This New Technology is More Accurate Than Existing Alternatives

 - Feb 11, 2016
References: & gizmag
A group of engineers and researchers working out of the University of California, San Diego have invented a high-tech pedestrian detection system that is capable of performing pedestrian recognition in a more accurate manner than existing systems.

Most pedestrian recognition technologies divide images into smaller sections that are processed in order to determine whether the image represents a human form. This makes things challenging because humans obviously come in different shapes and sizes, something which throws up complications. However this new pedestrian detection system detects images in stages rather than one go, allowing for easy rejection of image frames that don't contain human forms.

This pedestrian detection algorithm offers a lot of promise in various settings. Self-driving vehicles are the most obvious applications, but they could also be of use in robotics as well as image search systems.