Sea surface target detection method based on improved RBD significance calculation

A target detection and saliency technology, applied in the field of image processing, can solve problems such as poor real-time performance, large amount of calculation, and small saliency value, and achieve the effects of reducing the number of superpixels, improving accuracy, and shortening processing time

Inactive Publication Date: 2018-11-06
SHANGHAI UNIV
View PDF6 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since the algorithm performs saliency calculations on the entire image, it has the disadvantages of large amount of computation and poor real-time performance when processing sea surface images
In addition, because the RBD algorithm directly uses all the boundary superpixel information of the image to calculate the boundary connectivity of the image, it is not particularly sensitive to the target that has more contact with the image boundary (that is, the saliency value of the target area at the image boundary is relatively small). Small), there may be missed detection

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 target detection method based on improved RBD significance calculation
  • Sea surface target detection method based on improved RBD significance calculation
  • Sea surface target detection method based on improved RBD significance calculation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] A sea surface target detection method based on the improved RBD saliency calculation disclosed in the present invention is illustrated below with an example. The present embodiment adopts C++ programming language and OpenCV storehouse to realize, and concrete implementation steps are as follows:

[0065] (1) Obtain the original color sea surface image;

[0066] The original sea surface image is a 24-bit color image with a resolution of 640x480, such as figure 2 as shown in a;

[0067] (2) Using Simple Linear Iterative Clustering Algorithm (SLIC) to over-segment the image to generate SLIC superpixels;

[0068] Use the SLIC algorithm to perform superpixel segmentation on sea surface images, such as figure 2 as shown in b. Among them, the number of expected superpixels is set to 500, and the final number of superpixels generated may be slightly less than 500 according to the actual pixel distribution of the image, such as figure 2 as shown in b.

[0069] (3) Using...

Embodiment 2

[0080] The improved algorithm proposed by the present invention eliminates the target superpixels in contact with the image boundary due to screening the boundary set Bnd of the RBD algorithm, thereby improving the problem that the RBD algorithm is not sensitive to the target area at the image boundary. In order to verify the effectiveness of the present invention in improving the RBD algorithm, in this embodiment, except that the boundary set Bnd is not screened, other specific implementation steps are the same as those in Embodiment 1, so details are not repeated here.

[0081] image 3 a and image 3 b are the image boundary and the corresponding saliency map of the seawater area extracted by the RBD algorithm, respectively. It can be seen that the image boundary extracted by the improved algorithm in this paper is more reasonable, and the saliency map obtained based on it is also more accurate.

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 target detection method based on improved RBD significance calculation. The method comprises the following steps that (1) an original colored sea surface image isobtained; (2) a simple linear iteration clustering (SLIC) algorithm is used to carry out super-pixel segmentation on the sea surface image; (3) a semantic segmentation algorithm based on a Gaussian mixture model (GMM) is established, the image is segmented into sky and seawater areas, and a corresponding sea-sky line obtained by fitting boundary points of the sky and seawater areas into a straight line; (5) all super pixels are divided into seawater and sky types according to position information of the sea-sky line; (5) the significance is calculated according to super pixel characteristic information of the sea water type via the improved RBD (robustness background detection) algorithm, and a salient map of the sea water area is obtained; and (6) the salient map is segmented according to a fixed threshold, and a foreground target, namely the sea surface target, is extracted. Thus, the sea surface target can be detected from the complex background effectively, and the accuracy is higher.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a sea surface target detection method based on improved RBD saliency calculation. Background technique [0002] As a key component of the environment perception of the unmanned vehicle, the sea surface target detection technology is a prerequisite for its autonomous obstacle avoidance and safe navigation. At present, the sea surface target detection technology of unmanned vehicles mainly includes radar-based target detection technology, underwater acoustic-based target detection technology, and vision-based target detection technology. Among them, radar-based target detection technology mainly emits electromagnetic waves to irradiate sea targets and receives their echoes, so as to obtain information such as target distance and azimuth; underwater acoustic target detection technology mainly uses the propagation characteristics of sound waves in water, through Electroacou...

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): G06K9/00G06K9/34G06K9/62
CPCG06V20/13G06V10/26G06V2201/07G06F18/23
Inventor 刘靖逸李恒宇丁长权罗均谢少荣
Owner SHANGHAI UNIV
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