A Pilot Study for Estimating the Cardiopulmonary Signals of Diverse Exotic Animals Using a Digital Camera

Abstract

Monitoring the cardiopulmonary signal of animals is a challenge for veterinarians in conditions when contact with a conscious animal is inconvenient, difficult, damaging, distressing or dangerous to personnel or the animal subject. In this pilot study, we demonstrate a computer vision-based system and use examples of exotic, untamed species to demonstrate this means to extract the cardiopulmonary signal. Subject animals included the following species: Giant panda (Ailuropoda melanoleuca), African lions (Panthera leo), Sumatran tiger (Panthera tigris sumatrae), koala (Phascolarctos cinereus), red kangaroo (Macropus rufus), alpaca (Vicugna pacos), little blue penguin (Eudyptula minor), Sumatran orangutan (Pongo abelii) and Hamadryas baboon (Papio hamadryas). The study was done without need for restriction, fixation, contact or disruption of the daily routine of the subjects. The pilot system extracts the signal from the abdominal-thoracic region, where cardiopulmonary activity is most likely to be visible using image sequences captured by a digital camera. The results show motion on the body surface of the subjects that is characteristic of cardiopulmonary activity and is likely to be useful to estimate physiological parameters (pulse rate and breathing rate) of animals without any physical contact. The results of the study suggest that a fully controlled study against conventional physiological monitoring equipment is ethically warranted, which may lead to a novel approach to non-contact physiological monitoring and remotely sensed health assessment of animals. The method shows promise for applications in veterinary practice, conservation and game management, animal welfare and zoological and behavioral studies.

Keywords: animal health; cardiopulmonary signal; conservation; denoising; non-contact; veterinary; vital signs; wavelet; wildlife.

Figure 1

Data collection from 10 zoo animals, (a) giant panda, (b) African lion, (c) African lioness, (d) Sumatran tiger, (e) koala, (f) red kangaroo, (g) alpaca, (h) penguin, (i) Sumatran orangutan, and (j) Hamadryas baboon.

Figure 2

Schematic diagram illustrating the process by which non-contact video data obtained were acquired using a digital camera to extract the cardiopulmonary signal of unrestrained animals.

Figure 3

The graphical user interface (GUI) main panel of the experimental proposed image analysing system.

Figure 4

Temporal signal analysis of the giant Panda, (a) One minute observed time series signal $i_Y\left(t\right)$ of the selected region of interest (ROI), (b) the frequency spectrum, (c) the denoised signal using wavelet, (d) the smoothed signal using moving average filter with span equal to 5, (e) the cardiac signal after applying a band-pass filter of 1.1667 to 2 Hz, and (f) the breathing signal after applying a band-pass filter of 0.333 to 0.667 Hz.

Figure 5

Box plots show the minimum, maximum, 25–75th percentile and median value of the cardiopulmonary range obtained from 10 zoo animals for (a) PR results, and (b) BR results.