Image processing method and system in garden design based on generative adversarial network

An image processing and gardening technology, applied in biological neural network models, neural learning methods, design optimization/simulation, etc., can solve the increasingly complex factors of landscape design, more time and energy, heavy workload and mental pressure And other issues

Inactive Publication Date: 2021-05-28
CHONGQING JIAOTONG UNIVERSITY +1
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] (1) Due to changes in the environment, development of technology, and advancement of concepts, the factors affecting landscape design are becoming more and more complex
[0005] (2) The reusability of landscape garden design is very low, which belongs to "non-standard customization" products, which makes it necessary for designers to spend more time and energy on non-original, normative and basic work in...

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image processing method and system in garden design based on generative adversarial network
  • Image processing method and system in garden design based on generative adversarial network
  • Image processing method and system in garden design based on generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0049] Aiming at the problems existing in the prior art, the present invention provides an image processing method in garden design based on confrontational generative networks. The present invention will be described in detail below in conjunction with the accompanying drawings.

[0050] The image processing method in the garden design based on the confrontation generation network provided by the present invention is based on the fact that the garden design is essentially based on certain explicit or latent rules of image changes, and pix2pix is ​​naturally compatible with the garden design. Firstly, a data set for trainin...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention belongs to the technical field of image processing in garden design, and discloses an image processing method and system in garden design based on an adversarial generative network. The method comprises the steps: obtaining a data set for training, the data sets are respectively a site environment condition graph before design and a garden design plane layout conceptual graph after design, then training the data sets according to a GAN iterative training method and a picture translation generation method, and generating the garden design plane layout conceptual graph. The GAN comprises a generator which is used for generating tasks, has one input according to different tasks, and then outputs corresponding pixel images. The discriminator is used for discriminating whether the picture is true or false, the input is the picture, and the output is a label for discriminating the picture. A traditional design mode can be changed by utilizing an intelligent generation design technology, and the effects of reducing the design threshold, improving the design efficiency, optimizing the design quality, expanding the thought of a designer and stimulating the design inspiration of the designer are achieved.

Description

technical field [0001] The invention belongs to the technical field of image processing in garden design, and discloses an image processing method, system and terminal in garden design based on an adversarial generation network. Background technique [0002] At present, landscape design is the core link in the process of garden construction, and it is also the basic decision-making link that determines the effect of implementation. Therefore, the role of designers in the process of garden construction is self-evident. The traditional design process is a process in which designers ask questions based on users' needs for the site, set goals, generate solutions, and evaluate them. In this process, designers need to participate in the whole process, and use their own knowledge and experience to form design results to meet the needs of builders and users. In today's era, due to changes in the environment, development of technology, and advancement of concepts, the factors affect...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F30/13G06F30/27G06N3/04G06N3/08
CPCG06F30/13G06F30/27G06N3/08G06N3/045
Inventor 艾乔敖翔周韦世李宽姚阳刘华
Owner CHONGQING JIAOTONG UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products