Image semantic segmentation method and device based on channel attention
A semantic segmentation and attention technology, applied in the field of computer vision, can solve problems such as encoder improvement and neglect
Active Publication Date: 2021-09-07
PEOPLE CN CO LTD +1
View PDF4 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Existing work in the direction of semantic segmentation is often dedicated to proposing newer and more complex decoder structures to achieve better segmentation results, but the improvement of the encoder has been ignored
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0027] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.
[0028] figure 1 A schematic flowchart of a method for image semantic segmentation based on channel attention according to an embodiment of the present invention is shown. Such as figure 1 As shown, the method includes the following steps:
[0029] Step S101, preprocessing the original image to obtain an input image to be segmented;
[0030] Step S102, input the input image into the feature extraction network of the image semantic segmentatio...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an image semantic segmentation method and device based on channel attention. The method comprises the steps that: preprocessing is carried out on an original image so as to obtain a to-be-segmented input image; the input image is input into a feature extraction network of an image semantic segmentation model, and feature extraction is performed on the input image by using the feature extraction network to obtain a feature image, a channel attention module is inserted into each bottleneck module of each stage of the feature extraction network, and is used for carrying out horizontal pooling and vertical pooling on input features to obtain two matrixes; the two matrixes are processed in parallel by using one-dimensional convolution from a channel angle, normalization processing is performed, and then an average value is taken to obtain a channel weight; and the feature image is input into a decoder of the image semantic segmentation model, and the feature image is processed by using the decoder to obtain a predicted segmentation map. According to the method, the performance of the encoder is improved through the channel attention mechanism, the encoder can be conveniently transplanted to various segmentation networks, and the performance can be obviously improved.
Description
technical field [0001] The invention relates to the technical field of computer vision, in particular to an image semantic segmentation method and device based on channel attention. Background technique [0002] Image semantic segmentation is one of the basic topics of computer vision and can be applied to many fields. Its purpose is to give a label to each pixel in the image. Currently, most semantic segmentation models are studied based on the fully convolutional network (FCN) framework. They can be divided into two parts, the encoder and the decoder. The encoder part usually uses a pre-trained classification network to extract features, while the decoder has a different structure and is used to process the features to calculate the final prediction result map. Existing work in the direction of semantic segmentation is often dedicated to proposing newer and more complex decoder structures to achieve better segmentation results, but improvements to the encoder have been ne...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/34G06K9/46G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 郭俊波郭筱凤靳国庆马凌峰谢洪涛张勇东
Owner PEOPLE CN CO LTD