Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Sea surface recovery target detection method based on eagle-eye-imitating vision and objectness

A target detection and object-like technology, applied in the field of computer vision, can solve the problems of slow GPS update frequency, damage, low precision, etc., and achieve the effect of reducing the complexity of the algorithm

Pending Publication Date: 2022-07-15
BEIHANG UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the GPS navigation system can achieve all-weather uninterrupted positioning and navigation, but the GPS update frequency is slow and the accuracy is low, it cannot guarantee the real-time navigation of the UAV during the recovery process, and it is easily damaged and invalidated during special wars
The inertial navigation system does not send and receive information from the outside world. It has good concealment, strong anti-interference ability, and higher update frequency than GPS, but error accumulation will occur over time.
The combined navigation method can combine the advantages of various navigation methods to make the navigation system more accurate and reliable, but the cost of this navigation method is relatively high. When one of the navigation methods fails, the above-mentioned GPS navigation or inertial navigation will appear again. The shortcomings of the way

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
  • Sea surface recovery target detection method based on eagle-eye-imitating vision and objectness
  • Sea surface recovery target detection method based on eagle-eye-imitating vision and objectness
  • Sea surface recovery target detection method based on eagle-eye-imitating vision and objectness

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0079] The effectiveness of the method proposed by the present invention is verified below through a specific example of target detection for an unmanned ship recovered at sea. The experimental computer is configured with Intel Core i7-4790 processor, 3.60Ghz main frequency, 4G memory, and the software is MATLAB 2014a version. The specific steps of a sea surface recovery target detection method based on imitation eagle-eye vision and similarity are as follows:

[0080] Step 1: Obtain the image of the quasi-physical property window

[0081] The similarity detection method of binary gradient normalization BING is used to detect the similarity of the original input image I, and N=12 similarity window regions are selected, and the score of each similarity window is obtained. Sort according to the score from high to low, and the score is used to represent the probability ω that the window contains the target feature i >ω j ,i image 3 shown.

[0082] Step 2: Create an eagle eye ...

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 sea surface recovery target detection method based on eagle-eye-imitating vision and objectness. The sea surface recovery target detection method comprises the following steps: step 1, acquiring an objectness window image; 2, establishing an eagle-eye-imitating color space; 3, selecting an image with a relatively high score for subsequent processing; 4, calculating significance values of the same color; 5, eagle-eye-imitating color space smoothing processing is carried out; step 6, summing saliency results of the object-like window; and step 7, outputting a saliency detection result of the offshore recovery device. According to the invention, saliency detection is carried out on a window result of likelihood detection, so that the algorithm complexity of saliency detection is greatly reduced; according to the method, the eagle-eye-imitating color space is introduced into the process of detecting the saliency features of the object-like window, and the distance relation between pixels of a real image can be closer in the process of evaluating the image color space distance.

Description

technical field [0001] The invention relates to a research method for the saliency detection of sea surface recovery targets based on biological vision, in particular to a sea surface recovery target detection method based on imitation eagle-eye vision and similarity, and belongs to the field of computer vision. Background technique [0002] The full name of UAV is "unmanned aerial vehicle". It is an unmanned aircraft operated by radio remote control equipment and self-provided program control device. It is a high-tech product of the information age. [0003] With the three-dimensional and multi-level rapid development of modern naval warfare, small unmanned boats, unmanned ships, and intelligent floating recovery devices have many advantages such as convenience, flexibility, and autonomy, and can realize complex sea environments and dangerous oceans. The approach, survey and reconnaissance of the area and the unknown island environment have been more and more widely studied...

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): G06V10/25G06V10/56G06V10/764G06K9/62
CPCG06F18/241
Inventor 段海滨徐小斌邓亦敏周锐吴江
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products