Multi-scale image segmentation method based on weight learning

Abstract

The invention discloses a multi-scale image segmentation method based on weight learning. According to the neural network designed by the invention, the target features are fully extracted on different scales, the edge and morphological features of the target are fully ensured, and the learnable weight is used to reserve useful features to eliminate noisy features. The network model mainly comprises an encoding part and a decoding part, in the encoding stage, features under different scales are extracted through a network, the features of a multi-layer feature space are fused in the decoding stage, a category probability distribution diagram can be obtained through each enhanced feature, and the obtained enhanced features are weighted through learnable self-adaptive weights to obtain finalfeatures. Experiments show that the method provided by the invention has higher accuracy and recall rate in road extraction, and is closer to the contour of a real road in the aspect of road appearance.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and is a multi-scale image convolution layer feature learning method based on weight learning, which can be applied to image feature extraction stages such as image target recognition and image segmentation. Background technique [0002] Feature extraction is an important step in object recognition and image segmentation. Target features mainly include target color features, texture features, shape features and spatial relationship features. The color feature is a global feature that describes the surface properties of the scene corresponding to the image or image region; the texture feature is also a global feature, which also describes the surface properties of the scene corresponding to the image or image region; there are two types of shape features Representation methods, one is the contour feature, the other is the regional feature, the contour feature of the image ...

AI Technical Summary

Problems solved by technology

But in practice, it is generally done manually. However, manually selecting features is a very laborious and heuristic method. Whether it can be selected depends largely on experience and luck, and its adjustment takes a lot of time.

Images