Saving Lives Behind the Wheel: Artificial Intelligence and Computer Vision for Road Safety

More than 1.35 million people die in road crashes each year. These deaths are avoidable and unnecessary and governments all over the world are resolving to reduce them, through their “Vision-Zero” programs. We will take a technology deep-dive into this problem to first show how a lack of technological innovations has failed to lower this trend over the past 20 years. Then we will argue how three enabling trends, 1) video-analytics maturity, 2) availability of powerful edge-computing hardware, and 3) proliferation of CCTV cameras, are poised to change the traffic safety landscape for the better, to reduce fatalities and crashes. We will summarize the challenges in this industry, and show how real-time edge-based deep-learning systems can tackle them effectively by retrofitting existing camera infrastructure for road safety.