The present invention relates to a method for generating a processed image, the method comprising: obtaining a target image; generating a target image mask corresponding to the target image using the target image and a first artificial neural network, wherein the first artificial neural network is trained to generate an image mask from a first image, and is trained by using an error calculated from a second artificial neural network, and wherein the second artificial neural network is configured to discriminate a second image generated by applying the image mask to the first image and a reference image of which the image mask is not applied; and generating the processed image of which an environmental noise is reduced from the target image by applying the target image mask to the target image.
Method for acquiring object information and apparatus for performing same
2024-07-30
Patent
Electronic Resource
English
Method for Acquiring Object Information and Apparatus for Performing Same
European Patent Office | 2023
|METHOD FOR ACQUIRING OBJECT INFORMATION AND APPARATUS FOR PERFORMING SAME
European Patent Office | 2022
|METHOD FOR ACQUIRING MOVEMENT ATTRIBUTES OF MOVING OBJECT AND APPARATUS FOR PERFORMING THE SAME
European Patent Office | 2023
|INFORMATION ACQUIRING DEVICE AND INFORMATION ACQUIRING METHOD
European Patent Office | 2017
|APPARATUS FOR ACQUIRING VEHICLE INFORMATION AND METHOD THEREOF
European Patent Office | 2016
|