Active Pedestrian Safety: from Research to Reality

Active Pedestrian Safety: from Research to Reality

This is a very good talk about advances in computer vision with applications in automotive pedestrian detection. Details @ Microsoft’s site.

One of the most significant large-scale deployments of intelligent systems in our daily life nowadays involves driver assistance in smart cars.  The past decade has witnessed a steady increase of interest in the plight of the vulnerable road users, i.e. pedestrians and bicyclists. Accident statistics show that roughly one quarter of all traffic fatalities world-wide involve vulnerable road users; most accidents occur in an urban setting. Devising an effective driver assistance system for vulnerable road users has long been impeded, however, by the ‘perception bottleneck’, i.e. not being able to detect and localize vulnerable road users sufficiently accurate. The problem is challenging due to the large variation in object appearance, the dynamic and cluttered urban backgrounds, and the potentially irregular object motion. Topping these off are stringent performance criteria and real-time constraints. I give an overview of the remarkable research progress that has been achieved in this area and discuss its main enablers: the algorithms, the data, the hardware and the tests.

Our long-standing research on vulnerable road users has recently paid off.  Our company, Daimler, deploys an advanced set of driver assistance functions for its Mercedes-Benz 2013 E- and S-Class models, termed “Intelligent Drive”, using stereo vision sensing. It includes a pedestrian safety component which facilitates fully automatic emergency braking – the system works day and night. I conclude by discussing future research directions, on the road towards accident-free driving.





Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: