Image semantic segmentation method and device

Abstract

The invention provides an image semantic segmentation method and device. The method comprises the steps of inputting a to-be-processed image into an image recognition model, wherein the image recognition model comprises a short-time dense connection network layer and a decoding network layer, the short-time dense connection network layer comprises a convolution module, a plurality of short-time dense connection layers and an output module, and each short-time dense connection layer comprises a plurality of short-time dense connection modules; calling a convolution module to process the to-be-processed image to obtain a first feature map corresponding to the to-be-processed image; calling a short-time dense connection layer to process the first feature map to obtain a second feature map; calling an output module to process the second feature map to obtain a third feature map; calling a decoding network layer to perform up-sampling on the third feature map and mapping the third feature map to the segmentation category to obtain a fourth feature map of which the channel number is the segmentation category number; and determining a semantic segmentation result corresponding to the to-be-processed image according to the fourth feature map. According to the invention, the network structure redundancy can be reduced, and the image semantic segmentation performance and efficiency are improved.

Description

technical field [0001] Embodiments of the present disclosure relate to the technical field of image processing, and in particular, to a method and device for image semantic segmentation. Background technique [0002] Semantic segmentation is a basic direction in the field of computer vision. With the progress of deep learning methods in recent years, the direction of semantic segmentation has also made great progress, and has been applied in more and more scenarios, such as autonomous driving, human-computer interaction, and medical treatment. Analytics, augmented reality, and more. [0003] In order to take into account the real-time and effectiveness requirements of semantic segmentation, a mainstream practice in the design of real-time semantic segmentation is: select the existing lightweight backbone network for encoding, and independently design a lightweight decoding network to achieve improved segmentation. Efficiency, among which ResNet-18, Xception-39, etc. are oft...

AI Technical Summary

Problems solved by technology

[0003] In order to take into account the real-time and effectiveness requirements of semantic segmentation, a mainstream practice in the design of real-time semantic segmentation is: select an existing lightweight backbone network for encoding, and independently design a lightweight decoding network to achieve improved segmentation. Efficiency, among which ResNet-18, Xception-39, etc. are often selected backbone networks, but these backbone networks lack customized design for segmentation tasks, and their own structure may produce structural redundancy for segmentation tasks, directly use As a backbone network will lead to a decline in semantic segmentation performance and efficiency

Images