CN109635762A - A kind of city management method, system and device - Google Patents
A kind of city management method, system and device Download PDFInfo
- Publication number
- CN109635762A CN109635762A CN201811552539.2A CN201811552539A CN109635762A CN 109635762 A CN109635762 A CN 109635762A CN 201811552539 A CN201811552539 A CN 201811552539A CN 109635762 A CN109635762 A CN 109635762A
- Authority
- CN
- China
- Prior art keywords
- image
- images
- city management
- module
- color histogram
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000012706 support-vector machine Methods 0.000 claims abstract description 23
- 238000012512 characterization method Methods 0.000 claims abstract description 7
- 238000004891 communication Methods 0.000 claims description 17
- 238000010200 validation analysis Methods 0.000 claims description 16
- 230000009466 transformation Effects 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 description 6
- 230000000694 effects Effects 0.000 description 3
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 1
- 241000482268 Zea mays subsp. mays Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012549 training Methods 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
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The present invention discloses a kind of city management method, system and device.The present invention determines the contrast images after denoising and difference characteristic region distinct between standard picture using support vector machines, the corresponding image in difference characteristic region is exported into higher dimensional space using feature space classification method, dimensional images are obtained, determine that characterization has the contrast images feature vector for occupying road conditions and comparison color histogram using small wave converting method.In practical application, after the image feature vector and color histogram that extract Aerial Images using same step, the case where it is compared with contrast images feature vector and comparison color histogram, can be automatically determined in Target scalar with the presence or absence of road is occupied respectively.City management method, system and device provided by the invention, can effectively improve the efficiency of management of municipal administration personnel, can be managed immediately for there is the case where occupying road, timeliness is good.
Description
Technical field
The present invention relates to city management technical fields, more particularly to a kind of city management method, system and device.
Background technique
With the quickening of modernization of urban construction, great variety is had occurred in appearance of city.In city management field
Outstanding problem is law enforcement aspect, there is difficulty of much enforcing the law, is mainly shown as that city management spatial dimension is big, single
It is pure to be managed low efficiency, poor in timeliness by municipal administration personnel.
Summary of the invention
The object of the present invention is to provide a kind of city management method, system and device, can automatically determine Target scalar
In with the presence or absence of occupy road the case where, the efficiency of management of municipal administration personnel can be effectively improved, for exist occupy road feelings
Condition can be managed immediately, and timeliness is good.
To achieve the above object, the present invention provides following schemes:
A kind of city management method, the city management method are used to determine in Target scalar with the presence or absence of occupancy road
Situation, the city management method include:
Obtain the Aerial Images of Target scalar；
It determines to whether there is in Target scalar according to Aerial Images, contrast images feature vector and comparison color histogram and account for
The case where with road；Wherein, the contrast images feature vector and the determination method of the comparison color histogram include:
Contrast images and standard picture are obtained, the contrast images are to exist to occupy road conditions in the Target scalar
Image, the standard picture are that there is no the images for occupying road conditions in the Target scalar；
Denoising is carried out to the contrast images using median filtering and wavelet transformation, obtains denoising image；
Difference characteristic area distinct between the denoising image and the standard picture is determined using support vector machines
Domain；
The corresponding image in the difference characteristic region is exported into higher dimensional space using feature space classification method, is obtained high
Tie up image；
The image feature vector and color histogram that the dimensional images are determined using small wave converting method, are deposited as characterization
In the contrast images feature vector and comparison color histogram for occupying road conditions.
Optionally, the kernel function of the support vector machines is Radial basis kernel function.
Optionally, the image feature vector and color histogram that the dimensional images are determined using small wave converting method
Later, further includes:
Validation data set is obtained, the validation data set includes multiple data pair, and each data are including mesh described in a frame
Mark the image and the corresponding type of described image of atural object；The type characterizes the corresponding Target scalar of described image
Occupy road conditions；
The corresponding mesh of each frame described image is determined according to the contrast images feature vector and the comparison color histogram
The occupancy road conditions of atural object are marked, verifying recognition result is obtained；
Recognition accuracy is determined according to the type of the verifying recognition result and each described image；
Judge whether the recognition accuracy is more than or equal to accuracy rate threshold value, obtains the first judging result；
When first judging result indicates that the recognition accuracy is less than accuracy rate threshold value, the supporting vector is adjusted
The punishment parameter and nuclear parameter of machine, described in return " using support vector machines determine the denoising image and the standard picture it
Between distinct difference characteristic region ".
A kind of city management system, the city management system are used to determine in Target scalar with the presence or absence of occupancy road
Situation, the city management system include:
Aerial Images obtain module, for obtaining the Aerial Images of Target scalar；
Road occupying identification module, for determining mesh according to Aerial Images, contrast images feature vector and comparison color histogram
The case where marking in atural object with the presence or absence of road is occupied；Wherein, the contrast images feature vector and the comparison color histogram
Really stator system includes:
Image collection module, for obtaining contrast images and standard picture, the contrast images are in the Target scalar
In the presence of the image for occupying road conditions, the standard picture is that there is no the images for occupying road conditions in the Target scalar；
Denoising module is obtained for carrying out denoising to the contrast images using median filtering and wavelet transformation
Image must be denoised；
Support vector machines module is deposited between the denoising image and the standard picture for being determined using support vector machines
In the difference characteristic region of difference；
Feature space categorization module, for utilizing feature space classification method by the corresponding image in the difference characteristic region
Higher dimensional space is exported to, dimensional images are obtained；
Wavelet transformation module, for determining the image feature vector and color of the dimensional images using small wave converting method
There is the contrast images feature vector for occupying road conditions and comparison color histogram as characterization in histogram.
Optionally, the city management system further include:
Validation data set obtains module, and for obtaining validation data set, the validation data set includes multiple data pair, often
A data are the image and the corresponding type of described image for including Target scalar described in a frame；The type characterizes institute
State the occupancy road conditions of the corresponding Target scalar of image；
Verification result determining module, for being determined according to the contrast images feature vector and the comparison color histogram
The occupancy road conditions of the corresponding Target scalar of each frame described image obtain verifying recognition result；
Accuracy rate determining module determines for the type according to the verifying recognition result and each described image and knows
Other accuracy rate；
Judgment module, judges whether the recognition accuracy is more than or equal to accuracy rate threshold value, obtains judging result；
Parameter adjustment module, for adjusting when the judging result indicates that the recognition accuracy is less than accuracy rate threshold value
The punishment parameter and nuclear parameter of the whole support vector machines.
A kind of city management device, the city management device include: unmanned plane, video camera and processor, wherein
The video camera is set to the unmanned plane, the video camera for photographic subjects cartographic feature as Aerial Images,
The standard picture of the Target scalar is previously stored in the processor, the standard picture is not deposit in the Target scalar
In the image for occupying road conditions；
The processor is connect with the video camera, and the processor is used to determine mesh according to the city management method
The case where marking in atural object with the presence or absence of road is occupied.
Optionally, the city management device further includes 4G communication module and mobile terminal, the 4G communication module and institute
Processor connection is stated, the processor pushes the identification for occupying road conditions by the 4G communication module to the mobile terminal
As a result.
Optionally, the city management device further includes wireless communication module, the wireless communication module respectively with it is described
Processor is connected with the law enforcement platform of municipal administration belonging to the Target scalar, and the processor passes through the wireless communication module to institute
State the recognition result that municipal administration's law enforcement platform push occupies road conditions.
The specific embodiment provided according to the present invention, the invention discloses following technical effects:
City management method, system and device provided by the invention, after determining denoising using support vector machines first
Contrast images and standard picture between distinct difference characteristic region, wherein contrast images are to exist in Target scalar
The image of road conditions is occupied, standard picture is that there is no the images for occupying road conditions in Target scalar.Then feature is utilized
The corresponding image in difference characteristic region is exported to higher dimensional space by spatial classification method, obtains dimensional images.Finally utilize small echo
Transform method determines the image feature vector and color histogram of dimensional images, there is the comparison for occupying road conditions as characterization
Image feature vector and comparison color histogram.In practical application, the characteristics of image of Aerial Images is extracted using same step
After vector sum color histogram, it is compared with contrast images feature vector and comparison color histogram respectively, it can be certainly
Dynamic the case where determining in Target scalar with the presence or absence of road is occupied.City management method, system and device provided by the invention, energy
The efficiency of management for enough effectively improving municipal administration personnel can be managed immediately for there is the case where occupying road, and timeliness is good.
Detailed description of the invention
It in order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, below will be to institute in embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is a kind of flow chart of city management method provided in an embodiment of the present invention；
Fig. 2 is the stream of the determination method of contrast images feature vector provided in an embodiment of the present invention and comparison color histogram
Cheng Tu；
Fig. 3 is a kind of structural block diagram of city management system provided in an embodiment of the present invention；
Fig. 4 is contrast images feature vector provided in an embodiment of the present invention and comparison color histogram stator system really
Structural block diagram；
Fig. 5 is a kind of structural block diagram of city management device provided in an embodiment of the present invention；
Fig. 6 is the Aerial Images of intersection under normal condition provided in an embodiment of the present invention；
Fig. 7 is that intersection is taken photo by plane photo under the state provided in an embodiment of the present invention there are illegal parking；
Fig. 8 is the illegal parking effect picture provided in an embodiment of the present invention extracted in intersection.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The object of the present invention is to provide a kind of city management method, system and device, can automatically determine Target scalar
In with the presence or absence of occupy road the case where, the efficiency of management of municipal administration personnel can be effectively improved, for exist occupy road feelings
Condition can be managed immediately, and timeliness is good.
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, with reference to the accompanying drawing and specific real
Applying mode, the present invention is described in further detail.
Fig. 1 is a kind of flow chart of city management method provided in an embodiment of the present invention.As shown in Figure 1, a kind of city pipe
The case where reason method, the city management method is for determining in Target scalar with the presence or absence of road is occupied, the city management
Method includes:
Step 11: obtaining the Aerial Images of Target scalar；
Step 12: being determined in Target scalar according to Aerial Images, contrast images feature vector and comparison color histogram is
It is no to there is the case where occupying road.
Fig. 2 is the stream of the determination method of contrast images feature vector provided in an embodiment of the present invention and comparison color histogram
Cheng Tu.As shown in Fig. 2, the contrast images feature vector and the determination method of the comparison color histogram include:
Step 21: obtaining contrast images and standard picture, the contrast images are to exist to occupy road in the Target scalar
The image of road situation, the standard picture are that there is no the images for occupying road conditions in the Target scalar.
Step 22: denoising being carried out to the contrast images using median filtering and wavelet transformation, obtains denoising image.
Unmanned plane in flight course may by Gaussian noise influenced, these noises can be to subsequent image data
Classification generates interference, and the present embodiment is based on median filtering and wavelet transformation and carries out denoising to contrast images, utilizes 3*3 template
Windowing calculating is carried out to other pixels in addition to image border, rejects popcorn noise point using median filtering, due to two-dimentional high
The pixel weight of this spatial function increases with distance and is reduced, and carries out small echo by setting threshold value and using inverse distance-weighting method
Transformation removal Gaussian noise.
Step 23: being determined using support vector machines (SVM) distinct between the denoising image and the standard picture
Difference characteristic region.The kernel function of the support vector machines is Radial basis kernel function.
Step 24: the corresponding image in the difference characteristic region being exported into higher-dimension sky using feature space classification method
Between, obtain dimensional images.
Step 25: determining the image feature vector and color histogram of the dimensional images using small wave converting method, make
There is the contrast images feature vector for occupying road conditions and comparison color histogram to characterize.
In the present embodiment, after execution step 25, further includes:
Validation data set is obtained, the validation data set includes multiple data pair, and each data are including mesh described in a frame
Mark the image and the corresponding type of described image of atural object；The type characterizes the corresponding Target scalar of described image
Occupy road conditions；
The corresponding mesh of each frame described image is determined according to the contrast images feature vector and the comparison color histogram
The occupancy road conditions of atural object are marked, verifying recognition result is obtained；
Recognition accuracy is determined according to the type of the verifying recognition result and each described image；
Judge whether the recognition accuracy is more than or equal to accuracy rate threshold value, obtains the first judging result；
When first judging result indicates that the recognition accuracy is less than accuracy rate threshold value, the supporting vector is adjusted
Return step 23: the punishment parameter and nuclear parameter of machine determine the denoising image and the standard picture using support vector machines
Between distinct difference characteristic region.
The characteristics of SVM method is that have in the identification of non-linear and high dimensional pattern only using structural risk minimization as criterion
Special advantage.The present embodiment will be had using the feature difference between the C-SVM identification image pixel of Radial basis kernel function mapping
The 80% of image data set is used as training dataset, using the image data set of residue 20% as validation data set, extracts image
Essential characteristic and obtain iamge description subcharacter, learnt by supervised machine and constantly adjustment correlated inputs parameter be sub to image
Feature is learnt, and then obtains the particular space that image indicates, is finally obtained and is exported between two target images to be identified
Different zones, retain Target scalar after removal road vehicle, the specific factors such as pedestrian, realize position of disorderly setting up a stall, random occupied road, disobey
Advise the extraction of spatial information disorderly to stop.
Fig. 3 is a kind of structural block diagram of city management system provided in an embodiment of the present invention.As shown in figure 3, a kind of city
The case where management system, the city management system is for determining in Target scalar with the presence or absence of road is occupied, the city pipe
Reason system includes:
Aerial Images obtain module 31, for obtaining the Aerial Images of Target scalar；
Road occupying identification module 32, for being determined according to Aerial Images, contrast images feature vector and comparison color histogram
With the presence or absence of the case where occupying road in Target scalar
Fig. 4 is contrast images feature vector provided in an embodiment of the present invention and comparison color histogram stator system really
Structural block diagram.As shown in figure 4, stator system includes: really for the contrast images feature vector and the comparison color histogram
Image collection module 41, for obtaining contrast images and standard picture, the contrast images are the Target scalar
Middle to there is the image for occupying road conditions, the standard picture is that there is no the figures for occupying road conditions in the Target scalar
Picture；
Denoising module 42, for carrying out denoising to the contrast images using median filtering and wavelet transformation,
Obtain denoising image；
Support vector machines module 43, for being determined between the denoising image and the standard picture using support vector machines
Distinct difference characteristic region；
Feature space categorization module 44, for utilizing feature space classification method by the corresponding figure in the difference characteristic region
As exporting to higher dimensional space, dimensional images are obtained；
Wavelet transformation module 45, for determining the image feature vector and face of the dimensional images using small wave converting method
There is the contrast images feature vector for occupying road conditions and comparison color histogram as characterization in Color Histogram.
In the present embodiment, the city management system further include:
Validation data set obtains module, and for obtaining validation data set, the validation data set includes multiple data pair, often
A data are the image and the corresponding type of described image for including Target scalar described in a frame；The type characterizes institute
State the occupancy road conditions of the corresponding Target scalar of image；
Verification result determining module, for being determined according to the contrast images feature vector and the comparison color histogram
The occupancy road conditions of the corresponding Target scalar of each frame described image obtain verifying recognition result；
Accuracy rate determining module determines for the type according to the verifying recognition result and each described image and knows
Other accuracy rate；
Judgment module, judges whether the recognition accuracy is more than or equal to accuracy rate threshold value, obtains judging result；
Parameter adjustment module, for adjusting when the judging result indicates that the recognition accuracy is less than accuracy rate threshold value
The punishment parameter and nuclear parameter of the whole support vector machines.
Fig. 5 is a kind of structural block diagram of city management device provided in an embodiment of the present invention.As shown in figure 5, a kind of city
Managing device, the city management device include: unmanned plane 51, video camera 52 and processor 53.
The video camera 52 is set to the unmanned plane 51, and the video camera 52 is used as photographic subjects cartographic feature and takes photo by plane
Image is previously stored with the standard picture of the Target scalar in the processor 53, and the standard picture is for the target
There is no the images for occupying road conditions in object；
The processor 53 is connect with the video camera 52, and the processor 53 is used for according to the city management method
The case where determining in Target scalar with the presence or absence of road is occupied.
In the present embodiment, the city management device further includes 4G communication module, mobile terminal and wireless communication module.Its
In, the 4G communication module is connect with the processor 53, and the processor 53 is by the 4G communication module to the movement
Terminal push occupies the recognition result of road conditions.The wireless communication module is respectively with the processor 53 and the target
The law enforcement platform connection of municipal administration belonging to object, the processor are pushed by the wireless communication module to municipal administration law enforcement platform
Occupy the recognition result of road conditions.
A kind of city management method, system and device based on machine learning provided by the invention will can also take photo by plane in real time
The spatial data of the target area of image and multisensor timing acquiring is combined, and automatically determining in Target scalar whether there is
The case where occupying road, and analysis result is pushed to municipal administration's law enforcement platform automatically.Fig. 6 is provided in an embodiment of the present invention normal
The Aerial Images of intersection under state.Fig. 7 is intersection under the state provided in an embodiment of the present invention there are illegal parking
Mouth is taken photo by plane photo.Fig. 8 is the illegal parking effect picture provided in an embodiment of the present invention extracted in intersection, in Fig. 8
It is illegal vehicle within the scope of circle.As Figure 6-Figure 8, city management device provided by the invention, can be realized to set up a stall through
Battalion, random occupied road, the violation of law that disorderly parking etc. occupies road carry out intelligent recognition and early warning, effectively improve city management people
The management timeliness and the efficiency of management of member, docking managing numeralization city platform are generated, are distributed, handling municipal administration's case.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.For system disclosed in embodiment
For, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is said referring to method part
It is bright.
Used herein a specific example illustrates the principle and implementation of the invention, and above embodiments are said
It is bright to be merely used to help understand method and its core concept of the invention；At the same time, for those skilled in the art, foundation
Thought of the invention, there will be changes in the specific implementation manner and application range.In conclusion the content of the present specification is not
It is interpreted as limitation of the present invention.
Claims (8)
1. a kind of city management method, which is characterized in that the city management method whether there is for determining in Target scalar
The case where occupying road, the city management method includes:
Obtain the Aerial Images of Target scalar；
It is determined in Target scalar according to Aerial Images, contrast images feature vector and comparison color histogram with the presence or absence of occupancy road
The case where road；Wherein, the contrast images feature vector and the determination method of the comparison color histogram include:
Contrast images and standard picture are obtained, the contrast images are the presence of the figure for occupying road conditions in the Target scalar
Picture, the standard picture are that there is no the images for occupying road conditions in the Target scalar；
Denoising is carried out to the contrast images using median filtering and wavelet transformation, obtains denoising image；
Difference characteristic region distinct between the denoising image and the standard picture is determined using support vector machines；
The corresponding image in the difference characteristic region is exported into higher dimensional space using feature space classification method, obtains higher-dimension figure
Picture；
The image feature vector and color histogram that the dimensional images are determined using small wave converting method are existed as characterization and are accounted for
With the contrast images feature vector and comparison color histogram of road conditions.
2. city management method according to claim 1, which is characterized in that the kernel function of the support vector machines is radial
Base kernel function.
3. city management method according to claim 1, which is characterized in that described in the utilization small wave converting method determines
After the image feature vector and color histogram of dimensional images, further includes:
Validation data set is obtained, the validation data set includes multiple data pair, and each data are including target described in a frame
The corresponding type of image and described image of object；The type characterizes the occupancy of the corresponding Target scalar of described image
Road conditions；
With determining the corresponding target of each frame described image according to the contrast images feature vector and the comparison color histogram
The occupancy road conditions of object obtain verifying recognition result；
Recognition accuracy is determined according to the type of the verifying recognition result and each described image；
Judge whether the recognition accuracy is more than or equal to accuracy rate threshold value, obtains the first judging result；
When first judging result indicates that the recognition accuracy is less than accuracy rate threshold value, the support vector machines is adjusted
Punishment parameter and nuclear parameter " are determined using support vector machines and are deposited between the denoising image and the standard picture described in return
In the difference characteristic region of difference ".
4. a kind of city management system, which is characterized in that the city management system whether there is for determining in Target scalar
The case where occupying road, the city management system includes:
Aerial Images obtain module, for obtaining the Aerial Images of Target scalar；
Road occupying identification module, for according to Aerial Images, contrast images feature vector and comparison color histogram with determining target
The case where in object with the presence or absence of road is occupied；Wherein, the contrast images feature vector and the comparison color histogram be really
Stator system includes:
Image collection module, for obtaining contrast images and standard picture, the contrast images are to exist in the Target scalar
The image of road conditions is occupied, the standard picture is that there is no the images for occupying road conditions in the Target scalar；
Denoising module is gone for carrying out denoising to the contrast images using median filtering and wavelet transformation
It makes an uproar image；
Support vector machines module, for determining that there are areas between the denoising image and the standard picture using support vector machines
Other difference characteristic region；
Feature space categorization module, for being exported the corresponding image in the difference characteristic region using feature space classification method
To higher dimensional space, dimensional images are obtained；
Wavelet transformation module, for determining the image feature vector and color histogram of the dimensional images using small wave converting method
There is the contrast images feature vector for occupying road conditions and comparison color histogram as characterization in figure.
5. city management system according to claim 4, which is characterized in that the city management system further include:
Validation data set obtains module, and for obtaining validation data set, the validation data set includes multiple data pair, every number
According to the image and the corresponding type of described image for including Target scalar described in a frame；The type characterizes the figure
As the occupancy road conditions of corresponding Target scalar；
Verification result determining module, for determining each frame according to the contrast images feature vector and the comparison color histogram
The occupancy road conditions of the corresponding Target scalar of described image obtain verifying recognition result；
Accuracy rate determining module determines that identification is quasi- for the type according to the verifying recognition result and each described image
True rate；
Judgment module, judges whether the recognition accuracy is more than or equal to accuracy rate threshold value, obtains judging result；
Parameter adjustment module, for adjusting institute when the judging result indicates that the recognition accuracy is less than accuracy rate threshold value
State the punishment parameter and nuclear parameter of support vector machines.
6. a kind of city management device, which is characterized in that the city management device includes: unmanned plane, video camera and processor,
Wherein,
The video camera be set to the unmanned plane, the video camera for photographic subjects cartographic feature as Aerial Images, it is described
The standard picture of the Target scalar is previously stored in processor, the standard picture is that there is no account in the Target scalar
With the image of road conditions；
The processor is connect with the video camera, and the processor is used for city according to claim 1-3
Management method determines in Target scalar the case where with the presence or absence of road is occupied.
7. city management device according to claim 6, which is characterized in that the city management device further includes 4G communication
Module and mobile terminal, the 4G communication module are connected to the processor, the processor by the 4G communication module to
The mobile terminal push occupies the recognition result of road conditions.
8. city management device according to claim 6, which is characterized in that the city management device further includes channel radio
Believe module, the wireless communication module respectively with municipal administration belonging to the processor and the Target scalar law enforcement platform connect,
The processor occupies the recognition result of road conditions by the wireless communication module to municipal administration law enforcement platform push.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811552539.2A CN109635762A (en) | 2018-12-18 | 2018-12-18 | A kind of city management method, system and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811552539.2A CN109635762A (en) | 2018-12-18 | 2018-12-18 | A kind of city management method, system and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109635762A true CN109635762A (en) | 2019-04-16 |
Family
ID=66075324
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811552539.2A Pending CN109635762A (en) | 2018-12-18 | 2018-12-18 | A kind of city management method, system and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109635762A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110276254A (en) * | 2019-05-17 | 2019-09-24 | 恒锋信息科技股份有限公司 | No peddler region street pedlar's automatic identification method for early warning based on unmanned plane |
| CN114639251A (en) * | 2022-05-17 | 2022-06-17 | 深圳联和智慧科技有限公司 | Multi-unmanned aerial vehicle cooperative intelligent inspection method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080204553A1 (en) * | 2000-09-11 | 2008-08-28 | Pinotage L.L.C. | System and method for obtaining and utilizing maintenance information |
| US20110064305A1 (en) * | 2009-09-15 | 2011-03-17 | Fuji Xerox Co., Ltd. | Image processing apparatus, image processing method and computer readable medium |
| US20180217599A1 (en) * | 2017-01-30 | 2018-08-02 | SkyRyse, Inc. | Vehicle system and method for providing services |
| CN108510750A (en) * | 2018-04-25 | 2018-09-07 | 济南浪潮高新科技投资发展有限公司 | A method of the unmanned plane inspection parking offense based on neural network model |
| CN108831158A (en) * | 2018-08-20 | 2018-11-16 | 贵州宜行智通科技有限公司 | It disobeys and stops monitoring method, device and electric terminal |
-
2018
- 2018-12-18 CN CN201811552539.2A patent/CN109635762A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080204553A1 (en) * | 2000-09-11 | 2008-08-28 | Pinotage L.L.C. | System and method for obtaining and utilizing maintenance information |
| US20110064305A1 (en) * | 2009-09-15 | 2011-03-17 | Fuji Xerox Co., Ltd. | Image processing apparatus, image processing method and computer readable medium |
| US20180217599A1 (en) * | 2017-01-30 | 2018-08-02 | SkyRyse, Inc. | Vehicle system and method for providing services |
| CN108510750A (en) * | 2018-04-25 | 2018-09-07 | 济南浪潮高新科技投资发展有限公司 | A method of the unmanned plane inspection parking offense based on neural network model |
| CN108831158A (en) * | 2018-08-20 | 2018-11-16 | 贵州宜行智通科技有限公司 | It disobeys and stops monitoring method, device and electric terminal |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110276254A (en) * | 2019-05-17 | 2019-09-24 | 恒锋信息科技股份有限公司 | No peddler region street pedlar's automatic identification method for early warning based on unmanned plane |
| CN110276254B (en) * | 2019-05-17 | 2024-06-07 | 恒锋信息科技股份有限公司 | Unmanned aerial vehicle-based automatic recognition and early warning method for bootlegged area bootlegged |
| CN114639251A (en) * | 2022-05-17 | 2022-06-17 | 深圳联和智慧科技有限公司 | Multi-unmanned aerial vehicle cooperative intelligent inspection method and system |
| CN114639251B (en) * | 2022-05-17 | 2022-08-09 | 深圳联和智慧科技有限公司 | Multi-unmanned aerial vehicle cooperative intelligent inspection method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102509291B (en) | Pavement disease detecting and recognizing method based on wireless online video sensor | |
| US10706330B2 (en) | Methods and systems for accurately recognizing vehicle license plates | |
| WO2019223586A1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| US20200364467A1 (en) | Method and device for detecting illegal parking, and electronic device | |
| CN103136766B (en) | A kind of object conspicuousness detection method based on color contrast and color distribution | |
| Zhang et al. | Vehicle recognition algorithm based on Haar-like features and improved Adaboost classifier | |
| CN112329776B (en) | License plate detection method and device based on improved CenterNet network | |
| CN103077384A (en) | Method and system for positioning and recognizing vehicle logo | |
| CN107886507B (en) | A kind of salient region detecting method based on image background and spatial position | |
| CN102663405B (en) | Prominence and Gaussian mixture model-based method for extracting foreground of surveillance video | |
| CN102768731A (en) | Method and system for automatic positioning and identifying target based on high definition video images | |
| CN110490150A (en) | A kind of automatic auditing system of picture violating the regulations and method based on vehicle retrieval | |
| CN102902957A (en) | Video-stream-based automatic license plate recognition method | |
| CN102542244A (en) | Face detection method and system and computer program product | |
| CN102799862A (en) | System and method for pedestrian rapid positioning and event detection based on high definition video monitor image | |
| CN110245600B (en) | Unmanned aerial vehicle road detection method for self-adaptive initial quick stroke width | |
| CN103049788B (en) | Based on space number for the treatment of object detection system and the method for computer vision | |
| CN112396000A (en) | Method for constructing multi-mode dense prediction depth information transmission model | |
| CN106991821A (en) | Vehicles peccancy hand-held mobile terminal data collecting system | |
| CN109635762A (en) | A kind of city management method, system and device | |
| CN104766344A (en) | Vehicle detecting method based on moving edge extractor | |
| CN108537223B (en) | License plate detection method, system and equipment and storage medium | |
| CN111652033A (en) | Lane line detection method based on OpenCV | |
| CN107832598B (en) | Unlocking control method and related product | |
| CN106203302A (en) | Pedestrian detection that view-based access control model and wireless aware combine and statistical method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |