Real-time alerts from AI-enabled camera traps using the Iridium satellite network : A case-study in Gabon, Central Africa.
English Gabon, a Central African country, has long proven to be a fruitful testing ground for camera trap technology. The wealth of data generated means that there are large datasets from various projects. In this study, they built the real-time alert system by modifying standard camera traps (Bushnell™) ready to use. The system uses communication through the Iridium satellite network, it works even in remote areas without a telephone signal or without reliable Wi-Fi. The results show that the alert system can work for at least 3 months in the absence of humans when capturing a median of 17.23 images per day. The median time difference between taking images and receiving an alert was about 7,35 min, although some outliers showed delays of 5 days or more when the system was incorrectly installed initially and unable to connect to the Iridium satellite network. These models of artificial intelligence and the addition of other sensors such as microphones will expand the potential of...