The automated elephant detection and deterrence system (Elephant A.I.) was devised to provide a solution to human-elephant conflict.
The conflict that arises between humans and elephants in countries such as India, Sri Lanka, and Kenya, claims many hundreds of human and elephant lives per year. These negative interactions arise when humans meet elephants on their trails, when elephants raid fields for food, and when elephants try to cross railways. The system has two components: an elephant detector (two raspberry pi’s with IR and NoIR filtered cameras) and an elephant deter device (one raspberry pi zero with an amplifier and speakers). The elephant detector camera is triggered by a PIR, it acquires images which are then classified as elephant/not elephant using a convolutional neural network (CNN) based image classifier. If an elephant is detected, the elephant detector will notify the elephant deter device ,which will play audio of a stimuli which elephants dislike (e.g. the sounds of bees). The system was a finalist for the 2017 Hackaday Prize.