Unlock instant, AI-driven research and patent intelligence for your innovation.

Street view image scoring method based on color distribution learning

A color distribution and image technology, applied in the field of street view image scoring based on color distribution learning, can solve problems such as difficult to simulate learning scoring mechanism

Pending Publication Date: 2021-11-19
JIANGSU INST OF URBAN PLANNING & DESIGN
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If such essential conditions are not given, it is difficult for machine learning to simulate and learn people's scoring mechanism

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
  • Street view image scoring method based on color distribution learning
  • Street view image scoring method based on color distribution learning
  • Street view image scoring method based on color distribution learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:

[0031] When calculating the specific image color, the present invention also adopts the following innovations in the design of technical methods. The Retinex image enhancement algorithm can significantly enhance the image contrast, improve the visual effect, and enhance the light and dark convex parts of the image. The basic theory of Retinex theory is that the color of an object is determined by the object's ability to reflect long-wave (red), medium-wave (green), and short-wave (blue) light, rather than by the absolute value of the reflected light intensity. The color of the object is not affected by the non-uniformity of illumination, and has consistency, that is, Retinex is based on color consistency (color constancy). Different from the traditional linear and non-linear methods that can only enhance a certain type of image features, Retinex c...

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 discloses a street view image scoring method based on color distribution learning, and relates to the fields of urban planning, urban traffic, machine learning modeling and the like. The method comprises the steps: firstly constructing a learning sample library of street view images, and carrying out semantic segmentation of the learning sample library; secondly, calculating the ratio and color distribution condition of various entities of each street view image in the learning sample library; thirdly, forming a pre-training model according to a pre-scoring result of a user on the learning sample library; and finally, completing scoring work of all street view images by using the pre-training model. According to the invention, the machine learning model can better learn how to evaluate and perceive the street view images by considering the street view color distribution. Meanwhile, the invention also provides a novel street view image color calculation method, and the accuracy and the calculation speed of image color calculation can be improved.

Description

technical field [0001] The invention relates to the technical fields of urban planning, urban traffic, and machine learning modeling, in particular to a method for scoring street view images based on color distribution learning. Background technique [0002] Urban street view perception and evaluation has important research significance and practical value for urban planning and urban transportation, and is an important technical means for people to comprehensively and comprehensively understand the urban development environment. The existing research results mainly use the proportion of objects in the street view image to let the machine learning model evaluate how people score the street view image. Although this method is very important, there are still some deficiencies in the scheme of relying solely on the calculation index of proportion for the quality of people's perception of street view. For example, different colors of houses with the same proportion in the stree...

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): G06K9/00G06K9/34G06K9/62G06N20/00
CPCG06N20/00G06F18/23G06F18/24323G06F18/214
Inventor 韦胜姚秀利
Owner JIANGSU INST OF URBAN PLANNING & DESIGN