Multi-scale image semantic segmentation method
A semantic segmentation and multi-scale technology, applied in the field of computer vision, can solve the problems of loss of details of segmentation results, low utilization efficiency of receptive field features, and insufficient robustness of segmentation, etc., to reduce the amount of calculation and the number of parameters, and reduce the calculation volume and number of parameters, the effect of increasing utilization
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2019-09-13
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to the field of computer vision, in particular to a multi-scale image semantic segmentation method. Background technique
[0002] Semantic segmentation is an important issue in the field of computer vision. At present, various application scenarios (such as object detection, recognition, etc.) need to be realized through semantic segmentation. The task of semantic segmentation is to judge the category of each pixel of the image and label it.
[0003] The semantic segmentation problem puts forward two requirements for the algorithm: (1) classification: the labels of the pixels in the target range belonging to the same category must be consistent; (2) localization: the pixels at the edge of the target can also be accurately classified. Among these two requirements, the former requires high-level semantic features, which can usually be obtained by setting the convolution step size, pooling downsampling, etc.; while the latter requir...
Examples
Embodiment
[0047] Such as figure 1 As shown, a multi-scale image semantic segmentation method includes the following steps:
[0048] S1. Obtain an image to be segmented and a corresponding label, the image to be segmented is a three-channel color image, and the label is a category label corresponding to each pixel position;
[0049] S2. Construct a fully convolutional deep neural network, such as Figure 4 As shown, the full convolution deep neural network includes a convolution module, a hole convolution module, a pyramid pooling module, a 1×1×depth convolution layer, and a deconvolution structure; the hole convolution module includes several groups A multi-scale atrous convolution structure, the multi-scale atrous convolution structure is provided with atrous convolution kernels of different expansion rates, and extracts information of low, medium, and high-resolution targets from the feature image; step S2 specifically includes the following steps:
[0050] S21. The fully convoluti...