CN102610102A - Suspect vehicle inspection and control method and system - Google Patents
Suspect vehicle inspection and control method and system Download PDFInfo
- Publication number
- CN102610102A CN102610102A CN2012100456015A CN201210045601A CN102610102A CN 102610102 A CN102610102 A CN 102610102A CN 2012100456015 A CN2012100456015 A CN 2012100456015A CN 201210045601 A CN201210045601 A CN 201210045601A CN 102610102 A CN102610102 A CN 102610102A
- Authority
- CN
- China
- Prior art keywords
- similarity
- color
- supplemental characteristic
- image
- suspected vehicles
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000007689 inspection Methods 0.000 title abstract description 6
- 230000000153 supplemental effect Effects 0.000 claims description 81
- 239000000284 extract Substances 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 6
- 239000000463 material Substances 0.000 abstract description 6
- 238000009826 distribution Methods 0.000 description 10
- 230000001939 inductive effect Effects 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 230000033001 locomotion Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000000903 blocking effect Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 244000188472 Ilex paraguariensis Species 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000033772 system development Effects 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a suspect vehicle inspection and control method and system. The method comprises real-time acquiring a video stream and snap-shooting a vehicle image; subjecting the snap-shot image and a suspect vehicle sample image to color contrast to determine color similarity, and if the color similarity exceeds a set color similarity threshold, going to the next step; subjecting the snap-shot image and the suspect vehicle sample image to auxiliary characteristic contrast, to determine auxiliary characteristic similarity, the auxiliary characteristics including at least one of texture characteristics and shape characteristics; and comprehensively judging, and if the auxiliary characteristic similarity is larger than a set threshold, determining the comprehensive similarity by the auxiliary characteristic similarity or allowing the comprehensive similarity to depend on the auxiliary characteristic similarity. The vehicle image snap-shooting can be carried out by virtual coil triggering. Template match based on color can also be adopted to extract the auxiliary characteristics from a match region of the snap-shot image to be contrasted with the suspect vehicle sample image. The invention can realize rapid, efficient and accurate inspection and control effects, and save manpower and material resources.
Description
Technical field
The present invention relates to the monitoring technique field, relate in particular to a kind of suspected vehicles check and control method and system.
Background technology
Along with the fast development of national highway communication construction and popularizing of motor vehicles; Criminal and the case involving public security relevant with road and motor vehicles rises year by year; The hit-and-run of particularly carrying out via intercity network of highways, robbery of motor vehicle, vehicle smuggling etc. are becoming increasingly rampant especially; This has not only caused great threat to social security; Simultaneously also destroyed the political situation of stability and unity, thereby caused the great attention of national relevant ministries and commissions, setting up trans-departmental, a trans-regional automobile control comprehensive application system is the inexorable trend of public security Construction of Information System development.But this type criminal case since its on a large scale, the characteristics of flowability and rapidity have increased difficulty for the investigation work of public security department, also have higher requirement.
In order to solve these comparatively distinct issues; Accelerate to carry out the informatization of automobile control aspect; Raising work scientific and technological content, improve way to manage, strengthen law-enforcing supervision, improve the level of keeping a lookout of public security; General now the employing carried out identification mode to the motor vehicles number plate; Chinese patent for example: a kind of traffic offence that has concurrently is captured the equipment of function and public security bayonet socket function (publication number: CN201188270, open day: 2009-01-28), method for associative search of suspected vehicles (publication number: CN101593418, open day: 2009-12-02).To need the suspected vehicles information input blacklist storehouse of check and control through the inspection platform of deploying to ensure effective monitoring and control of illegal activities; When suspected vehicles passes through each bayonet socket; The watch-dog system will find immediately and in time report to the police; The value machine people's police of inspection post Control Room can receive warning message and vehicle pictures from computer, outdoor loudspeaker and LED large-size screen monitors also will be reported warning message simultaneously, and warning message also arrives command centre of detachment with synchronous transmission.But in the process that reality is used, suspected vehicles generally can adopt the mode of blocking car plate or changing car plate to hide inspection and deploy to ensure effective monitoring and control of illegal activities, thereby the practical function that causes checking the system of deploying to ensure effective monitoring and control of illegal activities is little.
Summary of the invention
Partly statement in the description hereinafter of aspect of the present invention and advantage perhaps can be described obviously from this, perhaps can learn through putting into practice the present invention.
Discern according to car plate and detect for overcoming existing suspected vehicles check and control; But most suspected vehicles adopt the means of blocking car plate or changing car plate to hide the shortcoming of check and control; The present invention provides a kind of suspected vehicles check and control method and system; Color through extracting vehicle and comprise textural characteristics and shape facility at least one supplemental characteristic carry out the vehicle comparison and come intelligent check and control suspected vehicles, reached fast, efficient, the accurate effect of check and control, saved manpower and materials; And image comparison method of the present invention can improve the speed and the precision of image comparison greatly; The triggering of vehicle is simultaneously captured and can have been avoided broken road breaking face, the shortcoming that the landfill inductive coil is brought on the road surface through the mode of video virtual coil.
It is following that the present invention solves the problems of the technologies described above the technical scheme that is adopted:
According to an aspect of the present invention, a kind of suspected vehicles check and control method is provided, it may further comprise the steps:
S1. obtain video flowing in real time, vehicle is being arranged through the out-of-date candid photograph of carrying out vehicle image;
S2. will capture image and suspected vehicles sample image and carry out the color comparison, confirm the color similarity degree, if said color similarity degree surpasses the color similarity degree threshold value of setting then gets into next step; Otherwise, eliminating suspicion;
S3. will capture image and suspected vehicles sample image and carry out the supplemental characteristic comparison, and confirm the supplemental characteristic similarity, said supplemental characteristic comprises at least one in textural characteristics and the shape facility;
S4. on the basis of color similarity degree and supplemental characteristic similarity; Carry out synthetic determination; Draw the comprehensive similarity of capturing vehicle and said suspected vehicles; Under the situation of supplemental characteristic similarity greater than the supplemental characteristic similarity threshold of setting, said comprehensive similarity is main by the decision of supplemental characteristic similarity or with the supplemental characteristic similarity.
According to a preferred embodiment of the present invention, in said step S1, through virtual coil triggering the carrying out candid photograph of vehicle image.
According to a preferred embodiment of the present invention; In said step S2; Through capturing image and suspected vehicles sample image carries out the template matches based on color, confirm the color similarity degree, and confirm to capture the matching area the most similar in the image simultaneously with suspected vehicles; In said step S3, compare through the supplemental characteristic that from the said matching area of said candid photograph image, extracts supplemental characteristic and said suspected vehicles sample image, confirm the supplemental characteristic similarity.
Preferably, in said step S2, image carries out color space transformation and the color layering is calculated to capturing earlier, and then carries out said template matches based on color.
Preferably, in said step S2, carry out said template matches based on color through color histogram.
Preferably, in said step S3, said supplemental characteristic adopts textural characteristics.
Preferably, said textural characteristics comprises in the feature one or multinomial: the textural characteristics of gray level co-occurrence matrixes, the constant textural characteristics of rotation convergent-divergent.
Preferably, in said step S4, the method for carrying out synthetic determination is following: the first threshold and second threshold value of at first setting the textural characteristics similarity; If the textural characteristics similarity is greater than the first threshold of setting, then said comprehensive similarity is determined by the textural characteristics similarity; If the textural characteristics similarity is less than the first threshold of setting but greater than second threshold value of setting, then said comprehensive similarity is with color similarity degree and textural characteristics similarity synthetic determination, but is main with the textural characteristics similarity; If the textural characteristics similarity is less than second threshold value of setting, then said comprehensive similarity is with color similarity degree and textural characteristics similarity synthetic determination, but is main with the color similarity degree.
Preferably, in said step S4, set alarm threshold value, if said comprehensive similarity is then carried out alarm greater than the alarm threshold value of setting.
According to another aspect of the present invention, a kind of suspected vehicles check and control system is provided, it comprises the suspected vehicles comparing module, and said suspected vehicles comparing module comprises:
The image receiver module is used to receive the vehicle image of candid photograph;
The color comparing module is used for candid photograph image and suspected vehicles sample image are carried out the color comparison, confirms the color similarity degree, handles if said color similarity degree surpasses the color similarity degree threshold value of setting then gets into the supplemental characteristic comparing module;
The supplemental characteristic comparing module is used for candid photograph image and suspected vehicles sample image are carried out the supplemental characteristic comparison, confirms the supplemental characteristic similarity, and said supplemental characteristic comprises at least one in textural characteristics and the shape facility;
The synthetic determination module; Be used for basis in color similarity degree and supplemental characteristic similarity; Carry out synthetic determination; Draw the comprehensive similarity of capturing vehicle and said suspected vehicles, under the situation of supplemental characteristic similarity greater than the supplemental characteristic similarity threshold of setting, said comprehensive similarity is main by the decision of supplemental characteristic similarity or with the supplemental characteristic similarity.
According to a preferred embodiment of the present invention; Said color comparing module is set to through capturing image and suspected vehicles sample image carries out the template matches based on color; Confirm the color similarity degree, and confirm to capture the matching area the most similar in the image simultaneously with suspected vehicles; Said supplemental characteristic comparing module is set to compare through the supplemental characteristic that from the said matching area of said candid photograph image, extracts supplemental characteristic and said suspected vehicles sample image, confirms the supplemental characteristic similarity.
Certainly, said suspected vehicles comparing module also can be set to carry out other or multinomial step in the above-mentioned suspected vehicles check and control method characteristic.
Compared with prior art; The present invention through extracting vehicle color and comprise textural characteristics and shape facility at least one supplemental characteristic carry out vehicle and compare the check and control suspected vehicles; When having avoided discerning check and control through car plate; Suspected vehicles block car plate or change car plate cause can't check and control a difficult problem, reached fast and the effect of efficiently and accurately check and control, saved manpower and materials.Utilize the present invention,, or else carry out blanket research with the labor manpower and materials to the escape of traffic accident vehicle, the searching of crime suspected vehicles, a fake-licensed car investigation.
Suspected vehicles intelligence check and control method of the present invention; Based on video retrieval technology, be mainly used in during police criminal detection solves a case, through with database in suspect vehicle information or the stolen vehicle storehouse (blacklist) of robbing compare; Find that suspect vehicle with Realtime Alerts, alleviates the workload of artificial check and control; The mode through the video virtual coil is captured in the triggering of vehicle simultaneously, has avoided broken road breaking face, the shortcoming that the landfill inductive coil is brought on the road surface.
Because the supplemental characteristic comparison is on the basis of color comparison, to carry out; Can from the matching area of capturing image, extract the supplemental characteristic of supplemental characteristic and suspected vehicles sample image compares; Avoided the processing direct comparison of two sub-pictures (promptly to) to whole pictures; Therefore improve speed and precision greatly, saved manpower and materials.
Through reading instructions, those of ordinary skills will understand characteristic and the aspect of these embodiment and other embodiment better.
Description of drawings
Below through with reference to accompanying drawing and combine instance to describe the present invention particularly; Advantage of the present invention and implementation will be more obvious; Wherein content shown in the accompanying drawing only is used for explaining to of the present invention, and does not constitute the restriction of going up in all senses of the present invention, in the accompanying drawings:
Fig. 1 is the structural representation of suspected vehicles check and control system according to an embodiment of the invention.
Fig. 2 detects general flow chart for suspected vehicles according to an embodiment of the invention.
Fig. 3 is the processing flow chart of suspected vehicles comparing module according to an embodiment of the invention.
Fig. 4 is the structural representation of suspected vehicles comparing module according to an embodiment of the invention.
Embodiment
As shown in Figure 1, according to one embodiment of the invention, a kind of suspected vehicles check and control system is provided; This system can be a network system, also can be a main frame, a equipment that also can be independent; Or software systems that can be installed in main frame or the specialized equipment; Key is that it has suspected vehicles comparing module of the present invention, and as shown in Figure 4, this suspected vehicles comparing module comprises:
The image receiver module is used to receive the vehicle image of candid photograph;
The color comparing module is used for candid photograph image and suspected vehicles sample image are carried out the color comparison, confirms the color similarity degree, handles if the color similarity degree surpasses the color similarity degree threshold value of setting then gets into the supplemental characteristic comparing module;
The supplemental characteristic comparing module is used for candid photograph image and suspected vehicles sample image are carried out the supplemental characteristic comparison, confirms the supplemental characteristic similarity, and supplemental characteristic comprises at least one in textural characteristics and the shape facility;
The synthetic determination module; Be used for basis in color similarity degree and supplemental characteristic similarity; Carry out synthetic determination; Draw the comprehensive similarity of capturing vehicle and suspected vehicles, under the situation of supplemental characteristic similarity greater than the supplemental characteristic similarity threshold of setting, comprehensive similarity is main by the decision of supplemental characteristic similarity or with the supplemental characteristic similarity.
And; According to a preferred embodiment of the present invention; The suspected vehicles comparing module is set to confirm the color similarity degree through capturing image and suspected vehicles sample image carries out the template matches based on color, and confirms to capture the matching area the most similar with suspected vehicles in the image simultaneously; The supplemental characteristic comparing module is set to compare through the supplemental characteristic that from the matching area of capturing image, extracts supplemental characteristic and suspected vehicles sample image, confirms the supplemental characteristic similarity.
Among the embodiment below; Adopting textural characteristics with supplemental characteristic is that example describes; Certainly those of ordinary skills also can adopt shape facility (the for example edge feature of vehicle) as supplemental characteristic; Also can adopt textural characteristics and shape facility as supplemental characteristic simultaneously, these are all within scope of the present invention.
Because supplemental characteristic (for example textural characteristics) comparison is on the basis of color comparison, to carry out; Can be from the matching area of capturing image texture feature extraction and suspected vehicles sample image texture features compare; Avoided the processing direct comparison of two sub-pictures (promptly to) to whole pictures; Therefore improve speed and precision greatly, saved manpower and materials.
Be that example specifies with the network system among Fig. 1 below; In network architecture; Be provided with many decometers mouth main frame; These bayonet socket main frames for example can be arranged on freeway toll station, and it is connected to command centre through network, and command centre possibly connect with public security private or other private.Utilize the present invention, the bayonet socket main frame not necessarily is arranged at the bayonet socket place, also can be the camera head that sets up on the highway.Suspected vehicles comparing module of the present invention can be arranged in the main frame or specialized equipment of command centre, also can be arranged in any equipment that is connected through network with command centre, or be set directly in some bayonet socket main frame.Those of ordinary skills can be arranged at suspected vehicles comparing module of the present invention in any suitable check and control system as required.
Among the embodiment as shown in Figure 2, show suspected vehicles and detect general flow chart, method of the present invention comprises: obtain video flowing in real time; If have vehicle through method through the video virtual coil trigger and capture image; Through colo(u)r breakup and the color histogram after obtaining layering carry out color comparison, to carry out aspect ratio right for the combined with texture characteristic on the basis of color comparison, on the right basis of color comparison and aspect ratio; Obtain the suspected vehicles similarity; Adopt certain rule to do synthetic determination and obtain comprehensive degree of confidence, if comprehensive degree of confidence greater than certain threshold value then think suspected vehicles, otherwise is not.Its concrete steps are following:
1, obtains video data from the live video stream decoding;
2, virtual coil triggers: if the vehicle process is arranged, trigger candid photograph through virtual coil;
The color space transformation and the color layering of 3, capturing two field picture are calculated;
4, color comparison (adopting template matches) based on color: on the basis of color layering, slightly compare through color histogram, and confirm with the suspected vehicles property data base in the most similar Probability Area (matching area) of suspected vehicles; If the color similarity degree surpasses the color similarity degree threshold value of setting then gets into next step; Otherwise, eliminating suspicion.
5, supplemental characteristic comparison: for example extracting, textural characteristics accurately matees; Compare through texture feature extraction and suspected vehicles sample image texture features from the matching area of capturing image, confirm the textural characteristics similarity.
6, threshold determination: combine thick comparison (being the color comparison) and thin comparison (being the supplemental characteristic comparison) to carry out synthetic determination, draw comprehensive degree of confidence according to certain rule; If comprehensive degree of confidence is greater than preset threshold then provide degree of confidence, the prompting staff notes, if less than preset threshold then think it can not is suspected vehicles, passes through.
Certainly, also can adopt the mode that the landfill inductive coil carries out the vehicle image candid photograph on the road surface in the prior art.The mode of utilizing the present invention preferably to capture through the video virtual coil has been avoided broken road breaking face, the shortcoming that the landfill inductive coil is brought on the road surface.
In the specific embodiment as shown in Figure 2, the detection of suspected vehicles comprises the following steps:
101. obtain video flowing in real time;
102. carry out video decode;
If 103. have vehicle through then method through the video virtual coil trigger and capture image;
104. compare, draw comprehensive degree of confidence through the suspected vehicles comparing module;
105. comprehensive degree of confidence and preset threshold are compared;
106. if comprehensive degree of confidence then starts the video interlink module greater than preset threshold; Otherwise withdraw from.
In the specific embodiment as shown in Figure 3, the treatment scheme of suspected vehicles comparing module comprises the following steps:
201. trigger the video data input;
202., carry out color space transformation in conjunction with the video parameter of input;
203. carrying out the color layering calculates;
204. carry out the color comparison with the suspected vehicles sample image in the suspected vehicles property data base;
205. from the video image of capturing, carry out the extraction of textural characteristics;
206. carry out the textural characteristics comparison with the suspected vehicles sample image in the suspected vehicles property data base;
207. carrying out the fusion of color and textural characteristics judges;
208. judge whether to meet requirement of confidence,, otherwise withdraw from if then provide comprehensive degree of confidence.
Several steps in the face of this embodiment is described in detail successively down:
The first step, obtain video data from live video stream decoding;
1) video decode upgrades up-to-date decode component and decoding relation table automatically;
2) equipment is searched corresponding decode component automatically;
3) making up complete decoding link automatically according to decode component decodes;
4) video decode and playing device each frame that produces of will decoding sends to analytic unit.
If there was the vehicle process in second step, triggers through virtual coil and capture
1) multi-modal Gaussian Background modeling is adopted in movement background modeling, this step;
The video image that adopts multi-modal Gaussian Background model that hard-wired video camera is taken carries out background modeling, and such as regional to each 3-5 of pixel definition, each zone is represented with a Gaussian distribution.Wherein, the step of each pixel being set up Gauss model is specially: the pixel of supposing the t two field picture of input is I
t, μ
I, t-1Be the average of pixel value of i the Gaussian distribution of (t-1) two field picture, the average of pixel value equal each pixel value addition and divided by the number of pixel, σ
I, t-1Be the standard deviation of pixel value of i the Gaussian distribution of (t-1) two field picture, D is for satisfying formula | I
t-μ
I, t-1|≤D. σ
I, t-1Preset parameter, this parameter can be obtained through practical experience, wherein, μ
I, t=(1-α) μ
I, t-1+ ρ I
t,
ρ=α/ω
I, t, α is a learning rate, 0≤α≤1, and ρ is the parameter learning rate, ω
I, tBe the weights of i Gaussian distribution of t two field picture.All weights that normalization calculates, and press ω to each gauss of distribution function
I, t/ σ
I, tArrange from big to small, if i
1, i
2... i
kRepresent each Gaussian distribution, with i
1, i
2... i
kAccording to ω
I, t/ σ
I, tOrder is from big to small arranged, if a preceding M Gaussian distribution satisfies formula:
τ is the weights threshold values, can obtain according to actual conditions, usually τ value 0.7.
2) through the frame difference target detection of taking exercises
After having confirmed background distributions; The background model that present frame is corresponding with the background distributions of current frame is subtracted each other; Obtain the moving region of current frame, binaryzation and morphology processing are carried out in the moving region that obtains, make and cut apart more complete, the independence of the fuzzy motion target area that obtains.After obtaining fuzzy motion target area; Can extract the static nature of this fuzzy motion target area; Comprise the size, area, length breadth ratio, center, color projection histogram of boundary rectangle etc., the static nature of extraction can be as the characteristic that detects the target area.
3) if moving target triggers virtual coil then triggers.
The 3rd step, color space transformation and color layering are calculated
1) color space transformation;
Owing to need come colo(u)r breakup at HSV (hue, saturation, intensity) color space, thus at first with image from RGB (red, green, blue) color space conversion to the hsv color space:
2) the color layering is calculated
The color layering is exactly that color space is mapped in certain subclass, thereby improves image comparison speed.General color of image system nearly 2
24Plant color, and the color that human eye can really be distinguished is limited, therefore when carrying out Flame Image Process, need carries out layering to color space, the dimension size of layering is extremely important, and the layering dimension is high more, and comparison accuracy is just high more, but comparison speed can descend thereupon.
The color layering is divided into colo(u)r breakup of equivalent spacing and the colo(u)r breakup of non-equivalent spacing, if because the dimension of equivalent spacing layering is low excessively, then precision can descend greatly; If too highly can cause calculation of complex again; Through analyzing and experiment, present embodiment is selected the colo(u)r breakup of non-equivalent spacing for use, and step is following:
According to people's perception, be divided into 8 parts to tone H, saturation degree S and brightness V are divided into 3 parts, according to color space and people the subjective perception characteristic of color are quantized layering, and formula is following:
According to above method color space is divided into 72 kinds of colors.
The 4th step, color comparison: on the basis of color layering, slightly compare, confirm the Probability Area the most similar with suspected vehicles through color histogram
When having new sample to compare in the suspected vehicles property data base, according to cutting apart the color region that obtains, calculate the similarity of sample color region and video to be checked, adopt the absolute value Furthest Neighbor here.
If two color regions are respectively I, Q, with the concentric rectangles division methods image is divided, obtain a n concentric rectangles, according to the 72 dimension HSV histograms that the front layering obtains, the distance B of counterpart
iFor:
Wherein, h
i(j), h
q(j) corresponding color area I, Q tie up histogrammic value at j respectively, to the result of calculation ordering, find out the most similar zone as matching area.
The 5th step, supplemental characteristic comparison: extract supplemental characteristic (is example with the textural characteristics) and accurately mate
Textural characteristics can comprise in the feature one or multinomial: the textural characteristics of gray level co-occurrence matrixes, the rotation constant textural characteristics of convergent-divergent (like the SIFT characteristic).
1) textural characteristics of gray level co-occurrence matrixes
At first converting coloured image to gray level image, is the image of N level for gray scale, and co-occurrence matrix is a N*N dimension matrix, promptly
Wherein, be positioned at (h, element m k)
HkValue representation at a distance of (h, gray scale k) is h, and another gray scale is the number of times of pixel to occurring of k.
Four characteristic quantities that extracted by the texture co-occurrence matrix are:
Contrast:
Energy:
Entropy:
Relevant:
Wherein,
It is every column element sum in the matrix M;
It is every row element sum; μ
x, μ
y, σ
x, σ
yBe respectively m
x, m
yAverage and standard deviation.
Concrete steps in the present invention are following:
A, the gray scale of image is divided into 64 gray shade scales;
B, structure four direction gray level co-occurrence matrixes: M (1,0), M (0,1), M (1,1), M (1 ,-1)
C, calculate four texture characteristic amounts on each co-occurrence matrix respectively;
Average and standard deviation with each characteristic quantity: μ
CON, σ
CON, μ
ASM, σ
ASM, μ
ENT, σ
ENT, μ
COR, σ
COREight components as textural characteristics.
2) SIFT (conversion of yardstick invariant features) characteristic
The SIFT algorithm is a kind of algorithm that extracts local feature, seeks extreme point, extracting position, yardstick, rotational invariants at metric space.
It is following that it mainly detects step:
A) detect yardstick spatial extrema point;
B) accurately locate extreme point;
C) be each key point assigned direction parameter;
D) generation of key point descriptor.
3) comprehensive characteristics
Utilizing single characteristic to carry out the image comparison has advantage separately, and in order to improve the accuracy of comparison, color combining characteristic of the present invention and supplemental characteristic (is example with the textural characteristics) are constructed a structured features and carried out the image comparison.Because the physical significance of color characteristic and textural characteristics is inequality, does not have direct comparability, need do normalization to them and handle, formula is following:
D＝w
1d
1+w
2d
2 (12)
Wherein, d
1, d
2Represent the color characteristic amount of 2 width of cloth images, the distance between the texture characteristic amount respectively; w
1, w
2Weights (0≤w for characteristic quantity
1≤1, and w
1+ w
2=1).
The 6th step, threshold determination: combine thick comparison and thin comparison to carry out synthetic determination, draw comprehensive degree of confidence according to certain rule
Because vehicle is the rigid body target, textural characteristics has stability, therefore, if the textural characteristics similarity greater than the textural characteristics similarity threshold of setting, then comprehensive similarity can be main by the decision of textural characteristics similarity or with the textural characteristics similarity directly.
In the present embodiment, for example can set two threshold values 1 and threshold value 2. of textural characteristics
If the similarity of textural characteristics is greater than preset threshold 1, then the similarity of suspected vehicles is determined by textural characteristics;
If the similarity of textural characteristics is less than preset threshold 1 but greater than preset threshold 2, then the similarity of suspected vehicles is with color and textural characteristics synthetic determination, but is main with the similarity of textural characteristics;
If the similarity of textural characteristics is less than preset threshold 2, then the similarity of suspected vehicles is with color and textural characteristics synthetic determination, but the similarity of suspected vehicles is main with color, and its similar degree is also corresponding minimum.
In addition, can set alarm threshold value, if, then can pass through video interlink module alarm staff greater than the alarm threshold value of setting, otherwise eliminating suspicion or let vehicle pass-through.
In the above-described embodiments, realization of the present invention mainly comprises three parts: color comparison, supplemental characteristic (is example with the textural characteristics) comparison and threshold determination; The color comparison confirms to comprise the approximate region of suspected vehicles according to the color histogram after the colo(u)r breakup; The textural characteristics comparison can further be confirmed on the basis of color comparison; Threshold determination is to obtain similarity according to color comparison and textural characteristics comparison, draws the comprehensive degree of confidence of target vehicle through certain rule.
The present invention passes through said method; Having overcome existing suspected vehicles check and control discerns according to car plate and detects; But most suspected vehicles can adopt the problem of blocking car plate or changing car plate; A kind of method of coming the check and control suspected vehicles based on video frequency searching is provided, has also replaced the method for the landfill inductive coil on former destruction road surface simultaneously through the method for video virtual coil.
Above with reference to description of drawings the preferred embodiments of the present invention, those skilled in the art do not depart from the scope and spirit of the present invention, and can have multiple flexible program to realize the present invention.For example, the characteristic that illustrates or describe as the part of an embodiment can be used for another embodiment to obtain another embodiment.More than be merely the preferable feasible embodiment of the present invention, be not so limit to interest field of the present invention, the equivalence that all utilizations instructions of the present invention and accompanying drawing content are done changes, and all is contained within the interest field of the present invention.
Claims (10)
1. a suspected vehicles check and control method is characterized in that, may further comprise the steps:
S1. obtain video flowing in real time, vehicle is being arranged through the out-of-date candid photograph of carrying out vehicle image;
S2. will capture image and suspected vehicles sample image and carry out the color comparison, confirm the color similarity degree, if said color similarity degree surpasses the color similarity degree threshold value of setting then gets into next step;
S3. will capture image and suspected vehicles sample image and carry out the supplemental characteristic comparison, and confirm the supplemental characteristic similarity, said supplemental characteristic comprises at least one in textural characteristics and the shape facility;
S4. on the basis of color similarity degree and supplemental characteristic similarity; Carry out synthetic determination; Draw the comprehensive similarity of capturing vehicle and said suspected vehicles; Under the situation of supplemental characteristic similarity greater than the supplemental characteristic similarity threshold of setting, said comprehensive similarity is main by the decision of supplemental characteristic similarity or with the supplemental characteristic similarity.
2. suspected vehicles check and control method according to claim 1 is characterized in that, in said step S1, through virtual coil triggering the carrying out candid photograph of vehicle image.
3. suspected vehicles check and control method according to claim 1 and 2; It is characterized in that; In said step S2; Through capturing image and suspected vehicles sample image carries out the template matches based on color, confirm the color similarity degree, and confirm to capture the matching area the most similar in the image simultaneously with suspected vehicles; In said step S3, compare through the supplemental characteristic that from the said matching area of said candid photograph image, extracts supplemental characteristic and said suspected vehicles sample image, confirm the supplemental characteristic similarity.
4. suspected vehicles check and control method according to claim 3 is characterized in that, in said step S2, image carries out color space transformation and the color layering is calculated to capturing earlier, and then carries out said template matches based on color.
5. suspected vehicles check and control method according to claim 3 is characterized in that, in said step S2, carries out said template matches based on color through color histogram.
6. suspected vehicles check and control method according to claim 3; It is characterized in that; In said step S3, said supplemental characteristic adopts textural characteristics, and said textural characteristics comprises in the feature one or multinomial: the textural characteristics of gray level co-occurrence matrixes, the constant textural characteristics of rotation convergent-divergent.
7. suspected vehicles check and control method according to claim 6 is characterized in that, in said step S4, the method for carrying out synthetic determination is following: the first threshold and second threshold value of at first setting the textural characteristics similarity; If the textural characteristics similarity is greater than the first threshold of setting, then said comprehensive similarity is determined by the textural characteristics similarity; If the textural characteristics similarity is less than the first threshold of setting but greater than second threshold value of setting, then said comprehensive similarity is with color similarity degree and textural characteristics similarity synthetic determination, but is main with the textural characteristics similarity; If the textural characteristics similarity is less than second threshold value of setting, then said comprehensive similarity is with color similarity degree and textural characteristics similarity synthetic determination, but is main with the color similarity degree.
8. suspected vehicles check and control method according to claim 7 is characterized in that, in said step S4, sets alarm threshold value, if said comprehensive similarity is then carried out alarm greater than the alarm threshold value of setting.
9. a suspected vehicles check and control system is characterized in that, comprises the suspected vehicles comparing module, and said suspected vehicles comparing module comprises:
The image receiver module is used to receive the vehicle image of candid photograph;
The color comparing module is used for candid photograph image and suspected vehicles sample image are carried out the color comparison, confirms the color similarity degree, handles if said color similarity degree surpasses the color similarity degree threshold value of setting then gets into the supplemental characteristic comparing module;
The supplemental characteristic comparing module is used for candid photograph image and suspected vehicles sample image are carried out the supplemental characteristic comparison, confirms the supplemental characteristic similarity, and said supplemental characteristic comprises at least one in textural characteristics and the shape facility;
The synthetic determination module; Be used for basis in color similarity degree and supplemental characteristic similarity; Carry out synthetic determination; Draw the comprehensive similarity of capturing vehicle and said suspected vehicles, under the situation of supplemental characteristic similarity greater than the supplemental characteristic similarity threshold of setting, said comprehensive similarity is main by the decision of supplemental characteristic similarity or with the supplemental characteristic similarity.
10. suspected vehicles check and control according to claim 9 system; It is characterized in that; Said color comparing module is set to through capturing image and suspected vehicles sample image carries out the template matches based on color; Confirm the color similarity degree, and confirm to capture the matching area the most similar in the image simultaneously with suspected vehicles; Said supplemental characteristic comparing module is set to compare through the supplemental characteristic that from the said matching area of said candid photograph image, extracts supplemental characteristic and said suspected vehicles sample image, confirms the supplemental characteristic similarity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210045601.5A CN102610102B (en) | 2012-02-27 | 2012-02-27 | Suspect vehicle inspection and control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210045601.5A CN102610102B (en) | 2012-02-27 | 2012-02-27 | Suspect vehicle inspection and control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102610102A true CN102610102A (en) | 2012-07-25 |
| CN102610102B CN102610102B (en) | 2014-05-14 |
Family
ID=46527436
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210045601.5A Expired - Fee Related CN102610102B (en) | 2012-02-27 | 2012-02-27 | Suspect vehicle inspection and control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102610102B (en) |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116986A (en) * | 2013-01-21 | 2013-05-22 | 信帧电子技术（北京）有限公司 | Vehicle identification method |
| CN103136831A (en) * | 2013-02-19 | 2013-06-05 | 江苏开拓信息与系统有限公司 | Multi-device linkage snapshot monitoring system in community and method |
| CN103150898A (en) * | 2013-01-25 | 2013-06-12 | 大唐移动通信设备有限公司 | Method and device for detection of vehicle at night and method and device for tracking of vehicle at night |
| CN103150904A (en) * | 2013-02-05 | 2013-06-12 | 中山大学 | Bayonet vehicle image identification method based on image features |
| CN103208185A (en) * | 2013-03-19 | 2013-07-17 | 东南大学 | Method and system for nighttime vehicle detection on basis of vehicle light identification |
| CN103366566A (en) * | 2013-06-25 | 2013-10-23 | 中国科学院信息工程研究所 | Running track prediction method aiming at specific vehicle potential group |
| CN103678558A (en) * | 2013-12-06 | 2014-03-26 | 中科联合自动化科技无锡有限公司 | Suspicion vehicle search method based on sift characteristic |
| CN103838750A (en) * | 2012-11-23 | 2014-06-04 | 苏州千视通信科技有限公司 | Video investigation technique for obtaining vehicle features based on video retrieval abstract |
| CN103942962A (en) * | 2014-01-02 | 2014-07-23 | 浙江宇视科技有限公司 | License plate shielding violation processing device and method |
| CN104123553A (en) * | 2014-06-16 | 2014-10-29 | 孙晓航 | License plate positioning method and system based on cascading morphological transformation |
| CN104149431A (en) * | 2014-08-08 | 2014-11-19 | 常州山由帝杉防护材料制造有限公司 | Ultraviolet-blocking colored antifogging and heat-insulating window film |
| CN104239881A (en) * | 2013-06-08 | 2014-12-24 | 杭州海康威视数字技术股份有限公司 | Method and system for automatically finding and registering target in surveillance video |
| CN104392232A (en) * | 2014-11-07 | 2015-03-04 | 北京邮电大学 | Method for correcting video metadata in traffic scenes |
| CN104700620A (en) * | 2014-03-28 | 2015-06-10 | 杭州海康威视数字技术股份有限公司 | Traffic checkpoint-based method and device for recognizing fake-licensed vehicles |
| CN105139011A (en) * | 2015-09-07 | 2015-12-09 | 浙江宇视科技有限公司 | Method and apparatus for identifying vehicle based on identification marker image |
| CN105321350A (en) * | 2014-08-05 | 2016-02-10 | 北京大学 | Method and device for detection of fake plate vehicles |
| CN105551261A (en) * | 2016-03-04 | 2016-05-04 | 博康智能网络科技股份有限公司 | False-license-plate vehicle detection method and system |
| CN106128090A (en) * | 2016-06-30 | 2016-11-16 | 北京小米移动软件有限公司 | Identify the method and device of information of vehicles |
| CN106485241A (en) * | 2016-12-07 | 2017-03-08 | 云赛智联股份有限公司 | A kind of data analysis system |
| CN107248294A (en) * | 2017-07-31 | 2017-10-13 | 合肥桥旭科技有限公司 | A kind of multifunctional parking area management control system |
| CN107491753A (en) * | 2017-08-16 | 2017-12-19 | 电子科技大学 | A kind of parking offense detection method based on background modeling |
| CN107506368A (en) * | 2017-07-04 | 2017-12-22 | 青岛海信网络科技股份有限公司 | The determination method and device of one species case suspected vehicles |
| CN108009513A (en) * | 2017-12-14 | 2018-05-08 | 合肥寰景信息技术有限公司 | A kind of image processing method of vehicle dynamic behaviour analysis |
| CN108022428A (en) * | 2016-11-02 | 2018-05-11 | 杭州海康威视系统技术有限公司 | A kind of vehicle identification method and device |
| CN108492580A (en) * | 2018-04-23 | 2018-09-04 | 泰华智慧产业集团股份有限公司 | Judge the method and system of case-involving suspected vehicles |
| CN108572974A (en) * | 2017-03-10 | 2018-09-25 | 杭州海康威视数字技术股份有限公司 | A kind of vehicle pictures search method and device |
| CN109992604A (en) * | 2019-01-09 | 2019-07-09 | 武汉白虹软件科技有限公司 | A kind of land route investigates and seizes information system and investigates and seizes method |
| CN110689725A (en) * | 2019-09-03 | 2020-01-14 | 北京理工大学 | Security robot system for crossing comprehensive inspection and processing method thereof |
| CN111009120A (en) * | 2019-10-22 | 2020-04-14 | 广州阳光耐特电子有限公司 | Vehicle comprehensive application management system |
| CN112733578A (en) * | 2019-10-28 | 2021-04-30 | 普天信息技术有限公司 | Vehicle weight identification method and system |
| CN112750151A (en) * | 2020-12-30 | 2021-05-04 | 成都云盯科技有限公司 | Clothing color matching method, device and equipment based on mathematical statistics |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS61176808A (en) * | 1985-02-01 | 1986-08-08 | Nec Corp | Vehicle identifying device |
| DE4446642A1 (en) * | 1994-12-19 | 1996-06-20 | Teledrive Telematik Im Verkehr | Automatic control appts. for control of vehicles entry in traffic space or authorisation to stop there |
| US20060244830A1 (en) * | 2002-06-04 | 2006-11-02 | Davenport David M | System and method of navigation with captured images |
| CN101504717A (en) * | 2008-07-28 | 2009-08-12 | 上海高德威智能交通系统有限公司 | Characteristic area positioning method, car body color depth and color recognition method |
| CN201317339Y (en) * | 2008-09-01 | 2009-09-30 | 艾伯资讯（深圳）有限公司 | Device for identifying suspected stolen vehicle |
| CN101593418A (en) * | 2009-05-31 | 2009-12-02 | 上海宝康电子控制工程有限公司 | Method for associative search of suspected vehicles |
| CN102034080A (en) * | 2009-09-24 | 2011-04-27 | 北京汉王智通科技有限公司 | Vehicle color identification method and device |
| US20110170763A1 (en) * | 2010-01-09 | 2011-07-14 | Ford Global Technologies, Llc | Rapid color verification system using digital imaging and curve comparison algorithm |
-
2012
- 2012-02-27 CN CN201210045601.5A patent/CN102610102B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS61176808A (en) * | 1985-02-01 | 1986-08-08 | Nec Corp | Vehicle identifying device |
| DE4446642A1 (en) * | 1994-12-19 | 1996-06-20 | Teledrive Telematik Im Verkehr | Automatic control appts. for control of vehicles entry in traffic space or authorisation to stop there |
| US20060244830A1 (en) * | 2002-06-04 | 2006-11-02 | Davenport David M | System and method of navigation with captured images |
| CN101504717A (en) * | 2008-07-28 | 2009-08-12 | 上海高德威智能交通系统有限公司 | Characteristic area positioning method, car body color depth and color recognition method |
| CN201317339Y (en) * | 2008-09-01 | 2009-09-30 | 艾伯资讯（深圳）有限公司 | Device for identifying suspected stolen vehicle |
| CN101593418A (en) * | 2009-05-31 | 2009-12-02 | 上海宝康电子控制工程有限公司 | Method for associative search of suspected vehicles |
| CN102034080A (en) * | 2009-09-24 | 2011-04-27 | 北京汉王智通科技有限公司 | Vehicle color identification method and device |
| US20110170763A1 (en) * | 2010-01-09 | 2011-07-14 | Ford Global Technologies, Llc | Rapid color verification system using digital imaging and curve comparison algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 吴德会等: "基于车牌特征颜色相似度的定位方法", 《公路交通科技》, no. 01, 15 January 2005 (2005-01-15) * |
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103838750A (en) * | 2012-11-23 | 2014-06-04 | 苏州千视通信科技有限公司 | Video investigation technique for obtaining vehicle features based on video retrieval abstract |
| CN103116986B (en) * | 2013-01-21 | 2014-12-10 | 信帧电子技术（北京）有限公司 | Vehicle identification method |
| CN103116986A (en) * | 2013-01-21 | 2013-05-22 | 信帧电子技术（北京）有限公司 | Vehicle identification method |
| CN103150898B (en) * | 2013-01-25 | 2015-07-29 | 大唐移动通信设备有限公司 | A kind of vehicle detection at night method, tracking and device |
| CN103150898A (en) * | 2013-01-25 | 2013-06-12 | 大唐移动通信设备有限公司 | Method and device for detection of vehicle at night and method and device for tracking of vehicle at night |
| CN103150904A (en) * | 2013-02-05 | 2013-06-12 | 中山大学 | Bayonet vehicle image identification method based on image features |
| CN103136831A (en) * | 2013-02-19 | 2013-06-05 | 江苏开拓信息与系统有限公司 | Multi-device linkage snapshot monitoring system in community and method |
| CN103136831B (en) * | 2013-02-19 | 2016-09-07 | 江苏开拓信息与系统有限公司 | The many equipment linkages in a kind of community capture monitoring system and method |
| CN103208185A (en) * | 2013-03-19 | 2013-07-17 | 东南大学 | Method and system for nighttime vehicle detection on basis of vehicle light identification |
| CN104239881B (en) * | 2013-06-08 | 2020-04-24 | 杭州海康威视数字技术股份有限公司 | Method and system for automatically discovering and registering target in monitoring video |
| CN104239881A (en) * | 2013-06-08 | 2014-12-24 | 杭州海康威视数字技术股份有限公司 | Method and system for automatically finding and registering target in surveillance video |
| CN103366566A (en) * | 2013-06-25 | 2013-10-23 | 中国科学院信息工程研究所 | Running track prediction method aiming at specific vehicle potential group |
| CN103678558A (en) * | 2013-12-06 | 2014-03-26 | 中科联合自动化科技无锡有限公司 | Suspicion vehicle search method based on sift characteristic |
| CN103942962A (en) * | 2014-01-02 | 2014-07-23 | 浙江宇视科技有限公司 | License plate shielding violation processing device and method |
| CN104700620A (en) * | 2014-03-28 | 2015-06-10 | 杭州海康威视数字技术股份有限公司 | Traffic checkpoint-based method and device for recognizing fake-licensed vehicles |
| CN104700620B (en) * | 2014-03-28 | 2018-06-22 | 杭州海康威视数字技术股份有限公司 | A kind of fake license plate vehicle recognition method and device based on traffic block port |
| CN104123553B (en) * | 2014-06-16 | 2017-10-20 | 孙晓航 | A kind of license plate locating method and system based on cascade morphological transformation |
| CN104123553A (en) * | 2014-06-16 | 2014-10-29 | 孙晓航 | License plate positioning method and system based on cascading morphological transformation |
| CN105321350A (en) * | 2014-08-05 | 2016-02-10 | 北京大学 | Method and device for detection of fake plate vehicles |
| CN105321350B (en) * | 2014-08-05 | 2018-01-23 | 北京大学 | Fake-licensed car detection method and device |
| CN104149431B (en) * | 2014-08-08 | 2016-04-27 | 常州山由帝杉防护材料制造有限公司 | Intercept ultraviolet color anti-fog thermal-insulation window film |
| CN104149431A (en) * | 2014-08-08 | 2014-11-19 | 常州山由帝杉防护材料制造有限公司 | Ultraviolet-blocking colored antifogging and heat-insulating window film |
| CN104392232A (en) * | 2014-11-07 | 2015-03-04 | 北京邮电大学 | Method for correcting video metadata in traffic scenes |
| CN104392232B (en) * | 2014-11-07 | 2017-09-29 | 北京邮电大学 | The bearing calibration of video metadata under a kind of traffic scene |
| CN105139011B (en) * | 2015-09-07 | 2019-03-08 | 浙江宇视科技有限公司 | A kind of vehicle identification method and device based on mark object image |
| CN105139011A (en) * | 2015-09-07 | 2015-12-09 | 浙江宇视科技有限公司 | Method and apparatus for identifying vehicle based on identification marker image |
| CN105551261A (en) * | 2016-03-04 | 2016-05-04 | 博康智能网络科技股份有限公司 | False-license-plate vehicle detection method and system |
| CN106128090A (en) * | 2016-06-30 | 2016-11-16 | 北京小米移动软件有限公司 | Identify the method and device of information of vehicles |
| CN108022428B (en) * | 2016-11-02 | 2021-05-25 | 杭州海康威视系统技术有限公司 | Vehicle identification method and device |
| CN108022428A (en) * | 2016-11-02 | 2018-05-11 | 杭州海康威视系统技术有限公司 | A kind of vehicle identification method and device |
| CN106485241A (en) * | 2016-12-07 | 2017-03-08 | 云赛智联股份有限公司 | A kind of data analysis system |
| CN108572974A (en) * | 2017-03-10 | 2018-09-25 | 杭州海康威视数字技术股份有限公司 | A kind of vehicle pictures search method and device |
| CN108572974B (en) * | 2017-03-10 | 2021-06-29 | 杭州海康威视数字技术股份有限公司 | Vehicle picture retrieval method and device |
| CN107506368A (en) * | 2017-07-04 | 2017-12-22 | 青岛海信网络科技股份有限公司 | The determination method and device of one species case suspected vehicles |
| CN107248294A (en) * | 2017-07-31 | 2017-10-13 | 合肥桥旭科技有限公司 | A kind of multifunctional parking area management control system |
| CN107491753A (en) * | 2017-08-16 | 2017-12-19 | 电子科技大学 | A kind of parking offense detection method based on background modeling |
| CN108009513A (en) * | 2017-12-14 | 2018-05-08 | 合肥寰景信息技术有限公司 | A kind of image processing method of vehicle dynamic behaviour analysis |
| CN108492580A (en) * | 2018-04-23 | 2018-09-04 | 泰华智慧产业集团股份有限公司 | Judge the method and system of case-involving suspected vehicles |
| CN109992604A (en) * | 2019-01-09 | 2019-07-09 | 武汉白虹软件科技有限公司 | A kind of land route investigates and seizes information system and investigates and seizes method |
| CN109992604B (en) * | 2019-01-09 | 2021-12-03 | 武汉白虹软件科技有限公司 | Land pursuit and seizing informatization system and seizing method |
| CN110689725A (en) * | 2019-09-03 | 2020-01-14 | 北京理工大学 | Security robot system for crossing comprehensive inspection and processing method thereof |
| CN111009120A (en) * | 2019-10-22 | 2020-04-14 | 广州阳光耐特电子有限公司 | Vehicle comprehensive application management system |
| CN112733578A (en) * | 2019-10-28 | 2021-04-30 | 普天信息技术有限公司 | Vehicle weight identification method and system |
| CN112733578B (en) * | 2019-10-28 | 2024-05-24 | 普天信息技术有限公司 | Vehicle re-identification method and system |
| CN112750151A (en) * | 2020-12-30 | 2021-05-04 | 成都云盯科技有限公司 | Clothing color matching method, device and equipment based on mathematical statistics |
| CN112750151B (en) * | 2020-12-30 | 2023-09-26 | 成都云盯科技有限公司 | Clothing color matching method, device and equipment based on mathematical statistics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102610102B (en) | 2014-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102610102B (en) | Suspect vehicle inspection and control method and system | |
| CN101778260B (en) | Method and system for monitoring and managing videos on basis of structured description | |
| CN103069434B (en) | For the method and system of multi-mode video case index | |
| CN105608455B (en) | A kind of license plate sloped correcting method and device | |
| CN110188807A (en) | Tunnel pedestrian target detection method based on cascade super-resolution network and improvement Faster R-CNN | |
| CN102662949B (en) | Method and system for retrieving specified object based on multi-feature fusion | |
| CN110619277A (en) | Multi-community intelligent deployment and control method and system | |
| CN105469105A (en) | Cigarette smoke detection method based on video monitoring | |
| CN109949579A (en) | A kind of illegal automatic auditing method that makes a dash across the red light based on deep learning | |
| TW202013252A (en) | License plate recognition system and license plate recognition method | |
| CN101630361A (en) | Plate number, body color and mark identification-based equipment and plate number, body color and mark identification-based method for identifying fake plate vehicles | |
| KR102035592B1 (en) | A supporting system and method that assist partial inspections of suspicious objects in cctv video streams by using multi-level object recognition technology to reduce workload of human-eye based inspectors | |
| CN106534789A (en) | Integrated intelligent security and protection video monitoring system | |
| CN106331636A (en) | Intelligent video monitoring system and method of oil pipelines based on behavioral event triggering | |
| CN108010242B (en) | Security alarm method, system and storage medium based on video identification | |
| CN104616021A (en) | Method and device for processing traffic sign symbols | |
| CN106878670A (en) | A kind of method for processing video frequency and device | |
| CN103294775A (en) | Police service cloud image recognition vehicle management and control system based on geographic space-time constraint | |
| CN105844245A (en) | Fake face detecting method and system for realizing same | |
| CN106991821A (en) | Vehicles peccancy hand-held mobile terminal data collecting system | |
| CN105095831A (en) | Face recognition method, device and system | |
| CN104463232A (en) | Density crowd counting method based on HOG characteristic and color histogram characteristic | |
| CN110096945B (en) | Indoor monitoring video key frame real-time extraction method based on machine learning | |
| CN111008574A (en) | Key person track analysis method based on body shape recognition technology | |
| CN105657372A (en) | Method and system for realizing intelligent detection and early warning of on-duty guard posts by videos |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20171019 Address after: 200070 room 912, Gonghe Road, 504, Shanghai, Jingan District Patentee after: SHANGHAI QINGTIAN ELECTRONIC TECHNOLOGY Co.,Ltd. Address before: 41, 518034 floor, Press Plaza, Shennan Avenue, Futian District, Guangdong, Shenzhen Patentee before: ANKE SMART CITY TECHNOLOGY (PRC) Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 41, 518034 floor, Press Plaza, Shennan Avenue, Futian District, Guangdong, Shenzhen Patentee after: ANKE ROBOT CO.,LTD. Address before: 41, 518034 floor, Press Plaza, Shennan Avenue, Futian District, Guangdong, Shenzhen Patentee before: ANKE SMART CITY TECHNOLOGY (PRC) Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20171204 Address after: 200070 room 912, Gonghe Road, 504, Shanghai, Jingan District Patentee after: SHANGHAI QINGTIAN ELECTRONIC TECHNOLOGY Co.,Ltd. Address before: 41, 518034 floor, Press Plaza, Shennan Avenue, Futian District, Guangdong, Shenzhen Patentee before: ANKE ROBOT CO.,LTD. |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140514 |