CN108053448B - Target positioning method and system for sound pressure sensitive nuclear sound image - Google Patents
Target positioning method and system for sound pressure sensitive nuclear sound image Download PDFInfo
- Publication number
- CN108053448B CN108053448B CN201711474596.9A CN201711474596A CN108053448B CN 108053448 B CN108053448 B CN 108053448B CN 201711474596 A CN201711474596 A CN 201711474596A CN 108053448 B CN108053448 B CN 108053448B
- Authority
- CN
- China
- Prior art keywords
- level
- pressure sensitive
- target
- sensitive nuclear
- result
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/203—Drawing of straight lines or curves
-
- 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
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
Abstract
The invention provides a target positioning method and a system thereof aiming at a sound pressure sensitive nuclear sound image, comprising the following steps: step 1) normalizing the sound pressure sensitive nuclear sound image to determine contour lines with different levels; step 2), deleting contour lines with the area smaller than a certain threshold value; step 3) sequentially processing according to the level from small to large, processing contour lines belonging to the same level each time, and selecting the largest area as the result of the level; 4) and calculating the gravity center of the last level result, wherein the gravity center is the target. The method improves the automation degree of target positioning and has high precision.
Description
Technical Field
The invention relates to the field of image processing, in particular to a target positioning method and a target positioning system for a sound pressure sensitive nuclear sound image.
Background
There are many methods for processing the acoustic image to perform target positioning, but the acoustic images obtained by different methods have different characteristics, and at present, there is no automatic processing method for performing target positioning specially for the sound pressure sensitive nuclear acoustic image. The method for processing other sound images by direct migration often has larger error. The first common method of other sonograms is: a single threshold is set to determine an approximate region, and then the maximum value is searched for in the approximate region. By using the method to process the sound pressure sensitive nuclear sound image, a false target is easy to locate, and a large error is caused. The second common method of other sonograms: the target region is determined by using a single threshold, and then the geometric barycenter of the region is calculated. When the method is used for processing the sound pressure sensitive nuclear sound image, the target area can not be found due to the excessively high threshold setting, and a plurality of areas can not be easily found due to the excessively low threshold setting. Even if a target area is found, the actual position of the target is located at one corner of the whole area due to unreasonable threshold setting, so that the error of calculating the geometric center of gravity is large. In summary, a target localization method suitable for sound pressure sensitive nuclear maps is needed.
Disclosure of Invention
Aiming at the technical problem that the sound pressure sensitive nuclear sound image is not subjected to target positioning in the prior art, the target positioning method and the system for the sound pressure sensitive nuclear sound image are provided, the automation degree in target positioning is improved, and the precision is high and the error is small.
The invention relates to a target positioning method for a sound pressure sensitive nuclear sound map, which is characterized by comprising the following steps of:
step 1) normalizing the sound pressure sensitive nuclear sound image to determine contour lines with different levels;
step 2), deleting contour lines with the area smaller than a certain threshold value;
step 3) processing according to the level from small to large, processing the contour lines belonging to the same level each time, and selecting the contour line with the largest area;
4) and calculating the gravity center of the last level result, wherein the gravity center is the target.
Further, the contour processing method with the largest area in the step 3) directly selects the contour with the largest area for the smallest level as the result of the level; other levels need to select an alternative contour line first, and then the result of the level with the largest area is selected from the alternatives, and the condition of selecting the alternative is that the contour line is positioned in the upper level result.
The invention also provides an object localization system for sound pressure sensitive nuclear sound mapping, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the above method when executing the program.
The invention has the advantages that:
according to the method and the system for automatically processing the sound pressure sensitive nuclear sound image to locate the target, which are provided by the invention, a plurality of thresholds are set for searching contour lines with different levels, and the multi-threshold method reduces the risk of unreasonable selection of a single threshold. And when the final effective contour line of each level is selected, the characteristics of the sound pressure sensitive nuclear sound map are utilized, and the position relation among different contour lines is considered, so that not only can the interference area be eliminated, but also the positioning precision can be improved. A large amount of manual processing is omitted, and the automation degree is improved.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a comparison of the results of a process of the present invention and a prior art process.
(a) Example 1 normalized sound pressure sensitive nuclear sound map
(b) Example 1 results of searching for local maximum by the comparative method
(c) Example 1 extraction of contours of different levels of a sonogram
(d) Example 1 elimination of contour lines with smaller area
(e) Example 1 selection of contour for each level according to the described algorithm
FIG. 3 is a comparison of the results of the two processes of the present invention and the prior art method.
(a) Example 2 normalized sound pressure sensitive Nuclear ("SOR") map
(b) EXAMPLE 2 partial enlargement
(c) Example 2 case of low threshold setting in the comparative method
(d) Example 2 unreasonable threshold selection in the comparison method
(e) Example 2 extracting contour lines of different levels of sonogram
(f) Example 2 elimination of contour lines with smaller area
(g) Example 2 selection of contour for each level according to the described algorithm
Detailed Description
The invention is further described below with reference to the accompanying drawings. The invention comprises the following steps:
step 1) normalizing the sound pressure sensitive nuclear sound image, and determining contour lines of different levels (levels);
step 2) deleting contour lines with the area smaller than a certain threshold value, and reducing false targets;
and 3) sequentially processing according to the level from small to large, wherein each time the contour lines belonging to the same level are processed. The minimum level directly selects the contour line with the largest area as the result of the level. Other levels need to select an alternative contour line first, and then the result of the level with the largest area is selected from the alternatives, and the condition of selecting the alternative is that the contour line is positioned in the upper level result. The characteristics of the sound pressure sensitive nuclear sound image are utilized, the position relation among different contour lines is considered, the interference area can be eliminated, and the positioning precision can be improved;
4) and calculating the gravity center of the last level result, wherein the gravity center is the target.
Example 1:
in this embodiment, an acoustic pressure sensitive nuclear map with a target located at (54.8m,17.6m) is obtained by simulation, as shown in fig. 2(a), in which the approximate position of the target is marked with a box. Fig. 2(b) is a partial enlarged view, using the first common method of processing other sonograms: firstly, setting a single threshold value to determine an approximate region, and then searching a maximum value in the approximate region to obtain the target position as shown in an elliptic mark in a figure 2(b), wherein coordinates are (63.0m,18.1m), so that the method is easy to locate a false target and cause large errors.
The acoustic map is processed by the method provided by the invention, the intermediate process and the final result are respectively shown in fig. 2(c) (d) and (e), fig. 2(c) is to extract contours of different levels in the acoustic map, which can be seen to contain many false objects, fig. 2(d) is to delete the contour with a smaller area, which is found to successfully remove the false position located by the comparison method, fig. 2(e) is to select the contour of each level according to the algorithm of the invention, the black dot is the gravity center of the contour of the last level, and the coordinates are (54.7m,17.6 m).
Through comparison, the comparison method can be found out that the maximum value is directly searched locally, the false target is easily positioned under the influence of the quality of the sound image, and the target positioning method provided by the invention is more suitable for the sound pressure sensitive nuclear sound image.
Example 2:
in this embodiment, an acoustic pressure sensitive nuclear map with a target located at (14.6m,17.6m) is obtained by simulation, as shown in fig. 3(a), in which the approximate position of the target is marked with a box. Fig. 3(b) is a partial enlarged view of a second conventional method for processing other sonograms: the target region is determined by using a single threshold, and then the geometric barycenter of the region is calculated. When the sound pressure sensitive nuclear sound map of the embodiment is processed by the method, the target area may not be found when the threshold setting is too high, and a plurality of areas may not be easily found when the threshold setting is too low, as shown in fig. 3 (c). Even if a target area is found, the actual position of the target is located at one corner of the whole area due to unreasonable threshold setting, so that the error of calculating the geometric barycenter is large, as shown in fig. 3(d), the black origin is the area barycenter, and the coordinates are (12.2m,17.7 m).
Processing the sound map by using the method provided by the invention, wherein the intermediate process and the final result are respectively shown in fig. 3(e) (f) and (g), the fig. 3(e) is a contour line for extracting different levels in the sound map, the fig. 3(f) is a result after deleting the contour line with a smaller area, the fig. 3(g) is the contour line of each level obtained by screening according to the algorithm of the invention, the black dot is the gravity center of the contour line of the last level, the coordinates are (14.2m,17.5m), and compared with the second comparison method, which sets a single threshold value and calculates the gravity center, can reduce the influence of a false target, but still has some situations that the target cannot be correctly positioned; the method of the invention can be closer to the actual position of the target while ensuring that the target area is found.
Through the embodiment, the target positioning method provided by the invention is more suitable for the sound pressure sensitive nuclear sound image.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention and are not limited. Although the present invention has been described in detail with reference to the embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (2)
1. A method of target localization for acoustic pressure sensitive nuclear maps, comprising the steps of:
step 1) normalizing the sound pressure sensitive nuclear sound image to determine contour lines with different levels;
step 2), deleting contour lines with the area smaller than a certain threshold value;
step 3) processing according to the level from small to large, processing the contour lines belonging to the same level each time, and selecting the contour line with the largest area;
4) calculating the gravity center of the last level result, wherein the gravity center is the target;
the contour line processing method with the largest area in the step 3) directly selects the contour line with the largest area for the smallest level as the result of the level; other levels need to select an alternative contour line first, and then the result of the level with the largest area is selected from the alternatives, and the condition of selecting the alternative is that the contour line is positioned in the upper level result.
2. An object localization system for acoustic pressure sensitive nuclear mapping comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of claim 1 are carried out when the program is executed by the processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711474596.9A CN108053448B (en) | 2017-12-29 | 2017-12-29 | Target positioning method and system for sound pressure sensitive nuclear sound image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711474596.9A CN108053448B (en) | 2017-12-29 | 2017-12-29 | Target positioning method and system for sound pressure sensitive nuclear sound image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108053448A CN108053448A (en) | 2018-05-18 |
CN108053448B true CN108053448B (en) | 2019-12-24 |
Family
ID=62128932
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711474596.9A Active CN108053448B (en) | 2017-12-29 | 2017-12-29 | Target positioning method and system for sound pressure sensitive nuclear sound image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108053448B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1152372A2 (en) * | 2000-05-01 | 2001-11-07 | GE Medical Systems Global Technology Company LLC | Method and apparatus for automatic detection and sizing of cystic objects |
CN103745483A (en) * | 2013-12-20 | 2014-04-23 | 成都体育学院 | Mobile-target position automatic detection method based on stadium match video images |
CN104799882A (en) * | 2014-01-28 | 2015-07-29 | 三星麦迪森株式会社 | Method and ultrasound apparatus for displaying ultrasound image corresponding to region of interest |
CN105738869A (en) * | 2014-12-08 | 2016-07-06 | 中国科学院声学研究所 | Deepwater beacon searching and positioning method suitable for single hydrophone |
CN107133955A (en) * | 2017-04-14 | 2017-09-05 | 大连理工大学 | A kind of collaboration conspicuousness detection method combined at many levels |
-
2017
- 2017-12-29 CN CN201711474596.9A patent/CN108053448B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1152372A2 (en) * | 2000-05-01 | 2001-11-07 | GE Medical Systems Global Technology Company LLC | Method and apparatus for automatic detection and sizing of cystic objects |
CN103745483A (en) * | 2013-12-20 | 2014-04-23 | 成都体育学院 | Mobile-target position automatic detection method based on stadium match video images |
CN104799882A (en) * | 2014-01-28 | 2015-07-29 | 三星麦迪森株式会社 | Method and ultrasound apparatus for displaying ultrasound image corresponding to region of interest |
CN105738869A (en) * | 2014-12-08 | 2016-07-06 | 中国科学院声学研究所 | Deepwater beacon searching and positioning method suitable for single hydrophone |
CN107133955A (en) * | 2017-04-14 | 2017-09-05 | 大连理工大学 | A kind of collaboration conspicuousness detection method combined at many levels |
Also Published As
Publication number | Publication date |
---|---|
CN108053448A (en) | 2018-05-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110717489B (en) | Method, device and storage medium for identifying text region of OSD (on Screen display) | |
CN109509200B (en) | Checkerboard corner detection method based on contour extraction and computer readable storage medium | |
CN107133966B (en) | Three-dimensional sonar image background segmentation method based on sampling consistency algorithm | |
US11189032B2 (en) | Method and apparatus for extracting a satellite image-based building footprint | |
CN114529837A (en) | Building outline extraction method, system, computer equipment and storage medium | |
CN112215856A (en) | Image segmentation threshold determination method and device, terminal and storage medium | |
CN116740072B (en) | Road surface defect detection method and system based on machine vision | |
CN109325492B (en) | Character cutting method, device, computer equipment and storage medium | |
CN111433780A (en) | Lane line detection method, lane line detection apparatus, and computer-readable storage medium | |
CN111027343A (en) | Bar code area positioning method and device | |
US20220207860A1 (en) | Similar area detection device, similar area detection method, and computer program product | |
CN114359665A (en) | Training method and device of full-task face recognition model and face recognition method | |
CN110598771A (en) | Visual target identification method and device based on deep semantic segmentation network | |
CN108053448B (en) | Target positioning method and system for sound pressure sensitive nuclear sound image | |
US20170213346A1 (en) | Image processing method and process simulation apparatus | |
WO2018053710A1 (en) | Morphological processing method of digital image and digital image processing device | |
CN110807286A (en) | Structural grid identification method | |
JP6874987B2 (en) | Feature shape extraction device, feature shape extraction method, and program | |
CN112614146B (en) | Method and device for judging chessboard calibration corner points and computer readable storage medium | |
CN112183229B (en) | Word lattice extraction method and device of operation paper image based on calculation dynamic parameters | |
CN110298816B (en) | Bridge crack detection method based on image regeneration | |
CN114187195A (en) | 2D (two-dimensional) forward-looking sonar image denoising method | |
CN109408888B (en) | Roughness calculation method of two-dimensional cutting surface, computer-readable storage medium and terminal | |
CN114078140B (en) | Landslide track extraction method based on landslide boundary polygons and slope map | |
CN110930426B (en) | Weak point target extraction method based on peak region shape identification |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |