Third Eye: Wearable ML Device Using CNN and Advanced Distance Estimation For Enhanced Cyclist Road Safety

Annually, over 1,000 cyclists lose their lives, and 130,000 sustain injuries in the US due to insufficient awareness and collisions with vehicles. Every few weeks there’s always news of someone being killed or hurt in crashes with cars. According to the National Highway Traffic Safety Administration, an enormous 82.3% of fatal collisions between vehicles and cyclists occur with the point of impact at the front of the vehicle, indicating that collisions frequently occur because vehicles approach from behind and strike the cyclist. Current existing solutions, such as handlebar mirrors or bike sensors, do not provide adequate situational awareness for the biker, since fatal encounters between vehicles and cyclists continue to occur frequently. To help mitigate this problem, this study introduces Third Eye, a novel safety innovation aimed to address the substantial risks encountered by cyclists on urban roads. Using machine learning on a lightweight computing system, Third Eye provides cyclists with a reliable rearview warning system. Third Eye’s distance algorithm generates audio warnings, promptly alerting cyclists to approaching dangers from the rear. With a primary emphasis on accessibility and functionality, Third Eye represents a significant advancement in bike safety technology, potentially able to revolutionize the cycling experience and potentially save lives on a global scale.