Object detection using multiple neural networks trained on different image fields

摘要

Systems and methods related to object detection include receiving an image frame comprising an array of pixels captured by an image sensor associated with a processing device, identifying a near field image segment and a far field image segment in the image frame, and near field. Applying a first neural network trained on the near field image segments to the near field image segment to detect the object presented in the image segment, and training on the far field image segments to detect the object presented on the near field image segment. The second neural network may be applied to the far field image segment.