Skip to main content

This pedestrian detection system can spot jaywalkers as quickly as you can

A world where everything is automated should be perfectly safe, in theory. In this reality, vehicles travel along predisposed channels and factories run themselves, bringing the potential for collisions, congestion, and other incidents very close to zero. We don’t live in that world, however, and so long as people are around, robots will have to act accordingly.

A group of researchers from the University of California, San Diego (UCSD) have devised a new way for machines and humans to coexist, and it comes in the form of a pedestrian detection system that is much more precise than those being used today. Developed at the university’s Statistical Visual Computing Lab, the technology has a variety of applications, the most notable of which is helping self-driving cars see more clearly.

Recommended Videos

While conventional pedestrian detection systems scan everything in the vehicle’s path for people, the UCSD team’s design leans on cascade detection, which automatically cuts out areas that it can easily recognize as empty — the sky, for example. Then, a unique algorithm scans person-like shapes such as trees, using deep learning and complex pattern recognition to eliminate false alerts.

Because the system only has to focus on small detection windows, it can spot people at a rate of 2 to 4 frames per second (near real-time), resulting in much greater accuracy and response time overall. According to the engineers behind the project, their versions make half as many mistakes as are made on the road right now.

As of now, the system can only recognize one type of object at a time, so there’s a long way to go before it’s ready for production. That being said, the groundwork has been laid, and eventually, the UCSD team could revolutionize pedestrian detection in cars.

Andrew Hard
Andrew first started writing in middle school and hasn't put the pen down since. Whether it's technology, music, sports, or…
Waymo, Nexar present AI-based study to protect ‘vulnerable’ road users
waymo data vulnerable road users ml still  1 ea18c3

Robotaxi operator Waymo says its partnership with Nexar, a machine-learning tech firm dedicated to improving road safety, has yielded the largest dataset of its kind in the U.S., which will help inform the driving of its own automated vehicles.

As part of its latest research with Nexar, Waymo has reconstructed hundreds of crashes involving what it calls ‘vulnerable road users’ (VRUs), such as pedestrians walking through crosswalks, biyclists in city streets, or high-speed motorcycle riders on highways.

Read more
Are self-driving cars the death of car ownership?
Tesla Cybercab at night

Self-driving cars are coming. It remains to be seen how long that will take. Plenty of vehicles can more or less drive themselves on highways, but for now, they still can't completely reliably drive themselves on all streets, in all conditions, taking into account all different variables. One thing is clear, though: the tech industry sees autonomous driving as the future of personal transportation, and they're spending billions to reach that goal.

But what happens when we get there? Tesla made headlines for not only announcing its new Cybercab fully autonomous vehicle, but simultaneously claiming that customers will be able to buy one. That's right, at least if Tesla is to be believed, the Cybercab doesn't necessarily represent Tesla building its own Uber-killing fleet of self-driving cars, but instead giving people the ownership over the self-driving car industry.

Read more
Uber to bring robotaxis to its ridesharing app via Cruise deal
A passenger getting into a Cruise robotaxi.

Uber and autonomous car specialist Cruise are teaming up to offer robotaxi rides starting as early as next year.

Ridesharing giant Uber announced the multiyear partnership on Thursday, saying it will use Cruise’s modified Chevy Bolt vehicles for the service.

Read more