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

A Band Selection Method Based on Multispectral Detection

A band selection and multi-spectral image technology, applied in the direction of color/spectral characteristic measurement, etc., can solve the problems that skin detection cannot be applied, and multi-spectral imaging is not given quantitatively.

Inactive Publication Date: 2016-04-06
BEIJING JIAOTONG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is mainly used to extract the skin (hand) of the data entry personnel sitting in front of the computer screen during computer data entry, and cannot be applied to skin detection in large-scale and complex scenes
Moreover, this method does not quantitatively give a method of how to select the appropriate band for multispectral imaging

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
  • A Band Selection Method Based on Multispectral Detection
  • A Band Selection Method Based on Multispectral Detection
  • A Band Selection Method Based on Multispectral Detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] After the equipment is connected and the scene setting is completed, the process of light calibration, shooting, feature extraction and band selection needs to be carried out. The specific process is as follows.

[0053] Calibration process: turn on the camera 200 , the computer 300 , the PWM control 500 and the light source 100 . Place the filters 401 (420nm) to 431 (1000nm) in front of the camera 200 in sequence, and adjust the PWM control 500 to maintain the average brightness of the captured image at 150 to 200 (brightness 0 is the darkest, 255 is the brightest). Record the PWM output control value under the corresponding band.

[0054] Shooting process: turn on the camera 200, the computer 300, the PWM control 500 and the light source 100. Place the filters 401 (420nm) to 431 (1000nm) in front of the camera 200 in sequence, import the output value of the PWM control 500, and adjust the brightness corresponding to each band. First take the skin of the human arm a...

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 multispectral detection-based waveband selection method. Through a multispectral imaging system, reflectance characteristics of an object at a plurality of spectral bands can be obtained, and by the reflectance characteristics as features, waveband selection is realized. The multispectral imaging system adopts a narrowband optical filter and calibrates light source brightness output. The multiple photographed and calibrated multispectral images comprise positive samples and negative samples needed by waveband selection. Reflectance characteristics of the positive and negative samples at different wavebands are calculated and extracted and are used as features and by the features, waveband selection is carried out. The multispectral detection-based waveband selection method is an iterative computation method based on one-dimensional histogram distance measurement. The multispectral detection-based waveband selection method overcomes defects such as high complexity and large calculated amount of high-dimensional spatial distance measurement, and improves waveband selection efficiency.

Description

technical field [0001] The present invention relates to imaging equipment and information processing methods for multispectral images. More specifically, the present invention is aimed at the acquisition of reflectance of objects in multispectral images, and the selection of appropriate spectral bands for the acquisition and processing of multispectral images. imaging device and information processing method. Background technique [0002] In recent years, multispectral image processing technology has been applied in many aspects, such as target detection and recognition, feature extraction and image enhancement. The wavelength range of multi-spectrum can range from 400nm to about 2000nm, resulting in complex imaging equipment and difficulties in obtaining multi-spectral images. Therefore, band selection as a method of selecting a suitable band has become one of the important parts of multi-spectral detection. The multi-spectral imaging system can be simplified, the workload...

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 Patents(China)
IPC IPC(8): G01N21/25
Inventor 侯亚丽郝晓莉郭长青王悦扬袁雪陈后金蔡伯根
Owner BEIJING JIAOTONG UNIV