Method for labeling sequence of captured images, used in driver assistance system, involves performing previously captured image tracking operations in each keyframe and comparing output of previously captured image from each keyframe

摘要

The method involves selecting two recorded keyframes (2,2') in different preset times from an image sequence (1) according to predetermined criteria. A label is assigned to an identical object in each recorded keyframe. The previously captured image is tracked (3) from the identical labeled object in the keyframes using the image analysis software. The previously captured image tracking operations (3,3') are performed independently in each keyframe (2) and output of previously captured image from each keyframe are compared with each other.