Image multispectral analysis method used for video monitoring or machine vision field

A machine vision and video surveillance technology, applied in the fields of image processing, intelligent transportation, and video surveillance, can solve the problems of limited dynamic range, low target recognition, low contrast, etc., to achieve high detail visibility, low computational complexity, saving The effect of data bandwidth

Inactive Publication Date: 2014-12-17
NANJING GMINNOVATION TECH CO LTD
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method for segmenting and segmenting the video image grayscale spectrum and expanding and stretching the video image in the video camera system in the field of video monitoring and machine vision, so as to expand the spectrum segment concerned to the entire available dynamic range and solve the problem of Video capture devices or monitors can only capture or reproduce images with a fixed and limited dynamic range, resulting in unclear details, low contrast, and low target recognition of the acquired video images, which makes the application of machine vision unable to satisfy human visual perception of the outside world It is difficult to replace the problem of real-time monitoring of human eyes, so that the image details presented by the scene objects of interest are clearer, so that the image information within the dynamic range of the photoelectric signal of interest can be specially analyzed, processed, restored, transmitted, etc.

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 multispectral analysis method used for video monitoring or machine vision field
  • Image multispectral analysis method used for video monitoring or machine vision field
  • Image multispectral analysis method used for video monitoring or machine vision field

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0055] Example 1, backend display analysis application

[0056] According to a certain rule, select a scene with a certain dynamic range spectrum to perform spectrum expansion; and then perform spectrum expansion analysis one by one by moving the dynamic range window; so that the contrast of each spectrum image information is increased, and more details can be reproduced .

[0057] Image 6 It is a typical traffic imaging image. Because the actual lighting is very strong, the backlight is serious, and the contrast between light and dark in multi-target scenes is huge, it is impossible for ordinary sensors and display devices to reproduce a clear image of each target in intelligent traffic. The license plate, driver, vehicle and road surface in the picture are not well represented as a whole.

[0058] Figure 7 It is the image after multi-spectral analysis with the license plate as the target. Obviously, the license plate can be clearly reproduced, and other non-interesting ...

example 2

[0060] Example 2, sensor-side application in video acquisition

[0061] Traditional sensor image acquisition compresses the entire dynamic range into low-bit-number narrow dynamic range image data, which results in a narrow distribution of image brightness from dark to bright scenes, and there are useless spectral bands, which are finally reflected in image contrast Very weak, multi-object local details cannot be guaranteed. The video image multi-spectral analysis method provided by the present invention is used in video recording, and the scenes in the limited dynamic range are selectively captured during video recording, such as only dark areas or bright areas are captured, and they are expanded when recorded into data signals to the entire spectrum. The contrast reflected in this effect is very strong, which solves the common problem of missing or unclear details in different areas.

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 an image multispectral analysis method used for a video monitoring or machine vision field, belongs to the fields of image processing, video monitoring and intelligent transportation, and particularly relates to a video image histogram spectrum segmentation method applied to the video monitoring or machine vision field, and a method for local spectrums to extend and stretch to whole spectral space. A gray scale histogram spectrum of an integral video image is segmented according to requirements, and then, an interested spectrum is stretched to expand to the whole spectral space. Only the interested gray scale spectrum is stretched to the whole spectral space, or each spectrum is stretched to the whole spectral space one by one, so that the dynamic range of the corresponding image of a corresponding spectrum is expanded, the visibility of image details is improved, and the perception and identification problems of vision information under a condition of a wide dynamic range can be favorably solved, and uninterested spectrums can be removed so as to save data bandwidth.

Description

technical field [0001] The invention relates to the fields of image processing, video monitoring, and intelligent transportation, and in particular to a method for segmenting video image histograms and a method for extending and stretching local spectral segments to the entire spectral space, which are applied in the fields of video monitoring and machine vision. Background technique [0002] With the development of technology and the maturity of industrialization, video images and machine vision have been widely used in various fields from scientific research, industrial production, military industry, security to communication and entertainment. [0003] The intensity of photoelectric imaging signals in real scenes is distributed in a limited range. The intensity of the imaging signal is expressed as bright and dark levels on the video image. Image dynamic range in machine vision refers to the signal strength range from "darkest" to "brightest" in a video image, while the ...

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): G06T7/00H04N7/18
Inventor 王兴国郑伟国穆科明
Owner NANJING GMINNOVATION TECH CO LTD
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