20240020959. Method and System for Generating Test Cases for Visual Train Positioning simplified abstract (Beijing Jiaotong University)
Contents
Method and System for Generating Test Cases for Visual Train Positioning
Organization Name
Inventor(s)
Method and System for Generating Test Cases for Visual Train Positioning - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240020959 titled 'Method and System for Generating Test Cases for Visual Train Positioning
Simplified Explanation
The patent application describes a method and system for generating test cases for visual train positioning. The method involves obtaining real environment images around a train and classifying them based on blur types. A generative adversarial network (GAN)-based image generation network is then trained using non-blurred and blurred training images of different blur types, along with a preset blur type, to obtain an image generation model. Each real non-blurred image and target reference data are inputted into the image generation model to generate a target reconstructed blurred image. Images with structural similarities lower than a set threshold are deleted.
- The method involves obtaining real environment images around a train and classifying them based on blur types.
- A generative adversarial network (GAN)-based image generation network is trained using non-blurred and blurred training images of different blur types, along with a preset blur type, to obtain an image generation model.
- Each real non-blurred image and target reference data are inputted into the image generation model to generate a target reconstructed blurred image.
- Images with structural similarities lower than a set threshold are deleted.
Potential applications of this technology:
- Testing and validation of visual train positioning systems.
- Development of simulation environments for train positioning algorithms.
- Training and evaluation of machine learning models for train positioning.
Problems solved by this technology:
- Lack of realistic test cases for visual train positioning systems.
- Difficulty in generating diverse and representative training data for train positioning algorithms.
- Limited availability of real-world blurred images for testing and evaluation.
Benefits of this technology:
- Improved accuracy and reliability of visual train positioning systems.
- Enhanced development and testing capabilities for train positioning algorithms.
- Cost-effective and efficient generation of test cases for train positioning.
Original Abstract Submitted
a method and system for generating test cases for visual train positioning are provided and relate to the technical field of train positioning. the method includes: first obtaining real environment images around a train, and classifying the real environment images based on blur types; training a generative adversarial network (gan)-based image generation network with each non-blurred training image, each blurred training image of any blur type in a same scenario and a preset blur type as inputs, and a reconstructed blurred image and a corresponding blur type as outputs, to obtain an image generation model; then inputting each real non-blurred image and target reference data into the image generation model to generate a target reconstructed blurred image, and then deleting target reconstructed blurred images with structural similarities lower than a set threshold.
