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

CN110490082BActive Publication Date: 2022-04-05ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY
7 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2022-04-05

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a road scene semantic segmentation method that effectively integrates neural network features. It constructs a convolutional neural network in the training stage, which includes an input layer, a hidden layer, and an output layer. The hidden layer includes three neural network blocks. Spatial feature extraction channel, background feature extraction channel composed of 5 neural network blocks, and feature fusion channel composed of the fifth fusion block; each original road scene image in the training set is input into the convolutional neural network for training , to obtain 12 semantic segmentation prediction maps corresponding to each original road scene image; by calculating the set of 12 semantic segmentation prediction maps corresponding to each original road scene image and processing the 12 corresponding real semantic segmentation images Convolutional neural network training model is obtained by one-hot encoding the loss function value between sets of images; in the test phase, the convolutional neural network training model is used for prediction; the advantage is high segmentation accuracy and strong robustness.
Need to check novelty before this filing date? Find Prior Art

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. ...