CN106199610B - A kind of supersonic sounding device with identification function - Google Patents
A kind of supersonic sounding device with identification function Download PDFInfo
- Publication number
- CN106199610B CN106199610B CN201610524416.2A CN201610524416A CN106199610B CN 106199610 B CN106199610 B CN 106199610B CN 201610524416 A CN201610524416 A CN 201610524416A CN 106199610 B CN106199610 B CN 106199610B
- Authority
- CN
- China
- Prior art keywords
- target
- profile
- point
- characteristic
- ultrasonic wave
- 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.)
- Expired - Fee Related
Links
- 239000011121 hardwood Substances 0.000 claims abstract description 38
- 230000010365 information processing Effects 0.000 claims abstract description 26
- 238000004040 coloring Methods 0.000 claims abstract description 22
- 238000006243 chemical reaction Methods 0.000 claims abstract description 20
- 238000011156 evaluation Methods 0.000 claims abstract description 8
- 238000011161 development Methods 0.000 claims description 47
- 230000005540 biological transmission Effects 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 17
- 238000012935 Averaging Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 7
- 230000004069 differentiation Effects 0.000 claims description 7
- 239000000463 material Substances 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 description 12
- 230000000007 visual effect Effects 0.000 description 8
- 230000005611 electricity Effects 0.000 description 6
- 238000005286 illumination Methods 0.000 description 6
- 230000002401 inhibitory effect Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/66—Sonar tracking systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/52—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S15/00
- G01S7/56—Display arrangements
- G01S7/62—Cathode-ray tube displays
- G01S7/6263—Cathode-ray tube displays in which different colours are used
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of supersonic sounding devices with identification function,Including supersonic sounding device and the Target Identification Unit being connected with supersonic sounding device,Target Identification Unit view-based access control model feature carries out recognition and tracking to target,Including sequentially connected suspection Target Acquisition module,Colouring information processing module,Profile information processing module,Feature evaluation module,Wherein colouring information processing module carries out from RGB color to the conversion in hsv color space the original hardwood image and constructs the suspection target in the tonal color model in hsv color space,The area type that profile information processing module is used to carry out the actual profile of the original hardwood image characteristic area and non-characteristic area divides,Adjacent same type region is merged,And the filter for choosing different parameters is smoothed the characteristic area after merging with non-characteristic area respectively.The present invention has the advantages that accuracy of identification is high, recognition speed is fast.
Description
Technical field
The present invention relates to ultrasonic listening fields, and in particular to a kind of supersonic sounding device with identification function.
Background technique
In the related technology, on supersonic sounding device using radar to target tracked positioning accuracy and tracking at
Have very big advantage on power, but only be difficult to distinguish clarification of objective from the range information that radar obtains, especially exists
Target is blocked under multi-target condition, is difficult to realize target effective recognition and tracking.Using target visual information (such as color,
Profile etc.) target signature is portrayed, carrying out recognition and tracking to target based on target visual feature is the effective way to solve the above problems
Diameter.
Summary of the invention
In view of the above-mentioned problems, the present invention provides a kind of supersonic sounding device with identification function.
The purpose of the present invention is realized using following technical scheme：
A kind of supersonic sounding device with identification function, including supersonic sounding device and and supersonic sounding device
Connected Target Identification Unit, characterized in that the supersonic sounding device includes：
Supersonic generator, transmission cable, ultrasonic wave send and receive device, and the ultrasonic wave sends and receives device
It is connect with supersonic generator by transmission cable, ultrasonic wave sends and receives device and receives supersonic generator from transmission electricity
After the ultrasonic wave of cable conveying, emit to detection position；Focusing ultrasonic wave lens are set to before ultrasonic wave sends and receives device
End focuses ultrasonic wave；Shell accommodates the ultrasonic wave and sends and receives device, transmission cable and focusing ultrasonic wave lens.
Preferably, the shell is made of rubber material.
Preferably, the surface of shell is provided with decorative pattern.
Preferably, the Target Identification Unit includes：
(1) suspect Target Acquisition module, include to suspect target for identification to be suspected target and read in monitor video
Original hardwood image comprising the infrared CCD connecting with field computer, the infrared CCD will be defeated
Picture signal out is input to field computer and is made whether there is the differentiation processing for suspecting target；
(2) colouring information processing module carries out from RGB color to hsv color space the original hardwood image
Conversion and construct the suspection target in the tonal color model in hsv color space, conversion formula is as follows：
V=Max (r, g, b)
Wherein, (r, g, b) is RGB coordinate value of the pixel of original hardwood image in RGB color, virtual value model
Enclose is (0,1)；H is form and aspect component of the pixel in hsv color space, and s is saturation of the pixel in hsv color space
Component is spent, v is chrominance component of the pixel in hsv color space；
Tonal color model is as follows：
Herein
Wherein, function δ [d (xi)-w] it is pixel xiProjection in the region of w-th of subspace, w are characterized the rope in space
Draw, bwFor the weight of each subspace,It is with pixel xcCentered on kernel function in two dimensional image；
Preferably, the Target Identification Unit further includes：
(3) profile information processing module carries out characteristic area and non-spy for the actual profile to the original hardwood image
The area type in sign region is divided, is merged to adjacent same type region, and chooses the filter of different parameters to merging
Characteristic area afterwards is smoothed respectively with non-characteristic area, and the selection area in the actual profile is judged as feature
The decision condition in region is：
Herein
Wherein, t indicates the profile point of the actual profile of the original hardwood image, t0It is located at the selection area to be preset
Interior starting profile point, s are preset development length, and the value of development length is the edge contour point of selection area to the starting
The distance of profile point,It is repaired for the real-time curvature for correcting the development length s at starting profile point
Positive coefficient,For originate profile point radius of curvature,To be obtained by the window function that preset width range is [3,5]
Profile starting point mean radius of curvature；F (t) is the characteristic function for determining profile point and whether being characterized a little, and f (t)=1 is indicated
The profile point is characterized a little, and f (t)=0 indicates that the profile point is non-characteristic point, NF (t)=1Indicate possessed spy in selection area
Levy the number of point, NyFor the number for needing the characteristic point for including as characteristic area of setting, k'N(t) for by the window function pair
Actual profile carries out actual profile curvature obtained from neighborhood averaging, max | k'N(t) | indicate the absolute value of actual profile curvature
Maximum value, T is that the value range of weight and T are [0.2,0.5]；
(4) feature evaluation module, for the target set in processed colouring information and profile information and database
Feature is compared matching and calculates matching degree, and the matching degree determines that the suspection target is when reaching preset matching threshold
Tracking target simultaneously exports judgement result；
Preferably, the profile information processing module includes the first filter being smoothed to all characteristic areas
With the second filter being smoothed to all non-characteristic areas, the length of the confidence interval of the first filter is institute
There is 1/2 of the minimum development length in characteristic area, the length of the confidence interval of the second filter is all non-characteristic areas
1/2 of minimum development length in domain；Different according to the curvature of difference, development length correspondingly automatic adaptive change has
Effect reduces the distortion phenomenon after merging, and identifies convenient for more acurrate to target.
Beneficial effects of the present invention are：
1, tracking target is described in such a way that colouring information and profile information combine, and is had to the variation of extraneous illumination
Very strong robustness is avoided and target is described using single features, and the precision of identification is improved；
2, revised color space conversion formula is more in line with the visual effect of the mankind, is able to reflect richer letter
Breath, is easy to implement quick recognition and tracking, and space weight is introduced in tonal color model and is divided, repeatedly filters, makes model more
Science, practicability are stronger；
3, be arranged profile information processing module, for the original hardwood image actual profile carry out characteristic area with it is non-
The area type of characteristic area is divided, is merged to adjacent same type region, and chooses the filter pairing of different parameters
Characteristic area after and is smoothed respectively with non-characteristic area, and calculation amount is simultaneously uncomplicated, and smooth denoising effect is good, is considered
Otherness of the profile between different type region is inhibiting noise and is retaining to obtain good balance between details, according to
The curvature of difference is different, and development length correspondingly be convenient for by automatic adaptive change, the distortion phenomenon after effectively reducing merging
It is more acurrate that target is identified.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is Target Identification Unit module connection diagram of the invention.
Specific embodiment
The invention will be further described with the following Examples.
Embodiment 1
Referring to Fig. 1, a kind of supersonic sounding device with identification function of the present embodiment, including supersonic sounding device and
The Target Identification Unit being connected with supersonic sounding device, characterized in that the supersonic sounding device includes：
Supersonic generator, transmission cable, ultrasonic wave send and receive device, and the ultrasonic wave sends and receives device
It is connect with supersonic generator by transmission cable, ultrasonic wave sends and receives device and receives supersonic generator from transmission electricity
After the ultrasonic wave of cable conveying, emit to detection position；Focusing ultrasonic wave lens are set to before ultrasonic wave sends and receives device
End focuses ultrasonic wave；Shell accommodates the ultrasonic wave and sends and receives device, transmission cable and focusing ultrasonic wave lens.
Preferably, the shell is made of rubber material.
Preferably, the surface of shell is provided with decorative pattern.
Preferably, the Target Identification Unit includes：
(1) suspect Target Acquisition module, include to suspect target for identification to be suspected target and read in monitor video
Original hardwood image comprising the infrared CCD connecting with field computer, the infrared CCD will be defeated
Picture signal out is input to field computer and is made whether there is the differentiation processing for suspecting target；
(2) colouring information processing module carries out from RGB color to hsv color space the original hardwood image
Conversion and construct the suspection target in the tonal color model in hsv color space, conversion formula is as follows：
V=Max (r, g, b)
Wherein, (r, g, b) is RGB coordinate value of the pixel of original hardwood image in RGB color, virtual value model
Enclose is (0,1)；H is form and aspect component of the pixel in hsv color space, and s is saturation of the pixel in hsv color space
Component is spent, v is chrominance component of the pixel in hsv color space；
Tonal color model is as follows：
Herein
Wherein, function δ [d (xi)-w] it is pixel xiProjection in the region of w-th of subspace, w are characterized the rope in space
Draw, bwFor the weight of each subspace,It is with pixel xcCentered on kernel function in two dimensional image；
Preferably, the Target Identification Unit further includes：
(3) profile information processing module carries out characteristic area and non-spy for the actual profile to the original hardwood image
The area type in sign region is divided, is merged to adjacent same type region, and chooses the filter of different parameters to merging
Characteristic area afterwards is smoothed respectively with non-characteristic area, and the selection area in the actual profile is judged as feature
The decision condition in region is：
Herein
Wherein, t indicates the profile point of the actual profile of the original hardwood image, t0It is located at the selection area to be preset
Interior starting profile point, s are preset development length, and the value of development length is the edge contour point of selection area to the starting
The distance of profile point,It is repaired for the real-time curvature for correcting the development length s at starting profile point
Positive coefficient,For originate profile point radius of curvature,To be obtained by the window function that preset width range is [3,5]
Profile starting point mean radius of curvature；F (t) is the characteristic function for determining profile point and whether being characterized a little, and f (t)=1 is indicated
The profile point is characterized a little, and f (t)=0 indicates that the profile point is non-characteristic point, NF (t)=1Indicate possessed spy in selection area
Levy the number of point, NyFor the number for needing the characteristic point for including as characteristic area of setting, k'N(t) for by the window function pair
Actual profile carries out actual profile curvature obtained from neighborhood averaging, max | k'N(t) | indicate the absolute value of actual profile curvature
Maximum value, T is that the value range of weight and T are [0.2,0.5]；
(4) feature evaluation module, for the target set in processed colouring information and profile information and database
Feature is compared matching and calculates matching degree, and the matching degree determines that the suspection target is when reaching preset matching threshold
Tracking target simultaneously exports judgement result；
Wherein, the profile information processing module include first filter that all characteristic areas are smoothed and
To the second filter that all non-characteristic areas are smoothed, the length of the confidence interval of the first filter is all
1/2 of minimum development length in characteristic area, the length of the confidence interval of the second filter are all non-characteristic areas
In minimum development length 1/2；It is different according to the curvature of difference, development length correspondingly automatic adaptive change, effectively
The distortion phenomenon after merging is reduced, target is identified convenient for more acurrate.
The present embodiment describes tracking target, the change to extraneous illumination in such a way that colouring information and profile information combine
Changing has very strong robustness, avoids and target is described using single features, improve the precision of identification；Revised face
Colour space conversion formula is more in line with the visual effect of the mankind, is able to reflect richer information, be easy to implement quickly identification with
Track introduces space weight in tonal color model and divides, repeatedly filters, keep model more scientific, practicability is stronger；Setting wheel
Wide message processing module, the filter for choosing different parameters carry out smoothly the characteristic area after merging with non-characteristic area respectively
Processing, it is contemplated that otherness of the profile between different type region, it is good inhibiting noise and retaining to obtain between details
Balance, different according to the curvature of difference, development length correspondingly automatic adaptive change effectively reduces the distortion after merging
Phenomenon identifies target convenient for more acurrate, wherein settingWidth be 3, the value of weight T is 0.2, identification essence
Degree improves 2%, and recognition speed improves 1%.
Embodiment 2
Referring to Fig. 1, a kind of supersonic sounding device with identification function of the present embodiment, including supersonic sounding device and
The Target Identification Unit being connected with supersonic sounding device, characterized in that the supersonic sounding device includes：
Supersonic generator, transmission cable, ultrasonic wave send and receive device, and the ultrasonic wave sends and receives device
It is connect with supersonic generator by transmission cable, ultrasonic wave sends and receives device and receives supersonic generator from transmission electricity
After the ultrasonic wave of cable conveying, emit to detection position；Focusing ultrasonic wave lens are set to before ultrasonic wave sends and receives device
End focuses ultrasonic wave；Shell accommodates the ultrasonic wave and sends and receives device, transmission cable and focusing ultrasonic wave lens.
Preferably, the shell is made of rubber material.
Preferably, the surface of shell is provided with decorative pattern.
Preferably, the Target Identification Unit includes：
(1) suspect Target Acquisition module, include to suspect target for identification to be suspected target and read in monitor video
Original hardwood image comprising the infrared CCD connecting with field computer, the infrared CCD will be defeated
Picture signal out is input to field computer and is made whether there is the differentiation processing for suspecting target；
(2) colouring information processing module carries out from RGB color to hsv color space the original hardwood image
Conversion and construct the suspection target in the tonal color model in hsv color space, conversion formula is as follows：
V=Max (r, g, b)
Wherein, (r, g, b) is RGB coordinate value of the pixel of original hardwood image in RGB color, virtual value model
Enclose is (0,1)；H is form and aspect component of the pixel in hsv color space, and s is saturation of the pixel in hsv color space
Component is spent, v is chrominance component of the pixel in hsv color space；
Tonal color model is as follows：
Herein
Wherein, function δ [d (xi)-w] it is pixel xiProjection in the region of w-th of subspace, w are characterized the rope in space
Draw, bwFor the weight of each subspace,It is with pixel xcCentered on kernel function in two dimensional image；
Preferably, the Target Identification Unit further includes：
(3) profile information processing module carries out characteristic area and non-spy for the actual profile to the original hardwood image
The area type in sign region is divided, is merged to adjacent same type region, and chooses the filter of different parameters to merging
Characteristic area afterwards is smoothed respectively with non-characteristic area, and the selection area in the actual profile is judged as feature
The decision condition in region is：
Herein
Wherein, t indicates the profile point of the actual profile of the original hardwood image, t0It is located at the selection area to be preset
Interior starting profile point, s are preset development length, and the value of development length is the edge contour point of selection area to the starting
The distance of profile point,It is repaired for the real-time curvature for correcting the development length s at starting profile point
Positive coefficient,For originate profile point radius of curvature,To be obtained by the window function that preset width range is [3,5]
Profile starting point mean radius of curvature；F (t) is the characteristic function for determining profile point and whether being characterized a little, and f (t)=1 is indicated
The profile point is characterized a little, and f (t)=0 indicates that the profile point is non-characteristic point, NF (t)=1Indicate possessed spy in selection area
Levy the number of point, NyFor the number for needing the characteristic point for including as characteristic area of setting, k'N(t) for by the window function pair
Actual profile carries out actual profile curvature obtained from neighborhood averaging, max | k'N(t) | indicate the absolute value of actual profile curvature
Maximum value, T is that the value range of weight and T are [0.2,0.5]；
(4) feature evaluation module, for the target set in processed colouring information and profile information and database
Feature is compared matching and calculates matching degree, and the matching degree determines that the suspection target is when reaching preset matching threshold
Tracking target simultaneously exports judgement result；
Wherein, the profile information processing module include first filter that all characteristic areas are smoothed and
To the second filter that all non-characteristic areas are smoothed, the length of the confidence interval of the first filter is all
1/2 of minimum development length in characteristic area, the length of the confidence interval of the second filter are all non-characteristic areas
In minimum development length 1/2；It is different according to the curvature of difference, development length correspondingly automatic adaptive change, effectively
The distortion phenomenon after merging is reduced, target is identified convenient for more acurrate.
The present embodiment describes tracking target, the change to extraneous illumination in such a way that colouring information and profile information combine
Changing has very strong robustness, avoids and target is described using single features, improve the precision of identification；Revised face
Colour space conversion formula is more in line with the visual effect of the mankind, is able to reflect richer information, be easy to implement quickly identification with
Track introduces space weight in tonal color model and divides, repeatedly filters, keep model more scientific, practicability is stronger；Setting wheel
Wide message processing module, the filter for choosing different parameters carry out smoothly the characteristic area after merging with non-characteristic area respectively
Processing, it is contemplated that otherness of the profile between different type region, it is good inhibiting noise and retaining to obtain between details
Balance, different according to the curvature of difference, development length correspondingly automatic adaptive change effectively reduces the distortion after merging
Phenomenon identifies target convenient for more acurrate, wherein settingWidth be 4, the value of weight T is 0.3, identification essence
Degree improves 1%, and recognition speed improves 2%.
Embodiment 3
Referring to Fig. 1, a kind of supersonic sounding device with identification function of the present embodiment, including supersonic sounding device and
The Target Identification Unit being connected with supersonic sounding device, characterized in that the supersonic sounding device includes：
Supersonic generator, transmission cable, ultrasonic wave send and receive device, and the ultrasonic wave sends and receives device
It is connect with supersonic generator by transmission cable, ultrasonic wave sends and receives device and receives supersonic generator from transmission electricity
After the ultrasonic wave of cable conveying, emit to detection position；Focusing ultrasonic wave lens are set to before ultrasonic wave sends and receives device
End focuses ultrasonic wave；Shell accommodates the ultrasonic wave and sends and receives device, transmission cable and focusing ultrasonic wave lens.
Preferably, the shell is made of rubber material.
Preferably, the surface of shell is provided with decorative pattern.
Preferably, the Target Identification Unit includes：
(1) suspect Target Acquisition module, include to suspect target for identification to be suspected target and read in monitor video
Original hardwood image comprising the infrared CCD connecting with field computer, the infrared CCD will be defeated
Picture signal out is input to field computer and is made whether there is the differentiation processing for suspecting target；
(2) colouring information processing module carries out from RGB color to hsv color space the original hardwood image
Conversion and construct the suspection target in the tonal color model in hsv color space, conversion formula is as follows：
V=Max (r, g, b)
Wherein, (r, g, b) is RGB coordinate value of the pixel of original hardwood image in RGB color, virtual value model
Enclose is (0,1)；H is form and aspect component of the pixel in hsv color space, and s is saturation of the pixel in hsv color space
Component is spent, v is chrominance component of the pixel in hsv color space；
Tonal color model is as follows：
Herein
Wherein, function δ [d (xi)-w] it is pixel xiProjection in the region of w-th of subspace, w are characterized the rope in space
Draw, bwFor the weight of each subspace,It is with pixel xcCentered on kernel function in two dimensional image；
Preferably, the Target Identification Unit further includes：
(3) profile information processing module carries out characteristic area and non-spy for the actual profile to the original hardwood image
The area type in sign region is divided, is merged to adjacent same type region, and chooses the filter of different parameters to merging
Characteristic area afterwards is smoothed respectively with non-characteristic area, and the selection area in the actual profile is judged as feature
The decision condition in region is：
Herein
Wherein, t indicates the profile point of the actual profile of the original hardwood image, t0It is located at the selection area to be preset
Interior starting profile point, s are preset development length, and the value of development length is the edge contour point of selection area to the starting
The distance of profile point,It is repaired for the real-time curvature for correcting the development length s at starting profile point
Positive coefficient,For originate profile point radius of curvature,To be obtained by the window function that preset width range is [3,5]
Profile starting point mean radius of curvature；F (t) is the characteristic function for determining profile point and whether being characterized a little, and f (t)=1 is indicated
The profile point is characterized a little, and f (t)=0 indicates that the profile point is non-characteristic point, NF (t)=1Indicate possessed spy in selection area
Levy the number of point, NyFor the number for needing the characteristic point for including as characteristic area of setting, k'N(t) for by the window function pair
Actual profile carries out actual profile curvature obtained from neighborhood averaging, max | k'N(t) | indicate the absolute value of actual profile curvature
Maximum value, T is that the value range of weight and T are [0.2,0.5]；
(4) feature evaluation module, for the target set in processed colouring information and profile information and database
Feature is compared matching and calculates matching degree, and the matching degree determines that the suspection target is when reaching preset matching threshold
Tracking target simultaneously exports judgement result；
Wherein, the profile information processing module include first filter that all characteristic areas are smoothed and
To the second filter that all non-characteristic areas are smoothed, the length of the confidence interval of the first filter is all
1/2 of minimum development length in characteristic area, the length of the confidence interval of the second filter are all non-characteristic areas
In minimum development length 1/2；It is different according to the curvature of difference, development length correspondingly automatic adaptive change, effectively
The distortion phenomenon after merging is reduced, target is identified convenient for more acurrate.
The present embodiment describes tracking target, the change to extraneous illumination in such a way that colouring information and profile information combine
Changing has very strong robustness, avoids and target is described using single features, improve the precision of identification；Revised face
Colour space conversion formula is more in line with the visual effect of the mankind, is able to reflect richer information, be easy to implement quickly identification with
Track introduces space weight in tonal color model and divides, repeatedly filters, keep model more scientific, practicability is stronger；Setting wheel
Wide message processing module, the filter for choosing different parameters carry out smoothly the characteristic area after merging with non-characteristic area respectively
Processing, it is contemplated that otherness of the profile between different type region, it is good inhibiting noise and retaining to obtain between details
Balance, different according to the curvature of difference, development length correspondingly automatic adaptive change effectively reduces the distortion after merging
Phenomenon identifies target convenient for more acurrate, wherein settingWidth be 5, the value of weight T is 0.4, identification essence
Degree improves 2%, and recognition speed improves 3%.
Embodiment 4
Referring to Fig. 1, a kind of supersonic sounding device with identification function of the present embodiment, including supersonic sounding device and
The Target Identification Unit being connected with supersonic sounding device, characterized in that the supersonic sounding device includes：
Supersonic generator, transmission cable, ultrasonic wave send and receive device, and the ultrasonic wave sends and receives device
It is connect with supersonic generator by transmission cable, ultrasonic wave sends and receives device and receives supersonic generator from transmission electricity
After the ultrasonic wave of cable conveying, emit to detection position；Focusing ultrasonic wave lens are set to before ultrasonic wave sends and receives device
End focuses ultrasonic wave；Shell accommodates the ultrasonic wave and sends and receives device, transmission cable and focusing ultrasonic wave lens.
Preferably, the shell is made of rubber material.
Preferably, the surface of shell is provided with decorative pattern.
Preferably, the Target Identification Unit includes：
(1) suspect Target Acquisition module, include to suspect target for identification to be suspected target and read in monitor video
Original hardwood image comprising the infrared CCD connecting with field computer, the infrared CCD will be defeated
Picture signal out is input to field computer and is made whether there is the differentiation processing for suspecting target；
(2) colouring information processing module carries out from RGB color to hsv color space the original hardwood image
Conversion and construct the suspection target in the tonal color model in hsv color space, conversion formula is as follows：
V=Max (r, g, b)
Wherein, (r, g, b) is RGB coordinate value of the pixel of original hardwood image in RGB color, virtual value model
Enclose is (0,1)；H is form and aspect component of the pixel in hsv color space, and s is saturation of the pixel in hsv color space
Component is spent, v is chrominance component of the pixel in hsv color space；
Tonal color model is as follows：
Herein
Wherein, function δ [d (xi)-w] it is pixel xiProjection in the region of w-th of subspace, w are characterized the rope in space
Draw, bwFor the weight of each subspace,It is with pixel xcCentered on kernel function in two dimensional image；
Preferably, the Target Identification Unit further includes：
(3) profile information processing module carries out characteristic area and non-spy for the actual profile to the original hardwood image
The area type in sign region is divided, is merged to adjacent same type region, and chooses the filter of different parameters to merging
Characteristic area afterwards is smoothed respectively with non-characteristic area, and the selection area in the actual profile is judged as feature
The decision condition in region is：
Herein
Wherein, t indicates the profile point of the actual profile of the original hardwood image, t0It is located at the selection area to be preset
Interior starting profile point, s are preset development length, and the value of development length is the edge contour point of selection area to the starting
The distance of profile point,It is repaired for the real-time curvature for correcting the development length s at starting profile point
Positive coefficient,For originate profile point radius of curvature,To be obtained by the window function that preset width range is [3,5]
Profile starting point mean radius of curvature；F (t) is the characteristic function for determining profile point and whether being characterized a little, and f (t)=1 is indicated
The profile point is characterized a little, and f (t)=0 indicates that the profile point is non-characteristic point, NF (t)=1Indicate possessed spy in selection area
Levy the number of point, NyFor the number for needing the characteristic point for including as characteristic area of setting, k'N(t) for by the window function pair
Actual profile carries out actual profile curvature obtained from neighborhood averaging, max | k'N(t) | indicate the absolute value of actual profile curvature
Maximum value, T is that the value range of weight and T are [0.2,0.5]；
(4) feature evaluation module, for the target set in processed colouring information and profile information and database
Feature is compared matching and calculates matching degree, and the matching degree determines that the suspection target is when reaching preset matching threshold
Tracking target simultaneously exports judgement result；
Wherein, the profile information processing module include first filter that all characteristic areas are smoothed and
To the second filter that all non-characteristic areas are smoothed, the length of the confidence interval of the first filter is all
1/2 of minimum development length in characteristic area, the length of the confidence interval of the second filter are all non-characteristic areas
In minimum development length 1/2；It is different according to the curvature of difference, development length correspondingly automatic adaptive change, effectively
The distortion phenomenon after merging is reduced, target is identified convenient for more acurrate.
The present embodiment describes tracking target, the change to extraneous illumination in such a way that colouring information and profile information combine
Changing has very strong robustness, avoids and target is described using single features, improve the precision of identification；Revised face
Colour space conversion formula is more in line with the visual effect of the mankind, is able to reflect richer information, be easy to implement quickly identification with
Track introduces space weight in tonal color model and divides, repeatedly filters, keep model more scientific, practicability is stronger；Setting wheel
Wide message processing module, the filter for choosing different parameters carry out smoothly the characteristic area after merging with non-characteristic area respectively
Processing, it is contemplated that otherness of the profile between different type region, it is good inhibiting noise and retaining to obtain between details
Balance, different according to the curvature of difference, development length correspondingly automatic adaptive change effectively reduces the distortion after merging
Phenomenon identifies target convenient for more acurrate, wherein settingWidth be 5, the value of weight T is 0.5, identification essence
Degree improves 2%, and recognition speed improves 2.5%.
Embodiment 5
Referring to Fig. 1, a kind of supersonic sounding device with identification function of the present embodiment, including supersonic sounding device and
The Target Identification Unit being connected with supersonic sounding device, characterized in that the supersonic sounding device includes：
Supersonic generator, transmission cable, ultrasonic wave send and receive device, and the ultrasonic wave sends and receives device
It is connect with supersonic generator by transmission cable, ultrasonic wave sends and receives device and receives supersonic generator from transmission electricity
After the ultrasonic wave of cable conveying, emit to detection position；Focusing ultrasonic wave lens are set to before ultrasonic wave sends and receives device
End focuses ultrasonic wave；Shell accommodates the ultrasonic wave and sends and receives device, transmission cable and focusing ultrasonic wave lens.
Preferably, the shell is made of rubber material.
Preferably, the surface of shell is provided with decorative pattern.
Preferably, the Target Identification Unit includes：
(1) suspect Target Acquisition module, include to suspect target for identification to be suspected target and read in monitor video
Original hardwood image comprising the infrared CCD connecting with field computer, the infrared CCD will be defeated
Picture signal out is input to field computer and is made whether there is the differentiation processing for suspecting target；
(2) colouring information processing module carries out from RGB color to hsv color space the original hardwood image
Conversion and construct the suspection target in the tonal color model in hsv color space, conversion formula is as follows：
V=Max (r, g, b)
Wherein, (r, g, b) is RGB coordinate value of the pixel of original hardwood image in RGB color, virtual value model
Enclose is (0,1)；H is form and aspect component of the pixel in hsv color space, and s is saturation of the pixel in hsv color space
Component is spent, v is chrominance component of the pixel in hsv color space；
Tonal color model is as follows：
Herein
Wherein, function δ [d (xi)-w] it is pixel xiProjection in the region of w-th of subspace, w are characterized the rope in space
Draw, bwFor the weight of each subspace,It is with pixel xcCentered on kernel function in two dimensional image；
Preferably, the Target Identification Unit further includes：
(3) profile information processing module carries out characteristic area and non-spy for the actual profile to the original hardwood image
The area type in sign region is divided, is merged to adjacent same type region, and chooses the filter of different parameters to merging
Characteristic area afterwards is smoothed respectively with non-characteristic area, and the selection area in the actual profile is judged as feature
The decision condition in region is：
Herein
Wherein, t indicates the profile point of the actual profile of the original hardwood image, t0It is located at the selection area to be preset
Interior starting profile point, s are preset development length, and the value of development length is the edge contour point of selection area to the starting
The distance of profile point,It is repaired for the real-time curvature for correcting the development length s at starting profile point
Positive coefficient,For originate profile point radius of curvature,To be obtained by the window function that preset width range is [3,5]
Profile starting point mean radius of curvature；F (t) is the characteristic function for determining profile point and whether being characterized a little, and f (t)=1 is indicated
The profile point is characterized a little, and f (t)=0 indicates that the profile point is non-characteristic point, NF (t)=1Indicate possessed spy in selection area
Levy the number of point, NyFor the number for needing the characteristic point for including as characteristic area of setting, k'N(t) for by the window function pair
Actual profile carries out actual profile curvature obtained from neighborhood averaging, max | k'N(t) | indicate the absolute value of actual profile curvature
Maximum value, T is that the value range of weight and T are [0.2,0.5]；
(4) feature evaluation module, for the target set in processed colouring information and profile information and database
Feature is compared matching and calculates matching degree, and the matching degree determines that the suspection target is when reaching preset matching threshold
Tracking target simultaneously exports judgement result；
Wherein, the profile information processing module include first filter that all characteristic areas are smoothed and
To the second filter that all non-characteristic areas are smoothed, the length of the confidence interval of the first filter is all
1/2 of minimum development length in characteristic area, the length of the confidence interval of the second filter are all non-characteristic areas
In minimum development length 1/2；It is different according to the curvature of difference, development length correspondingly automatic adaptive change, effectively
The distortion phenomenon after merging is reduced, target is identified convenient for more acurrate.
The present embodiment describes tracking target, the change to extraneous illumination in such a way that colouring information and profile information combine
Changing has very strong robustness, avoids and target is described using single features, improve the precision of identification；Revised face
Colour space conversion formula is more in line with the visual effect of the mankind, is able to reflect richer information, be easy to implement quickly identification with
Track introduces space weight in tonal color model and divides, repeatedly filters, keep model more scientific, practicability is stronger；Setting wheel
Wide message processing module, the filter for choosing different parameters carry out smoothly the characteristic area after merging with non-characteristic area respectively
Processing, it is contemplated that otherness of the profile between different type region, it is good inhibiting noise and retaining to obtain between details
Balance, different according to the curvature of difference, development length correspondingly automatic adaptive change effectively reduces the distortion after merging
Phenomenon identifies target convenient for more acurrate, wherein settingWidth be 4, the value of weight T is 0.3, identification essence
Degree improves 2.5%, and recognition speed improves 3.5%.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered
Work as understanding, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (3)
1. a kind of supersonic sounding device with identification function, including supersonic sounding device and with supersonic sounding device phase
Target Identification Unit even, characterized in that the supersonic sounding device includes：
Supersonic generator, transmission cable, ultrasonic wave send and receive device, and the ultrasonic wave sends and receives device and surpasses
Sonic generator is connected by transmission cable, and ultrasonic wave sends and receives device, and to receive supersonic generator defeated from transmission cable
After the ultrasonic wave sent, emit to detection position；Focusing ultrasonic wave lens are set to ultrasonic wave and send and receive device front end, gather
Burnt ultrasonic wave；Shell accommodates the ultrasonic wave and sends and receives device, transmission cable and focusing ultrasonic wave lens；
The Target Identification Unit includes：
(1) Target Acquisition module is suspected, for target to be suspected in identification in monitor video and reading is comprising suspecting the original of target
Hardwood image comprising the infrared CCD connecting with field computer, the infrared CCD is by output
Picture signal is input to field computer and is made whether there is the differentiation processing for suspecting target；
(2) colouring information processing module turn from RGB color to hsv color space to the original hardwood image
It changes and constructs the suspection target in the tonal color model in hsv color space, conversion formula is as follows：
V=Max (r, g, b)
Wherein, (r, g, b) is RGB coordinate value of the pixel in RGB color of original hardwood image, and valid value range is equal
For (0,1)；H is form and aspect component of the pixel in hsv color space, and s is saturation degree of the pixel in hsv color space point
Amount, v are chrominance component of the pixel in hsv color space；
Tonal color model is as follows：
Herein
Wherein, function δ [d (xi)-w] it is pixel xiProjection in the region of w-th of subspace, w are characterized the index in space,
bwFor the weight of each subspace,It is with pixel xcCentered on kernel function in two dimensional image；
The Target Identification Unit further includes：
(3) profile information processing module carries out characteristic area and non-characteristic area for the actual profile to the original hardwood image
The area type in domain is divided, is merged to adjacent same type region, and after choosing the filters of different parameters to merging
Characteristic area is smoothed respectively with non-characteristic area, and the selection area in the actual profile is judged as characteristic area
Decision condition be：
Herein
Wherein, t indicates the profile point of the actual profile of the original hardwood image, t0It is located in the selection area to be preset
Profile point is originated,sFor preset development length, the value of development length is the edge contour point of selection area to the starting profile
The distance of point,For the real-time curvature amendment system for correcting the development length s at starting profile point
Number,For originate profile point radius of curvature,For the wheel obtained by the window function that preset width range is [3,5]
The mean radius of curvature of wide starting point；F (t) is the characteristic function for determining profile point and whether being characterized a little, and f (t)=1 indicates the wheel
Exterior feature point is characterized a little, and f (t)=0 indicates that the profile point is non-characteristic point, NF (t)=1Indicate possessed characteristic point in selection area
Number, NyFor the number for needing the characteristic point for including as characteristic area of setting, k'NIt (t) is by the window function to reality
Profile carries out actual profile curvature obtained from neighborhood averaging, max | k'N(t) | indicate the absolute value of actual profile curvature most
Big value, T are that the value range of weight and T are [0.2,0.5]；
(4) feature evaluation module, for the target signature set in processed colouring information and profile information and database
Matching is compared and calculates matching degree, the matching degree determines the suspection target for tracking when reaching preset matching threshold
Target simultaneously exports judgement result；
The profile information processing module includes the first filter being smoothed to all characteristic areas and to all non-
The second filter that characteristic area is smoothed, the length of the confidence interval of the first filter are all characteristic areas
In minimum development length 1/2, the length of the confidence interval of the second filter is the minimum in all non-characteristic areas
The 1/2 of development length.
2. a kind of supersonic sounding device with identification function according to claim 1, characterized in that the shell
It is made of rubber material.
3. a kind of supersonic sounding device with identification function according to claim 2, characterized in that the shell
Surface is provided with decorative pattern.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610524416.2A CN106199610B (en) | 2016-06-29 | 2016-06-29 | A kind of supersonic sounding device with identification function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610524416.2A CN106199610B (en) | 2016-06-29 | 2016-06-29 | A kind of supersonic sounding device with identification function |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106199610A CN106199610A (en) | 2016-12-07 |
| CN106199610B true CN106199610B (en) | 2018-11-27 |
Family
ID=57465887
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610524416.2A Expired - Fee Related CN106199610B (en) | 2016-06-29 | 2016-06-29 | A kind of supersonic sounding device with identification function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106199610B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115937219B (en) * | 2023-03-14 | 2023-05-12 | 合肥合滨智能机器人有限公司 | Ultrasonic image part identification method and system based on video classification |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101371795A (en) * | 2007-11-13 | 2009-02-25 | 上海雷硕医疗器械有限公司 | Supersonic sounding device |
| CN102694974A (en) * | 2011-03-24 | 2012-09-26 | 佳能株式会社 | focus detection apparatus, method for controlling the same, and image capturing apparatus having a focus detection apparatus |
| CN103559507A (en) * | 2013-11-18 | 2014-02-05 | 沈阳工业大学 | Method for detecting traffic signs based on combination of color feature and shape feature |
-
2016
- 2016-06-29 CN CN201610524416.2A patent/CN106199610B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101371795A (en) * | 2007-11-13 | 2009-02-25 | 上海雷硕医疗器械有限公司 | Supersonic sounding device |
| CN102694974A (en) * | 2011-03-24 | 2012-09-26 | 佳能株式会社 | focus detection apparatus, method for controlling the same, and image capturing apparatus having a focus detection apparatus |
| CN103559507A (en) * | 2013-11-18 | 2014-02-05 | 沈阳工业大学 | Method for detecting traffic signs based on combination of color feature and shape feature |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106199610A (en) | 2016-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108596849B (en) | Single image defogging method based on sky region segmentation | |
| CN102426649B (en) | Simple steel seal digital automatic identification method with high accuracy rate | |
| US7324701B2 (en) | Image noise reduction | |
| KR101051716B1 (en) | Method for multi sensor image fusion | |
| US7068840B2 (en) | Determination of an illuminant of digital color image by segmentation and filtering | |
| CN117764986B (en) | Titanium plate surface defect detection method based on image processing | |
| CN111709968B (en) | Low-altitude target detection tracking method based on image processing | |
| CN111144207A (en) | Human body detection and tracking method based on multi-mode information perception | |
| Al-Sammaraie | Contrast enhancement of roads images with foggy scenes based on histogram equalization | |
| CN106199610B (en) | A kind of supersonic sounding device with identification function | |
| CN109829858A (en) | A kind of shipborne radar image spilled oil monitoring method based on local auto-adaptive threshold value | |
| CN110781712B (en) | Human head space positioning method based on human face detection and recognition | |
| CN106077971B (en) | A kind of laser cutting device for being capable of autonomous classification | |
| CN106101632A (en) | The image processing apparatus of view-based access control model feature | |
| CN106127187A (en) | A kind of have the intelligent robot identifying function | |
| CN106096587A (en) | There is the vehicle monitoring system of target recognition function | |
| CN109523594A (en) | A kind of vision tray characteristic point coordinate location method and system | |
| CN117075109A (en) | Low-altitude obstacle collaborative detection method based on millimeter wave radar and optical system | |
| CN106205077B (en) | A kind of alarm system quickly identified | |
| JPH1141521A (en) | Image pickup device, instrument and method for measuring distance between vehicles | |
| CN105921886B (en) | A kind of laser process machine of high recognition performance | |
| CN115439349A (en) | Underwater SLAM optimization method based on image enhancement | |
| Shen | Complex Lane Line Detection Under Autonomous Driving | |
| CN106127485A (en) | A kind of electronic transaction verification system based on the technology of identification | |
| CN112967304A (en) | Edge detection algorithm for multi-edge window collaborative filtering |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20181011 Address after: 226500 28 Xingyuan Road, Rucheng street, Rugao, Nantong, Jiangsu Applicant after: JIANGSU YINTUO POWER TECHNOLOGY Co.,Ltd. Address before: No. 32, Zhenhai District, Zhejiang Province, Zhenhai District, Drum Tower East Road, Ningbo, Zhejiang Applicant before: Wei Xingfei |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181127 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |