A train-time loss in a system and method for calibrating object detection

An autonomous vehicle control system, comprising:

• at least one camera mounted on the autonomous vehicle for capturing an image of an environment outside of the autonomous vehicle;
• a controller connected to the at least one camera,
• the controller configured to
• receive an image captured by the at least one camera,
• predict, using a deep learning network (DNN), a bounding box and corresponding class label,
• evaluate the prediction with a total loss function including
• an object detection loss function,
• a box regression loss function, and
• a calibration loss function that takes into account precision and confidence;
• and
• output a calibrated image with the object bounding box, the corresponding label, and a respective confidence score, wherein the confidence score is a probability associated with the predicted class label.

A non-transitory computer-readable storage medium including computer executable instructions, wherein the instructions, when executed by a computer, cause the computer to perform a method comprising:

• capturing an image by a camera;
• receiving, by the computer, the image;
• predicting, using a deep learning neural network DNN, a bounding box and corresponding class label;
• evaluating, by the computer, the prediction with a total loss function including
• an object detection loss function,
• a box regression loss function, and
• a calibration loss function that takes into account precision and confidence;
• and
• outputting, by the computer, a calibrated image with the object bounding box, the corresponding label, and a respective confidence score, wherein the confidence score is a probability associated with the predicted class label.