V2V LEARNING METHOD AND LEARNING DEVICE FOR INTEGRATING OBJECT DETECTION INFORMATION ACQUIRED THROUGH V2V COMMUNICATION FROM OTHER AUTONOMOUS VEHICLE WITH OBJECT DETECTION INFORMATION GENERATED BY PRESENT AUTONOMOUS VEHICLE AND TESTING METHOD AND TESTING DEVICE USING THE SAME

摘要

Disclosed is a learning method for generating integrated object detection information by integrating first object detection information and second object detection information. That is, (a) allowing the learning device to generate one or more pair feature vectors by the concatenating network; (b) causing the learning device to generate (i) a discriminant vector and (ii) a box regression vector by applying an FC operation to the pair feature vector by the discriminating network; And (c) the learning device causes the loss unit to generate an integrated loss by referring to the discrimination vector, the box regression vector, and the corresponding GT (Ground Truth), and using the integrated loss. The method according to claim 1, comprising: learning at least some of the parameters included in the DNN by performing backpropagation.