CN106651969A - Color identification method and apparatus for vehicle - Google Patents
Color identification method and apparatus for vehicle Download PDFInfo
- Publication number
- CN106651969A CN106651969A CN201611238820.XA CN201611238820A CN106651969A CN 106651969 A CN106651969 A CN 106651969A CN 201611238820 A CN201611238820 A CN 201611238820A CN 106651969 A CN106651969 A CN 106651969A
- Authority
- CN
- China
- Prior art keywords
- headstock
- image
- vehicle
- color
- yuyv
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
Embodiments of the invention disclose a color identification method and apparatus for a vehicle. The method comprises the steps of obtaining a vehicle image of the vehicle; identifying license plate information in the vehicle image, wherein the license plate information comprises the length, width and position of a license plate; determining a vehicle head region and a vehicle head image of the vehicle head region according to the license plate information; converting the vehicle head image into an image in a YUV format to obtain a vehicle head YUV image; extracting Y component data, U component data and V component data from the vehicle head YUV image, and performing recombination to obtain a vehicle head YUYV image with a preset size; inputting the vehicle head YUYV image to a convolutional neural network model trained based on the YUYV image; and determining a color of a vehicle head of the vehicle according to an output result of the convolutional neural network model. An embodiment of the invention provides a deep learning-based vehicle color identification method.
Description
Technical field
The present invention relates to image processing field, more particularly to a kind of color identification method and device for vehicle.
Background technology
In the prior art, at present for the color component point that the colour recognition of vehicle is mainly counted by statistical method
Cloth carries out contrast identification, and the advantage of this method is that recognition speed is fast, has the disadvantage that discrimination is not high, easily affected by environment, one
As for pre-identification or rough sort.Still an alternative is that by the way of traditional pattern learning, by the face of training sample
Color characteristic model is classified to car color, and the training effectiveness of this method is not high.
The content of the invention
The embodiment of the present application provides a kind of color identification method and device for vehicle, there is provided one kind is based on depth
The vehicle color identification method of habit.
In view of this, a first aspect of the present invention provides a kind of color identification method for vehicle, including：
Obtain the vehicle image of vehicle；
License board information in identification vehicle image, license board information includes length, width and the position of car plate；
The headstock image in headstock region and headstock region is determined according to license board information；
Headstock image is converted into the image of yuv format, headstock YUV image is obtained；
Y-component data, U component datas, V component data are extracted from headstock YUV image and is reconfigured and preset
The headstock YUYV images of size；
Headstock YUYV images are input into the convolutional neural networks model based on the training of YUYV images；
The color of the headstock of vehicle is determined according to the output result of convolutional neural networks model.
With reference to the embodiment of the present invention in a first aspect, the first embodiment of the first aspect in the embodiment of the present invention
In, determine that headstock region and the headstock image in headstock region include according to license board information：
The length and width of car plate are obtained according to license board information；
Using the length value of car plate according to the first default ratio increase and as the length value in headstock region；
Using the width value of car plate according to the second default ratio increase and as the width value in headstock region；
Determine headstock region and obtain the headstock image in headstock region.
With reference to the embodiment of the present invention in a first aspect, in the first embodiment of first aspect any one, in the present invention
In second embodiment of the first aspect of embodiment, Y-component data, U component datas, V are extracted from headstock YUV image
Component data and reconfiguring obtains the headstock YUYV images of default size to be included：
Y-component data, U component datas, V component data are extracted from headstock YUV image according to pre-conditioned；
Headstock YUYV figures are obtained according to Y-component data, U component datas, Y-component data, the sequential combination of V component data
Picture.
With reference to the embodiment of the present invention in a first aspect, the first embodiment of first aspect is into second embodiment
Any one, in the third embodiment of the first aspect of the embodiment of the present invention, headstock YUYV images is input into being based on
Also include before the convolutional neural networks model of YUYV images training：
Training convolutional neural networks model, including：
Obtain the color YUYV image that solid color image more than a kind of color is converted into, the size of color YUYV image
It is equal in magnitude with headstock YUYV images；
Using color YUYV image training convolutional neural networks model.
With reference to the embodiment of the present invention in a first aspect, the first embodiment of first aspect is into the third embodiment
Any one, in the 4th kind of embodiment of the first aspect of the embodiment of the present invention, according to the output of convolutional neural networks model
As a result after determining the color of headstock of vehicle, also include：
The color of vehicle is determined according to the color of the headstock of vehicle.
A second aspect of the present invention provides a kind of device, including：
Acquisition module, for obtaining the vehicle image of vehicle；
Identification module, for recognizing vehicle image in license board information, the length of license board information including car plate, width and
Position；
First determining module, for determining the headstock image in headstock region and headstock region according to license board information；
Modular converter, for headstock image to be converted into the image of yuv format, obtains headstock YUV image；
Abstraction module, for extracting Y-component data, U component datas, V component data and again from headstock YUV image
Combination obtains the headstock YUYV images of default size；
Input module, for headstock YUYV images to be input into the convolutional neural networks model based on the training of YUYV images；
Second determining module, for determining the color of the headstock of vehicle according to the output result of convolutional neural networks model.
With reference to the second aspect of the embodiment of the present invention, in the first embodiment of the second aspect of the embodiment of the present invention
In, the first determining module includes：
First acquisition unit, for obtaining the length and width of car plate according to license board information；
First increase unit, for the length value of car plate to be increased and as the length in headstock region according to the first default ratio
Angle value；
Second increase unit, for the width value of car plate to be increased and as the width in headstock region according to the second default ratio
Angle value；
Determining unit, for determining headstock region and obtaining the headstock image in headstock region.
With reference to the second aspect of the embodiment of the present invention, in the first embodiment of second aspect any one, in the present invention
In second embodiment of the second aspect of embodiment, abstraction module includes：
Extracting unit, for extracting Y-component data, U component datas, V point according to pre-conditioned from headstock YUV image
Amount data；
Assembled unit, for obtaining according to the sequential combination of Y-component data, U component datas, Y-component data, V component data
To headstock YUYV images.
With reference to the second aspect of the embodiment of the present invention, the first embodiment of second aspect is into second embodiment
Any one, in the third embodiment of the second aspect of the embodiment of the present invention, also includes：
Training module, for training convolutional neural networks model, including：
Second acquisition unit, for obtaining the color YUYV image that solid color image more than a kind of color is converted into,
The size of color YUYV image is equal in magnitude with headstock YUYV images；
Training unit, for using color YUYV image training convolutional neural networks model.
With reference to the second aspect of the embodiment of the present invention, the first embodiment of second aspect is into the third embodiment
Any one, in the 4th kind of embodiment of the second aspect of the embodiment of the present invention, also includes：
3rd determining module, for determining the color of vehicle according to the color of the headstock of vehicle.
As can be seen from the above technical solutions, the embodiment of the present invention has advantages below：
The embodiment of the present invention provides a kind of color identification method and device for vehicle, there is provided one kind is based on deep learning
Vehicle color identification method, using headstock colouring information replace vehicle body local color information, reduce to vehicle body local color
The requirement of information zone location to be identified, enhances robustness of the headstock colour recognition to local illumination.Meanwhile, for whole
Headstock carries out the time-consuming problem of colour recognition, and the method for turning YUV gray level images using coloured image constructs the color ladder of YUYV
Degree feature reduces data dimension is used for sample training and identification.
Description of the drawings
Technical scheme in order to be illustrated more clearly that the embodiment of the present invention, below by to be used needed for embodiment
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are only embodiments of the invention, general for this area
For logical technical staff, on the premise of not paying creative work, can be with according to the other accompanying drawings of accompanying drawing acquisition for providing.
Fig. 1 is a kind of one embodiment schematic diagram of the color identification method for vehicle in the embodiment of the present invention；
Fig. 2 is a kind of headstock area schematic of the color identification method for vehicle in the embodiment of the present invention；
Fig. 3 is a kind of view data schematic diagram of the color identification method for vehicle in the embodiment of the present invention；
Fig. 4 is a kind of one embodiment schematic diagram of device in the embodiment of the present invention.
Specific embodiment
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, is clearly and completely described to the technical scheme in the embodiment of the present invention, it is clear that described embodiment is only
The embodiment of a part of the invention, rather than the embodiment of whole.Based on the embodiment in the present invention, ordinary skill people
The every other embodiment that member is obtained under the premise of creative work is not made, should all belong to the model of present invention protection
Enclose.
The (if present)s such as term " first ", " second " in description and claims of this specification and above-mentioned accompanying drawing
It is the object for distinguishing similar, without being used to describe specific order or precedence.It should be appreciated that the number for so using
According to can exchange in the appropriate case, so as to the embodiments described herein can with except the content for illustrating here or describing with
Outer order is implemented.Additionally, term " comprising " and " having " and their any deformation, it is intended that cover non-exclusive bag
Contain, for example, process, method, system, product or the equipment for containing series of steps or unit is not necessarily limited to what is clearly listed
Those steps or unit, but may include clearly not listing or intrinsic for these processes, method, product or equipment
Other steps or unit.
A kind of a kind of color identification method for vehicle of the embodiment of the present invention, there is provided vehicle color based on deep learning
Recognition methods.Fig. 1 is referred to, Fig. 1 is one embodiment schematic diagram of the embodiment of the present invention.
Step 101, the vehicle image for obtaining vehicle；
The image of vehicle is obtained, the image that vehicle frontal contains car plate is mainly obtained.
License board information in step 102, identification vehicle image；
After the vehicle image of vehicle is got, the car plate in vehicle image can be positioned, according to License Plate
As a result size, long width values and the position of car plate are obtained, license board information is obtained.
Step 103, the headstock image that headstock region and headstock region are determined according to license board information；
After license board information is obtained, the headstock region of vehicle can be determined according to predetermined method.In actual applications, may be used
It is enlarged with the long width values according to car plate and is obtained based on the headstock region of the long width values of car plate.Fig. 2 is referred to herein, for example, from
Up and down four direction extends out acquisition headstock region according to the length and width information of car plate in varing proportions.Can be by the car plate left side
Boundary extends out to the left the left margin that 1 car plate width obtains headstock region；1.5 car plate width are extended out to the right with car plate right margin to obtain
To the right margin in headstock region；The coboundary that 4 car plate width obtain headstock region is extended out upwards with car plate coboundary；With car plate
Lower boundary extends out downwards the lower boundary that 2 car plate width obtain headstock region.So extend out respectively from four direction and obtain headstock
Region, then obtains the headstock image in the headstock region of correlation according to headstock region.
Step 104, the image that headstock image is converted into yuv format, obtain headstock YUV image；
Change the colored headstock image dress for getting the image of yuv format into, previous half data is Y point in YUV image
Amount data, i.e. greyscale image data, later half data storage is UV data, i.e. colour difference information image.
Step 105, extract from headstock YUV image Y-component data, U component datas, V component data and reconfigure
Obtain the headstock YUYV images of default size；
Y-component data, U component datas, V component number will be gone out according to set rule extraction in the headstock YUV image for obtaining
According to then reconfiguring to data and obtain headstock YUYV images.Fig. 3 is referred to herein, and concrete implementation mode can be as follows：Will
The data of headstock YUV image are marked according to data position sequence, and the first row first row of Y-component data is labeled as Y11, the first row
Secondary series is designated as Y12, and the second row first row is designated as Y21.Y, U, V component data are all marked by that analogy.Wherein Y-component data
Each data has corresponding mark, and U, V component data correspondence Y data are marked, and U component datas only have in the row of odd number
Exist, such as U11, U13, U15 etc.；V component data only have in the row of even number and exist, such as V12, V14, V16 etc..From headstock
The first row first row data bit Y11 in YUV image starts to extract, and then extracts and Y11 coordinate identical U component data U11,
The Y12 adjacent with Y11 and corresponding V component data V12, the new data combination of this four compositions one are extracted again
Y11U11Y12V12.Y11U11Y12V12 is the data of the beginning of the first row of headstock YUYV images, afterwards again in headstock YUV figures
Start to extract in the Y-component data of picture, extract and be separated by the Y15 and adjacent Y16 of two row with Y12, then it is corresponding extract U15 with
V16.So decimation rule is to be combined into one group of number after the Y-component data and corresponding U, V component data for extracting adjacent two row
According to, two row are separated by afterwards and extract adjacent two group Y-component data and corresponding U, V component data again, so constitute first
Driving head YUYV images.For the data of the headstock YUYV images of the second row, from the Y for being separated by a line with the first row Y-component data
Component data starts to extract, i.e., the first row headstock YUYV images start to extract from Y11, and the second driving head YUYV images are opened from Y31
Begin to extract, other decimation rules are as hereinbefore.The data of whole headstock YUYV images are finally obtained, as shown in Figure 3.Extract
Data stop after the headstock YUYV images for obtaining default size, for example, can be the headstock that 128 pixels are multiplied by 32 pixels
YUYV images.
Step 106, by headstock YUYV images be input into based on YUYV images training convolutional neural networks model；
After obtaining headstock YUYV images, headstock YUYV images are input into trained convolutional neural networks model.It is right
In the training of convolutional neural networks model, concrete grammar is as follows：Obtain multiple color plurality of pictures, for example can obtain it is black,
128 pixels of the color such as in vain, silver-colored, grey, red, yellow, blue, green, purple, brown, orange, powder, the different angles of every kind of collection 2000 and size
It is multiplied by the YUYV images of 32 pixels.The acquisition modes of YUYV images are similar to the mode that headstock YUYV images are obtained in step 105.
After getting the YUYV images of color, data processing is carried out, by it and normalize to -1 to 1.Then caffe frameworks are used, if
Count 5 layer network models.Ground floor is 17 convolutional layers for being multiplied by 5, generates 6 maps；The second layer is the 4 pooling layers for being multiplied by 4,
6 maps of correspondence；Third layer is 9 convolutional layers for being multiplied by 2, generates 16 maps；4th layer is the 2 pooling layers for being multiplied by 2, right
Answer 16 maps；Layer 5 is 10 convolutional layers for being multiplied by 3, generates 500 maps；Layer 6 is full articulamentum, and correspondence 12 is multiplied by 1
Output result, wherein 12 is 12 kinds of colour types.
Step 107, determined according to the output result of convolutional neural networks model vehicle headstock color；
Headstock YUYV images are input into the convolutional neural networks model based on the training of YUYV images, the face for exporting is obtained
The color that headstock is determined after color is the color result of convolutional neural networks model output.
Step 108, the color that vehicle is determined according to the color of headstock；
After obtaining the color of headstock, from the color of headstock the color of overall vehicle is determined.This employing headstock region entirety
Colouring information replaces vehicle body local color information, reduces the requirement to vehicle body local color zone location to be identified, enhances
Robustness of the headstock region entirety colour recognition to local illumination.
It is described from a kind of method for detecting parking stalls of the embodiment of the present invention above, below to one kind of the embodiment of the present invention
Device is described.
Fig. 4 is referred to, a kind of device of the embodiment of the present invention includes：
Device includes acquisition module 401, identification module 402, the first determining module 403, modular converter 404, abstraction module
405th, input module 406, the second determining module 407, training module 408, the 3rd determining module 409.
Acquisition module 401, for obtaining the vehicle image of vehicle.
Identification module 402, for recognizing vehicle image in license board information, length, the width of license board information including car plate
And position.
First determining module 403, for determining the headstock image in headstock region and headstock region according to license board information.
Further, the first determining module 403 includes that the increase unit 4032, second of first acquisition unit 4031, first increases
Big unit 4033, determining unit 4034.
First acquisition unit 4031, for obtaining the length and width of car plate according to license board information.
First increase unit 4032, for the length value of car plate to be increased and as headstock region according to the first default ratio
Length value.
Second increase unit 4033, for the width value of car plate to be increased and as headstock region according to the second default ratio
Width value.
Determining unit 4034, for determining headstock region and obtaining the headstock image in headstock region.
Modular converter 404, for headstock image to be converted into the image of yuv format, obtains headstock YUV image.
Abstraction module 405, for Y-component data, U component datas, V component data to be extracted from headstock YUV image simultaneously
Reconfigure the headstock YUYV images for obtaining default size.
Further, abstraction module 405 includes extracting unit 4051, assembled unit 4052.
Extracting unit 4051, for extracting Y-component data, U number of components according to pre-conditioned from headstock YUV image
According to, V component data.
Assembled unit 4052, for according to Y-component data, U component datas, Y-component data, the order group of V component data
Conjunction obtains headstock YUYV images.
Input module 406, for headstock YUYV images to be input into the convolutional neural networks mould based on the training of YUYV images
Type.
Second determining module 407, for determining the face of the headstock of vehicle according to the output result of convolutional neural networks model
Color.
Training module 408, for training convolutional neural networks model.
Further, training module 408 includes second acquisition unit 4081, training unit 4082.
Second acquisition unit 4081, for obtaining the color YUYV figure that solid color image more than a kind of color is converted into
Picture, the size of color YUYV image is equal in magnitude with headstock YUYV images.
Training unit 4082, for using color YUYV image training convolutional neural networks model.
3rd determining module 409, for determining the color of vehicle according to the color of the headstock of vehicle.
Those skilled in the art can be understood that, for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, may be referred to the corresponding process in preceding method embodiment, will not be described here.
In several embodiments provided herein, it should be understood that disclosed system, apparatus and method can be with
Realize by another way.For example, device embodiment described above is only schematic, for example, the unit
Divide, only a kind of division of logic function can have other dividing mode, such as multiple units or component when actually realizing
Can with reference to or be desirably integrated into another system, or some features can be ignored, or not perform.It is another, it is shown or
The coupling each other for discussing or direct-coupling or communication connection can be the indirect couplings by some interfaces, device or unit
Close or communicate to connect, can be electrical, mechanical or other forms.
The unit as separating component explanation can be or may not be it is physically separate, it is aobvious as unit
The part for showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can according to the actual needs be selected to realize the mesh of this embodiment scheme
's.
The above, above example only to illustrate technical scheme, rather than a limitation；Although with reference to front
State embodiment to be described in detail the present invention, it will be understood by those within the art that：It still can be to front
State the technical scheme described in each embodiment to modify, or equivalent is carried out to which part technical characteristic；And these
Modification is replaced, and does not make the spirit and scope of the essence disengaging various embodiments of the present invention technical scheme of appropriate technical solution.
Claims (10)
1. a kind of color identification method for vehicle, it is characterised in that include：
Obtain the vehicle image of vehicle；
The license board information in the vehicle image is recognized, the license board information includes length, width and the position of car plate；
The headstock image in headstock region and the headstock region is determined according to the license board information；
The headstock image is converted into the image of yuv format, headstock YUV image is obtained；
Y-component data, U component datas, V component data are extracted from the headstock YUV image and is reconfigured and preset
The headstock YUYV images of size；
The headstock YUYV images are input into the convolutional neural networks model based on the training of YUYV images；
The color of the headstock of the vehicle is determined according to the output result of the convolutional neural networks model.
2. the color identification method for vehicle according to claim 1, it is characterised in that described to be believed according to the car plate
Breath determines that headstock region and the headstock image in the headstock region include：
The length and width of the car plate are obtained according to the license board information；
Using the length value of the car plate according to the first default ratio increase and as the length value in the headstock region；
Using the width value of the car plate according to the second default ratio increase and as the width value in the headstock region；
Determine the headstock region and obtain the headstock image in the headstock region.
3. the color identification method for vehicle according to claim 2, it is characterised in that described from the headstock YUV
Y-component data, U component datas, V component data are extracted in image and the headstock YUYV images for obtaining default size are reconfigured
Including：
The Y-component data, the U component datas, the V point is extracted from the headstock YUV image according to pre-conditioned
Amount data；
Sequential combination according to the Y-component data, the U component datas, the Y-component data, the V component data is obtained
The headstock YUYV images.
4. the color identification method for vehicle according to claim 3, it is characterised in that described by the headstock YUYV
Image is input into before the convolutional neural networks model based on the training of YUYV images also to be included：
The convolutional neural networks model is trained, including：
Obtain the color YUYV image that solid color image more than a kind of color is converted into, the size of the color YUYV image
It is equal in magnitude with the headstock YUYV images；
The convolutional neural networks model is trained using the color YUYV image.
5. the color identification method for vehicle according to claim 4, it is characterised in that described according to convolution god
The output result of Jing network models determines after the color of the headstock of the vehicle, also includes：
The color of the vehicle is determined according to the color of the headstock of the vehicle.
6. a kind of device, it is characterised in that include：
Acquisition module, for obtaining the vehicle image of vehicle；
Identification module, for recognizing the vehicle image in license board information, length, the width of the license board information including car plate
And position；
First determining module, for determining the headstock image in headstock region and the headstock region according to the license board information；
Modular converter, for the headstock image to be converted into the image of yuv format, obtains headstock YUV image；
Abstraction module, for extracting Y-component data, U component datas, V component data and again from the headstock YUV image
Combination obtains the headstock YUYV images of default size；
Input module, for the headstock YUYV images to be input into the convolutional neural networks model based on the training of YUYV images；
Second determining module, for determining the face of the headstock of the vehicle according to the output result of the convolutional neural networks model
Color.
7. device according to claim 6, it is characterised in that first determining module includes：
First acquisition unit, for obtaining the length and width of the car plate according to the license board information；
First increase unit, for the length value of the car plate to be increased and as the headstock region according to the first default ratio
Length value；
Second increase unit, for the width value of the car plate to be increased and as the headstock region according to the second default ratio
Width value；
Determining unit, for determining the headstock region and obtaining the headstock image in the headstock region.
8. device according to claim 7, it is characterised in that the abstraction module includes：
Extracting unit, for extracting the Y-component data, the U components according to pre-conditioned from the headstock YUV image
Data, the V component data；
Assembled unit, for according to the Y-component data, the U component datas, the Y-component data, the V component data
Sequential combination obtain the headstock YUYV images.
9. device according to claim 8, it is characterised in that also include：
Training module, for training the convolutional neural networks model, including：
Second acquisition unit, it is described for obtaining the color YUYV image that solid color image more than a kind of color is converted into
The size of color YUYV image is equal in magnitude with the headstock YUYV images；
Training unit, for training the convolutional neural networks model using the color YUYV image.
10. device according to claim 9, it is characterised in that also include：
3rd determining module, for determining the color of the vehicle according to the color of the headstock of the vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611238820.XA CN106651969A (en) | 2016-12-28 | 2016-12-28 | Color identification method and apparatus for vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611238820.XA CN106651969A (en) | 2016-12-28 | 2016-12-28 | Color identification method and apparatus for vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106651969A true CN106651969A (en) | 2017-05-10 |
Family
ID=58836309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611238820.XA Pending CN106651969A (en) | 2016-12-28 | 2016-12-28 | Color identification method and apparatus for vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106651969A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109145928A (en) * | 2017-06-16 | 2019-01-04 | 杭州海康威视数字技术股份有限公司 | It is a kind of based on the headstock of image towards recognition methods and device |
| US20190026603A1 (en) * | 2017-07-19 | 2019-01-24 | Beijing ICETech Science & Technology Co., Ltd. | Method and system for vehicle recognition |
| CN111353585A (en) * | 2020-02-25 | 2020-06-30 | 北京百度网讯科技有限公司 | Structure searching method and device of neural network model |
| WO2022095595A1 (en) * | 2020-11-05 | 2022-05-12 | Oppo广东移动通信有限公司 | Image recognition method, apparatus, electronic device, and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104715239A (en) * | 2015-03-12 | 2015-06-17 | 哈尔滨工程大学 | Vehicle color identification method based on defogging processing and weight blocking |
| CN104978746A (en) * | 2015-06-26 | 2015-10-14 | 西安理工大学 | Running vehicle body color identification method |
| CN105160691A (en) * | 2015-08-29 | 2015-12-16 | 电子科技大学 | Color histogram based vehicle body color identification method |
| CN106023220A (en) * | 2016-05-26 | 2016-10-12 | 史方 | Vehicle exterior part image segmentation method based on deep learning |
-
2016
- 2016-12-28 CN CN201611238820.XA patent/CN106651969A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104715239A (en) * | 2015-03-12 | 2015-06-17 | 哈尔滨工程大学 | Vehicle color identification method based on defogging processing and weight blocking |
| CN104978746A (en) * | 2015-06-26 | 2015-10-14 | 西安理工大学 | Running vehicle body color identification method |
| CN105160691A (en) * | 2015-08-29 | 2015-12-16 | 电子科技大学 | Color histogram based vehicle body color identification method |
| CN106023220A (en) * | 2016-05-26 | 2016-10-12 | 史方 | Vehicle exterior part image segmentation method based on deep learning |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109145928A (en) * | 2017-06-16 | 2019-01-04 | 杭州海康威视数字技术股份有限公司 | It is a kind of based on the headstock of image towards recognition methods and device |
| CN109145928B (en) * | 2017-06-16 | 2020-10-27 | 杭州海康威视数字技术股份有限公司 | Method and device for identifying vehicle head orientation based on image |
| US20190026603A1 (en) * | 2017-07-19 | 2019-01-24 | Beijing ICETech Science & Technology Co., Ltd. | Method and system for vehicle recognition |
| US10460209B2 (en) * | 2017-07-19 | 2019-10-29 | Beijing ICETech Science & Technology Co., Ltd. | Method and system for vehicle recognition |
| CN111353585A (en) * | 2020-02-25 | 2020-06-30 | 北京百度网讯科技有限公司 | Structure searching method and device of neural network model |
| CN111353585B (en) * | 2020-02-25 | 2024-09-06 | 南京羽丰视讯科技有限公司 | Structure searching method and device of neural network model |
| WO2022095595A1 (en) * | 2020-11-05 | 2022-05-12 | Oppo广东移动通信有限公司 | Image recognition method, apparatus, electronic device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105354572B (en) | A kind of automatic license plate identification system based on simplified convolutional neural networks | |
| CN106651969A (en) | Color identification method and apparatus for vehicle | |
| CN106446949B (en) | A kind of vehicle model recognition methods and device | |
| CN107610141A (en) | A kind of remote sensing images semantic segmentation method based on deep learning | |
| CN103886760B (en) | Real-time vehicle detecting system based on traffic video | |
| CN103996041B (en) | Vehicle color identification method and system based on matching | |
| CN108021933A (en) | Neural network recognization model and recognition methods | |
| CN108830199A (en) | Identify method, apparatus, readable medium and the electronic equipment of traffic light signals | |
| CN108537239A (en) | A kind of method of saliency target detection | |
| CN106448257A (en) | Parking space occupation condition detection method and device | |
| CN106682601A (en) | Driver violation conversation detection method based on multidimensional information characteristic fusion | |
| CN108596892A (en) | A kind of identification of Weld Defects based on improvement LeNet-5 models | |
| CN107016362B (en) | Vehicle weight recognition method and system based on vehicle front windshield pasted mark | |
| CN105205489A (en) | License plate detection method based on color texture analyzer and machine learning | |
| CN101425182A (en) | Image object segmentation method | |
| CN105205804A (en) | Caryon-cytolymph separation method and apparatus of white blood cells in blood cell image, and classification method and apparatus of white blood cells in blood cell image | |
| CN107273894A (en) | Recognition methods, device, storage medium and the processor of car plate | |
| CN107578012A (en) | A kind of drive assist system based on clustering algorithm selection sensitizing range | |
| CN107292933A (en) | A kind of vehicle color identification method based on BP neural network | |
| CN103544480A (en) | Vehicle color recognition method | |
| CN109272513A (en) | Hand and object interactive segmentation method and device based on depth camera | |
| CN112906550B (en) | Static gesture recognition method based on watershed transformation | |
| CN106897747A (en) | A kind of method and device for differentiating vehicle color based on convolutional neural networks model | |
| CN107180230A (en) | General licence plate recognition method | |
| CN110298893A (en) | A kind of pedestrian wears the generation method and device of color identification model clothes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170510 |