The new device comes from four teen students at STEM School Highlands Ranch, a suburb just outside of Denver. The students have begun building a new device that combines infrared sensors and artificial intelligence to create "Project Deer."

As outlined in reports, the students aimed to reduce the number of collisions between cards and large animals, which the Federal Highway Administration reports are between one and two million instances every year. On a more local level, Colorado's Department of Transportation reports approximately 4,000 wildlife collisions in the state every year, which costs local drivers $80 million every year. Most of these collisions involve deer and elk.
The students outlined their plan, saying the device would leverage the power of an infrared camera to detect heat signatures created by the body heat of animals and, in this case, deer. Once the camera detects the animal, an algorithm tracks its heat and motion. That data is then placed into AI machine learning, which categorizes the data and logs the animal. In practise, once the device detects an animal, it will send a signal to another device that is located within the inside of the car that will warn the driver that there is an animal nearby. The warning will be both visual and audible.

"We have two components," Singh said. "One is the main processing and one is the camera. First, the camera's going to take eight pictures every second and store it. We have a machine-learning model on the processor, which through all these images will run through a processor and will output deer in this image, deer in (another) image, send a signal to an LED light. Run all thermal images through this model, which will output deer and trigger a response."