Target saliency detection method for improving anti-interference performance

A detection method, a remarkable technology, applied in the direction of instruments, calculations, character and pattern recognition, etc., can solve the problems of small targets, inaccurate target detection, small target detection, etc., to achieve detection, accurate and significant detection effect, suppress background interference effect

Active Publication Date: 2022-06-24
BEIJING INSTITUTE OF TECHNOLOGYGY +1
View PDF15 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The technical problem solved by the present invention is to solve the problem of inaccurate target detection caused by complex background, similar target size and interference size (or relatively small target) existing in the detection process of the target in the wild scene by the TV camera, and provides A target saliency detection method, which can eliminate the background interference of the target, overcomes the problem that the existing target saliency detection method is difficult to detect small targets (due to the long detection distance), and obtains a saliency image. saliency target area
[0010] The first target saliency detection method for improving anti-jamming performance of the present invention is a target saliency detection method for improving anti-jamming performance based on gray scale scarcity, which can not only solve the problem of target detection caused by relatively small targets The problem of inaccuracy, the problem that can be solved is to overcome the gradient background interference such as smoke and light vignetting in the background interference

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
  • Target saliency detection method for improving anti-interference performance
  • Target saliency detection method for improving anti-interference performance
  • Target saliency detection method for improving anti-interference performance

Examples

Experimental program
Comparison scheme
Effect test

no. 1 Embodiment approach

[0078] The first specific embodiment is a target saliency detection method for improving anti-interference performance, characterized in that the method comprises the following steps:

[0079] Step 1, obtain the color image of target (area) by camera, carry out grayscale conversion to the color image that detection target obtains, obtain grayscale image I gray :

[0080] Step 2: Obtain the target saliency image related to the gray-scale scarcity; including the following steps:

[0081] S4, set the gray level as m, select M values ​​for m, and for each gray level m, for the gray image I gray Quantize, that is, the grayscale image I gray Divide each pixel in (256 / m), respectively, to obtain a grayscale image corresponding to each m grayscale, a total of M quantized images; M is 4 or 8;

[0082] S5. For each quantized image, the gray value with a smaller number is assigned a larger significant value, that is, for each quantized image, the weight of the pixel with a larger numb...

no. 2 Embodiment approach

[0084] The second specific embodiment, a target saliency detection method for improving anti-interference performance, that is, a target saliency detection method combining grayscale stability and grayscale scarcity, the main steps are:

[0085] 1) Perform equal interval threshold segmentation on the grayscale image, and obtain multiple MSER regions by setting different judgment thresholds;

[0086] 2) Screen the number of pixels and aspect ratio of each MSER region, and superimpose the screened MSER regions to form an MSER significance map;

[0087] 3) Quantify the grayscale image by grades to obtain multiple quantized images;

[0088] 4) Count the grayscale histogram of each quantized image, and assign a larger significant value to the grayscale value with a smaller frequency in the histogram (corresponding to the scarce grayscale value in the image);

[0089] 5) Superimpose the saliency values ​​of different quantized images to form a gray-scale scarcity saliency map;

[...

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 provides a target saliency detection method for improving anti-interference performance, belongs to the technical field of image target detection, comprises a target saliency detection method based on gray scarcity, solves the problem of inaccurate detection caused by a small target, and also overcomes gradient interference. The method further comprises a target saliency detection method combining gray scale stability and gray scale scarcity so as to solve the saliency detection problem of multiple small targets and overcome small clutter type and gradual change type background interference. The target saliency detection method comprises the following steps: quantizing a grayscale image in a grading manner to obtain a quantized image; the gray value with the small statistical frequency is endowed with a larger significant value; and superposing the quantized images to form a gray scale scarcity saliency map. In addition, performing equal-interval threshold segmentation on the grayscale image to obtain an MSER region; carrying out superposition on the screened MSER regions to form a saliency map; and fusing the two saliency images. According to the method, the accuracy of target detection and recognition is improved.

Description

technical field [0001] The invention belongs to the technical field of visible light image target detection, and relates to a target saliency detection method. Background technique [0002] In the terminal guidance technology, the target detection and identification technology is the key technology for the initialization of the non-human guided target at the end of the loop, which directly affects the effect of the terminal guidance. [0003] For general targets, many very comprehensive datasets (such as Pascal VOC, COCO) can be provided for neural network training. [0004] For the TV seeker to detect the position of military vehicles in the field, it is difficult to obtain image data sets of military vehicle targets in the field, especially the data sets of military vehicle targets seen by the seeker in the terminal guidance and control scene are even more difficult to obtain. The reason is: due to the sensitivity of military vehicles, the image of the target cannot be di...

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): G06V10/46G06V10/26G06V10/80G06V20/00G06K9/62
CPCG06F18/253Y02D10/00
Inventor 李明马宇腾袁孜王在成毛亮姜春兰
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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