TY - UNPB
T1 - Real-time alerts from AI-enabled camera traps using the Iridium satellite network: a case-study in Gabon, Central Africa
AU - Whytock, Robin C
AU - Suijten, Thijs
AU - Deursen, Tim van
AU - Świeżewski, Jędrzej
AU - Mermiaghe, Hervé
AU - Madamba, Nazaire
AU - Moukoumou, Narcys
AU - Zwerts, Joeri A
AU - Pambo, Aurélie Flore Koumba
AU - Bahaa-el-din, Laila
AU - Brittain, Stephanie
AU - Cardoso, Anabelle W
AU - Henschel, Philipp
AU - Lehmann, David
AU - Momboua, Brice Roxan
AU - Makaga, Loïc
AU - Orbell, Christopher
AU - White, Lee JT
AU - Iponga, Donald Midoko
AU - Abernethy, Katharine A
N1 - Authors retain copyright and choose from several distribution/reuse options under which to make the article available (CC BY, CC BY-NC, CC BY-ND, CC BY-NC-ND, CC0, or no reuse).
PY - 2021/11/13
Y1 - 2021/11/13
N2 - Efforts to preserve, protect, and restore ecosystems are hindered by long delays between data collection and analysis. Threats to ecosystems can go undetected for years or decades as a result. Real-time data can help solve this issue but significant technical barriers exist. For example, automated camera traps are widely used for ecosystem monitoring but it is challenging to transmit images for real-time analysis where there is no reliable cellular or WiFi connectivity. Here, we present our design for a camera trap with integrated artificial intelligence that can send real-time information from anywhere in the world to end-users. We modified an off-the-shelf camera trap (Bushnell) and customised existing open-source hardware to rapidly create a 'smart' camera trap system. Images captured by the camera trap are instantly labelled by an artificial intelligence model and an 'alert' containing the image label and other metadata is then delivered to the end-user within minutes over the Iridium satellite network. We present results from testing in the Netherlands, Europe, and from a pilot test in a closed-canopy forest in Gabon, Central Africa. Results show the system can operate for a minimum of three months without intervention when capturing a median of 17.23 images per day. The median time-difference between image capture and receiving an alert was 7.35 minutes. We show that simple approaches such as excluding 'uncertain' labels and labelling consecutive series of images with the most frequent class (vote counting) can be used to improve accuracy and interpretation of alerts. We anticipate significant developments in this field over the next five years and hope that the solutions presented here, and the lessons learned, can be used to inform future advances. New artificial intelligence models and the addition of other sensors such as microphones will expand the system's potential for other, real-time use cases. Potential applications include, but are not limited to, wildlife tourism, real-time biodiversity monitoring, wild resource management and detecting illegal human activities in protected areas.
AB - Efforts to preserve, protect, and restore ecosystems are hindered by long delays between data collection and analysis. Threats to ecosystems can go undetected for years or decades as a result. Real-time data can help solve this issue but significant technical barriers exist. For example, automated camera traps are widely used for ecosystem monitoring but it is challenging to transmit images for real-time analysis where there is no reliable cellular or WiFi connectivity. Here, we present our design for a camera trap with integrated artificial intelligence that can send real-time information from anywhere in the world to end-users. We modified an off-the-shelf camera trap (Bushnell) and customised existing open-source hardware to rapidly create a 'smart' camera trap system. Images captured by the camera trap are instantly labelled by an artificial intelligence model and an 'alert' containing the image label and other metadata is then delivered to the end-user within minutes over the Iridium satellite network. We present results from testing in the Netherlands, Europe, and from a pilot test in a closed-canopy forest in Gabon, Central Africa. Results show the system can operate for a minimum of three months without intervention when capturing a median of 17.23 images per day. The median time-difference between image capture and receiving an alert was 7.35 minutes. We show that simple approaches such as excluding 'uncertain' labels and labelling consecutive series of images with the most frequent class (vote counting) can be used to improve accuracy and interpretation of alerts. We anticipate significant developments in this field over the next five years and hope that the solutions presented here, and the lessons learned, can be used to inform future advances. New artificial intelligence models and the addition of other sensors such as microphones will expand the system's potential for other, real-time use cases. Potential applications include, but are not limited to, wildlife tourism, real-time biodiversity monitoring, wild resource management and detecting illegal human activities in protected areas.
KW - ecology
U2 - 10.1101/2021.11.10.468078
DO - 10.1101/2021.11.10.468078
M3 - Preprint
BT - Real-time alerts from AI-enabled camera traps using the Iridium satellite network: a case-study in Gabon, Central Africa
PB - bioRxiv
ER -