Deep Learning Makes Driverless Cars Better at Spotting Pedestrians

Today’s car crash-avoidance systems and experimental driverless cars rely on radar and other sensors to detect pedestrians on the road. The next improvement may come from engineers at the University of California, San Diego (UCSD), who have developed a pedestrian detection system that can perform in close to real-time based on visual cues alone. This video-only detection could make systems for spotting pedestrians both cheaper and more effective.

Such a vision-based safety system has remained elusive in cars because computers typically face a tradeoff between analyzing video images quickly and drawing the right conclusions. On the one hand, a simple “cascade detection” computer vision algorithm can quickly detect many pedestrians in certain images, but lacks the sophistication to distinguish between pedestrians and similar-looking objects in the toughest cases. On the other hand, machine learning algorithms called deep neural networks can handle such complex pattern recognition, but work too slowly for real-time pedestrian detection.

Researchers combined the best of both approaches for the new system, said Nuno Vasconcelos,…[Read more]