A Target Detection Method for Line Sampling Hyperspectral Data Based on Difference and Convolution Kernel

A target detection and hyperspectral technology, applied in the field of hyperspectral images, to achieve the effects of low time complexity, high detection recognition rate and clear structure

Active Publication Date: 2018-03-30
HARBIN INST OF TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of target recognition and detection under a single background, the present invention proposes a line-sampling hyperspectral image detection method based on difference and convolution operations to realize the detection of target points in the background image

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 Target Detection Method for Line Sampling Hyperspectral Data Based on Difference and Convolution Kernel
  • A Target Detection Method for Line Sampling Hyperspectral Data Based on Difference and Convolution Kernel
  • A Target Detection Method for Line Sampling Hyperspectral Data Based on Difference and Convolution Kernel

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0022] Specific implementation mode 1: This implementation mode provides a line sampling hyperspectral data target detection method based on difference and convolution kernel, and obtains spectral information characteristics that can characterize a certain spatial region by using line sampling method for hyperspectral data sets ;Adopt the difference method to process the obtained two-dimensional spectral data, remove the inter-spectral correlation, and use the convolution kernel to denoise the image, highlighting the spectral characteristics of the target point; traverse the cuboid data row by row and column by column After that, the row and column where the pixel point set exceeding the threshold is located is the area where the target point is located. Such as figure 1 As shown, it is divided into five steps, and the specific steps are as follows:

[0023] Step 1: Data loading and parameter initialization

[0024] Due to the influence of atmospheric composition, especially...

specific Embodiment approach 2

[0043] Embodiment 2: In this embodiment, the detection method of line-sampling hyperspectral images based on differential and convolution operations is applied to the detection of aircraft in a single background.

[0044] The imaging equipment used in this embodiment is a V10-PS imaging spectrometer, the imaging wavelength range is 400nm-1000nm, and the spectral resolution is 8nm. The obtained data is cut, and a 50×50 pixel set image containing abnormal points is selected as input. To obtain a 50×50×520 dimensional three-dimensional cuboid hyperspectral data set, see image 3 .

[0045] Execution step 1: Load data image_50x50_520.mat as input I 50,50,520 , obtain hyperspectral three-dimensional cuboid data dimension information x=50, y=50, z=520; remove the bands affected by water vapor absorption (band number ΔZ=[311,319]); carry out mean value processing on hyperspectral images to obtain hyperspectral data set Set the height of the truncated cuboid h=5; set the threshold...

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 linear traveling line spectral data object detection method based on a difference and a convolution kernel, comprising steps of performing high spectral data pre-processing, removing exaggeration wave bands to perform de-equalization processing, choosing a suitable step length to perform traveling line sampling on the data, performing difference operation and convolution operation to obtain a characteristic value measuring the sampling cuboid, choosing a suitable threshold characteristic value to perform processing, wherein the area exceeding the threshold contains an object point, repeating the step 2 and the step 3 until traversing a whole cuboid data set to find the transverse position information of the object point, performing transposition on the hyperspectral data obtained from the step 1 in an image dimension, repeating the step 2 to step 4 until traversing the whole cuboid data set to find the column position information of the object point, and thus positioning the position information of the object point in the image. The method is clear in pricinple, clear in structure, small in calculation, low in time complexity, high in detection recognition and is applicable to the high speed object detection and positioning application of the high spectral image under the uniform background.

Description

technical field [0001] The invention relates to a hyperspectral image method, in particular to a line sampling hyperspectral detection method based on difference and convolution operations. Background technique [0002] Hyperspectral detection imaging is a multi-dimensional object spectral information acquisition technology that combines target detection technology with spectral imaging technology. The interspectral resolution of hyperspectral imaging is very high, and the general band width is within 10nm. The target object is imaged with nanometer ultra-high spectral resolution, and dozens or even hundreds of bands are acquired at the same time to form a continuous spectral image. Hyperspectral images can simultaneously acquire two-dimensional spatial information describing the distribution of ground objects and one-dimensional spectral information describing the spectral characteristics of ground objects. The spectral range covers visible light, near-infrared, short-wave ...

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): G01J3/28
CPCG01J3/2823
Inventor 张淼沈飞贾培源沈毅
Owner HARBIN INST OF TECH
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