both thermal images and blood samples were collected before and after each test. All 144 obtained IRT images were analyzed independently for 12 color components in four color models using eight texture-feature approaches, including 88 features. The similarity between blood biomarker levels and texture features was determined using linear regression models. In the horses’ thoracolumbar region, 12 texture features (nine in RGB, one in YIQ, and two in HSB) were related to blood biomarkers. Variance, sum of squares, and sum of variance in the RGB were highly repeatable between image processing protocols. The combination of two approaches of image texture (histogram statistics and gray-level co-occurrence matrix) and two color models (RGB, YIQ), should be considered in the application of digital image processing of equine IRT.

Monitoring Performance in Show Jumping Horses: Validity of Non-specific and Discipline-specific Field Exercise Tests for a Practicable Assessment of Aerobic Performance

Show jumping is a highly specialized equestrian discipline that requires technical skill but also power and fitness. Monitoring the horses’ aerobic performance is therefore essential in order to verify whether the training has induced the desired cardiovascular and muscular adaptations. This study therefore aimed at evaluating the validity of non-specific and discipline-specific field exercise tests for objective evaluation of aerobic performance in show jumpers. For this purpose, data obtained from horses competing at Junior and Young Rider level during show jumping competitions as well as field exercise tests were retrospectively analyzed. The effect of the level of difficulty, the horses’ age, the penalty score and the horses’ previous level of performance on blood lactate concentrations after show jumping competitions (100 observations in 49 horses) was evaluated by linear mixed effects models (horse as random effect). Estimated marginal means significantly increased from 140 (4.1 mmol/L) to 150 cm (5.2 mmol/L) classes (P = 0.02). Furthermore, post-exercise lactate values significantly increased with the horses’ age (P = 0.001). Another group of 12 horses performed a standardized incremental field exercise test on a track (SET_track), a standardized show jumping course (SET_course) and a standardized grid exercise (SET_grid) each on three consecutive days. Indices of aerobic performance, derived from the SET_track [velocity at a heart rate of 140 bpm (V₁₄₀) and at a lactate concentration of 2 mmol/L (V_La2)] were highly correlated with heart rate (V₁₄₀: r = −0.75, P = 0.005; V_La2: r =−0.66, P = 0.02) and lactate (V₁₄₀: r = −0.73, P = 0.02; V_La2: r = −0.72, P = 0.02) in response to SET_course as well as heart rate during SET_grid (V₁₄₀: r = −0.73, P = 0.02; V_La2: r = −0.76, P = 0.01). Subjective rating of muscular fatigue was significantly correlated to the mean heart rate during SET_course (r = −0.64, P = 0.05) and SET_grid (r = −0.74, P = 0.02) but not to the aerobic indices calculated from SET_track. Besides non-specific incremental field tests, performance monitoring in show jumpers should therefore also include discipline-specific tests that more closely reflect the internal load induced by show jumping competitions.

Heart rate and blood lactate responses during the cross-country test of 2-star to 5-star eventing competitions

The objective of this retrospective study was to evaluate the physiological demands of cross-country competitions at different levels. Heart rates (HR) and post exercise blood lactate concentrations (LAC) measured between 2010 and 2019 in response to 1,463 cross-country competitions (437 at 2-star, 703 at 3-star, 313 at 4-star and 10 at 5-star level) in 294 horses were analysed. The effect of competition level, mean velocity, height profile, total distance, number of jumping efforts, climate, age, sex, percentage of Thoroughbred blood and performance level on HR, LAC, HR recovery and LAC disappearance rates was evaluated by Linear Mixed Effects Models. Mean HR and LAC significantly increased from 2-star to 4-star level (P<0.001). Each 30 m/min increase in mean velocity was associated with a 3 beats/min increase in HR (P<0.001) and a 41% increase in LAC (P<0.001) and each 30 m increase in cumulative elevation with a 2 beats/min increase in HR (P<0.001) and a 32% increase in LAC (P<0.001). Each 20 m increase in mean distance per jumping effort was associated with a 1 beat/min decrease in HR (P<0.01) and a 13% decrease in LAC (P<0.001). Compared to Warmbloods, horses with 75% Thoroughbred blood had 4 beats/min lower HRs (P<0.05) and 34% lower LAC values (P<0.001). Each 5 years increase in age was associated with a 4 beats/min decrease in HR (P<0.001, only in mares) and an 11% decrease in LAC (P<0.01). The HRs during the first 3 minutes of recovery were higher at warmer and more humid conditions (P<0.05). The rate of LAC disappearance was higher in horses with higher percentages of Thoroughbred blood (P<0.05).