{"id":158967,"date":"2021-01-20T20:09:53","date_gmt":"2021-01-20T17:09:53","guid":{"rendered":"https:\/\/en.buradabiliyorum.com\/new-ai-system-counts-endangered-elephants-from-space\/"},"modified":"2021-01-20T20:09:53","modified_gmt":"2021-01-20T17:09:53","slug":"new-ai-system-counts-endangered-elephants-from-space","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/new-ai-system-counts-endangered-elephants-from-space\/","title":{"rendered":"#New AI system counts endangered elephants from space"},"content":{"rendered":"

“#New AI system counts endangered elephants from space<\/strong>”<\/p>\n

\n Scientists have unveiled a new tool for monitoring endangered wildlife: an AI system that automatically counts elephants from space.<\/p>\n

The tech combines satellite cameras with a convolutional neural network (CNN) to capture\u00a0African elephants moving through forests and grasslands.<\/span><\/p>\n

In tests, the surveying technique detected elephants as accurately as human observers, while eliminating the risk of disturbing the species.<\/p>\n

The research joins a growing range of AI projects that are\u00a0seeking to protect endangered animals.<\/span><\/p>\n

\u201cAccurate monitoring is essential if we\u2019re to save the species,\u201d said\u00a0Dr Olga Isupova, a computer scientist at the University of Bath who created the detection algorithm. \u201cWe need to know where the animals are and how many there are.\u201d<\/p>\n

[Read:\u00a0How Netflix shapes mainstream culture, explained by data<\/span>]<\/em><\/p>\n

The system also offers a more efficient alternative to manually\u00a0counting animals from low-flying airplanes.\u00a0Each satellite can collect\u00a0more than 5,000 km\u00b2 of imagery every few minutes. And if clouds obscure the land, the process can be repeated the following day, on\u00a0the satellite\u2019s next revolution of Earth.<\/p>\n

In addition, the technique can track animals as they roam across countries without having to\u00a0worry about border controls or conflicts.<\/p>\n

\"\"
Credit: 2020 Maxar Technologies<\/figcaption>
<\/a>The green rectangles show elephants detected by the algorithm from space, while the red ones show elephants verified by humans.<\/figcaption><\/figure>\n

The researchers trained and tested their model on endangered African elephants in\u00a0South Africa, using data from\u00a0the WorldView\u20103 and WorldView\u20104 satellites \u2014 the highest resolution satellite imagery that\u2019s commercially available.<\/p>\n

They also\u00a0app<\/a>lied the model to lower\u00a0resolution satellite images captured in Kenya \u2014 without any additional training data \u2014\u00a0to test whether it could work outside their study area.<\/span><\/p>\n

\u201cOur results show that the CNN performs with high accuracy, comparable to human detection capabilities,\u201d the team\u00a0wrote in their research paper.<\/p>\n

They chose African elephants for the study because they\u2019re the largest land animal in the world \u2014 which makes them relatively easy to spot. But the team believes their system could soon detect far smaller species.<\/p>\n

\u201cSatellite<\/span> imagery resolution increases every couple of years, and with every increase, we will be able to see smaller things in greater detail,\u201d said Dr Isupova.<\/p>\n

You can read the study paper<\/a> in the journal Remote Sensing in Ecology and Conservation<\/em>.<\/p>\n

\n Published January 20, 2021 \u2014 17:09 UTC\n <\/p>\n<\/p><\/div>\n