Systems and methods to train a prediction system for depth perception

A non-transitory computer-readable medium for training a depth model including instructions that, when executed by a processor, cause the processor to:

• segment an image to mask areas beyond bounding boxes and identify unmasked areas within the bounding boxes;
• train the depth model using depth losses from comparing weighted points associated with ranked pixels and a size of objects associated with a pixel count within the unmasked areas to ground-truth depth;
• and
• provide the depth model for object detection.

A method, comprising:

• segmenting an image to mask areas beyond bounding boxes and identify unmasked areas within the bounding boxes;
• training a depth model using depth losses from comparing weighted points associated with ranked pixels and a size of objects associated with a pixel count within the unmasked areas to ground-truth depth;
• and
• providing the depth model for object detection.