CNN LEARNING METHOD AND LEARNING DEVICE FOR OBJECT DETECTOR BASED ON CNN ADAPTABLE TO CUSTOMERS' REQUIREMENTS SUCH AS KEY PERFORMANCE INDEX USING TARGET OBJECT MERGING NETWORK AND TARGET REGION ESTIMATING NETWORK AND TESTING METHOD AND TESTING DEVICE USING THE SAME TO BE USED FOR MULTI-CAMERA OR SURROUND VIEW MONITORING

摘要

A method for learning parameters of a CNN-based object detector suitable for user requirements such as key performance indicators using a target object integration network and a target area prediction network is provided. The CNN may be redesigned as the scale of the object is changed by changing the resolution or focal length according to the key performance indicator. The method, wherein the learning device (i) causes the target region prediction network to find the kth prediction target region, (ii) causes the RPN to correspond to the object on the (k_1) to (k_n)th processed image generate (k_1)th to (k_n)th object proposals, (iii) cause the target object aggregation network to integrate the object proposals, and (k_1)th to (k_n)th object proposals output from the FC layer and allowing the object detection information to be integrated. The method may be usefully performed for multi-camera, surround view monitoring, and the like, since the accuracy of the 2D bounding box is improved.