{"id":2729,"date":"2020-06-22T15:17:13","date_gmt":"2020-06-22T19:17:13","guid":{"rendered":"https:\/\/blogs.mathworks.com\/headlines\/?p=2729"},"modified":"2020-06-22T15:17:13","modified_gmt":"2020-06-22T19:17:13","slug":"even-lions-can-rely-on-telemedicine-thanks-to-computer-vision","status":"publish","type":"post","link":"https:\/\/blogs.mathworks.com\/headlines\/2020\/06\/22\/even-lions-can-rely-on-telemedicine-thanks-to-computer-vision\/","title":{"rendered":"Even lions can rely on telemedicine thanks to computer vision"},"content":{"rendered":"

This week\u2019s blog post was written by guest blogger, Liz Ashforth. For this post, Liz discovered research that shows how computer vision and signal processing algorithms can make health exams safer for both non-domestic animals and their caretakers.<\/span><\/span><\/span><\/span><\/em><\/p>\n

A stethoscope is the tool of choice when a doctor listens to your heart rate and respiration. But when a lion gets a physical exam, the veterinarian can’t just say, “OK, take a deep breath.”<\/p>\n

Obtaining vital signs of animals is crucial for assessing their health. But for many animals, it can be quite <\/span><\/span>challenging. T<\/span><\/span>ypically, the animal<\/span><\/span>s are captured and tranquilized, their vital signs recorded, and then the animals are monitored as the tranquilizer wears off. This process cause<\/span><\/span>s<\/span><\/span> the animal stress and can lead to injury. It can be dangerous for their caretakers as well. A new <\/span><\/span>computer vision-based system<\/span><\/span>\u00a0enables\u00a0<\/span><\/span>veterinarians<\/span><\/span>\u202f<\/span><\/span>and\u00a0<\/span><\/span>zoo<\/span><\/span>keepers<\/span><\/span> to safely and accurately take an animal\u2019s vital signs<\/span><\/span> from a distance.<\/span><\/span>\u00a0<\/span><\/span><\/span><\/p>\n

 <\/p>\n

\"\"<\/a>

Image credit: Kevin Pluck, via Wikipedia<\/p><\/div><\/p>\n

New\u00a0<\/span><\/span>n<\/span><\/span>on-<\/span><\/span>i<\/span><\/span>nvasive t<\/span><\/span>echnique <\/span><\/span>s<\/span><\/span>afely\u00a0<\/span><\/span>m<\/span><\/span>easures a<\/span><\/span>nimal\u00a0<\/span><\/span>v<\/span><\/span>ital\u00a0<\/span><\/span>s<\/span><\/span>igns<\/span><\/span>\u00a0<\/span><\/h2>\n

A<\/span><\/span>s reported by\u00a0<\/span><\/span>Scientific American<\/span><\/span><\/a><\/em>,<\/em>\u00a0<\/span><\/span>Javaan<\/span>\u00a0Chahl<\/span><\/span>, a remote sensing engineer at the University of South Australia<\/span><\/span>,\u00a0<\/span><\/span>built a device that\u00a0<\/span><\/span>can<\/span><\/span>\u00a0capture\u00a0<\/span><\/span>and analyze images<\/span><\/span> providing insight into animals\u2019 vital signs. The device consists of a high-resolution\u00a0<\/span><\/span>digital video camera, a telephoto lens, and a signal processing program. <\/span><\/span>MATLAB<\/span><\/a> <\/span><\/span>analyzes\u00a0<\/span><\/span>the images\u00a0<\/span><\/span>remotely\u00a0<\/span><\/span>to determine an animal\u2019s breathing and heart rates<\/span><\/span>. <\/span><\/span><\/p>\n

And it works for more than just lions. According to <\/span><\/span>the journal <\/span><\/span>Sensors<\/span><\/span><\/a>,<\/span><\/span><\/em>\u00a0<\/span><\/span>s<\/span><\/span>ubject animals included the following species: Giant panda, African lions<\/span><\/span>,\u00a0<\/span><\/span>Sumatran tiger<\/span><\/span>,<\/span><\/span>\u00a0koala, red kangaroo, alpac<\/span><\/span>a,<\/span><\/span> little blue penguin, Sumatran orangutan, and a Hamadryas baboon<\/span><\/span>.<\/span><\/span>\u00a0<\/span><\/span><\/p>\n

 <\/p>\n

\"\"<\/a>

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. Image credit: Sensors (Basel). 2019 Dec; 19(24): 5445.<\/span><\/a><\/p><\/div><\/p>\n

 <\/p>\n

\u201cWe\u2019ve done quite a range of animals,\u201d\u00a0<\/span><\/span>Chahl<\/span><\/span>\u00a0says.<\/span><\/span> He believes the method could be used on almost any species, including very small ones. \u201cThe nice thing about light-based imagery, as opposed to radar or thermal cameras, is that you can go from looking at the moon to looking at bacteria just by changing lenses,\u201d he says. <\/span><\/span>A<\/span><\/span>nother\u00a0<\/span><\/span>benefit<\/span><\/span>\u00a0of light-based imagery is its high resolution, which allowed Chahl and his colleagues to monitor animals from 10 to 130 feet away.<\/span><\/span>\u202f<\/span><\/span><\/p>\n

Chahl\u2019s\u00a0experiments extracted signals from the\u00a0<\/span>abdominal-thoracic region<\/span>. <\/span>In this region,\u00a0<\/span>cardiopulmonary activity, such\u00a0<\/span>as expansion in the chest<\/span>,<\/span>\u00a0is\u00a0<\/span>observable<\/span>\u00a0<\/span>via the images c<\/span>aptured<\/span> by the digital camera. <\/span>MATLAB<\/span> analyzes the images\u00a0<\/span>and filters out \u201cnoise\u201d from\u00a0<\/span>the\u00a0<\/span>animal\u2019s movemen<\/span>t en<\/span>abling<\/span>\u00a0scientists and veterinarians to\u00a0<\/span>successfully<\/span>\u00a0<\/span>analyze<\/span> the animal\u2019s heart rate and breathing rate.<\/span><\/p>\n

 <\/p>\n

\"\"<\/a>

The graphical user interface (GUI) main panel of the experimental proposed image analysing system. Image credit: Sensors (Basel). 2019 Dec; 19(24): 5445.<\/p><\/div><\/p>\n

 <\/p>\n

\"\"<\/a>

Temporal signal analysis of the giant Panda, (a) One minute observed time series, (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. Image credit: Sensors (Basel). 2019 Dec; 19(24): 5445.<\/span><\/a><\/p><\/div><\/p>\n

While the program does\u00a0not\u00a0provide meaningful results\u00a0when an animal is running, it is a promising technology for further adoption for\u00a0both\u00a0animal and human use.\u00a0<\/span><\/p>\n

F<\/span><\/b>uture<\/span><\/b>\u00a0applications are diverse<\/span><\/b>\u00a0<\/span><\/p>\n

The<\/span>\u00a0remote imaging technique to assess vital signs could have many\u00a0<\/span>beneficial\u00a0<\/span>uses<\/span> in<\/span> veterinary practice, conservation and game management, animal welfare, and zoological studies<\/span>.<\/span> There could also be<\/span>\u00a0<\/span>human applications for this technology. For example, remote sensing could help with <\/span>mass health screenings, which is<\/span>\u00a0very applicable to today\u2019s\u00a0<\/span>COVID-19 screening<\/span>s<\/span> at airports and other public spaces. It could also be used in<\/span>\u00a0<\/span>a neonatal unit as a substitute for electrodes<\/span> that are taped to the newborn. <\/span><\/p>\n

Ultimately,\u00a0<\/span>Chahl<\/span>\u2019s\u00a0<\/span>method\u00a0<\/span>can\u00a0<\/span>simplify the collection of health data,\u00a0<\/span>help<\/span>ing<\/span>\u00a0many animals and humans\u00a0<\/span>minimize and avoid stressful and potentially damaging physical contact. <\/span>Now, who\u00a0<\/span>wouldn\u2019t want that?<\/span>\u00a0<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

<\/div>\n

This week\u2019s blog post was written by guest blogger, Liz Ashforth. For this post, Liz discovered research that shows how computer vision and signal processing algorithms can make health exams safer… read more >><\/a><\/p>\n","protected":false},"author":138,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"https:\/\/blogs.mathworks.com\/headlines\/wp-json\/wp\/v2\/posts\/2729"}],"collection":[{"href":"https:\/\/blogs.mathworks.com\/headlines\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.mathworks.com\/headlines\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.mathworks.com\/headlines\/wp-json\/wp\/v2\/users\/138"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.mathworks.com\/headlines\/wp-json\/wp\/v2\/comments?post=2729"}],"version-history":[{"count":1,"href":"https:\/\/blogs.mathworks.com\/headlines\/wp-json\/wp\/v2\/posts\/2729\/revisions"}],"predecessor-version":[{"id":2733,"href":"https:\/\/blogs.mathworks.com\/headlines\/wp-json\/wp\/v2\/posts\/2729\/revisions\/2733"}],"wp:attachment":[{"href":"https:\/\/blogs.mathworks.com\/headlines\/wp-json\/wp\/v2\/media?parent=2729"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.mathworks.com\/headlines\/wp-json\/wp\/v2\/categories?post=2729"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.mathworks.com\/headlines\/wp-json\/wp\/v2\/tags?post=2729"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}