The present invention relates to a method for detecting a remote small drone using deep learning. More specifically, without using special devices and technologies, using a convolutional neural network (CNN), one of deep learning technologies, it is possible to detect a small drone located at a distance so far that it is difficult for a human to identify it with the naked eye. It relates to a method for detecting a small drone from a distance using deep learning that can To this end, the present invention generates learning data that generates learning data that can identify only the drone object in the image including the background through the labeling process of setting a bounding box for the drone object in a plurality of images including the background and the drone object. process 100; A data conversion process 200 for converting learning data into an input form for deep learning network learning in order to detect a drone object using a deep learning network and track its location; and a deep learning network model including a convolutional neural network, using the training data converted in the data conversion process 200 as input data for the deep learning network model to detect a drone object on the image used as input data, , provides a remote small drone detection method using deep learning including a data learning process 300 for learning to track its location.
展开▼
