Pedestrian Detection

A computer vision task that identifies and locates people in images or video frames, typically using deep learning models such as convolutional neural networks. In accessibility applications, pedestrian detection is used in wearable assistive technologies for blind and low vision users to provide awareness of nearby people for purposes such as social interaction, personal safety, and social distancing. Challenges specific to blind users include the narrow field of view of head-worn cameras, idiosyncratic head movements that cause people to move out of frame, and the difficulty of detecting people at close range when only partial body parts are visible.