Feature-fusion-based vehicle shadow interference suppression method for open-air scene of highway

A highway and feature fusion technology, applied in the field of image processing, can solve problems such as noise interference, lack of targeted solutions, and scene adaptability problems

Active Publication Date: 2017-12-22
重庆大学溧阳智慧城市研究院
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are still scene adaptability problems in the actual application of highway scenes, and there is a lack of effective solutions
For problems such as noise interference in the scene, there is still a lack of targeted solutions

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
  • Feature-fusion-based vehicle shadow interference suppression method for open-air scene of highway
  • Feature-fusion-based vehicle shadow interference suppression method for open-air scene of highway
  • Feature-fusion-based vehicle shadow interference suppression method for open-air scene of highway

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] As shown in the figure, this embodiment provides a method for suppressing vehicle shadow interference in an open-air highway scene based on feature fusion, which can overcome the noise existing in the actual engineering application environment and realize accurate extraction of vehicle target areas. Aiming at the problem of scene noise interference, a shadow suppression method that combines color grayscale features and local gradient pattern direction histogram (Histogram of Local Gradient Patterns, HLGP) features is proposed.

[0067] First, the chroma and brightness similarity are used to preliminarily determine the shadow; then, for the local area with rich texture information, the local gradient pattern (Local Gradient Patterns, LGP) feature with noise robustness is used to extract the local texture, and the local gradient histogram is fused Consists of HLGP features. On this basis, the result of color shadow discrimination is corrected to reduce its false detection...

Embodiment 2

[0073] Step 1. Preliminary identification of shaded areas based on grayscale color features; for chromaticity and brightness characteristics, HSV space can decouple the coupling relationship between the two in RGB space. Therefore, the image in RGB space can be converted to HSV space for detection by means of color space conversion.

[0074] The shadow feature can be used to judge the color consistency from the brightness and chroma according to the following formula:

[0075]

[0076] Among them, c represents the color components in the current frame, here represent the components of the H channel and the S channel respectively, Ω 1 (x,y) is the neighborhood space of pixel I(x,y). In order to reduce the interference of noise, the color consistency of the local area of ​​the target pixel is used for discrimination. Therefore, the color consistency of the pixel in the local area can be obtained by the following formula:

[0077]

[0078] It can be seen from the above fo...

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 feature-fusion-based vehicle shadow interference suppression method for an open-air scene of a highway. A current to-be-processed image is obtained and a foreground region segmentation image is obtained by a background image; on the basis of an invariant color feature, a local region of the foreground region segmentation image is obtained and a smoothness value of the local region is calculated by a gradient information entropy; according to features of a histogram of local gradient patterns (HLGP), an HLGP gradient feature shadow determination result of the local region is calculated; and then according to the HLGP gradient feature shadow determination result and a cosine similarity value, calculation is carried out to obtain an HLGP shadow interference determination result of a shadow region. According to the method provided by the invention, shadow determination and suppression are carried out based on fusion of color grayscale features and local gradient coding features; an insufficient anti-noise-interference problem by the traditional local features is solved, the noise interference influence is reduced, and adaptability to the actual engineering application environment is improved; and the precise and ideal detection result is obtained in the environment.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a feature fusion-based method for suppressing vehicle shadow interference in an open-air highway scene. Background technique [0002] Accurate extraction of vehicle target areas is the key to abnormal event detection on expressways based on video surveillance. However, the vehicle shadow interference in the open-air highway scene makes the extracted vehicle target area distorted, expanded, connected or even lost. At the same time, noise and other disturbances in the scene image increase the difficulty of shadow suppression, making traditional shadow suppression methods difficult to apply. Therefore, it is of great theoretical and practical significance to study the vehicle shadow interference suppression method in the highway scene, and then improve the vehicle target detection accuracy. [0003] Expressway is not only an important symbol of transportation modernizatio...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00G06T5/40G06T7/11G06T7/136G06T7/194
CPCG06T5/002G06T5/40G06T2207/10024G06T2207/30232G06T7/11G06T7/136G06T7/194
Inventor 赵敏孙棣华郑林江梅登王齐天
Owner 重庆大学溧阳智慧城市研究院
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap