CN106971166A - The image pre-processing method and system of parking stall detection - Google Patents
The image pre-processing method and system of parking stall detection Download PDFInfo
- Publication number
- CN106971166A CN106971166A CN201710196929.XA CN201710196929A CN106971166A CN 106971166 A CN106971166 A CN 106971166A CN 201710196929 A CN201710196929 A CN 201710196929A CN 106971166 A CN106971166 A CN 106971166A
- Authority
- CN
- China
- Prior art keywords
- parking stall
- image
- scene image
- parking
- noise
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000001514 detection method Methods 0.000 title claims abstract description 27
- 238000007781 pre-processing Methods 0.000 title claims abstract description 24
- 230000000694 effects Effects 0.000 description 12
- 238000001914 filtration Methods 0.000 description 9
- 239000006002 Pepper Substances 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000000354 decomposition reaction Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000013139 quantization Methods 0.000 description 4
- 238000011084 recovery Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 235000002566 Capsicum Nutrition 0.000 description 2
- 241000722363 Piper Species 0.000 description 2
- 235000016761 Piper aduncum Nutrition 0.000 description 2
- 235000017804 Piper guineense Nutrition 0.000 description 2
- 235000008184 Piper nigrum Nutrition 0.000 description 2
- 239000000654 additive Substances 0.000 description 2
- 230000000996 additive effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G06T5/73—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30264—Parking
Abstract
The present invention provides the image pre-processing method and system of parking stall detection.Methods described includes：Obtain the reflector segment that parking stall scene is shown in parking stall scene image, the parking stall scene image；The parking stall scene image is handled using defogging algorithm, so as to protrude the information on each parking stall in the parking stall scene image, and mitigates the influence that the reflector segment is detected to parking stall.The present invention can effectively solve the problem that：The unsharp problem in parking stall, image effectively increase the efficiency and accuracy rate detected in the picture to parking stall the problem of noise is more caused by camera undesirable element etc. caused by the problem of reflective influence parking stall lines in place are extracted, environment are dark.
Description
Technical field
The present invention relates to the image pre-processing method and system of image processing field, more particularly to parking stall detection.
Background technology
The environment in parking lot is more complicated, especially underground parking.In panoramic view picture, due to originals such as visual angle distortion
Cause, it is extremely difficult that parking stall how is detected exactly, and the quality of collection image has pole to the parking stall measure of view-based access control model
Big influence.In the image of parking lot environment, the factor of influence parking stall measure mainly has following point：
1) parking lot is because of the difference of quality, and some places are reflective can be than more serious, and the striation of dispersion shape has a strong impact on parking stall
The extraction of lines.
2) some parking lot light are than dark (such as underground parking), and parking stall is unintelligible.
3) on camera dust or camera noise itself influence, the noise of image is relatively more, influences parking stall measure.
The content of the invention
The shortcoming of prior art in view of the above, it is an object of the invention to provide the image preprocessing of parking stall detection
Method and system, for solving above mentioned problem of the prior art.
In order to achieve the above objects and other related objects, the present invention provides a kind of image preprocessing side of parking stall detection
Method, including：Obtain the reflector segment that parking stall scene is shown in parking stall scene image, the parking stall scene image；Profit
The parking stall scene image is handled with defogging algorithm, so that each parking stall in the prominent parking stall scene image
Information, and mitigate the influence that the reflector segment is detected to parking stall.
It is described that the parking stall scene image is handled using defogging algorithm in one embodiment of the invention, including：
Obtain the ambient light intensity A of the parking stall scene image；The parking stall scene image is divided into several sub-image regions
Domain；Obtain the dark primary figure of each sub-image area；Calculate the transmission for obtaining each pixel in each dark primary figure
Rate t (X)；According to formulaThe image J (x) of gained after defogging is asked for, wherein, the I (x) is
The parking stall scene image.
In one embodiment of the invention, the parking stall scene image is panoramic view picture.
In one embodiment of the invention, before being handled using defogging algorithm the parking stall scene image, institute
Stating method also includes：Remove the noise of the panoramic view picture.
In one embodiment of the invention, the parking stall scene image is to be gathered to obtain in underground parking by camera
's.
In order to achieve the above objects and other related objects, the present invention provides a kind of image preprocessing system of parking stall detection
System, including：Image input module, parking stall is shown for obtaining in parking stall scene image, the parking stall scene image
The reflector segment of scene；Image processing module, for being handled using defogging algorithm the parking stall scene image, so that
The information on each parking stall in the prominent parking stall scene image, and mitigate the influence that the reflector segment is detected to parking stall.
In one embodiment of the invention, described image processing module is entered using defogging algorithm to the parking stall scene image
Row processing, is achieved in the following ways：Obtain the ambient light intensity A of the parking stall scene image；By the parking stall
Scene image is divided into several sub-image areas；Obtain the dark primary figure of each sub-image area；Calculating obtains each
The transmitance t (X) of each pixel in the dark primary figure；According to formulaAsk for institute after defogging
The image J (x) obtained, wherein, the I (x) is the parking stall scene image.
In one embodiment of the invention, the parking stall scene image is panoramic view picture.
In one embodiment of the invention, described image processing module is utilizing defogging algorithm to the parking stall scene image
Before being handled, it is additionally operable to remove the noise of the panoramic view picture.
In one embodiment of the invention, the parking stall scene image is to be gathered to obtain in underground parking by camera
's.
As described above, the image pre-processing method and system of the parking stall detection of the present invention, are efficiently solved from image
When detecting parking stall due to place it is reflective caused by parking stall lines hardly possible extract the problem of, parking stall is unsharp caused by environment is dark
Problem and obtain the camera of image and have the problems such as image noise is more caused by dust etc..Pass through the method pair of the present invention
Parking stall scene image is pre-processed, and can effectively improve the efficiency and accuracy rate detected in the picture to parking stall.
Brief description of the drawings
Figure 1A is shown as the image pre-processing method flow chart of the parking stall detection in one embodiment of the invention.
Figure 1B is shown as the image pre-processing method flow chart of the parking stall detection in another embodiment of the present invention.
Fig. 2 is shown as the image preprocessing system module figure of the parking stall detection in one embodiment of the invention.
Component label instructions
The image preprocessing system of 2 parking stalls detection
201 image input modules
202 image processing modules
S101~S102 steps
S1021~S1025
Embodiment
Illustrate embodiments of the present invention below by way of specific instantiation, those skilled in the art can be by this specification
Disclosed content understands other advantages and effect of the present invention easily.The present invention can also pass through specific realities different in addition
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints with application, without departing from
Various modifications or alterations are carried out under the spirit of the present invention.It should be noted that, in the case where not conflicting, following examples and implementation
Feature in example can be mutually combined.
It should be noted that the diagram provided in following examples only illustrates the basic structure of the present invention in a schematic way
Think, then in schema only display with relevant component in the present invention rather than according to component count, shape and the size during actual implement
Draw, it is actual when implementing, and kenel, quantity and the ratio of each component can be a kind of random change, and its assembly layout kenel
It is likely more complexity.
The present invention is proposed before Parking Cell Detection Algorithms are performed for the complex detection environment in parking lot, utilizes defogging algorithm
Image is pre-processed, so as to be favorably improved the efficiency and accuracy rate of parking stall measure.
Figure 1A is referred to, the image pre-processing method for the parking stall detection that the present invention is provided is mainly included the following steps that：
Step S101：Parking stall scene image I (x) is obtained, wherein, the parking stall scene image can be stopped in underground
The parking bit-plane image gathered in parking lot by common camera, or gathered and further splicing processing generation by fish-eye camera
Panoramic view picture, panoramic picture etc.；The parking stall scene image acquires produced due to underground parking quality reflective
Part, further, since collection be underground parking image, light is than dark, and parking stall may be not clear enough.
Step S102：The parking stall scene image is handled using defogging algorithm, so that the prominent parking stall
The information on each parking stall in scene image, and mitigate the influence that the reflector segment is detected to parking stall.
Existing defogging algorithm has a lot, for example：The dark defogging algorithm proposed based on doctor He Kaiming；Based on intermediate value
Filtering (can also be used Gauss average it is bilateral etc) defogging algorithm；Real-time defogging algorithm based on mean filter；It is based on
Multiple dimensioned Retinex image enhancement techniques；Based on adaptive histogram equalization algorithm；Increased based on adaptive contrast and color range
Strong image algorithm etc..In these defogging algorithms, have based on defogging physical model, also there is the enhancing hand based on normal image
Section.The present invention has carried out further simplification preferably based on the defogging algorithm of doctor He Kaiming to it, enabling allow
While step S102 reaches good result, save computing resource, improve treatment effeciency.Specifically as shown in Figure 1B, mainly include
Following steps：
Step S1021：Obtain the ambient light intensity A of the parking stall scene image；
Step S1022：The parking stall scene image is divided into several sub-image areas；
Step S1023：Obtain the dark primary figure of each sub-image area；
Step S1024：Calculate the transmitance t (X) for obtaining each pixel in each dark primary figure；
Step S1025：According to formulaAsk for the image J (x) of gained after defogging.
As the further improvement of above-mentioned embodiment, in step S102 using defogging algorithm to the parking stall scene graph
As before being handled, methods described also includes：Remove the noise of the parking stall scene image.
Detailed：Digital picture in reality is subjected to imaging device in digitlization and transmitting procedure and made an uproar with external environment condition
Acoustic jamming etc. influences, referred to as noisy image or noise image.The process for reducing noise in digital picture is referred to as image denoising.Noise
It is the major reason of image interference.One images there may be various noises in actual applications, and these noises may
Produce in the transmission, it is also possible to produced in the processing such as quantization.Three kinds of forms can be classified as according to the relation of noise and signal：
(f (x, y) represents given original picture, and g (x, y) presentation image signal, n (x, y) represents noise.
1) additive noise：This noise like is unrelated with input image signal, noisy image be represented by f (x, y)=g (x, y)+
The noise produced during the camera-scanning image of n (x, y), interchannel noise and vidicon just belongs to this noise like.
2) multiplicative noise：This noise like is relevant with picture intelligence, noisy image be represented by f (x, y)=g (x, y)+n (x,
Y) grain noise in the correlated noise in g (x, y), noise during flying-spot scanner scanned picture, TV image, film just belongs to
In this noise like.
3) quantizing noise：This noise like is unrelated with input image signal, is that quantizing process has quantization error, then reflect
Receiving terminal and produce.
Usual image denoising wave filter includes following several：
1st, mean filter
The particle for being highly suitable for removing in the image obtained by scanning using the mean filter of neighborhood averaging is made an uproar
Sound.The field method of average effectively inhibits noise, and blooming is caused as well as average, fog-level and field half
Footpath is directly proportional.
The smoothness that geometric mean wave filter is reached can be compared with arithmetic equal value wave filter.But the meeting in filtering
Lose less pictorial detail.Harmonic wave mean filter is more preferable to " salt " noise effects, but is not suitable for " pepper " noise.It
It is good at handling other noises as Gaussian noise.Inverse harmonic wave mean filter is more suitable for processing impulsive noise.But it has
Individual shortcoming, exactly must be it is to be understood that noise be dark noise or bright noise.In order to select suitable filter order numerical symbol, such as
The symbol of fruit exponent number, which has selected wrong, may cause catastrophic consequence.
2nd, adaptive wiener filter
It can adjust the output of wave filter according to the local variance of image, and local variance is bigger, the smooth work of wave filter
With stronger.Its final goal be make recovery image f^ (x, y) and original image f (x, y) mean square error e2=E [(f (x,
Y)-f^ (x, y) 2] it is minimum.The filter effect of this method is better than mean filter effect, to retain image edge and other
HFS is very useful, but amount of calculation is larger.Wiener filter is to the imaging filtering best results with white noise.
3rd, median filter
It is a kind of conventional Nonlinear Smoothing Filter.Its general principle is a bit in digital picture or Serial No.
Value replaced with the intermediate value of each point value in a field of the point its major function be allow surrounding pixel gray value difference than larger
Pixel change to take the value close with the pixel value of surrounding.So as to eliminate isolated noise spot, so medium filtering is for filter
Except the salt-pepper noise of image is highly effective.Median filter can be accomplished not only to have removed noise but also can protect the edge of image.So as to
Obtain relatively satisfactory recovery effect.Moreover, not needing the statistical property of image during actual operation.This also brings many sides
Just, it is but many to some details.The method that particularly the more image of point, line, pinnacle details should not use medium filtering.
4th, morphology scratch filter
It will open and closure combines and can be used to filter out noise, it is optional first to there is noisy image to carry out unlatching operation
Select structural element matrix bigger than the size of noise, thus the result opened is by the noise remove in background.It is finally to previous
Walk obtained image and carry out closed procedure, the noise on image is removed.According to the characteristics of the method it is recognised that the method is suitable
Image type is object size in image all than larger.And without tiny details, to such scene image partition
Effect can be relatively good.
5th, Wavelet Denoising Method
This method remains most of wavelet coefficient for including signal, therefore can preferably keep pictorial detail.It is small
Wave analysis, which carries out image denoising, mainly 3 steps：
(1) wavelet decomposition is carried out to picture intelligence；
(2) threshold value quantizing is carried out to the high frequency coefficient after hierachical decomposition；
(3) picture intelligence is reconstructed using 2-d wavelet.
Referring to Fig. 2, with above method embodiment principle similarly, the present invention provides a kind of image of parking stall detection
Pretreatment system 2, including：Image input module 201, image processing module 202.
Image input module 201 is used to obtain parking stall scene image I (x), wherein, the parking stall scene image can be with
It is the parking bit-plane image gathered in underground parking by common camera, or is gathered by fish-eye camera and further spelled
Connect panoramic view picture, panoramic picture of processing generation etc.；The parking stall scene image is acquired due to underground parking quality
The reflector segment of generation, further, since collection be underground parking image, light is than dark, and parking stall may be not clear enough.
Image processing module 202 is handled the parking stall scene image using defogging algorithm, so that prominent described
The information on each parking stall in the scene image of parking stall, and mitigate the influence that the reflector segment is detected to parking stall.Specifically include：
Obtain the ambient light intensity A of the parking stall scene image；The parking stall scene image is divided into several sub-image regions
Domain；Obtain the dark primary figure of each sub-image area；Calculate the transmission for obtaining each pixel in each dark primary figure
Rate t (X)；According to formulaAsk for the image J (x) of gained after defogging.
As the further improvement of above-mentioned embodiment, image processing module 202 is utilizing defogging algorithm to the parking
Before position scene image is handled, it is additionally operable to remove the noise of the parking stall scene image.
Detailed：Digital picture in reality is subjected to imaging device in digitlization and transmitting procedure and made an uproar with external environment condition
Acoustic jamming etc. influences, referred to as noisy image or noise image.The process for reducing noise in digital picture is referred to as image denoising.Noise
It is the major reason of image interference.One images there may be various noises in actual applications, and these noises may
Produce in the transmission, it is also possible to produced in the processing such as quantization.Three kinds of forms can be classified as according to the relation of noise and signal：
(f (x, y) represents given original picture, and g (x, y) presentation image signal, n (x, y) represents noise.
1) additive noise：This noise like is unrelated with input image signal, noisy image be represented by f (x, y)=g (x, y)+
The noise produced during the camera-scanning image of n (x, y), interchannel noise and vidicon just belongs to this noise like.
2) multiplicative noise：This noise like is relevant with picture intelligence, noisy image be represented by f (x, y)=g (x, y)+n (x,
Y) grain noise in the correlated noise in g (x, y), noise during flying-spot scanner scanned picture, TV image, film just belongs to
In this noise like.
3) quantizing noise：This noise like is unrelated with input image signal, is that quantizing process has quantization error, then reflect
Receiving terminal and produce.
Usual image denoising wave filter includes following several：
1st, mean filter
The particle for being highly suitable for removing in the image obtained by scanning using the mean filter of neighborhood averaging is made an uproar
Sound.The field method of average effectively inhibits noise, and blooming is caused as well as average, fog-level and field half
Footpath is directly proportional.
The smoothness that geometric mean wave filter is reached can be compared with arithmetic equal value wave filter.But the meeting in filtering
Lose less pictorial detail.Harmonic wave mean filter is more preferable to " salt " noise effects, but is not suitable for " pepper " noise.It
It is good at handling other noises as Gaussian noise.Inverse harmonic wave mean filter is more suitable for processing impulsive noise.But it has
Individual shortcoming, exactly must be it is to be understood that noise be dark noise or bright noise.In order to select suitable filter order numerical symbol, such as
The symbol of fruit exponent number, which has selected wrong, may cause catastrophic consequence.
2nd, adaptive wiener filter
It can adjust the output of wave filter according to the local variance of image, and local variance is bigger, the smooth work of wave filter
With stronger.Its final goal be make recovery image f^ (x, y) and original image f (x, y) mean square error e2=E [(f (x,
Y)-f^ (x, y) 2] it is minimum.The filter effect of this method is better than mean filter effect, to retain image edge and other
HFS is very useful, but amount of calculation is larger.Wiener filter is to the imaging filtering best results with white noise.
3rd, median filter
It is a kind of conventional Nonlinear Smoothing Filter.Its general principle is a bit in digital picture or Serial No.
Value replaced with the intermediate value of each point value in a field of the point its major function be allow surrounding pixel gray value difference than larger
Pixel change to take the value close with the pixel value of surrounding.So as to eliminate isolated noise spot, so medium filtering is for filter
Except the salt-pepper noise of image is highly effective.Median filter can be accomplished not only to have removed noise but also can protect the edge of image.So as to
Obtain relatively satisfactory recovery effect.Moreover, not needing the statistical property of image during actual operation.This also brings many sides
Just, it is but many to some details.The method that particularly the more image of point, line, pinnacle details should not use medium filtering.
4th, morphology scratch filter
It will open and closure combines and can be used to filter out noise, it is optional first to there is noisy image to carry out unlatching operation
Select structural element matrix bigger than the size of noise, thus the result opened is by the noise remove in background.It is finally to previous
Walk obtained image and carry out closed procedure, the noise on image is removed.According to the characteristics of the method it is recognised that the method is suitable
Image type is object size in image all than larger.And without tiny details, to such scene image partition
Effect can be relatively good.
5th, Wavelet Denoising Method
This method remains most of wavelet coefficient for including signal, therefore can preferably keep pictorial detail.It is small
Wave analysis, which carries out image denoising, mainly 3 steps：
(1) wavelet decomposition is carried out to picture intelligence；
(2) threshold value quantizing is carried out to the high frequency coefficient after hierachical decomposition；
(3) picture intelligence is reconstructed using 2-d wavelet.
In summary, the image pre-processing method and system of parking stall of the invention detection, effectively overcome prior art
In various shortcoming and have high industrial utilization.
The above-described embodiments merely illustrate the principles and effects of the present invention, not for the limitation present invention.It is any ripe
Know the personage of this technology all can carry out modifications and changes under the spirit and scope without prejudice to the present invention to above-described embodiment.Cause
This, those of ordinary skill in the art is complete without departing from disclosed spirit and institute under technological thought such as
Into all equivalent modifications or change, should by the present invention claim be covered.
Claims (10)
1. a kind of image pre-processing method of parking stall detection, it is characterised in that including：
Obtain the reflector segment that parking stall scene is shown in parking stall scene image, the parking stall scene image；
The parking stall scene image is handled using defogging algorithm, so as to respectively stop in the prominent parking stall scene image
The information of parking stall, and mitigate the influence that the reflector segment is detected to parking stall.
2. the image pre-processing method of parking stall detection according to claim 1, it is characterised in that the utilization defogging is calculated
Method is handled the parking stall scene image, including：
Obtain the ambient light intensity A of the parking stall scene image；
The parking stall scene image is divided into several sub-image areas；
Obtain the dark primary figure of each sub-image area；
Calculate the transmitance t (X) for obtaining each pixel in each dark primary figure；
According to formulaThe image J (x) of gained after defogging is asked for, wherein, the I (x) is described
Parking stall scene image.
3. the image pre-processing method of parking stall detection according to claim 1, it is characterised in that the parking stall scene
Image is panoramic view picture.
4. the image pre-processing method of parking stall detection according to claim 3, it is characterised in that utilizing defogging algorithm
Before handling the parking stall scene image, methods described also includes：Remove the noise of the panoramic view picture.
5. the image pre-processing method of parking stall detection according to claim 1, it is characterised in that the parking stall scene
Image is to be gathered to obtain in underground parking by camera.
6. a kind of image preprocessing system of parking stall detection, it is characterised in that including：
Image input module, parking stall scene is shown for obtaining in parking stall scene image, the parking stall scene image
Reflector segment；
Image processing module, for being handled using defogging algorithm the parking stall scene image, so as to stop described in prominent
The information on each parking stall in the scene image of parking stall, and mitigate the influence that the reflector segment is detected to parking stall.
7. the image preprocessing system of parking stall detection according to claim 6, it is characterised in that described image handles mould
Block is handled the parking stall scene image using defogging algorithm, is achieved in the following ways：Obtain the parking
The ambient light intensity A of position scene image；The parking stall scene image is divided into several sub-image areas；Obtain each institute
State the dark primary figure of sub-image area；Calculate the transmitance t (X) for obtaining each pixel in each dark primary figure；According to public affairs
FormulaThe image J (x) of gained after defogging is asked for, wherein, the I (x) is the parking stall scene
Image.
8. the image preprocessing system of parking stall detection according to claim 6, it is characterised in that the parking stall scene
Image is panoramic view picture.
9. the image preprocessing system of parking stall detection according to claim 8, it is characterised in that described image handles mould
Block is additionally operable to remove making an uproar for the panoramic view picture before the parking stall scene image is handled using defogging algorithm
Sound.
10. the image preprocessing system of parking stall detection according to claim 6, it is characterised in that the parking potential field
Scape image is to be gathered to obtain in underground parking by camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710196929.XA CN106971166A (en) | 2017-03-29 | 2017-03-29 | The image pre-processing method and system of parking stall detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710196929.XA CN106971166A (en) | 2017-03-29 | 2017-03-29 | The image pre-processing method and system of parking stall detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106971166A true CN106971166A (en) | 2017-07-21 |
Family
ID=59336083
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710196929.XA Pending CN106971166A (en) | 2017-03-29 | 2017-03-29 | The image pre-processing method and system of parking stall detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106971166A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109064426A (en) * | 2018-07-26 | 2018-12-21 | 电子科技大学 | A kind of method and device for inhibiting dazzle in low-light (level) image and enhancing image |
| CN109636752A (en) * | 2018-12-07 | 2019-04-16 | 宁波可凡电器有限公司 | Live anti-noise jamming platform |
| CN110170081A (en) * | 2019-05-14 | 2019-08-27 | 广州医软智能科技有限公司 | A kind of ICU instrument alarm processing method and system |
| CN110765304A (en) * | 2019-10-22 | 2020-02-07 | 珠海研果科技有限公司 | Image processing method, image processing device, electronic equipment and computer readable medium |
| CN112820141A (en) * | 2021-01-14 | 2021-05-18 | 浙江吉利控股集团有限公司 | Parking space detection method and system |
| DE102023203479A1 (en) | 2023-04-18 | 2024-02-29 | Zf Friedrichshafen Ag | System and method for finding a free parking space |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101807352A (en) * | 2010-03-12 | 2010-08-18 | 北京工业大学 | Method for detecting parking stalls on basis of fuzzy pattern recognition |
| US8620028B2 (en) * | 2007-02-08 | 2013-12-31 | Behavioral Recognition Systems, Inc. | Behavioral recognition system |
| CN103600707A (en) * | 2013-11-06 | 2014-02-26 | 同济大学 | Parking position detecting device and method of intelligent parking system |
| CN104346782A (en) * | 2014-10-29 | 2015-02-11 | 中国科学院深圳先进技术研究院 | Method and device for defogging single image |
| CN104794906A (en) * | 2015-04-16 | 2015-07-22 | 王爱云 | Vehicle management platform of outdoor parking lot exit |
| CN105389784A (en) * | 2015-12-07 | 2016-03-09 | 魅族科技（中国）有限公司 | Image processing method and terminal |
-
2017
- 2017-03-29 CN CN201710196929.XA patent/CN106971166A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8620028B2 (en) * | 2007-02-08 | 2013-12-31 | Behavioral Recognition Systems, Inc. | Behavioral recognition system |
| CN101807352A (en) * | 2010-03-12 | 2010-08-18 | 北京工业大学 | Method for detecting parking stalls on basis of fuzzy pattern recognition |
| CN103600707A (en) * | 2013-11-06 | 2014-02-26 | 同济大学 | Parking position detecting device and method of intelligent parking system |
| CN104346782A (en) * | 2014-10-29 | 2015-02-11 | 中国科学院深圳先进技术研究院 | Method and device for defogging single image |
| CN104794906A (en) * | 2015-04-16 | 2015-07-22 | 王爱云 | Vehicle management platform of outdoor parking lot exit |
| CN105389784A (en) * | 2015-12-07 | 2016-03-09 | 魅族科技（中国）有限公司 | Image processing method and terminal |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109064426A (en) * | 2018-07-26 | 2018-12-21 | 电子科技大学 | A kind of method and device for inhibiting dazzle in low-light (level) image and enhancing image |
| CN109064426B (en) * | 2018-07-26 | 2021-08-31 | 电子科技大学 | Method and device for suppressing glare in low-illumination image and enhancing image |
| CN109636752A (en) * | 2018-12-07 | 2019-04-16 | 宁波可凡电器有限公司 | Live anti-noise jamming platform |
| CN109636752B (en) * | 2018-12-07 | 2020-08-14 | 绍兴市侨陆智能科技有限公司 | On-site anti-noise interference platform |
| CN110170081A (en) * | 2019-05-14 | 2019-08-27 | 广州医软智能科技有限公司 | A kind of ICU instrument alarm processing method and system |
| CN110765304A (en) * | 2019-10-22 | 2020-02-07 | 珠海研果科技有限公司 | Image processing method, image processing device, electronic equipment and computer readable medium |
| CN112820141A (en) * | 2021-01-14 | 2021-05-18 | 浙江吉利控股集团有限公司 | Parking space detection method and system |
| CN112820141B (en) * | 2021-01-14 | 2022-04-19 | 浙江吉利控股集团有限公司 | Parking space detection method and system |
| DE102023203479A1 (en) | 2023-04-18 | 2024-02-29 | Zf Friedrichshafen Ag | System and method for finding a free parking space |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106971166A (en) | The image pre-processing method and system of parking stall detection | |
| US11127122B2 (en) | Image enhancement method and system | |
| Pan et al. | Underwater image de-scattering and enhancing using dehazenet and HWD | |
| Ma et al. | An effective fusion defogging approach for single sea fog image | |
| CN110400267A (en) | A kind of preprocess method based on inspection image | |
| CN104318529A (en) | Method for processing low-illumination images shot in severe environment | |
| CN104574293A (en) | Multiscale Retinex image sharpening algorithm based on bounded operation | |
| CN112561804A (en) | Low-illumination underwater image enhancement method based on multi-scale detail enhancement | |
| Thanh et al. | Single image dehazing based on adaptive histogram equalization and linearization of gamma correction | |
| Pan et al. | De-scattering and edge-enhancement algorithms for underwater image restoration | |
| Jiang et al. | Nighttime image enhancement based on image decomposition | |
| Zhu et al. | An adaptive and effective single image dehazing algorithm based on dark channel prior | |
| CN105427255A (en) | GRHP based unmanned plane infrared image detail enhancement method | |
| Das et al. | A comparative study of single image fog removal methods | |
| Gu et al. | A low-light image enhancement method based on image degradation model and pure pixel ratio prior | |
| Mu et al. | Low and non-uniform illumination color image enhancement using weighted guided image filtering | |
| Pandey et al. | A fast and effective vision enhancement method for single foggy image | |
| Wang et al. | Review of single image defogging | |
| Wang et al. | Single-image dehazing using color attenuation prior based on haze-lines | |
| Abu-Ein | A novel methodology for digital removal of periodic noise using 2D fast Fourier transforms | |
| Chen et al. | An adaptive image dehazing algorithm based on dark channel prior | |
| CN114648467A (en) | Image defogging method and device, terminal equipment and computer readable storage medium | |
| Honnutagi et al. | Optimized weight maps and fusion for underwater image enhancement | |
| Kansal et al. | Effect of non uniform illumination compensation on dehazing/de-fogging techniques | |
| Wang et al. | Enhancement of low-light image based on wavelet u-net |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170721 |
|
| RJ01 | Rejection of invention patent application after publication |