Wildlife poachers can now be located and arrested across the central African forests thanks to state-of-the-art AI listening technology.<\/p>\n
A network of microphones has been deployed across the rainforests to detect gunshots from illegal poaching of elephants and other animals, and American scientists are using AI to ensure the network can distinguish gunshots over the din of the jungle environment.<\/p>\n
The web of acoustic sensors was deployed in Gabon, Congo, and Cameroon, creating the possibility of real-time alerts to the sounds of gun-based poaching.<\/p>\n
But the belly of the rainforest is loud, and scientists say sorting through a constant influx of sound data is computationally demanding. Detectors can distinguish a loud bang from the whistles, chirps, and rasps of birds and bugs, but they often confuse the sounds of branches cracking or trees falling with gunshot noises, resulting in a high percentage of false positives.<\/p>\n
Project leader Naveen Dhar at Center for Conservation Bioacoustics at Cornell University aimed to develop a lightweight gunshot detection neural network that can accompany sensors and process signals in real-time to minimize false positives.<\/p>\n
He worked alongside colleagues at the Elephant Listening Project to create a model that will work through autonomous recording units (ARUs), which are power-efficient microphones that capture continuous, long-term soundscapes.<\/p>\n
\u201cThe proposed system utilizes a web of ARUs deployed across the forest, each performing real-time detection, with a central hub that handles more complex processing.\u201d<\/p>\n
An initial scan filters all audio for \u201cgunshot likely\u201d signals and sends them to the ARU\u2019s microprocessor, where the lightweight gunshot detection model lives.<\/p>\n
If confirmed as a gunshot by the microprocessor, the ARU passes the information to the central hub, initiating data collection from other devices in the web.<\/p>\n
By determining if other sensors also hear a \u201cgunshot likely\u201d noise, the central hub then decides whether the event was a true gunshot or a potential false positive.<\/p>\n
If it determines a true positive, the central hub collates audio files from each sensor, allowing it to pinpoint the location of the gunshot and alert rangers on the ground with coordinates for immediate poaching intervention.<\/p>\n
\u201cDown the road, the device can be used as a tool for rangers and conservation managers, providing accurate and verifiable alerts for on-the-ground intervention along with low-latency data on the spatiotemporal trends of poachers,\u201d Dhar said.<\/p>\n
He plans to expand the model to detect the type of gun that fires each gunshot and other human activities, such as chainsaws or trucks, before field-testing the system, which is currently under development.<\/p>\n
\u201cI hope the device can coalesce with Internet of Things infrastructure innovations and cost reduction of materials to produce a low-cost, open-source framework for real-time detection usable in any part of the globe.\u201d<\/p>\n
He is due to present his findings at a joint meeting of the Acoustical Society of America and Acoustical Society of Japan, in Honolulu, Hawaii.<\/p>\n