CN115330858A - Hough transformation parameter space peak value extraction method for power line detection in complex environment - Google Patents

Hough transformation parameter space peak value extraction method for power line detection in complex environment Download PDF

Info

Publication number
CN115330858A
CN115330858A CN202210989977.5A CN202210989977A CN115330858A CN 115330858 A CN115330858 A CN 115330858A CN 202210989977 A CN202210989977 A CN 202210989977A CN 115330858 A CN115330858 A CN 115330858A
Authority
CN
China
Prior art keywords
accumulation
alternative
straight line
matrix
accumulation units
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210989977.5A
Other languages
Chinese (zh)
Inventor
廖桂生
赵新雅
罗丰
张林让
尹应增
赵峰锋
张宇航
王映中
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Research Institute Of Xi'an University Of Electronic Science And Technology
Xidian University
Original Assignee
Hangzhou Research Institute Of Xi'an University Of Electronic Science And Technology
Xidian University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hangzhou Research Institute Of Xi'an University Of Electronic Science And Technology, Xidian University filed Critical Hangzhou Research Institute Of Xi'an University Of Electronic Science And Technology
Priority to CN202210989977.5A priority Critical patent/CN115330858A/en
Publication of CN115330858A publication Critical patent/CN115330858A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/48—Extraction of image or video features by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Mathematics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computing Systems (AREA)
  • Geometry (AREA)
  • Quality & Reliability (AREA)
  • Algebra (AREA)
  • Multimedia (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Current-Collector Devices For Electrically Propelled Vehicles (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a Hough transformation parameter space peak value extraction method for power line detection in a complex environment, which comprises the steps of generating a position matrix of an alternative accumulation unit, and recording the accumulation unit meeting a threshold condition; analyzing the position matrix of the alternative accumulation units, grouping the alternative accumulation units, and grouping the alternative accumulation units belonging to the same straight line; extracting peak value coordinates of the alternative accumulation units belonging to the same straight line based on an image gravity center algorithm, finding parameter information of the straight line, updating a position matrix of the alternative accumulation units, and clearing information of the detected straight line; and repeating the operation on the updated alternative accumulation unit matrix for analysis, and finally completing the linear detection. The method of the invention improves the detection capability of a plurality of power lines.

Description

Hough transformation parameter space peak value extraction method for power line detection in complex environment
Technical Field
The invention relates to the technical field of image processing, in particular to a Hough transformation parameter space peak value extraction method for power line detection in a complex environment.
Background
The power line is difficult to be found by naked eyes under the conditions of poor sight, shielding in the front and the like due to small volume, so the power line is the most dangerous obstacle in low-altitude flight of the aircraft.
The millimeter wave radar has the characteristics of small volume, high resolution, all-weather use all the day and the like when being used for detecting a power line, and becomes a preferred choice for developing a low-altitude collision prevention system in all countries in the world in recent years. The power line detection is carried out on the image generated by the data measured by the millimeter wave radar, so that the detection of the low-altitude environment threat elements has important practical significance and wide application prospect. However, the target of the power line is small, the reflection intensity is weak, a plurality of power lines often appear at the same time, the distance is short, only one power line can be detected, or the trend of the power line is judged wrongly, which brings difficulty to detection.
The Hough transform is one of the commonly used methods in line detection. After Hough transformation, a common processing method is to extract a peak value of a parameter space as a feature point of a data space to obtain a target straight line. The candidate straight line estimation parameters are usually determined by setting a threshold value. For these straight line estimation parameters, a fast and accurate estimation method is needed to extract the feature points of the multi-target straight line.
In the patent document "an onboard millimeter wave radar power line detection method" (patent application No. 201710747304.8, publication No. 107561509A) applied by the university of electronic technology, a signal gate is positioned by using a power line rack, and the general power line direction is determined by using position information of the power line rack. However, for short-range measurement airborne millimeter-wave radar, when the positions of the power line frames at the two ends of the power line exceed the detection range, the trend of the power line cannot be determined if the position information of the power line frames is lost, and certain application limitations exist.
The King Juannan adopts an image gravity center algorithm to extract the peak value aiming at the Hough parameter space peak value in the published academic paper ' radar weak target detection technology research ' (Shanxi: western's electronics university, 2012). The method can be used for processing a single target straight line and cannot cope with a plurality of power lines in a complex environment.
In a journal article published by chengahua et al, "peak extraction based on Hough transformation straight line detection" (taiyuan university of science and technology, 2006, 27 (4)), a peak extraction method for extracting actual estimation parameters in an alternative accumulation matrix by comparing variance of accumulation unit samples is disclosed. However, the method has poor classification effect on the alternative accumulation units of the parallel target straight lines, so that parameters obtained by subsequent operations cannot be used as straight line parameters.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a Hough transformation parameter space peak value extraction method for power line detection in a complex environment, and the method provided by the invention can be used for improving the detection capability of a plurality of power lines.
In order to achieve the purpose, the invention adopts the following technical scheme:
a Hough transformation parameter space peak value extraction method for power line detection in a complex environment comprises the following steps:
s1, generating a position matrix of an alternative accumulation unit, and recording the accumulation units meeting a threshold condition;
s2, analyzing the position matrix of the alternative accumulation units, grouping the alternative accumulation units, and grouping the alternative accumulation units belonging to the same straight line into a group;
s3, extracting peak value coordinates of alternative accumulation units belonging to the same straight line based on an image gravity center algorithm, and finding parameter information of the straight line;
s4, updating the position matrix of the alternative accumulation unit, and clearing the information of the detected straight line;
and S5, the updated alternative accumulation unit matrix is analyzed by repeating the operation, and finally, the linear detection is completed.
It should be noted that, setting a threshold, extracting accumulation units meeting the threshold condition, recording the position coordinates of the accumulation units in the whole accumulation matrix H, and storing the position coordinates into a two-dimensional array, which is called as an alternative accumulation unit position matrix C; the first column element of the matrix represents the row number of the accumulation unit meeting the threshold condition, and the second column element represents the column number of the accumulation unit meeting the threshold condition; the accumulation units meeting the threshold condition are called alternative accumulation units;
Figure BDA0003803471680000031
in addition, the step S2 includes:
s2.1, a one-dimensional array rowfinal is defined, and position coordinates of accumulation units located on the same straight line are stored and recorded in the number of rows of the position matrix of the alternative accumulation units.
S2.2 extract the latest line number of rowfinal record (initial record is 1), noted as k.
S2.3 subtracts the element of the kth row from the element of the (k + 1) th row of the elements of the first column in the matrix of alternative accumulator unit positions, as follows.
Δ 1 ＝|c k+1,1 -c k,1 |
If the absolute value of the difference Δ 1 Less than T 1 The element of the k-th row is subtracted from the element of the k + 1-th row of the element of the second column in the alternative accumulation unit position matrix, as follows.
Δ 2 ＝|c k+1,2 -c k,2 |
If the absolute value of the difference Δ 2 Less than T 2 The row number for that element is recorded to rowfinal. The parameters determined by the two accumulation units are considered to correspond to the same straight line.
If the row element k +1 of the position matrix of the alternative accumulation unit does not satisfy the two conditions, the row elements k +2, k +3, \ 8230in the position matrix of the alternative accumulation unit are operated according to the following formula until the conditions are satisfied or the row element p in the position matrix of the alternative accumulation unit is operated.
Δ 1 ＝|c i,1 -c k,1 |
Δ 2 ＝|c i,2 -c k,2 |
i＝k+2,k+3,…,p。
In addition, the step S3 includes:
s3.1 one-dimensional array rowfinal = [ r = 1 ,r 2 ,…,t q ] T R of i The accumulation units corresponding to the elements in the row number of the alternative accumulation unit position matrix recorded in (i =1,2, \8230;, q) are the accumulation units of the same straight line.
S3.2, a gravity center algorithm is used for extracting the gravity center coordinates of the image; the (m + n) step size of a pixel f (x, y) at coordinates (x, y) is defined as:
Figure BDA0003803471680000041
l 00 is the sum of the gray levels of f (x, y). For a first distance l 01 And l 10 With l 00 The center of gravity coordinate G (x) is obtained by standardization G ,y G )；
According to the peak value extraction method based on the image gravity center, the corresponding accumulation values are weighted by the alternative accumulation units of the same straight line at the position coordinates of the accumulation matrix H, the accumulation values weighted by the same straight line are summed, and then the position coordinates of the accumulation mean value of the alternative accumulation units of the same straight line are obtained, namely the image gravity center;
the elements H of the accumulation units of the same straight line extracted from the accumulation matrix H are expressed by the following formula i,j (i, j are the elements in the matrix respectively)Number of rows and columns in H) are calculated:
Figure BDA0003803471680000051
Figure BDA0003803471680000052
Figure BDA0003803471680000053
Figure BDA0003803471680000054
Figure BDA0003803471680000055
I G ,J G and rounding to obtain the peak coordinate of the straight line to be extracted.
In addition, step S4 includes:
s4.1, clearing elements corresponding to the line number of the position matrix C of the alternative accumulation unit recorded by the one-dimensional array rowfinal.
S4.2, clearing rowfinal, and recording the first non-zero row number in the first column of the alternative accumulation unit position matrix C in rowfinal after clearing.
The invention has the beneficial effects that:
1. in order to inhibit the interference of other power lines in a complex environment, the invention groups the alternative accumulation units by utilizing the position characteristics of the alternative accumulation units of the same target straight line in the whole accumulation matrix, and divides the alternative accumulation units belonging to the same straight line into a group, thereby effectively eliminating the influence between the parallel power lines in a short distance.
2. The method aims to solve the defect that real-time requirements are difficult to meet due to large operation amount when Hough transform is used for straight line detection. The invention uses the position information of the alternative accumulation unit to weight the corresponding accumulation value based on the image gravity center algorithm, thereby reducing the operation amount and improving the real-time property of the processing.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a mapping graph of a target straight line in a parameter space after Hough transformation in simulation according to the present invention;
FIG. 3 is a data space diagram of the present invention simulation in which peak points obtained after peak extraction are inversely mapped to data space.
Detailed Description
The present invention will be further described below, and it should be noted that the following examples are provided to illustrate the detailed embodiments and specific procedures based on the technical solution, but the scope of the present invention is not limited to the examples.
Examples
The specific implementation steps of the present invention are described in further detail with reference to fig. 1.
Step 1, generating a position matrix of the alternative accumulation unit.
According to the following formula, a threshold is set, accumulation units meeting the threshold condition are extracted, position coordinates of the accumulation units in the whole accumulation matrix H are recorded, and the position coordinates are stored into a two-dimensional array called an alternative accumulation unit position matrix C. The first column element of the matrix represents the number of rows where the accumulation units satisfying the threshold condition are located, and the second column element represents the number of columns where the accumulation units satisfying the threshold condition are located. The accumulation units that satisfy the threshold condition are referred to as alternative accumulation units.
Figure BDA0003803471680000071
And 2, analyzing the position matrix of the alternative accumulation units, and grouping the alternative accumulation units.
(1) And defining a one-dimensional array rowfinal, and storing the number of rows of position coordinates of the accumulation units which are positioned on the same straight line and recorded in a position matrix of the alternative accumulation units.
(2) The latest line number of rowfinal record (initial record is 1), denoted as k, is extracted.
(3) The element of the k-th row is subtracted from the element of the k + 1-th row of the element of the first column in the matrix of candidate accumulation unit positions, as follows.
Δ 1 ＝|c k+1,1 -c k,1 |
If the absolute value of the difference Δ 1 Less than T 1 The element of the k-th row is subtracted from the element of the k + 1-th row of the element of the second column in the alternative accumulation unit location matrix, as follows.
Δ 2 ＝|c k+1,2 -c k,2 |
If the absolute value of the difference Δ 2 Less than T 2 The row number for that element is recorded to rowfinal. The parameters determined by the two accumulation units are considered to correspond to the same straight line.
If the row element k +1 of the position matrix of the alternative accumulation unit does not satisfy the two conditions, the row elements k +2, k +3, \ 8230in the position matrix of the alternative accumulation unit are operated according to the following formula until the conditions are satisfied or the row element p in the position matrix of the alternative accumulation unit is operated.
Δ 1 ＝|c i,1 -c k,1 |
Δ 2 ＝|c i,2 -c k,2 |
i＝k+2,k+3,…,p
And 3, performing an image gravity center algorithm.
(1) One-dimensional array rowfinal = [ r 1 ,r 2 ,…,r q ] T R of i The accumulation units corresponding to the elements in the row number of the alternative accumulation unit position matrix recorded in (i =1,2, \8230;, q) are the accumulation units of the same straight line.
(2) And the gravity center algorithm is to extract the gravity center coordinates of the image. The (m + n) step size of a pixel f (x, y) at coordinates (x, y) is defined as:
Figure BDA0003803471680000081
l 00 is the sum of the gray levels of f (x, y). For a first distance l 01 And l 10 By l 00 The center of gravity coordinate G (x) is obtained by standardization G ,y G )。
According to the peak value extraction method based on the image gravity center, the position coordinates of the alternative accumulation units on the same straight line in the accumulation matrix H are used for weighting corresponding accumulation values, the accumulation values weighted by the same straight line are summed, and then the position coordinates of the accumulation mean value of the alternative accumulation units on the same straight line, namely the image gravity center, are obtained.
The elements H of the accumulation units of the same straight line extracted from the accumulation matrix H are expressed by the following formula i,j (i, j are the number of rows and columns, respectively, of the element in the matrix H):
Figure BDA0003803471680000082
Figure BDA0003803471680000083
Figure BDA0003803471680000084
Figure BDA0003803471680000091
Figure BDA0003803471680000092
I G ,J G and rounding to obtain the peak coordinate of the straight line to be extracted.
And 4, updating the position matrix C of the alternative accumulation unit.
(1) And clearing elements corresponding to the row number of the position matrix C of the alternative accumulation unit recorded by the one-dimensional array rowfinal.
(2) And clearing the rowfinal, and recording the first non-zero row number in the first column in the alternative accumulation unit position matrix C in the rowfinal.
And 5, performing the operations of the steps 2, 3 and 4 until all elements in the position matrix C of the alternative accumulation units are zero. Wherein, T 1 ，T 2 The value of (b) can be determined according to actual needs.
Simulation test
1. Simulation parameters:
table 1 simulation parameters summary
Target straight line numbering Inclination angle (°) Distance (m)
1 175 70
2 175 80
3 8 80
4 5 90
5 5 80
6 13 60
7 165 100
2. Simulation content and result analysis:
assuming 7 straight lines as in table 1 above, a Hough transform is performed to map from data space to parameter space as shown in fig. 2. Carrying out binary accumulation in the parameter space to obtain a parameter space transformation matrix, setting a threshold, then adopting the technology of the invention to carry out peak value extraction in the parameter space, carrying out inverse mapping according to the corresponding relation between the data space and the parameter space to obtain a straight line of the data space. The simulation results are shown in fig. 3.
In fig. 3, the white dotted line is a point of the target straight line in the data space before Hough transformation, and the red straight line is a straight line obtained after the point is subjected to Hough transformation, and then subjected to peak value extraction and inverse mapping to the data space. The number 2 of the target straight line is parallel to the number 1 of the target straight line and intersects with the number 3 of the target straight line. It can be seen that the superposition effect of the straight line after inverse mapping and the white dotted line is better. Therefore, the method can extract the peak value in the Hough parameter space, realize the detection of multi-target straight lines, and can be applied to the detection of a plurality of power lines in a complex environment.
Various corresponding changes and modifications can be made by those skilled in the art based on the above technical solutions and concepts, and all such changes and modifications should be included in the protection scope of the present invention.

Claims (5)

1. A Hough transformation parameter space peak value extraction method for power line detection in a complex environment is characterized by comprising the following steps:
s1, generating a position matrix of an alternative accumulation unit, and recording the accumulation units meeting a threshold condition;
s2, analyzing the position matrix of the alternative accumulation units, grouping the alternative accumulation units, and grouping the alternative accumulation units belonging to the same straight line into a group;
s3, extracting peak value coordinates of alternative accumulation units belonging to the same straight line based on an image gravity center algorithm, and finding parameter information of the straight line;
s4, updating the position matrix of the alternative accumulation unit, and clearing the information of the detected straight line;
and S5, the updated alternative accumulation unit matrix is analyzed by repeating the operation, and finally, the linear detection is completed.
2. The Hough transform parameter space peak extraction method for power line detection in a complex environment according to claim 1, wherein a threshold is set, the accumulation units which meet the threshold condition are extracted, position coordinates of the accumulation units in the whole accumulation matrix H are recorded, and the position coordinates are stored into a two-dimensional array, which is called as an alternative accumulation unit position matrix C; the first column element of the matrix represents the row number of the accumulation unit meeting the threshold condition, and the second column element represents the column number of the accumulation unit meeting the threshold condition; the accumulation units meeting the threshold condition are called alternative accumulation units;
Figure FDA0003803471670000011
3. the Hough transform parameter spatial peak extraction method for power line detection in complex environment according to claim 1, wherein the step S2 comprises:
s2.1, defining a one-dimensional array rowfinal, and storing the position coordinates of the accumulation units positioned on the same straight line and recording the row number of the position matrix of the alternative accumulation units.
S2.2 extract the latest line number of rowfinal record (initial record is 1), noted as k.
S2.3 subtracts the element of the kth row from the element of the (k + 1) th row of the elements of the first column in the matrix of alternative accumulator unit positions, as follows.
Δ 1 ＝|c k+1,1 -c k,1 |
If the absolute value of the difference Δ 1 Less than T 1 The element of the k-th row is subtracted from the element of the k + 1-th row of the element of the second column in the alternative accumulation unit position matrix, as follows.
Δ 2 ＝|c k+1,2 -c k,2 |
If the absolute value of the difference Δ 2 Less than T 2 The line number of this element is recorded to rowfinal. The parameters determined by the two accumulation units are considered to correspond to the same straight line.
If the row element k +1 of the position matrix of the alternative accumulation unit does not satisfy the two conditions, the row elements k +2, k +3, \ 8230in the position matrix of the alternative accumulation unit are operated according to the following formula until the conditions are satisfied or the row element p in the position matrix of the alternative accumulation unit is operated.
Δ 1 ＝|c i,1 -c k,1 |
Δ 2 ＝|c i,2 -c k,2 |
i＝k+2,k+3,…,p。
4. The Hough transform parameter spatial peak extraction method for power line detection in complex environment according to claim 1, wherein the step S3 comprises:
s3.1 one-dimensional array rowfinal = [ r = 1 ,r 2 ,…,r q ] T R of i The accumulation units corresponding to the elements in the row number of the alternative accumulation unit position matrix recorded in (i =1,2, \8230;, q) are the accumulation units of the same straight line.
S3.2, a gravity center algorithm is used for extracting gravity center coordinates of the image; define the (m + n) step size of the pixel f (x, y) at coordinates (x, y) as:
Figure FDA0003803471670000031
l 00 is the sum of the gray levels of f (x, y). For a first distance l 01 And l 10 With l 00 The center of gravity coordinate G (x) is obtained by standardization G ,y G )；
According to the peak value extraction method based on the image gravity center, weighting corresponding accumulation values by using the position coordinates of the alternative accumulation units on the same straight line in an accumulation matrix H, summing the accumulation values weighted by the same straight line, and then solving the position coordinates of the accumulation mean value of the accumulation values of the alternative accumulation units on the same straight line, namely the image gravity center;
the elements H of the accumulation units of the same straight line extracted from the accumulation matrix H are expressed by the following formula i,j (i, j are the number of rows and columns, respectively, of the element in the matrix H):
Figure FDA0003803471670000032
Figure FDA0003803471670000033
Figure FDA0003803471670000034
Figure FDA0003803471670000035
Figure FDA0003803471670000036
I G ,J G and rounding to obtain the peak coordinate of the straight line to be extracted.
5. The Hough transform parameter space peak extraction method for power line detection in a complex environment according to claim 1, wherein the step S4 comprises:
s4.1, clearing elements corresponding to the row number of the position matrix C of the alternative accumulation unit recorded by the one-dimensional array rowfinal.
S4.2, clearing rowfinal, and recording the first non-zero row number in the first column of the alternative accumulation unit position matrix C in rowfinal after clearing.
CN202210989977.5A 2022-08-18 2022-08-18 Hough transformation parameter space peak value extraction method for power line detection in complex environment Pending CN115330858A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210989977.5A CN115330858A (en) 2022-08-18 2022-08-18 Hough transformation parameter space peak value extraction method for power line detection in complex environment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210989977.5A CN115330858A (en) 2022-08-18 2022-08-18 Hough transformation parameter space peak value extraction method for power line detection in complex environment

Publications (1)

Publication Number Publication Date
CN115330858A true CN115330858A (en) 2022-11-11

Family

ID=83924139

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210989977.5A Pending CN115330858A (en) 2022-08-18 2022-08-18 Hough transformation parameter space peak value extraction method for power line detection in complex environment

Country Status (1)

Country Link
CN (1) CN115330858A (en)

Similar Documents

Publication Publication Date Title
CN109409292B (en) Heterogeneous image matching method based on refined feature optimization extraction
CN108960190B (en) SAR video target detection method based on FCN image sequence model
CN107203973A (en) A kind of sub-pixel positioning method of three-dimensional laser scanning system center line laser center
CN115291210B (en) 3D-CNN ground penetrating radar three-dimensional image pipeline identification method combined with attention mechanism
CN111239704B (en) Atmosphere detection radar signal identification method, device, equipment and medium
CN109458994B (en) Method and system for judging matching correctness of laser point cloud ICP (inductively coupled plasma) pose of space non-cooperative target
CN108562885B (en) High-voltage transmission line airborne LiDAR point cloud extraction method
CN112561940B (en) Dense multi-target parameter extraction method and device and terminal equipment
CN109901154B (en) Self-adaptive adjustment method based on recursive RTHT-TBD
CN113486961A (en) Radar RD image target detection method and system based on deep learning under low signal-to-noise ratio and computer equipment
CN108181620A (en) A kind of three-dimensional radar point mark method for evaluating quality
CN107479037B (en) PD radar clutter area distinguishing method
CN109508674B (en) Airborne downward-looking heterogeneous image matching method based on region division
CN110929598A (en) Unmanned aerial vehicle-mounted SAR image matching method based on contour features
CN107729903A (en) SAR image object detection method based on area probability statistics and significance analysis
CN115330858A (en) Hough transformation parameter space peak value extraction method for power line detection in complex environment
CN116819561A (en) Point cloud data matching method, system, electronic equipment and storage medium
CN107403136B (en) SAR target model identification method based on structure-preserving dictionary learning
CN103605980B (en) ISAR (inverse synthetic aperture radar) target component detection method based on local feature matching
CN111948638B (en) Target length estimation method based on high-resolution range profile and application thereof
CN106845489B (en) SAR image target feature extraction method based on improved Krawtchouk moment
CN110490889B (en) Radar target extraction method based on edge detection
CN111553876B (en) Pneumatic optical sight error image processing method and system
CN108830290B (en) SAR image classification method based on sparse representation and Gaussian distribution
CN113093164A (en) Translation-invariant and noise-robust radar image target identification method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination