AI at the Edge

Chapter 11. Use Case: Wildlife Monitoring

Now that we understand the basics of developing machine learning models for edge applications, the first realm of use cases we will cover is related to wildlife conservation and monitoring. We will explore possible problems and their associated solutions for each use case chapter in this book via the development workflow outlined in Chapter 9.

There is a rapid decline of threatened species worldwide due to various human civilization impacts and environmental reasons or disasters. The primary drivers of this decline are habitat loss, degradation, and fragmentation.¹ The causes of these drivers are human activity, such as urbanization, agriculture, and resource extraction. As a result of this decline, many species are at risk of extinction.

A growing number of AI and edge AI applications are being developed with the aim of helping to protect wildlife. These applications range from early detection of illegal wildlife trade to monitoring of endangered species to automated identification of poachers. As previously discussed in this book, edge AI is used to process data locally on the device instead of in the cloud. This is important for wildlife conservation purposes because it can be used to process data in remote locations without the need for an internet connection. This means that data can be processed quickly and without the need for expensive infrastructure, helping prevent future poaching and thus protecting our planet’s most vulnerable ...