CN108960308A - Traffic sign recognition method, device, car-mounted terminal and vehicle - Google Patents
Traffic sign recognition method, device, car-mounted terminal and vehicle Download PDFInfo
- Publication number
- CN108960308A CN108960308A CN201810658519.7A CN201810658519A CN108960308A CN 108960308 A CN108960308 A CN 108960308A CN 201810658519 A CN201810658519 A CN 201810658519A CN 108960308 A CN108960308 A CN 108960308A
- Authority
- CN
- China
- Prior art keywords
- traffic sign
- sign recognition
- recognition method
- layer
- convolutional layer
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims abstract description 6
- 238000010801 machine learning Methods 0.000 claims abstract description 6
- 238000003475 lamination Methods 0.000 claims description 8
- 230000001537 neural effect Effects 0.000 claims 1
- 238000013145 classification model Methods 0.000 abstract description 3
- 230000004913 activation Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 240000007651 Rubus glaucus Species 0.000 description 1
- 235000011034 Rubus glaucus Nutrition 0.000 description 1
- 235000009122 Rubus idaeus Nutrition 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/582—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of traffic signs
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (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 present invention relates to technical field of image processing, a kind of traffic sign recognition method, device, car-mounted terminal and vehicle are specifically provided.Aim to solve the problem that the technical issues of how accurately identifying to traffic sign.Traffic Sign Images are identified for this purpose, traffic sign recognition method provided by the invention can use the Traffic Sign Recognition model constructed in advance, to determine the type of sign of traffic sign to be identified.Wherein, Traffic Sign Recognition model is based on convolutional neural networks and using the image classification model of machine learning algorithm building, which can be the neural network based on lightweight network frame (such as tiny_dnn network frame) building.The type of traffic sign can be quickly and accurately identified based on the above method, to reduce the driving risk of vehicle.Meanwhile device provided by the invention, car-mounted terminal and vehicle can execute above-mentioned traffic sign recognition method.
Description
Technical field
The present invention relates to technical field of image processing, and in particular to a kind of traffic sign recognition method, device, car-mounted terminal
And vehicle.
Background technique
Traffic sign is a kind of road sign for being guided with text or symbol transmitting, being limited, alerting or indicate information, to
Traffic and instruction direction of traffic are managed to guarantee the coast is clear and traffic safety.Currently, Traffic Sign Recognition relies primarily on vehicle
Driver estimates traffic sign to judge traffic sign type.When vehicle driver observe not in time traffic sign or
When person's traffic sign is unintelligible, it will the driving risk of vehicle is significantly greatly increased.
Summary of the invention
In order to solve the above problem in the prior art, in order to solve the skill how to be accurately identified to traffic sign
Art problem.For this purpose, the present invention provides a kind of traffic sign recognition method, device, car-mounted terminal and vehicles.
In a first aspect, traffic sign recognition method includes the following steps: in the present invention
Obtain the Traffic Sign Images of traffic sign to be identified；
The Traffic Sign Images are identified using the Traffic Sign Recognition model constructed in advance, are determined described wait know
The type of sign of other traffic sign；
Wherein, the Traffic Sign Recognition model is based on convolutional neural networks and to utilize the figure of machine learning algorithm building
As disaggregated model.
Further, an optimal technical scheme provided by the invention is:
" being identified using the Traffic Sign Recognition model constructed in advance to the Traffic Sign Images " the step of it
Before, the method also includes:
Change of scale is carried out to the Traffic Sign Images；
Each pixel of Traffic Sign Images after the change of scale is normalized.
Further, an optimal technical scheme provided by the invention is:
The convolutional neural networks are the neural networks based on the building of tiny_dnn network frame.
Further, an optimal technical scheme provided by the invention is:
The convolutional neural networks include sequentially connected input layer, the first convolution unit, the first pond layer, the second convolution
Unit, the second pond layer, third convolution unit and full articulamentum；
First convolution unit, the second convolution unit and third convolution unit include a convolutional layer or it is multiple sequentially
The convolutional layer of connection, and each convolutional layer includes multiple convolution kernels.
Further, an optimal technical scheme provided by the invention is:
First convolution unit includes the first convolutional layer and the second convolutional layer and first convolutional layer and volume Two
Lamination includes 63 × 3 convolution kernels；
Second convolution unit includes third convolutional layer and Volume Four lamination and the third convolutional layer and Volume Four
Lamination includes 16 3 × 3 convolution kernels；
The third convolution unit includes the 5th convolutional layer and the 5th convolutional layer includes 160 7 × 7 convolution
Core.
Further, an optimal technical scheme provided by the invention is:
First pond layer and the second pond layer are the pond windows of average pond layer and the average pond layer
It is 2 × 2.
Storage device in second aspect, the present invention is stored with a plurality of program, and described program is suitable for being loaded by processor
To execute traffic sign recognition method described in above-mentioned technical proposal.
Control device in the third aspect, the present invention includes processor and storage equipment, and the storage equipment is suitable for depositing
A plurality of program is stored up, described program is suitable for being loaded as the processor to execute Traffic Sign Recognition side described in above-mentioned technical proposal
Method.
Car-mounted terminal in fourth aspect, the present invention includes control device described in above-mentioned technical proposal.
Vehicle includes car-mounted terminal described in above-mentioned technical proposal in the 5th aspect, the present invention.
Compared with the immediate prior art, above-mentioned technical proposal is at least had the advantages that
1, the traffic sign recognition method in the present invention can use the Traffic Sign Recognition model constructed in advance to traffic
Sign image is identified, to determine the type of sign of traffic sign to be identified.Wherein, Traffic Sign Recognition model is based on volume
Product neural network and the image classification model for utilizing machine learning algorithm building, the convolutional neural networks can be based on lightweight
The neural network of network frame (such as tiny_dnn network frame) building.It can quickly and accurately be identified based on the above method
The type of traffic sign, to reduce the driving risk of vehicle.
2, car-mounted terminal provided by the invention includes the control device for being able to carry out above-mentioned traffic sign recognition method, is based on
Above-mentioned lightweight network frame can reduce the equipment cost and calculation amount of control device.
Detailed description of the invention
Fig. 1 is a kind of key step schematic diagram of traffic sign recognition method in the embodiment of the present invention；
Fig. 2 is a kind of primary structure signal of the convolutional neural networks of Traffic Sign Recognition model in the embodiment of the present invention
Figure.
Specific embodiment
The preferred embodiment of the present invention described with reference to the accompanying drawings.It will be apparent to a skilled person that this
A little embodiments are used only for explaining technical principle of the invention, it is not intended that limit the scope of the invention.
A kind of traffic sign recognition method provided by the invention is illustrated with reference to the accompanying drawing.Refering to attached drawing 1, Fig. 1
Illustrate the key step of traffic sign recognition method in the present embodiment.As shown in Figure 1, traffic sign in the present embodiment
Recognition methods may include steps of:
Step S101: the Traffic Sign Images of traffic sign to be identified are obtained.
Specifically, it can use vehicle mounted imaging apparatus in the present embodiment and obtain the traffic sign to be identified being located at outside car body
Image.
Step S102: change of scale is carried out to Traffic Sign Images.
Specifically, Traffic Sign Images can be converted to the figure of specific pixel size (such as 40 × 40) in the present embodiment
Picture.
Step S103: each pixel of the Traffic Sign Images after change of scale is normalized.
Specifically, the number that can be normalized to each pixel of Traffic Sign Images in the present embodiment in (- 1,1)
Value.
Step S104: identifying Traffic Sign Images using the Traffic Sign Recognition model constructed in advance, determine to
Identify the type of sign of traffic sign.
In the present embodiment, Traffic Sign Recognition model is constructed based on convolutional neural networks and using machine learning algorithm
Image classification model.Wherein, convolutional neural networks can be the neural network based on the building of tiny_dnn network frame.
In a preferred embodiment of the present embodiment, the convolutional neural networks in Traffic Sign Recognition model be can wrap
Include sequentially connected input layer, the first convolution unit, the first pond layer, the second convolution unit, the second pond layer, third convolution list
First and full articulamentum.Specifically, the first convolution unit, the second convolution unit and third convolution unit include a convolutional layer or
Multiple sequentially connected convolutional layers, and each convolutional layer includes multiple convolution kernels.
Refering to attached drawing 2, Fig. 2 illustrates the primary structure of convolutional neural networks in the present embodiment.As shown in Fig. 2,
In the present embodiment convolutional neural networks include sequentially connected input layer, the first convolutional layer, the second convolutional layer, the first pond layer,
Third convolutional layer, Volume Four lamination, the second pond layer, the 5th convolutional layer and full articulamentum.Wherein, the first pond layer and the second pond
Changing layer is average pond layer.
Specifically, in the present embodiment the input data of input layer be Pixel Dimensions be 40 × 40 rgb format input
Image.First convolutional layer includes 63 × 3 convolution kernels and above-mentioned input picture can be transformed to 6 pictures by the first convolutional layer
Plain size is 38 × 38 image.Second convolutional layer includes 63 × 3 convolution kernels and the second convolutional layer can be by above-mentioned " 6
A Pixel Dimensions are 38 × 38 images " it is transformed to the image that 6 Pixel Dimensions are 36 × 36.The pond window of first pond layer
Be 2 × 2 and first pond layer above-mentioned " 6 Pixel Dimensions be 36 × 36 image " can be transformed to 6 Pixel Dimensions and be
18 × 18 image.Third convolutional layer includes 16 3 × 3 convolution kernels and third convolutional layer can be by above-mentioned " 6 pixel rulers
Very little is 18 × 18 image " it is transformed to the image that 16 Pixel Dimensions are 16 × 16.Volume Four lamination includes 16 3 × 3 volumes
It is 14 that above-mentioned " 16 Pixel Dimensions be 16 × 16 image " can be transformed to 16 Pixel Dimensions by product core and Volume Four lamination
× 14 image.The pond window of second pond layer be 2 × 2 and second pond layer can by above-mentioned " 16 Pixel Dimensions are
14 × 14 image " is transformed to the image that 16 Pixel Dimensions are 7 × 7.5th convolutional layer include 160 7 × 7 convolution kernel simultaneously
And the 5th convolutional layer above-mentioned " 16 Pixel Dimensions be 7 × 7 image " can be transformed to 160 one-dimensional vectors.Based on above-mentioned
Structure can greatly reduce the number of parameters in convolutional network using multiple lesser biggish convolution kernels of convolution nuclear subsitution.
The activation primitive of full articulamentum can be softmax function, the activation primitive of each convolutional layer in the present embodiment
It can be tanh function.Further, in this embodiment can be based on such as German traffic sign data of preset training dataset
Collect (German Traffic Sign Recognition Benchmark, GTSRB) and using machine learning algorithm to Fig. 2 institute
The convolutional neural networks shown carry out network training, are optimized with treating Optimal Parameters.
Although each step is described in the way of above-mentioned precedence in above-described embodiment, this field
Technical staff is appreciated that the effect in order to realize the present embodiment, executes between different steps not necessarily in such order,
It (parallel) execution simultaneously or can be executed with reverse order, these simple variations all protection scope of the present invention it
It is interior.
Based on above-mentioned traffic sign recognition method embodiment, the present invention also provides a kind of storage device, the storage devices
In be stored with a plurality of program and these programs can be loaded by processor to execute above-mentioned traffic sign recognition method embodiment
The traffic sign recognition method.
Further, it is based on above-mentioned traffic sign recognition method embodiment, the present invention also provides a kind of control devices, should
Control device may include processor and storage equipment.Specifically, storage equipment may be adapted to store a plurality of program and these
Program can be loaded as processor to execute traffic sign recognition method described in above-mentioned traffic sign recognition method embodiment.
Further, it is based on above-mentioned control device embodiment, the present invention also provides a kind of car-mounted terminal, the vehicle-mounted ends
End may include control device described in above-mentioned control device embodiment.Optionally, in the present embodiment control device processor
Can be raspberry pie (Raspberry Pi, PRi) and can use the basic environment of the Ubuntu system building processor with
And using tiny_dnn network frame construct the processor terminal switched network (Terminal Switched Network,
TSNet), i.e., the terminal switched network of car-mounted terminal can be the friendship based on convolutional neural networks shown in Fig. 2 in the present embodiment
Logical landmark identification model.
In a preferred embodiment of the present embodiment, when the German traffic sign data set of use is to above-mentioned car-mounted terminal
Terminal switched network carry out network training after, the car-mounted terminal 43 class traffic signs can be carried out classification and classification results
Accuracy can achieve 93.7%, while the car-mounted terminal is less than 0.0156s to the classification time of every Traffic Sign Images.
Still further, being based on above-mentioned car-mounted terminal embodiment, the present invention also provides a kind of vehicle, which be can wrap
Car-mounted terminal described in above-mentioned car-mounted terminal embodiment is included, the vehicle is enabled to tell the type of traffic sign automatically, from
And reduce the driving risk of vehicle.
It will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments is wrapped
Certain features for including rather than other feature, but the combination of the feature of different embodiments mean in the scope of the present invention it
It is interior and form different embodiments.For example, in claims of the present invention, embodiment claimed it is any it
One can in any combination mode come using.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and ability
Field technique personnel can be designed alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between parentheses should not be configured to limitations on claims.Word "comprising" and " comprising " are not arranged
Except there are element or steps not listed in the claims.Word "a" or "an" located in front of the element does not exclude the presence of more
A such element.The present invention can by means of include several different elements hardware and by means of properly programmed PC come
It realizes.The use of word first, second, and third does not indicate any sequence.These words can be construed to title.
So far, it has been combined preferred embodiment shown in the drawings and describes technical solution of the present invention, still, this field
Technical staff is it is easily understood that protection scope of the present invention is expressly not limited to these specific embodiments.Without departing from this
Under the premise of the principle of invention, those skilled in the art can make equivalent change or replacement to the relevant technologies feature, these
Technical solution after change or replacement will fall within the scope of protection of the present invention.
Claims (10)
1. a kind of traffic sign recognition method, characterized by comprising:
Obtain the Traffic Sign Images of traffic sign to be identified；
The Traffic Sign Images are identified using the Traffic Sign Recognition model constructed in advance, determine the friendship to be identified
The type of sign of logical mark；
Wherein, the Traffic Sign Recognition model is based on convolutional neural networks and to utilize the image point of machine learning algorithm building
Class model.
2. traffic sign recognition method according to claim 1, which is characterized in that " utilizing the traffic mark constructed in advance
Will identification model identifies the Traffic Sign Images " the step of before, the method also includes:
Change of scale is carried out to the Traffic Sign Images；
Each pixel of Traffic Sign Images after the change of scale is normalized.
3. traffic sign recognition method according to claim 1, which is characterized in that the convolutional neural networks are to be based on
The neural network of tiny_dnn network frame building.
4. traffic sign recognition method according to any one of claim 1-3, which is characterized in that the convolutional Neural net
Network includes sequentially connected input layer, the first convolution unit, the first pond layer, the second convolution unit, the second pond layer, third volume
Product unit and full articulamentum；
First convolution unit, the second convolution unit and third convolution unit include a convolutional layer or multiple are sequentially connected with
Convolutional layer, and each convolutional layer includes multiple convolution kernels.
5. traffic sign recognition method according to claim 4, which is characterized in that
First convolution unit includes the first convolutional layer and the second convolutional layer and first convolutional layer and the second convolutional layer
It include 63 × 3 convolution kernels；
Second convolution unit includes third convolutional layer and Volume Four lamination and the third convolutional layer and Volume Four lamination
It include 16 3 × 3 convolution kernels；
The third convolution unit includes the 5th convolutional layer and the 5th convolutional layer includes 160 7 × 7 convolution kernels.
6. traffic sign recognition method according to claim 4, which is characterized in that
First pond layer and the second pond layer be average pond layer and the pond window for being averaged pond layer be 2 ×
2。
7. a kind of storage device, wherein being stored with a plurality of program, which is characterized in that described program is suitable for being loaded by processor to hold
Row traffic sign recognition method of any of claims 1-6.
8. a kind of control device, including processor and storage equipment, the storage equipment are suitable for storing a plurality of program, feature exists
In described program, which is suitable for being loaded as the processor, requires Traffic Sign Recognition side described in any one of 1-6 with perform claim
Method.
9. a kind of car-mounted terminal, it is characterised in that including control device according to any one of claims 8.
10. a kind of vehicle, it is characterised in that including car-mounted terminal as claimed in claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810658519.7A CN108960308A (en) | 2018-06-25 | 2018-06-25 | Traffic sign recognition method, device, car-mounted terminal and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810658519.7A CN108960308A (en) | 2018-06-25 | 2018-06-25 | Traffic sign recognition method, device, car-mounted terminal and vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108960308A true CN108960308A (en) | 2018-12-07 |
Family
ID=64486227
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810658519.7A Pending CN108960308A (en) | 2018-06-25 | 2018-06-25 | Traffic sign recognition method, device, car-mounted terminal and vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108960308A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109901595A (en) * | 2019-04-16 | 2019-06-18 | 山东大学 | A kind of automated driving system and method based on monocular cam and raspberry pie |
| CN110188705A (en) * | 2019-06-02 | 2019-08-30 | 东北石油大学 | A kind of remote road traffic sign detection recognition methods suitable for onboard system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103366190A (en) * | 2013-07-26 | 2013-10-23 | 中国科学院自动化研究所 | Method for identifying traffic sign |
| CN104700099A (en) * | 2015-03-31 | 2015-06-10 | 百度在线网络技术（北京）有限公司 | Method and device for recognizing traffic signs |
| CN104992165A (en) * | 2015-07-24 | 2015-10-21 | 天津大学 | Extreme learning machine based traffic sign recognition method |
| US20160140438A1 (en) * | 2014-11-13 | 2016-05-19 | Nec Laboratories America, Inc. | Hyper-class Augmented and Regularized Deep Learning for Fine-grained Image Classification |
| CN107247949A (en) * | 2017-08-02 | 2017-10-13 | 北京智慧眼科技股份有限公司 | Face identification method, device and electronic equipment based on deep learning |
| CN107301383A (en) * | 2017-06-07 | 2017-10-27 | 华南理工大学 | A kind of pavement marking recognition methods based on Fast R CNN |
| CN107609485A (en) * | 2017-08-16 | 2018-01-19 | 中国科学院自动化研究所 | The recognition methods of traffic sign, storage medium, processing equipment |
-
2018
- 2018-06-25 CN CN201810658519.7A patent/CN108960308A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103366190A (en) * | 2013-07-26 | 2013-10-23 | 中国科学院自动化研究所 | Method for identifying traffic sign |
| US20160140438A1 (en) * | 2014-11-13 | 2016-05-19 | Nec Laboratories America, Inc. | Hyper-class Augmented and Regularized Deep Learning for Fine-grained Image Classification |
| CN104700099A (en) * | 2015-03-31 | 2015-06-10 | 百度在线网络技术（北京）有限公司 | Method and device for recognizing traffic signs |
| CN104992165A (en) * | 2015-07-24 | 2015-10-21 | 天津大学 | Extreme learning machine based traffic sign recognition method |
| CN107301383A (en) * | 2017-06-07 | 2017-10-27 | 华南理工大学 | A kind of pavement marking recognition methods based on Fast R CNN |
| CN107247949A (en) * | 2017-08-02 | 2017-10-13 | 北京智慧眼科技股份有限公司 | Face identification method, device and electronic equipment based on deep learning |
| CN107609485A (en) * | 2017-08-16 | 2018-01-19 | 中国科学院自动化研究所 | The recognition methods of traffic sign, storage medium, processing equipment |
Non-Patent Citations (2)
| Title |
|---|
| 朱东涛等: "基于双通路跃层卷积网络的交通标志识别算法", 《安徽建筑大学学报》 * |
| 聂旎: "基于图像视频的行车环境交通对象检测与识别算法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109901595A (en) * | 2019-04-16 | 2019-06-18 | 山东大学 | A kind of automated driving system and method based on monocular cam and raspberry pie |
| CN110188705A (en) * | 2019-06-02 | 2019-08-30 | 东北石油大学 | A kind of remote road traffic sign detection recognition methods suitable for onboard system |
| CN110188705B (en) * | 2019-06-02 | 2022-05-06 | 东北石油大学 | Remote traffic sign detection and identification method suitable for vehicle-mounted system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104794883B (en) | Taxi taking method and apparatus | |
| CN109426262A (en) | Shared processing to deep neural network | |
| CN107571867A (en) | Method and apparatus for controlling automatic driving vehicle | |
| US11797845B2 (en) | Model learning device, model learning method, and program | |
| CN103838772B (en) | A kind of multi-source traffic data fusion method | |
| DE102016221467B4 (en) | Method for determining a user authorization of a user of a motor vehicle | |
| CN105303823B (en) | Rule-breaking vehicle monitoring method and system | |
| CN109101914A (en) | It is a kind of based on multiple dimensioned pedestrian detection method and device | |
| CN107203738A (en) | Vehicle lane boundary alignment | |
| WO2015155029A1 (en) | Locating a head-mounted display (hmd) in a vehicle | |
| EP3819823B1 (en) | Object detection method and apparatus, computer system, and readable storage medium | |
| CN108197526A (en) | Detection method, system and computer readable storage medium | |
| DE112012005624T5 (en) | System for creating a spanning forest in a vehicle network | |
| CN108960261A (en) | A kind of obvious object detection method based on attention mechanism | |
| CN109003297A (en) | A kind of monocular depth estimation method, device, terminal and storage medium | |
| CN111723854B (en) | Expressway traffic jam detection method, equipment and readable storage medium | |
| CN109387210A (en) | Automobile navigation method and its device | |
| CN108960308A (en) | Traffic sign recognition method, device, car-mounted terminal and vehicle | |
| CN108036796A (en) | Navigation picture display methods, device and vehicle electronic device | |
| CN109866684A (en) | Lane departure warning method, system, readable storage medium storing program for executing and computer equipment | |
| CN112766206B (en) | High-order video vehicle detection method and device, electronic equipment and storage medium | |
| CN115631205B (en) | Method, device and equipment for image segmentation and model training | |
| CN117809275B (en) | Environment sensing method and system based on 360-degree circular system of civil aviation vehicle | |
| CN109345512A (en) | Processing method, device and the readable storage medium storing program for executing of automobile image | |
| DE102018132487A1 (en) | VEHICLE MONITORING OF INFRASTRUCTURE LIGHTING |
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 |
Application publication date: 20181207 |
|
| RJ01 | Rejection of invention patent application after publication |