METHOD AND COMPUTING DEVICE FOR GENERATING IMAGE DATA SET TO BE USED FOR HAZARD DETECTION AND LEARNING METHOD AND LEARNING DEVICE USING THE SAME

摘要

A method of generating an image data set for training to be used in a Convolutional Neural Network (CNN) for object detection in an input image to improve the ability to detect risk factors during driving, wherein a computing device comprises: (a) the object and the background obtaining a first label image in which an edge portion is set at a boundary between the background and each of the object and different label values are assigned; (b) extracting the edge portion to generate an edge image from the first label image; (c) generating a second label image by merging an edge-enhanced image generated by weighting the extracted edge portion to the first label image; and (d) storing the input image and the second label image as the training image data set. In addition, through the above method, it is possible to increase the degree of detection of traffic signals, signs, road markings, and the like.