Skip to main content

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

Pedestrian Detection
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.

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.

Editors' Recommendations

Andrew Hard
Former Digital Trends Contributor
Andrew first started writing in middle school and hasn't put the pen down since. Whether it's technology, music, sports, or…
Robotaxi firm Cruise ordered to halve fleet following incidents
A Cruise autonomous car.

Autonomous car company Cruise has been told by regulators to halve its robotaxi fleet in San Francisco following a crash with a fire truck on Thursday in which the driverless car's passenger suffered minor injuries.

The regulator -- the California Department of Motor Vehicles (DMV) -- said that it’s looking into “recent concerning incidents” involving self-driving Cruise cars operating on the city’s public roads.

Read more
An autonomous car in San Francisco got stuck in wet concrete
A Cruise autonomous car.

A self-driving car operated by General Motors-backed Cruise got stuck on Tuesday when it drove into a patch of wet concrete.

The incident happened in San Francisco and occurred just days after California's Public Utilities Commission made a landmark decision when it voted to allow autonomous-car companies Cruise and Waymo to expand their paid ridesharing services in the city to all hours of the day instead of just quieter periods.

Read more
Waymo taps the brakes on its autonomous-trucking project
A Waymo autonomous trick undergoing testing on a highway.

Six years after launching its autonomous-truck program, Waymo has said it’s decided to focus more on developing its ridesharing ambitions using its self-driving cars and minivans.

The California-based, Alphabet-owned company said its decision to effectively put autonomous trucking on the back burner is down to the “tremendous momentum and substantial commercial opportunity” that it’s seeing with the pilot ridesharing service it launched in Arizona in 2018 before taking it to several other states. Customers involved in the program can use an app to call a Waymo driverless car in the same way they would book an Uber.

Read more