Convolutional neural network rainfall intensity classification method for rainy day pictures
A convolutional neural network and rainfall intensity technology, applied in the field of real-time rainwater measurement in municipal engineering, can solve problems such as rare data sets, insufficient accuracy, and high price, and achieve excellent feature extraction performance, improved classification performance, and fast computing speed. Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0036] The present invention extracts rainy day picture features through the convolutional neural network, and completes the training of the convolutional neural network in two steps, that is, training in the synthetic data set and the real data set respectively, can effectively extract the rainfall information in the picture, and can ignore the background at the same time, Interference factors such as light and shade, rain mark angle, distribution, etc., have high classification accuracy.
[0037] Specifically, a convolutional neural network rainfall intensity classification method for rainy day pictures, such as figure 1 shown, including the following steps:
[0038] (1) Synthesize rainfall pictures through image processing software to obtain a synthetic data set;
[0039] (2) Build a convolutional neural network (CNN), and use the synthetic data set in step (1) to pre-train the convolutional neural network;
[0040] (3) Collect actual rainfall pictures to obtain real data...
Embodiment 2
[0067] Such as Figure 7 As shown, the convolutional neural network rainfall intensity online quantification method for rainy pictures provided by the present invention comprises the following steps:
[0068] (1) Synthesize rainfall pictures through image processing software to obtain a synthetic data set;
[0069] (2) Build and modify the structure of the convolutional neural network (CNN), and use the synthetic data set in step (1) to pre-train the convolutional neural network;
[0070](3) Collect actual rainfall pictures to obtain real data sets;
[0071] (4) Fine-tune the pre-trained model using the real data set in step (3) to obtain a trained model;
[0072] (5) Use the model trained in step (4) for online quantification of real-time rainfall intensity.
[0073] In some preferred modes, the specific process of step (1) is: adding different rainfall intensities to the original image by image processing software to obtain a synthetic rainfall image;
[0074] In some pr...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com