Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Frequency domain astronomical image target detection method and system

A technology for astronomical images and target detection, applied in the field of target detection, to reduce computational complexity, solve spectrum aliasing, and ensure accuracy

Pending Publication Date: 2021-09-03
NAT SPACE SCI CENT CAS
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the application of GPU in time-domain astronomy has greatly improved the data processing capability, it cannot fundamentally solve the problem of real-time data acquisition. Data processing mode in which the data is transmitted to the ground and then processed on the ground
Faced with more and more astronomical data, this traditional data processing mode is time-consuming and laborious. However, if part of the data processing and screening work can be performed on the satellite, redundant information can be filtered, and valuable observation information can be extracted and downloaded. For the ground, this can not only greatly improve the real-time performance of information acquisition, but also improve the level of intelligent information processing on the star and reduce the pressure of data transmission between the star and the ground.

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
  • Frequency domain astronomical image target detection method and system
  • Frequency domain astronomical image target detection method and system
  • Frequency domain astronomical image target detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] Embodiment 1 of the present invention proposes a frequency-domain astronomical image target detection method, comprising the following steps:

[0067] Based on the pre-obtained reference image, the original astronomical image collected is preprocessed by the CPU; the reference image and the preprocessed astronomical image are divided into image blocks by the method of overlapping and saving, and reference images with the same size and number are obtained Sub-images and astronomical image sub-images; Gaussian function and polynomial multiplication are used to obtain n sets of basis vectors of the convolution kernel and input to GPU;

[0068] According to the reference sub-image and astronomical sub-image, the GPU fits it with n sets of basis vectors to obtain the convolution kernel corresponding to each reference sub-image, and uses the convolution kernel to perform frequency-domain filtering and dedefinition processing on each reference sub-image to obtain template imag...

Embodiment 2

[0119] Embodiment 2 of the present invention proposes a frequency-domain astronomical image target detection system, the system includes: a preprocessing module deployed on the CPU, a basis function calculation module and a target detection module, and a convolution kernel calculation module deployed on the GPU and frequency domain filtering module, wherein,

[0120] The preprocessing module is used to preprocess the original astronomical image collected based on the pre-obtained reference image; it is also used to perform image segmentation on the reference image and the preprocessed astronomical image by overlapping and saving the method to obtain Reference image sub-images and astronomical image sub-images with the same size and number;

[0121] The basis function calculation module is used to multiply the Gaussian basis function and the polynomial to obtain n groups of basis vectors of the convolution kernel and input the convolution kernel calculation module;

[0122] Th...

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 frequency domain astronomical image target detection method and system, and the method is realized based on a CPU-GPU heterogeneous processor, and the method comprises the steps of carrying out the preprocessing of a collected original astronomical image through a CPU based on a reference image obtained in advance; respectively carrying out image partitioning on the reference image and the preprocessed astronomical image by adopting an overlapping storage method, multiplying a Gaussian basis function by a polynomial to obtain n groups of basis vectors of a convolution kernel, and inputting the n groups of basis vectors into a GPU; enabling the GPU to perform fitting according to the reference sub-images and the astronomical sub-images in combination with n groups of base vectors to obtain a convolution kernel corresponding to each reference sub-image, using the convolution kernels for performing frequency domain filtering blurring processing on each reference sub-image to obtain a template image, and inputting the template image into the CPU; and discarding the edge of the template image by the CPU, connecting the remaining parts and making a difference between the remaining parts and the original astronomical image to obtain a difference image, thereby realizing target detection of the astronomical image.

Description

technical field [0001] The invention belongs to the field of target detection, and relates to a frequency-domain astronomical image target detection method and system, which can be used in a space-borne embedded system. Background technique [0002] Among the space science and exploration missions announced by my country's space development plan, many tasks have a great impact on spacecraft artificial intelligence control, autonomous navigation and control, real-time on-orbit processing speed, storage data throughput, massive data processing, complex scientific calculations, and image processing. etc. have put forward urgent demands. Especially for deep space missions, due to the limitation of communication delay and bandwidth, for example, the communication delay to Mars is usually 20 minutes and the bandwidth is 250kbps, and the communication delay to Jupiter is 2 hours and the bandwidth is 120kbps. Raw data cannot all be transmitted back to the ground, so higher requireme...

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): G06T1/20G06T7/33G06T5/00G06T5/10G06F17/14G06F9/54G06K9/62
CPCG06T1/20G06T7/337G06T5/10G06F17/142G06F9/544G06T2207/10004G06F18/213G06T5/70
Inventor 王愉博薛长斌周莉
Owner NAT SPACE SCI CENT CAS
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
Eureka Blog
Learn More
PatSnap group products