CN105373586A - Vehicle inquiry method and device - Google Patents
Vehicle inquiry method and device Download PDFInfo
- Publication number
- CN105373586A CN105373586A CN201510662465.8A CN201510662465A CN105373586A CN 105373586 A CN105373586 A CN 105373586A CN 201510662465 A CN201510662465 A CN 201510662465A CN 105373586 A CN105373586 A CN 105373586A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- area
- profile
- checked
- characteristic
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a vehicle inquiry method and device. The method comprises the following steps: obtaining a picture of a vehicle, wherein the picture of the vehicle comprises a picture of a vehicle to be inquired and a picture of a vehicle to be compared; extracting the outline of a front windshield in the picture of the vehicle, wherein the outline of the front windshield is formed by a plurality of local outlines positioned in a non-driving area; calculating a characteristic value of each preset characteristic area, wherein the characteristic area comprises a plurality of local outlines positioned in a characteristic area range; and according to the characteristic value of each characteristic area, calculating a similarity value of the vehicle to be inquired and the vehicle to be compared to determine whether the vehicle to be inquired and the vehicle to be compared is the same vehicle. The outline of the driving area in the front windshield is removed to prevent the driving area from affecting an inquiry result, and meanwhile, vehicle inquiry efficiency and accuracy is improved through the fusion of multiple characteristic areas.
Description
Technical field
The application relates to technical field of video monitoring, particularly relates to a kind of vehicle query method and device.
Background technology
Existing vehicle query method normally utilizes the feature of car front windshield to carry out nonproductive poll on car plate or vehicle inquiry basis, such as, can inquire about according to the global feature of car front windshield, or inquire about according to the local feature of car front windshield, wherein, the former is subject to the interference of driver area feature, and the vehicle that the latter has identical local feature is more, therefore, all cannot accomplish quick and precisely to inquire about.
Summary of the invention
In view of this, the application provides a kind of vehicle query method and device.
Particularly, the application is achieved by the following technical solution:
The application provides a kind of vehicle query method, and the method comprises:
Obtain vehicle pictures, described vehicle pictures comprises vehicle pictures to be checked and vehicle pictures to be compared;
Extract car front windshield profile in described vehicle pictures, described car front windshield profile is made up of the multiple local configurations being positioned at non-driver area;
Calculate the eigenwert of each characteristic area preset, in described characteristic area, comprise some local configurations being positioned at this characteristic area scope;
The similar value of vehicle to be checked and vehicle to be compared is calculated, to determine whether described vehicle to be checked and described vehicle to be compared are same vehicle according to the eigenwert of each characteristic area described.
The application provides a kind of vehicle query device, and this device comprises:
Acquiring unit, for obtaining vehicle pictures, described vehicle pictures comprises vehicle pictures to be checked and vehicle pictures to be compared;
Extraction unit, for extracting car front windshield profile in described vehicle pictures, described car front windshield profile is made up of the multiple local configurations being positioned at non-driver area;
Computing unit, for calculating the eigenwert of each default characteristic area, comprises some local configurations being positioned at this characteristic area scope in described characteristic area;
Determining unit, for calculating the similar value of vehicle to be checked and vehicle to be compared according to the eigenwert of each characteristic area described, to determine whether described vehicle to be checked and described vehicle to be compared are same vehicle.
Described as can be seen from above, the application, by rejecting the profile of driver area in car front windshield, avoids driver area on the impact of Query Result, meanwhile, improves vehicle query efficiency and accuracy by the fusion in multiple features region.
Accompanying drawing explanation
Fig. 1 is a kind of vehicle query method flow diagram shown in the application one exemplary embodiment;
Fig. 2 is the initial profile figure of a kind of car front windshield shown in the application one exemplary embodiment;
Fig. 3 is a kind of driver area schematic diagram shown in the application one exemplary embodiment;
Fig. 4 is the car front windshield profile diagram after a kind of shown in the application one exemplary embodiment removes driver area profile;
Fig. 5 is a kind of car front windshield characteristic area schematic diagram shown in the application one exemplary embodiment;
Fig. 6 is characteristic area and local configuration position relationship schematic diagram in a kind of car front windshield shown in the application one exemplary embodiment;
Fig. 7 is the underlying hardware structural representation of a kind of vehicle query device place equipment shown in the application one exemplary embodiment;
Fig. 8 is the structural representation of a kind of vehicle query device shown in the application one exemplary embodiment.
Embodiment
Here will be described exemplary embodiment in detail, its sample table shows in the accompanying drawings.When description below relates to accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawing represents same or analogous key element.Embodiment described in following exemplary embodiment does not represent all embodiments consistent with the application.On the contrary, they only with as in appended claims describe in detail, the example of apparatus and method that some aspects of the application are consistent.
Only for describing the object of specific embodiment at term used in this application, and not intended to be limiting the application." one ", " described " and " being somebody's turn to do " of the singulative used in the application and appended claims is also intended to comprise most form, unless context clearly represents other implications.It is also understood that term "and/or" used herein refer to and comprise one or more project of listing be associated any or all may combine.
Term first, second, third, etc. may be adopted although should be appreciated that to describe various information in the application, these information should not be limited to these terms.These terms are only used for the information of same type to be distinguished from each other out.Such as, when not departing from the application's scope, the first information also can be called as the second information, and similarly, the second information also can be called as the first information.Depend on linguistic context, word as used in this " if " can be construed as into " ... time " or " when ... time " or " in response to determining ".
Current vehicle query technology mainly finds vehicle to be checked according to car plate or vehicle from the vehicle through each bayonet socket.But, when vehicle to be checked is fake license plate vehicle, then cannot be inquired about by car plate; Now can vehicle be utilized further to inquire about, but the vehicle fleet size of same model be huge, vehicle to be checked cannot be found fast.
For the problems referred to above, prior art generally utilizes some features of car front windshield to carry out nonproductive poll, mainly comprises following two kinds of methods:
Method one, extract the global feature of car front windshield, treat enquiring vehicle to compare with the feature of the car front windshield of each bayonet vehicle collected, such as, but this nonproductive poll method is subject to the impact of driver area feature, there is people/unmanned in copilot region, the car front windshield feature extracted is different, therefore, causes Query Result inaccurate.
Method two, extracts the local feature of car front windshield, and such as, region is pasted in car test, and pendant region, adopts the feature of these regional areas to compare.But the vehicle with similar annual check paste region or pendant region is also a lot, is still unfavorable for fast query.
For the problems referred to above, the embodiment of the present application proposes a kind of vehicle query method, and the method, by rejecting the profile of driver area in car front windshield, promotes the accuracy of Query Result, meanwhile, improves vehicle query efficiency by the fusion of multiple characteristic area.
See Fig. 1, be an embodiment process flow diagram of the application's vehicle query method, this embodiment is described vehicle query process.
Step 101, obtain vehicle pictures, described vehicle pictures comprises vehicle pictures to be checked and vehicle pictures to be compared.
Wherein, vehicle pictures to be checked is the picture comprising vehicle to be checked; Vehicle pictures to be compared is comprise the picture for the vehicle of comparing with vehicle to be checked, determines that whether vehicle to be compared is same vehicle with vehicle to be checked by comparison.Such as, when inquiring about vehicle, first a picture (vehicle pictures to be checked) comprising vehicle will be had, then the vehicle pictures (vehicle pictures to be compared) gathered by each bayonet socket is compared with vehicle picture respectively, to confirm by the vehicle of bayonet socket whether for vehicle, thus determine the whereabouts of vehicle.
Step 102, extracts car front windshield profile in described vehicle pictures, and described car front windshield profile is made up of the multiple local configurations being positioned at non-driver area.
Extract car front windshield profile to each vehicle pictures that step 101 obtains, concrete leaching process is as follows:
Car front windshield image is partitioned into from vehicle pictures.The embodiment of the present application is not construed as limiting concrete cutting procedure, and prior art can be adopted to realize, and such as, can adopt the car front windshield in adaboost algorithm identification vehicle pictures, thus be partitioned into car front windshield image.
Contours extract is carried out to the car front windshield image be partitioned into.The embodiment of the present application does not limit concrete leaching process, can adopt existing techniques in realizing.Such as, first to the smoothing process of car front windshield image, then can carry out closing operation of mathematical morphology, finally generate gray level image, from gray level image, extract profile.Some less profiles can be filtered out by this contour extraction method, obtain the initial profile figure of car front windshield as shown in Figure 2.
After the extraction completing car front windshield initial profile, from the multiple local configurations obtained, remove the local configuration being positioned at driver area, detailed process is:
First, the driver area scope preset is obtained.The embodiment of the present application in order to avoid main driving region and copilot region on the impact of car front windshield contours extract (such as, copilot region is with/without the personnel of riding, the extraction result of its car front windshield profile is different) pre-set two driver area scopes, i.e. main driving regional extent and copilot regional extent.Suppose, the wide of car front windshield is W, height is H, setting is by quadrilateral partition driver area scope, then four apex coordinates in main driving region can be A (0.6*W, 0.15*H), B (0.58*W, 0.9*H), C (0.88*W, 0.9*H), D (0.8*W, 0.15*H); Four apex coordinates in copilot region can be E (0.28*W, 0.25*H), F (0.2*W, 0.7*H), G (0.4*W, 0.7*H), M (0.35*W, 0.25*H), see Fig. 3, it is the driver area schematic diagram shown in the application one exemplary embodiment.In actual applications, driver area scope can be determined according to the priori of accumulation.
After determining driver area scope, judge whether the central point of the aforementioned local configuration obtained is positioned at driver area scope.When the central point of local configuration is positioned at default driver area scope, remove this local configuration.
Using the residue local configuration after above-mentioned process as car front windshield profile.See Fig. 4, for removing the car front windshield profile diagram after being positioned at driver area profile.
Step 103, calculates the eigenwert of each characteristic area preset, comprises some local configurations being positioned at this characteristic area scope in described characteristic area.
The embodiment of the present application plans the characteristic area of car front windshield in advance according to some prioris of car front windshield, see Fig. 5, is the car front windshield characteristic area schematic diagram shown in the application one exemplary embodiment.Wherein, characteristic area 1 and characteristic area 2 are annual check paste region; Characteristic area 3 is pendant region; Characteristic area 4 is pendulum decorations region.Also can be found out by Fig. 5, the embodiment of the present application not using driver area as characteristic area.
This step calculates the eigenwert of each characteristic area, and wherein, each characteristic area comprises some local configurations extracted by step 102.See Fig. 6, it is the position relationship schematic diagram of characteristic area and local configuration in the car front windshield shown in the application one exemplary embodiment.As seen from Figure 6, in the characteristic area 1 of Current vehicle, there are 3 annual check pastes, without annual check paste in characteristic area 2, in characteristic area 3, have pendant, without pendulum decorations in characteristic area 4.Due to different vehicle annual check paste paste position and whether put suspension member, pendulum decorations etc. and can there are differences, therefore, the eigenwert of the same characteristic area of different vehicle may be different.In one preferably account form, by calculating the eigenwert of cryptographic hash as character pair region of characteristic area.
Step 104, calculates the similarity of vehicle to be checked and vehicle to be compared according to the eigenwert of each characteristic area described, to determine whether described vehicle to be checked and described vehicle to be compared are same vehicle.
The embodiment of the present application treats the process that enquiring vehicle picture and vehicle pictures to be compared all perform step 101 ~ step 103, obtains the eigenwert of each characteristic area in vehicle pictures to be checked respectively, and the eigenwert of each characteristic area in vehicle pictures to be compared.
After the eigenwert getting each characteristic area, calculate the similarity of vehicle to be checked and vehicle to be compared, be specially:
Calculate the profile proportion of each characteristic area of vehicle to be checked, this profile proportion is the number percent that the local configuration area in current signature region accounts for the local configuration area summation in all characteristic areas of vehicle to be checked, represents by following formula:
Wherein, S
iit is the local configuration area of i-th characteristic area;
for the contour area summation of all characteristic areas (n characteristic area) of vehicle to be checked; A
ibe the profile proportion of i-th characteristic area.
After the profile proportion of each characteristic area obtaining vehicle to be checked, get it right according to this profile picnometer and answer the feature proportion of characteristic area, wherein, this feature proportion is that the profile proportion of characteristic area is multiplied by default proportion coefficients, represents by following formula:
T
i=A
i× R
iformula (2)
Wherein, A
ibe the profile proportion of i-th characteristic area; R
iit is the proportion coefficients of i-th characteristic area; T
ibe the feature proportion of i-th characteristic area.Wherein, proportion coefficients R
irelevant with the stability of characteristic area, such as, the aforementioned characteristic area 1 mentioned and characteristic area 2 are annual check paste region, because vehicle all will paste annual check paste usually, therefore, these two regions are relatively stable, suitably can increase the proportion coefficients in above-mentioned two regions when default proportion coefficients; On the contrary, characteristic area 3 (pendant region) and characteristic area 4 (pendulum decorations region) are relatively at random, relatively unstable, therefore, and predeterminable less proportion coefficients.Meanwhile, as can be seen from formula (2), at R
iwhen determining, feature proportion T
iwith profile proportion A
ibe directly proportional, namely in characteristic area, local configuration information is abundanter, then this characteristic area proportion in follow-up Similarity Measure is larger, to make final Query Result more rationally accurately.
In addition, the embodiment of the present application calculates the characteristic distance in character pair region between vehicle to be checked and vehicle to be compared according to the eigenwert of each characteristic area in vehicle to be checked and vehicle to be compared.In one preferably embodiment, by calculating the Hamming distance of character pair regional characteristic value as characteristic distance.Such as, suppose that the eigenwert of characteristic area is cryptographic hash, and this cryptographic hash adopts 64 bits to represent, then by the Hamming distance of the 64 bits calculating characteristic areas in character pair region in vehicle to be checked and vehicle to be compared.This Hamming distance distance values is larger, represents that the difference between character pair region is larger.
After the feature proportion obtaining each characteristic area and characteristic distance, the cumulative sum asking for the feature proportion of each characteristic area and the product of characteristic distance, as the similar value of vehicle to be checked and vehicle to be compared, represents by following formula:
Wherein, T
ibe the feature proportion of i-th characteristic area; F
iit is the characteristic distance of i-th characteristic area; G is the similar value between vehicle to be checked and vehicle to be compared.Visible, at T
iwhen determining, F
iless, then G is less, illustrates that vehicle to be checked is more similar with vehicle to be compared.
Need supplementary notes a bit, work as T
iwhen=0, i.e. A
i=0, illustrate in i-th characteristic area of vehicle to be checked do not have local configuration, below now needing point, two kinds of situations process:
Situation one, does not have local configuration in the i-th characteristic area of vehicle to be compared yet, then the characteristic distance F of i-th characteristic area
ibe 0, represent that vehicle to be checked is identical with the feature of i-th characteristic area in vehicle to be compared, there is no difference;
Situation two, has local configuration in i-th characteristic area of vehicle to be compared, then the characteristic distance F of i-th characteristic area
iget maximal value, suppose, F
ispan be 0 ~ 64, then F
i=64, represent the widely different of i-th characteristic area.But, if according to calculating T
i=0, then the difference of i-th characteristic area is left in the basket in final Similarity Measure, and this is obviously irrational, and therefore, the embodiment of the present application carries out special processing to this kind of situation, gets T
i=R
i, farthest embody the feature difference of i-th characteristic area.
After calculated the similar value between vehicle to be checked and each vehicle to be compared by step 101 ~ step 104, the minimum vehicle to be compared of similar value is selected to be vehicle to be checked.
As can be seen from foregoing description, the embodiment of the present application, by rejecting the profile of driver area in car front windshield, avoids driver area on the impact of Query Result, meanwhile, improves vehicle query efficiency and accuracy by the fusion in multiple features region.
Corresponding with the embodiment of aforementioned vehicle querying method, present invention also provides the embodiment of vehicle query device.
The embodiment of the application's vehicle query device can be applied on an electronic device.Device embodiment can pass through software simulating, also can be realized by the mode of hardware or software and hardware combining.For software simulating, as the device on a logical meaning, be that computer program instructions corresponding in the processor run memory by its place equipment is formed.Say from hardware view, as shown in Figure 7, for a kind of hardware structure diagram of the application's vehicle query device place equipment, except the processor shown in Fig. 7, network interface and storer, in embodiment, the equipment at device place is usually according to the actual functional capability of this equipment, other hardware can also be comprised, this is repeated no more.
Please refer to Fig. 8, is the structural representation of the vehicle query device in the application's embodiment.This vehicle query device comprises acquiring unit 801, extraction unit 802, computing unit 803 and determining unit 804, wherein:
Acquiring unit 801, for obtaining vehicle pictures, described vehicle pictures comprises vehicle pictures to be checked and vehicle pictures to be compared;
Extraction unit 802, for extracting car front windshield profile in described vehicle pictures, described car front windshield profile is made up of the multiple local configurations being positioned at non-driver area;
Computing unit 803, for calculating the eigenwert of each default characteristic area, comprises some local configurations being positioned at this characteristic area scope in described characteristic area;
Determining unit 804, for calculating the similar value of vehicle to be checked and vehicle to be compared according to the eigenwert of each characteristic area described, to determine whether described vehicle to be checked and described vehicle to be compared are same vehicle.
Further, described extraction unit 802, comprising:
Image segmentation module, for being partitioned into car front windshield image from described vehicle pictures;
Profile extraction module, for carrying out contours extract to described car front windshield image, obtains multiple local configuration;
Profile removes module, for removing the local configuration being positioned at driver area from described multiple local configuration;
Profile determination module, for using remaining local configuration as described car front windshield profile.
Further,
Described profile removes module, specifically for obtaining default driver area scope; Judge whether the central point of described local configuration is positioned at described default driver area scope; When the central point of described local configuration is positioned at described default driver area scope, remove described local configuration.
Further,
Described determining unit 804, specifically for calculating the profile proportion of each characteristic area of described vehicle to be checked, described profile proportion is the number percent that the local configuration area in current signature region accounts for the local configuration area summation in all characteristic areas of vehicle to be checked; Get it right according to the profile picnometer of each characteristic area described and answer the feature proportion of characteristic area, described feature proportion is that the profile proportion of characteristic area is multiplied by default proportion coefficients; The characteristic distance in character pair region between described vehicle to be checked and described vehicle to be compared is calculated according to the eigenwert of each characteristic area in described vehicle to be checked and described vehicle to be compared; The cumulative sum asking for the feature proportion of each characteristic area and the product of characteristic distance is as the similar value of described vehicle to be checked and described vehicle to be compared.
In said apparatus, the implementation procedure of the function and efficacy of unit specifically refers to the implementation procedure of corresponding step in said method, does not repeat them here.
For device embodiment, because it corresponds essentially to embodiment of the method, so relevant part illustrates see the part of embodiment of the method.Device embodiment described above is only schematic, the wherein said unit illustrated as separating component or can may not be and physically separates, parts as unit display can be or may not be physical location, namely can be positioned at a place, or also can be distributed in multiple network element.Some or all of module wherein can be selected according to the actual needs to realize the object of the application's scheme.Those of ordinary skill in the art, when not paying creative work, are namely appreciated that and implement.
The foregoing is only the preferred embodiment of the application, not in order to limit the application, within all spirit in the application and principle, any amendment made, equivalent replacements, improvement etc., all should be included within scope that the application protects.
Claims (8)
1. a vehicle query method, is characterized in that, the method comprises:
Obtain vehicle pictures, described vehicle pictures comprises vehicle pictures to be checked and vehicle pictures to be compared;
Extract car front windshield profile in described vehicle pictures, described car front windshield profile is made up of the multiple local configurations being positioned at non-driver area;
Calculate the eigenwert of each characteristic area preset, in described characteristic area, comprise some local configurations being positioned at this characteristic area scope;
The similar value of vehicle to be checked and vehicle to be compared is calculated, to determine whether described vehicle to be checked and described vehicle to be compared are same vehicle according to the eigenwert of each characteristic area described.
2. the method for claim 1, is characterized in that, car front windshield profile in the described vehicle pictures of described extraction, comprising:
Car front windshield image is partitioned into from described vehicle pictures;
Contours extract is carried out to described car front windshield image, obtains multiple local configuration;
The local configuration being positioned at driver area is removed from described multiple local configuration;
Using remaining local configuration as described car front windshield profile.
3. method as claimed in claim 2, is characterized in that, describedly from described multiple local configuration, removes the local configuration being positioned at driver area, comprising:
Obtain the driver area scope preset;
Judge whether the central point of described local configuration is positioned at described default driver area scope;
When the central point of described local configuration is positioned at described default driver area scope, remove described local configuration.
4. the method for claim 1, is characterized in that, described in described basis, the eigenwert of each characteristic area calculates the similar value of vehicle to be checked and vehicle to be compared, comprising:
Calculate the profile proportion of each characteristic area of described vehicle to be checked, described profile proportion is the number percent that the local configuration area in current signature region accounts for the local configuration area summation in all characteristic areas of vehicle to be checked;
Get it right according to the profile picnometer of each characteristic area described and answer the feature proportion of characteristic area, described feature proportion is that the profile proportion of characteristic area is multiplied by default proportion coefficients;
The characteristic distance in character pair region between described vehicle to be checked and described vehicle to be compared is calculated according to the eigenwert of each characteristic area in described vehicle to be checked and described vehicle to be compared;
The cumulative sum asking for the feature proportion of each characteristic area and the product of characteristic distance is as the similar value of described vehicle to be checked and described vehicle to be compared.
5. a vehicle query device, is characterized in that, this device comprises:
Acquiring unit, for obtaining vehicle pictures, described vehicle pictures comprises vehicle pictures to be checked and vehicle pictures to be compared;
Extraction unit, for extracting car front windshield profile in described vehicle pictures, described car front windshield profile is made up of the multiple local configurations being positioned at non-driver area;
Computing unit, for calculating the eigenwert of each default characteristic area, comprises some local configurations being positioned at this characteristic area scope in described characteristic area;
Determining unit, for calculating the similar value of vehicle to be checked and vehicle to be compared according to the eigenwert of each characteristic area described, to determine whether described vehicle to be checked and described vehicle to be compared are same vehicle.
6. device as claimed in claim 5, it is characterized in that, described extraction unit, comprising:
Image segmentation module, for being partitioned into car front windshield image from described vehicle pictures;
Profile extraction module, for carrying out contours extract to described car front windshield image, obtains multiple local configuration;
Profile removes module, for removing the local configuration being positioned at driver area from described multiple local configuration;
Profile determination module, for using remaining local configuration as described car front windshield profile.
7. device as claimed in claim 6, is characterized in that:
Described profile removes module, specifically for obtaining default driver area scope; Judge whether the central point of described local configuration is positioned at described default driver area scope; When the central point of described local configuration is positioned at described default driver area scope, remove described local configuration.
8. device as claimed in claim 5, is characterized in that:
Described determining unit, specifically for calculating the profile proportion of each characteristic area of described vehicle to be checked, described profile proportion is the number percent that the local configuration area in current signature region accounts for the local configuration area summation in all characteristic areas of vehicle to be checked; Get it right according to the profile picnometer of each characteristic area described and answer the feature proportion of characteristic area, described feature proportion is that the profile proportion of characteristic area is multiplied by default proportion coefficients; The characteristic distance in character pair region between described vehicle to be checked and described vehicle to be compared is calculated according to the eigenwert of each characteristic area in described vehicle to be checked and described vehicle to be compared; The cumulative sum asking for the feature proportion of each characteristic area and the product of characteristic distance is as the similar value of described vehicle to be checked and described vehicle to be compared.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510662465.8A CN105373586A (en) | 2015-10-14 | 2015-10-14 | Vehicle inquiry method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510662465.8A CN105373586A (en) | 2015-10-14 | 2015-10-14 | Vehicle inquiry method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105373586A true CN105373586A (en) | 2016-03-02 |
Family
ID=55375786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510662465.8A Pending CN105373586A (en) | 2015-10-14 | 2015-10-14 | Vehicle inquiry method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105373586A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109960742A (en) * | 2019-02-18 | 2019-07-02 | 苏州科达科技股份有限公司 | The searching method and device of local message |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103530366A (en) * | 2013-10-12 | 2014-01-22 | 湖北微模式科技发展有限公司 | Vehicle searching method and system based on user-defined features |
| CN104881661A (en) * | 2015-06-23 | 2015-09-02 | 河北工业大学 | Vehicle detection method based on structure similarity |
| CN104966066A (en) * | 2015-06-26 | 2015-10-07 | 武汉大学 | Traffic block port monitoring oriented in-car human face detection method and system |
-
2015
- 2015-10-14 CN CN201510662465.8A patent/CN105373586A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103530366A (en) * | 2013-10-12 | 2014-01-22 | 湖北微模式科技发展有限公司 | Vehicle searching method and system based on user-defined features |
| CN104881661A (en) * | 2015-06-23 | 2015-09-02 | 河北工业大学 | Vehicle detection method based on structure similarity |
| CN104966066A (en) * | 2015-06-26 | 2015-10-07 | 武汉大学 | Traffic block port monitoring oriented in-car human face detection method and system |
Non-Patent Citations (1)
| Title |
|---|
| 梅蓉: "论视频监控图像分析", 《山东警察学院学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109960742A (en) * | 2019-02-18 | 2019-07-02 | 苏州科达科技股份有限公司 | The searching method and device of local message |
| CN109960742B (en) * | 2019-02-18 | 2021-11-05 | 苏州科达科技股份有限公司 | Local information searching method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111460312A (en) | Method and device for identifying empty-shell enterprise and computer equipment | |
| CN113205037B (en) | Event detection method, event detection device, electronic equipment and readable storage medium | |
| CN109360421B (en) | Traffic information prediction method and device based on machine learning and electronic terminal | |
| CN112036389B (en) | Vehicle three-dimensional information detection method, device and equipment and readable storage medium | |
| CN113378760A (en) | Training target detection model and method and device for detecting target | |
| CN113377888A (en) | Training target detection model and method for detecting target | |
| CN107392139A (en) | A kind of method for detecting lane lines and terminal device based on Hough transformation | |
| EP3907659A2 (en) | Perception data detection method and apparatus | |
| CN112991374B (en) | Canny algorithm-based edge enhancement method, canny algorithm-based edge enhancement device, canny algorithm-based edge enhancement equipment and storage medium | |
| CN113392794B (en) | Vehicle line crossing identification method and device, electronic equipment and storage medium | |
| CN112763993A (en) | Method and device for calibrating radar parameters, electronic equipment and storage medium | |
| CN113945937A (en) | Precision detection method, device and storage medium | |
| CN113762397B (en) | Method, equipment, medium and product for training detection model and updating high-precision map | |
| CN113989300A (en) | Lane line segmentation method and device, electronic equipment and storage medium | |
| CN111860512B (en) | Vehicle identification method, device, electronic equipment and computer readable storage medium | |
| CN105373586A (en) | Vehicle inquiry method and device | |
| CN113191279A (en) | Data annotation method, device, equipment, storage medium and computer program product | |
| CN111427037A (en) | Obstacle detection method and device, electronic equipment and vehicle-end equipment | |
| CN113642533B (en) | Lane level positioning method and electronic equipment | |
| CN116168366B (en) | Point cloud data generation method, model training method, target detection method and device | |
| CN111044035B (en) | Vehicle positioning method and device | |
| CN114565681B (en) | Camera calibration method, device, equipment, medium and product | |
| CN114529768B (en) | Method, device, electronic equipment and storage medium for determining object category | |
| KR20220119167A (en) | Method and apparatus for identifying vehicle lane departure, electronic device, and storage medium | |
| CN118035788A (en) | Target vehicle relative position classification method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160302 |
|
| RJ01 | Rejection of invention patent application after publication |