Inshore vessel detection method based on contour refinement and improved generalized Hough transform

A generalized Hough transform, ship detection technology, applied in image data processing, instrumentation, computing and other directions, can solve the problems of low ship detection accuracy, relying on a large number of training samples, etc.

Active Publication Date: 2019-02-12
HARBIN INST OF TECH
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that the existing optical remote sensing image ship detection method is only suitable for images with better imaging quality and relies too much o

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
  • Inshore vessel detection method based on contour refinement and improved generalized Hough transform
  • Inshore vessel detection method based on contour refinement and improved generalized Hough transform
  • Inshore vessel detection method based on contour refinement and improved generalized Hough transform

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0029] Specific implementation mode one: combine figure 1 with figure 2 To illustrate this embodiment, the specific process of a detection method for nearshore vessels based on outline refinement and improved generalized Hough transform in this embodiment is as follows:

[0030] Step 1, according to the type of ship to be detected, input the grayscale image of the type of ship to be detected, utilize the Sobel operator to perform edge detection, obtain the length and width information of the type of ship to be detected and the binarized edge detection result image of the ship; Using the image of the binarized edge detection result of the ship, a Hough space voting gradient angle reference table is established;

[0031] Step 2. Perform equal-frequency quantization on the Hough space voting gradient angle reference table established in step 1 to obtain the equal-frequency quantization Hough space voting gradient angle reference table; the process of step 1 and step 2 is an off...

specific Embodiment approach 2

[0044] Specific implementation mode two: combination figure 2 with image 3 Describe this embodiment. This embodiment will further explain the detection method of near-shore vessels based on outline refinement and improved generalized Hough transform described in the first embodiment. The specific method is:

[0045] Step 31. Using the region growing algorithm to separate the ocean and land from the remote sensing image of the scene to be detected, respectively performing expansion processing on the separated ocean and land, and taking the junction zone between the ocean and land as the sea-land junction zone;

[0046] Step 32: Use the line segment detection algorithm to detect the straight line segment of the suspected ship body or wharf, take the neighborhood image of each straight line segment as the suspected parking sub-image, and obtain the suspected parking area of ​​the ship near the coastline.

[0047] In this embodiment, since the near-shore ships are docked at th...

specific Embodiment approach 3

[0048] Specific implementation mode three: combination Figure 4 with Figure 5 Describe this embodiment. This embodiment will further explain the detection method of near-shore vessels based on outline refinement and improved generalized Hough transform described in the first embodiment. The specific method of edge contour is:

[0049] Step 41: Use the scanline-based shadow completion algorithm to complete the outline of the ship with the incomplete bow outline in the suspected parking area of ​​the ship;

[0050] Step 42, using the curvature attribute of the contour point to remove the non-bow contour in the suspected parking area of ​​the ship, and obtain the edge contour of the suspected parking area of ​​the ship.

[0051] The contour completion of the bow adopts the shadow completion algorithm based on the scan line. Since the shadow of the ship structure will partially block the bow, resulting in the incomplete outline of the bow, the present invention uses the compu...

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

An inshore vessel detection method based on contour refinement and improved generalized Hough transform relates to an optical remote sensing image inshore vessel detection method. The method of the invention solves the problem of low ship detection accuracy when the training sample is insufficient and the bow contour is damaged in the detection. The method comprises the steps of obtaining the length and width information of the ship to be measured and the binary edge detection result image of the ship; acquiring an equal-frequency quantized Hough space voting gradient angle reference table, utilizing remote sensing images of scenes to be detected to acquire a plurality of suspected parking areas of ships near the coastline; voting each point of the edge contour of the suspected parking area in Hough space, wherein the point whose voting cumulative value is greater than the threshold value A is the center reference point of the bow in the suspected parking area; using a minimum rectangular frame to mark a suspected ship in a remote sensing image of a scene to be detected; using the minimum rectangular frame to mark a suspected ship in a remote sensing image of the scene to be detected; carring ou the removed false alarms and fusion overlap processing on all suspected vessels to complete the detection of inshore vessels. The method of the invention is applicable to the detectionand use of offshore ships.

Description

technical field [0001] The invention relates to a method for detecting near-shore vessels in optical remote sensing images. Background technique [0002] Inshore vessel detection in optical remote sensing images has many important application requirements, such as change detection and port dynamic monitoring, etc. Although remote sensing images with high spatial resolution can provide more details about objects and backgrounds for object analysis, nearshore vessel detection is still a challenging task due to the following reasons. This includes texture features of nearshore vessels similar to jetties and shore installations, nearshore vessels frequently berthed side by side at jetties, nearshore vessels are partially shaded by deck superstructures, etc. [0003] Existing offshore vessel detection methods can be mainly divided into model-based detection methods and contour-based detection methods. Model-based detection methods usually utilize a large number of training samp...

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): G06T7/13G06T7/181
CPCG06T2207/10032G06T7/13G06T7/181
Inventor 陈浩陈稳高通赵静
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

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