CN108241835A - Vehicle travels pattern recognition device - Google Patents
Vehicle travels pattern recognition device Download PDFInfo
- Publication number
- CN108241835A CN108241835A CN201611208493.3A CN201611208493A CN108241835A CN 108241835 A CN108241835 A CN 108241835A CN 201611208493 A CN201611208493 A CN 201611208493A CN 108241835 A CN108241835 A CN 108241835A
- Authority
- CN
- China
- Prior art keywords
- image
- vehicle traveling
- identified
- vehicle
- target object
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the present invention provides a kind of vehicle traveling pattern recognition device, belongs to technical field of image processing.Described device includes：Acquisition module travels image for obtaining vehicle to be identified, and the vehicle traveling image to be identified is image of the vehicle on road recorded in driving process；And identification module, for the target object in the vehicle traveling image to be identified to be identified using recongnition of objects model.The embodiment of the present invention only needs the vehicle traveling image to be identified of acquisition being input to recongnition of objects model, automatically, in real time, effectively, accurately the target object in vehicle traveling image to be identified can be identified, there is very high intelligent and robustness.
Description
Technical field
The present embodiments relate to technical field of image processing, and in particular, to a kind of vehicle travels pattern recognition device.
Background technology
In order to meet expectation of the user to device intelligence, more and more intelligence are automatically brought into operation studied and extension.Example
Such as, for vehicular field, while user's vehicle can be more intelligent, safer, the operation of user can be further reduced.
In order to realize the purpose, can be with installation data detection device in vehicle, such as camera etc., to be carried for automatically analyzing for vehicle
For data basis.
For example, for Vehicular automatic driving, the correct identification of target object in image is travelled for vehicle is
Vehicle is accurately positioned, the important evidence of path planning.For example, by target object for for lane line, lane line in the prior art
Detection method is mainly Computer Vision Detection method, based on image processing algorithm, detects the vehicle of image middle rolling car road
Diatom mark region.Present inventor has found in the implementation of the present invention：Since the type of track line index is various, vehicle
Crowded that lane line mark region is caused to be blocked, lane line may have the factors such as situation and the weather of corrosive wear can
No small challenge is brought to lane detection task.In addition, this kind of algorithm needs manually to go to adjust filter operator, according to algorithm
The targeted manual adjustment parameter of street scene feature, heavy workload and robustness is poor, when significant change occurs in environment
When, the detection result of lane line is bad.
Invention content
To achieve these goals, the embodiment of the present invention provides a kind of vehicle traveling pattern recognition device, which includes：
Acquisition module travels image for obtaining vehicle to be identified, and the vehicle traveling image to be identified is vehicle on road
Image recorded in driving process；And identification module, for utilizing recongnition of objects model to the vehicle to be identified
Traveling image in target object be identified.
Optionally, which further includes：Preprocessing module, for utilizing recongnition of objects model to described to be identified
Vehicle traveling image in target object be identified before the vehicle traveling image to be identified is pre-processed.
Optionally, the preprocessing module is further used for：The vehicle traveling image to be identified is carried out interested
Region (ROI) is extracted and/or image inverse perspective mapping (IPM).
Optionally, the recongnition of objects model is established according to following steps：The step of establishing training sample set, wherein
The step includes：It acquires multiple vehicle traveling images including target object and marks out in the multiple vehicle traveling image
The multiple vehicle is travelled the target object of image and corresponding mark by the target object in each vehicle traveling image
As training set sample；The step of establishing deep neural network, the wherein step include：Described in the training set sample
Multiple vehicles traveling images are as the inputting of deep neural network, the multiple vehicle traveling image in the training set sample
The target object of corresponding mark be trained as the output of the deep neural network；It and will be after the completion of training
Deep neural network is as recongnition of objects model.
Optionally, described the step of establishing training sample set, further comprises：The multiple vehicle traveling image is carried out
Pretreatment, the pretreatment includes extracting the multiple vehicle traveling image progress area-of-interest (ROI) and/or image is inverse
Perspective mapping (IPM)；And using the target object of pretreated multiple vehicle traveling images and corresponding mark as instruction
Practice collection sample.
Optionally, wherein the target object travels the lane line on the road in image for vehicle.
Optionally, the identification module is further used for：Identification is obtained using characteristic information cluster and least square method
The parametric equation of lane line and/or the quantity of lane line.
Through the above technical solutions, it only needs the vehicle traveling image to be identified of acquisition being input to recongnition of objects
Model, you can automatically, in real time, effectively, accurately to be carried out to the target object in vehicle traveling image to be identified
Identification has very high intelligent and robustness.
The other feature and advantage of the embodiment of the present invention will be described in detail in subsequent specific embodiment part.
Description of the drawings
Attached drawing is that the embodiment of the present invention is further understood for providing, and a part for constitution instruction, under
The specific embodiment in face is used to explain the embodiment of the present invention, but do not form the limitation to the embodiment of the present invention together.Attached
In figure：
Fig. 1 is a kind of structure diagram of the vehicle traveling pattern recognition device of embodiment according to embodiments of the present invention；
Fig. 2-3 is a kind of schematic diagram of the instance object object recognition process of embodiment according to embodiments of the present invention；
Fig. 4 is a kind of structure diagram of the vehicle traveling pattern recognition device of embodiment according to embodiments of the present invention；
Fig. 5 is a kind of schematic diagram of the instance object object recognition process of embodiment according to embodiments of the present invention；And
Fig. 6 is a kind of example flow diagram of the vehicle traveling image-recognizing method of embodiment according to embodiments of the present invention.
Specific embodiment
The specific embodiment of the embodiment of the present invention is described in detail below in conjunction with attached drawing.It should be understood that this
Locate described specific embodiment and be merely to illustrate and explain the present invention embodiment, be not intended to restrict the invention embodiment.
In order to realize that the target object progress travelled to vehicle in image automatically, in real time, effectively, is accurately known
Not, the embodiment of the present invention considers various embodiments, will be described in detail one by one below：
Embodiment 1
Fig. 1 is a kind of structural representation of the vehicle traveling pattern recognition device 100 of embodiment according to embodiments of the present invention
Figure, as shown in Figure 1, the device can include：Acquisition module 10 can be used in obtaining vehicle traveling image to be identified, described
Vehicle traveling image to be identified can be image of the vehicle on road recorded in driving process, such as described to be identified
Vehicle traveling image can be obtained from the figures such as the camera (such as industrial high-definition camera) installed on vehicle, automobile data recorder
As acquisition device；And identification module 20, it can be used in travelling the vehicle to be identified using recongnition of objects model
Target object in image is identified, wherein the target object can be in the image that user or technical staff need
Any object.For example, for Vehicular automatic driving, since the lane line on road is accurately positioned for vehicle, path planning
Important evidence, therefore, can by the vehicle of acquisition travel image in road on lane line be set as target object.Identification
Module 20 can be identified and be shown to lane line using recongnition of objects model.
Using the present embodiment, vehicle traveling pattern recognition device 100 needs the vehicle to be identified of acquisition travelling figure
As being input to recongnition of objects model, you can automatically, in real time, effectively, accurately to be travelled to vehicle to be identified
Target object in image is identified, and has very high intelligent and robustness.
Embodiment 2
Fig. 2-3 is a kind of schematic diagram of the instance object object recognition process of embodiment according to embodiments of the present invention, such as
Shown in Fig. 2, the target object that the vehicle traveling pattern recognition device 100 of embodiment 1 is further described in the embodiment 2 is known
A kind of example of other process.Specifically, identification module 20 can be inputted after vehicle traveling image to be identified is got
To the recongnition of objects model pre-established, which can be according to the image of input to wherein existing
Target object be identified, such as the target object is split from described image.By taking lane line as an example, target pair
The pixel region division of lane line in the picture is come out as identification model can be travelled from vehicle in image, with for subsequent vehicle
Road line analysis provides data basis, such as first-class for the path planning of Vehicular automatic driving system.
For the recongnition of objects model, as shown in Fig. 2, can be established according to following steps：
The step of establishing training sample set 1000, the wherein step can include：Acquire multiple vehicles including target object
Traveling image, as shown in figure 3, and marking out the mesh in each vehicle traveling image in the multiple vehicle traveling image
Mark object, such as shown in Fig. 31,2,3,4,5,6 etc., with different label (or color, here due in attached drawing without Faxian
Different colours are shown, therefore are replaced with label) mark the different lane lines in image, the line segment for belonging to same lane line is used
The multiple vehicle is travelled the target object of image and corresponding mark as training set by identical label or color mark
Sample；And
The step 1001 of deep neural network is established, wherein the step can include：By the institute in the training set sample
Multiple vehicles traveling images are stated as the inputting of deep neural network, the multiple vehicle traveling figure in the training set sample
The target object of the corresponding mark of picture is trained as the output of the deep neural network；And after the completion of training
Deep neural network as recongnition of objects model.Wherein deep neural network is a kind of deep learning process, by simple
The deeper multiple perceptron model of the number of plies of neuron composition realizes multi-dimensional no-protru-ding function using powerful nonlinear characteristic
Mathematical approach, mathematical description is very competent, and complicated network structure can go out representative from mass data learning
Feature.It should be understood that the deep neural network can select any appropriate neural network, such as multilayer feedforward (BP)
Neural network, radial direction base (RBF) neural network, fuzzy neural network, support vector machines (SVM) etc..
In order to further improve the accuracy of Model of Target Recognition and reduce the complexity of model, the deep neural network
Can be convolutional neural networks (Convolutional Neural Network).
Using such embodiment, recongnition of objects model can be identified rapidly, accurately in vehicle traveling image
Target object.For example, by taking lane line as an example, recongnition of objects model, which can be travelled from vehicle in image, is scheming lane line
Pixel region division as in comes out, to provide data basis, such as subsequent track line analysis for Vehicular automatic driving
The path planning of system is first-class.
Embodiment 3
Fig. 4 is a kind of structural representation of the vehicle traveling pattern recognition device 100 of embodiment according to embodiments of the present invention
Figure；Fig. 5 is a kind of schematic diagram of the instance object object recognition process of embodiment according to embodiments of the present invention, as shown in figure 4,
In the embodiment 3, difference from Example 2 is, which travels pattern recognition device 100 in addition to that can include obtaining
Except module 10 and identification module 20, preprocessing module 30 can also be included.
Specifically, which can travel the vehicle to be identified using recongnition of objects model
Target object in image pre-processes the vehicle traveling image to be identified before being identified, unnecessary to remove
Noise, and reduce the complexity of calculating.
For example, the preprocessing module can carry out area-of-interest (ROI) to the vehicle traveling image to be identified
Extraction；Or image inverse perspective mapping (IPM)；Or it carries out area-of-interest (ROI) and extracts and image inverse perspective mapping (IPM)
The two.This mainly it is considered that for example, vehicle as shown in Figure 3 traveling image, wherein most be illustrated that sky and
Other buildings (such as trees, street lamp, direction board) etc., this parts of images do not include lane line, therefore can be by the region
It is cut, only extracts interested region (i.e. ROI extractions), so as to reduce the size of image for needing to identify, carried
The execution efficiency of high program.
Also, the image of acquisition is mostly from the visual angle of driving, has a near big and far smaller effect, lane line nearby show compared with
Slightly, pixel accounting is high, then slowly attenuates at a distance, pixel accounting is fewer and fewer, and parallel lane line is answered finally to converge in one originally
A end point.And IPM mappings can eliminate this transparent effect.
It is thereby possible to select the image after region of interest ROI is extracted carries out IPM mappings, such lane line is located substantially
In parastate.In addition, area-of-interest down-sampling can also be reduced image resolution ratio, improve follow-up vehicle before IPM mappings
The speed of service of diatom identification process.
Accordingly, the image that training sample is concentrated can also be carried out similar in the recongnition of objects model stage
Pretreatment operation.As shown in figure 5, the step 1000 for establishing training sample set further comprises：By the multiple vehicle row
It sails image to be pre-processed, the pretreatment includes carrying out area-of-interest (ROI) extraction to the multiple vehicle traveling image
And/or image inverse perspective mapping (IPM)；And the target by pretreated multiple vehicle traveling images and corresponding mark
Object is as training set sample.
Using such embodiment, due to pre-processed (such as region of interest ROI extraction and/or image it is inverse thoroughly
Depending on mapping IPM), unnecessary noise is eliminated, the size of image to be identified is reduced and eliminates transparent effect,
Therefore vehicle traveling pattern recognition device 100 can more rapidly, accurately identify the target object in vehicle traveling image,
For example, by taking lane line as an example, the pixel in image by lane line in the picture can be more rapidly, accurately travelled from vehicle
Region segmentation comes out, and robustness is high, and segmentation result noise is small.
Embodiment 4
In the embodiment 4, the difference lies in the identification module 20 can further utilize spy with embodiment 1-3
It levies information cluster and least square method obtains the parametric equation of lane line of identification and/or the quantity of lane line.Specifically, pass through
Described in embodiment 1-3, the pixel region of the lane line divided by convolutional neural networks even depth neural network in the picture
After domain, identification module 20 can utilize characteristic information cluster (for example, position feature information cluster) to obtain belonging to same vehicle
The pixel region of diatom, and the point on each lane line is sampled, secondary song finally is carried out to lane line using least square method
Line is fitted, and acquires the parametric equation and lane line of the parametric equation of lane line or the quantity of lane line or lane line
Both quantity.
Using such embodiment, not only can the lane line in image be travelled with vehicle and be split, minimum can also be used
Square law carries out parametric regression to lane line, obtains lane line parametric equation and quantity, is the skills such as subsequent vehicle automatic running
The research and development of art provide technical foundation.
Vehicle provided in an embodiment of the present invention is travelled pattern recognition device and can be realized in the form of hardware or software, such as
It can be applied in the form of software in any appropriate scene that vehicle traveling image is identified, such as vehicle control
Plane processed, electronic control unit ECU and other mobile units etc., can also in the form of hardware with setting in above-mentioned scene
Standby integrated, the embodiment of the present invention is to this without limiting.It should be understood that those skilled in the art can be according to of the invention real
It applies the open of example and selects the combination of any one of above-mentioned various embodiments or the above-mentioned various embodiments of selection vehicle is configured
Pattern recognition device is travelled, and other alternative embodiments also fall into the protection domain of the embodiment of the present invention.
Fig. 6 is a kind of example flow diagram of the vehicle traveling image-recognizing method of embodiment according to embodiments of the present invention,
As shown in fig. 6, this method may comprise steps of：
Step S11, obtains vehicle traveling image to be identified, and the vehicle traveling image to be identified is vehicle in road
Image recorded in upper driving process；And
Step S12, using recongnition of objects model to the target object in the vehicle traveling image to be identified into
Row identification.
Optionally, this method further includes：Image is being travelled to the vehicle to be identified using recongnition of objects model
In target object be identified before, the vehicle traveling image to be identified is pre-processed.
Optionally, the pretreatment includes：Area-of-interest (ROI) is carried out to the vehicle traveling image to be identified to carry
It takes and/or image inverse perspective mapping (IPM).
Optionally, the recongnition of objects model is established according to following steps：The step of establishing training sample set, wherein
The step includes：It acquires multiple vehicle traveling images including target object and marks out in the multiple vehicle traveling image
The multiple vehicle is travelled the target object of image and corresponding mark by the target object in each vehicle traveling image
As training set sample；The step of establishing deep neural network, the wherein step include：Described in the training set sample
Multiple vehicles traveling images are as the inputting of deep neural network, the multiple vehicle traveling image in the training set sample
The target object of corresponding mark be trained as the output of the deep neural network；It and will be after the completion of training
Deep neural network is as recongnition of objects model.
Optionally, described the step of establishing training sample set, further comprises：The multiple vehicle traveling image is carried out
Pretreatment, the pretreatment includes extracting the multiple vehicle traveling image progress area-of-interest (ROI) and/or image is inverse
Perspective mapping (IPM)；And using the target object of pretreated multiple vehicle traveling images and corresponding mark as instruction
Practice collection sample.
Optionally, the deep neural network is convolutional neural networks (Convolutional Neural Network).
Optionally, wherein the target object travels the lane line on the road in image for vehicle.
Optionally, this method further includes：The ginseng of the lane line of identification is obtained using characteristic information cluster and least square method
The quantity of number equation and/or lane line.
It should be understood that each specific embodiment of above-mentioned vehicle traveling image-recognizing method, in example vehicle
It travels to have done in the embodiment of pattern recognition device and explains (as described above) in detail, details are not described herein.
Pattern recognition device and method are travelled using the vehicle of the embodiment of the present invention, it is only necessary to by the to be identified of acquisition
Vehicle traveling image be input to recongnition of objects model, you can with automatically, in real time, effectively, accurately to be identified
Vehicle traveling image in target object be identified, have very high intelligent and robustness.
The optional embodiment of the embodiment of the present invention is described in detail above in association with attached drawing, still, the embodiment of the present invention is simultaneously
The detail being not limited in the above embodiment, can be to of the invention real in the range of the technology design of the embodiment of the present invention
The technical solution for applying example carries out a variety of simple variants, these simple variants belong to the protection domain of the embodiment of the present invention.
It is further to note that specific technical features described in the above specific embodiments, in not lance
In the case of shield, it can be combined by any suitable means.In order to avoid unnecessary repetition, the embodiment of the present invention pair
Various combinations of possible ways no longer separately illustrate.
It will be appreciated by those skilled in the art that all or part of the steps of the method in the foregoing embodiments are can to pass through
Program is completed to instruct relevant hardware, which is stored in a storage medium, is used including some instructions so that one
A (can be microcontroller, chip etc.) or processor (processor) perform the whole of each embodiment the method for the application
Or part steps.And aforementioned storage medium includes：USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
In addition, arbitrary combination can also be carried out between a variety of different embodiments of the embodiment of the present invention, as long as it is not
The thought of the embodiment of the present invention is violated, should equally be considered as disclosure of that of the embodiment of the present invention.
Claims (7)
1. a kind of vehicle travels pattern recognition device, which is characterized in that the device includes：
Acquisition module travels image for obtaining vehicle to be identified, and the vehicle traveling image to be identified is vehicle in road
Image recorded in the driving process of road；And
Identification module, for using recongnition of objects model to the target object in the vehicle traveling image to be identified into
Row identification.
2. the apparatus according to claim 1, which is characterized in that the device further includes：
Preprocessing module, for the target pair in image is travelled to the vehicle to be identified using recongnition of objects model
As being pre-processed before being identified to the vehicle traveling image to be identified.
3. the apparatus of claim 2, which is characterized in that the preprocessing module is further used for：It waits to know to described
Other vehicle traveling image carries out area-of-interest (ROI) extraction and/or image inverse perspective mapping (IPM).
4. the apparatus according to claim 1, which is characterized in that the recongnition of objects model is built according to following steps
It is vertical：
The step of establishing training sample set, the wherein step include：
It acquires multiple vehicles traveling images including target object and marks out each in the multiple vehicle traveling image
The multiple vehicle is travelled the target object of image and corresponding mark as instruction by the target object in vehicle traveling image
Practice collection sample；
The step of establishing deep neural network, the wherein step include：
Using the multiple vehicle traveling image in the training set sample as the inputting of deep neural network, the training set
Output of the target object of the corresponding mark of the multiple vehicle traveling image in sample as the deep neural network
To be trained；And using the deep neural network after the completion of training as recongnition of objects model.
5. device according to claim 4, which is characterized in that described the step of establishing training sample set further comprises：
The multiple vehicle traveling image is pre-processed, the pretreatment includes carrying out the multiple vehicle traveling image
Area-of-interest (ROI) extracts and/or image inverse perspective mapping (IPM)；And
Using the target object of pretreated multiple vehicle traveling images and corresponding mark as training set sample.
6. according to the device described in any one of claim 1-5 claims, which is characterized in that wherein described target object is
The lane line on road in vehicle traveling image.
7. device according to claim 6, which is characterized in that the identification module is further used for：Utilize characteristic information
Cluster and least square method obtain the parametric equation of lane line of identification and/or the quantity of lane line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611208493.3A CN108241835A (en) | 2016-12-23 | 2016-12-23 | Vehicle travels pattern recognition device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611208493.3A CN108241835A (en) | 2016-12-23 | 2016-12-23 | Vehicle travels pattern recognition device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108241835A true CN108241835A (en) | 2018-07-03 |
Family
ID=62704243
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611208493.3A Pending CN108241835A (en) | 2016-12-23 | 2016-12-23 | Vehicle travels pattern recognition device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108241835A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109635719A (en) * | 2018-12-10 | 2019-04-16 | 宽凳（北京）科技有限公司 | A kind of image-recognizing method, device and computer readable storage medium |
-
2016
- 2016-12-23 CN CN201611208493.3A patent/CN108241835A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109635719A (en) * | 2018-12-10 | 2019-04-16 | 宽凳（北京）科技有限公司 | A kind of image-recognizing method, device and computer readable storage medium |
| CN109635719B (en) * | 2018-12-10 | 2023-11-17 | 宽凳（北京）科技有限公司 | Image recognition method, device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108241829A (en) | Vehicle travels image-recognizing method | |
| CN105069415B (en) | Method for detecting lane lines and device | |
| CN103324930B (en) | A kind of registration number character dividing method based on grey level histogram binaryzation | |
| WO2017041396A1 (en) | Driving lane data processing method, device, storage medium and apparatus | |
| CN103268489B (en) | Automotive number plate recognition methods based on sliding window search | |
| CN103093201B (en) | Vehicle-logo location recognition methods and system | |
| CN104156734A (en) | Fully-autonomous on-line study method based on random fern classifier | |
| CN103679168A (en) | Detection method and detection device for character region | |
| CN104700072A (en) | Lane line historical frame recognition method | |
| CN104299009A (en) | Plate number character recognition method based on multi-feature fusion | |
| CN105426863A (en) | Method and device for detecting lane line | |
| CN107704833A (en) | A kind of front vehicles detection and tracking based on machine learning | |
| Kavitha et al. | Pothole and object detection for an autonomous vehicle using yolo | |
| CN110807123A (en) | Vehicle length calculation method, device and system, computer equipment and storage medium | |
| CN107133588A (en) | Vehicle identification method based on vehicle window feature extraction | |
| Premachandra et al. | Road crack detection using color variance distribution and discriminant analysis for approaching smooth vehicle movement on non-smooth roads | |
| Hatolkar et al. | A survey on road traffic sign recognition system using convolution neural network | |
| Rakotondrajao et al. | Road boundary detection for straight lane lines using automatic inverse perspective mapping | |
| CN109977862B (en) | Recognition method of parking space limiter | |
| CN105512662A (en) | Detection method and apparatus for unlicensed vehicle | |
| Chen et al. | An effective detection algorithm of zebra-crossing | |
| Chen | Road vehicle recognition algorithm in safety assistant driving based on artificial intelligence | |
| CN108734170B (en) | License plate character segmentation method based on machine learning and template | |
| Li et al. | Traffic context aware data augmentation for rare object detection in autonomous driving | |
| Hechri et al. | Lanes and road signs recognition for driver assistance system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180712 Address after: 511458 9, Nansha District Beach Road, Guangzhou, Guangdong, 9 Applicant after: Rui Chi intelligent automobile (Guangzhou) Co., Ltd. Address before: 100026 8 floor 909, 105 building 3, Yao Yuan Road, Chaoyang District, Beijing. Applicant before: Music Automotive (Beijing) Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 511458 9, Nansha District Beach Road, Guangzhou, Guangdong, 9 Applicant after: Hengda Faraday future intelligent vehicle (Guangdong) Co., Ltd. Address before: 511458 9, Nansha District Beach Road, Guangzhou, Guangdong, 9 Applicant before: Rui Chi intelligent automobile (Guangzhou) Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190319 Address after: 100015 Building No. 7, 74, Jiuxianqiao North Road, Chaoyang District, Beijing, 001 Applicant after: FAFA Automobile (China) Co., Ltd. Address before: 511458 9, Nansha District Beach Road, Guangzhou, Guangdong, 9 Applicant before: Hengda Faraday future intelligent vehicle (Guangdong) Co., Ltd. |
|
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180703 |