View source for 20230162373. MOVING TARGET FOCUSING METHOD AND SYSTEM BASED ON GENERATIVE ADVERSARIAL NETWORK simplified abstract (University of Electronic Science and Technology of China)

=MOVING TARGET FOCUSING METHOD AND SYSTEM BASED ON GENERATIVE ADVERSARIAL NETWORK=


==Organization Name==

[[:Category:University of Electronic Science and Technology of China|University of Electronic Science and Technology of China]]


[[Category:University of Electronic Science and Technology of China]]

==Inventor(s)==

[[:Category:Jiang Qian of Chengdu (CN)|Jiang Qian of Chengdu (CN)]][[Category:Jiang Qian of Chengdu (CN)]]

[[:Category:Haitao Lyu of Xinyang (CN)|Haitao Lyu of Xinyang (CN)]][[Category:Haitao Lyu of Xinyang (CN)]]

[[:Category:Junzheng Jiang of Guilin (CN)|Junzheng Jiang of Guilin (CN)]][[Category:Junzheng Jiang of Guilin (CN)]]

[[:Category:Minfeng Xing of Chengdu (CN)|Minfeng Xing of Chengdu (CN)]][[Category:Minfeng Xing of Chengdu (CN)]]

==MOVING TARGET FOCUSING METHOD AND SYSTEM BASED ON GENERATIVE ADVERSARIAL NETWORK - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20230162373 titled 'MOVING TARGET FOCUSING METHOD AND SYSTEM BASED ON GENERATIVE ADVERSARIAL NETWORK

==Simplified Explanation==

The patent application describes a method and system for focusing on moving targets using a generative adversarial network (GAN). Here are the key points:

* The method involves generating a two-dimensional image with defocused moving targets using a range doppler algorithm.
* Ideal Gaussian points are generated at the center of each defocused moving target in the image to create training labels.
* A generative adversarial network (GAN) is constructed, consisting of a generative network and a discrimination network.
* The training sample and training labels are inputted into the GAN for repeated training until the generative network meets a preset condition, resulting in a trained network model.
* The trained network model can then be used to input a testing sample and output a focused image of the moving target.

Potential applications of this technology:

* Surveillance systems: Enhancing the focus on moving targets in surveillance footage.
* Autonomous vehicles: Improving the ability to detect and focus on moving objects in real-time.
* Medical imaging: Enhancing the focus on moving targets in ultrasound or MRI scans.
* Robotics: Improving object detection and tracking capabilities in robotic systems.

Problems solved by this technology:

* Traditional methods struggle to focus on moving targets accurately, resulting in blurred or distorted images.
* Manual adjustment of focus parameters is time-consuming and may not be feasible in real-time scenarios.
* Existing algorithms may not effectively handle defocused moving targets, leading to inaccurate results.

Benefits of this technology:

* Improved accuracy: The use of a generative adversarial network allows for more accurate focusing on moving targets.
* Real-time capability: The trained network model can provide focused images in real-time, enabling faster decision-making.
* Automation: The system eliminates the need for manual adjustment of focus parameters, reducing human intervention.
* Versatility: The technology can be applied to various domains, including surveillance, autonomous vehicles, medical imaging, and robotics.


==Original Abstract Submitted==

a moving target focusing method and system based on a generative adversarial network are provided. the method includes: generating, using a range doppler algorithm, a two-dimensional image including at least one defocused moving target, as a training sample; generating at least one ideal gaussian point in a position of at least one center of the at least one defocused moving target in the two-dimensional image, to generate a training label; constructing the generative adversarial network, the generative adversarial network includes a generative network and a discrimination network; inputting the training sample and the training label into the generative adversarial network to perform repeated training until an output of the generative network reaches a preset condition, to thereby obtain a trained network model; and inputting a testing sample into the trained network model, to output a moving target focused image.



[[Category:G06T7/20]]