Neural network training method, image processing method and device, equipment and medium

Abstract

The embodiment of the invention discloses a neural network training method, an image processing method and device, equipment and a medium. The method comprises steps of carrying out the splicing of sample images, and obtaining a spliced sample image; extracting feature data of the spliced sample images through a first neural network; splitting the extracted feature data according to a rule of splicing the sample images to obtain feature data of each spliced sample image; determining a prediction result of each image processing task through a first neural network according to the feature data of each sample image; according to the determined prediction result of each image processing task and the corresponding annotation result of each sample image, obtaining an annotation result. Accordingto the method, the network parameters of the first neural network are adjusted, training is carried out through the mixed data set, the network parameters of the first neural network are optimized through different data sets, and the first neural network with the optimized parameters can process a plurality of image processing tasks at the same time.

Description

technical field [0001] The present application relates to computer vision technology, especially a method for training a neural network, an image processing method, device, equipment and medium. Background technique [0002] Monocular depth estimation and scene semantic segmentation are very important problems in the field of computer vision. Monocular depth estimation is to estimate the real depth value of each pixel in the image based on the image obtained by a single camera. Scene semantic segmentation is to predict the category to which each pixel in the image belongs. Monocular depth estimation and scene semantic segmentation have a wide range of applications, especially in the fields of robot navigation and automatic driving. [0003] At present, the traditional depth estimation and scene semantic segmentation tasks require two independent networks to implement. The two networks will increase the burden on the processor and increase the time consumption, which is not...

AI Technical Summary

Problems solved by technology

[0003] At present, the traditional depth estimation and scene semantic segmentation tasks require two independent networks to implement, and the two networks will increase the burden on the processor and increase time-consuming, which is not conducive to practical applications

Images