A Road Scene Semantic Segmentation Method Effectively Fusion of Neural Network Features
A neural network and semantic segmentation technology, applied in neural learning methods, biological neural network models, scene recognition, etc., can solve the problem that simple fusion of low-level and high-level features is not effective, so as to improve the accuracy of semantic segmentation and information loss The effect of improving and enhancing robustness
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Publication Date
- 2022-04-05
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to a semantic segmentation method, in particular to a road scene semantic segmentation method which effectively integrates neural network features. Background technique
[0002] Semantic segmentation is a fundamental technique for many computer vision applications, such as scene understanding, autonomous driving, etc. With the development of Convolutional Neural Networks, especially Fully Convolutional Neural Networks (FCNs), many promising results have been achieved on benchmarks. The fully convolutional neural network has a typical encoder-decoder structure, semantic information is first embedded into the feature map through the encoder, and the decoder is responsible for generating segmentation results. Typically, the encoder extracts image features through a pre-trained convolutional model, and the decoder contains multiple upsampling components to recover resolution. Although the encoder's most important feature maps may be...
Examples
Embodiment Construction
[0042] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.
[0043] The present invention proposes a road scene semantic segmentation method that effectively integrates neural network features, which includes two processes, a training phase and a testing phase.
[0044] The specific steps of the described training phase process are:
[0045] Step 1_1: Select Q original road scene images and the real semantic segmentation images corresponding to each original road scene image, and form a training set, and record the qth original road scene image in the training set as {I q (i,j)}, combine the training set with {I q (i, j)} corresponding to the real semantic segmentation image is denoted as Then, the existing one-hot encoding technology (one-hot) is used to process the real semantic segmentation images corresponding to each original road scene image in the training set into 12 one-hot encoded images. ...