Model training method and device, map drawing method and device, computer equipment and medium

Abstract

The invention provides a model training method and device, and the method comprises the steps: constructing an initial network model which comprises a backbone network, a region suggestion network, a mask network and an attention mechanism-based recognition network; wherein the backbone network performs feature extraction on the input picture to obtain a feature map; the region suggestion network is used to generate candidate target boxes; and the mask network obtains a mask prediction result based on the feature map and the candidate target frame. The identification network obtains a classification prediction result and an outer bounding box prediction result based on the feature map, the candidate target frame and the mask prediction result; acquires a plurality of training pictures and respective labels of the plurality of training pictures, wherein the label of any training picture comprises the category of the target object in the any training picture, an outer wrapping frame and a mask; and trains the initial network model by using the plurality of training pictures and the respective labels of the plurality of training pictures to obtain a target network model. The invention further provides a map drawing method and device, computer equipment and a medium.

Description

technical field [0001] Embodiments of the present invention relate to the field of computer technology, and more particularly, to a model training method and apparatus, a map drawing method and apparatus, computer equipment, and a medium. Background technique [0002] In the production process of high-precision maps, various target objects on the road need to be drawn. [0003] In the process of realizing the present invention, the inventor found that there are at least the following problems in the prior art: if various target objects are artificially identified, extracted and drawn from road pictures, it will cost a lot of labor and the efficiency is extremely low. Automation alternative. However, in the existing automatic recognition schemes for target objects, there are often problems such as deviation of the positioning of the outer frame of the target object due to the influence of the background area, which in turn leads to the recognition deviation of the target obj...

AI Technical Summary

Problems solved by technology

[0003] In the process of realizing the present invention, the inventors have found that there are at least the following problems in the prior art: if artificially identifying, extracting and drawing various target objects from road pictures, it will cost a lot of labor costs and the efficiency is extremely low. Au

Images