Water body recognition method and device, electronic equipment and storage medium

Abstract

The invention provides a water body recognition method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring visible light image data to be detected; inputting the to-be-detected visible light image data into a water body recognition model to obtain a confidence coefficient that each pixel point output by the water body recognition model is a water body; determining a target water body area in the to-be-detected visible light image data based on the confidence of each pixel point as a water body; wherein the water body recognition model is obtained by training an initial network model based on image sample data; the initial network model comprises network layer connections of a plurality of preset paths. According to the water body recognition method and device, the electronic equipment and the storage medium provided by the invention, the number of connection layers in the network can be increased, and the increase of the number of connection layers means that more convolution features are reserved, so that the accuracy of water body recognition is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a water body recognition method, device, electronic equipment and storage medium. Background technique [0002] Water resources are not only closely related to human production and life, but also to the sustainable and stable development of urban economy. Therefore, it is particularly important to identify urban water bodies and dynamically analyze the state of urban water bodies. [0003] In related technologies, the water body area in the image data is usually identified by deep learning models such as convolutional neural network (Convolution Neural Network, CNN) or image semantic segmentation network (SegNet), but the above-mentioned deep learning model is limited by the depth of the network layer. , the learned features are less, which will reduce the accuracy of the deep learning model for water body recognition. Contents of the invention [0004] Aiming at the...

AI Technical Summary

Problems solved by technology

[0003] In related technologies, deep learning models such as Convolution Neural Network (CNN) or Image Semantic Segmentation Network (SegNet) are usually used to identify water body regions in image data, but the above deep learning models are limited by the depth of the network layer. , the learned features are less, which will reduce the accuracy of the deep learning model for water body recognition

Images