CN106092114A - The automobile real scene navigation apparatus of a kind of image recognition and method - Google Patents
The automobile real scene navigation apparatus of a kind of image recognition and method Download PDFInfo
- Publication number
- CN106092114A CN106092114A CN201610461454.8A CN201610461454A CN106092114A CN 106092114 A CN106092114 A CN 106092114A CN 201610461454 A CN201610461454 A CN 201610461454A CN 106092114 A CN106092114 A CN 106092114A
- Authority
- CN
- China
- Prior art keywords
- information
- module
- real scene
- road
- traffic marking
- 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
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
- Instructional Devices (AREA)
Abstract
The invention discloses a kind of automobile real scene navigation apparatus and the method for image recognition, including analysis module, picture recognition module, GPS locating module, path planning module, management map module, real scene navigation management module;Described analysis module is connected with picture recognition module;Described real scene navigation management module is connected with picture recognition module, GPS locating module, management map module, path planning module respectively;Map denotation is provided by car navigation device, path indicates, image in conjunction with drive recorder collection carries out image recognition, identification especially for the traffic marking board of changeable driveway, how prompting and prompting user select turning roadway or Through Lane when close to crossing, user is reminded to travel or parking according to actual traffic RST, it is achieved real scene navigation.Add the New function of auto navigation, add Consumer's Experience impression.
Description
Technical field
The invention belongs to technical field of automobile control, particularly relate to automobile real scene navigation apparatus and the side of a kind of image recognition
Method.
Background technology
Along with the universal of digital photographing technique, GPS location technology and wireless Internet and development, associated vehicle navigation sets
Standby, the automotive accessory such as drive recorder is provided with 1080P the most high-resolution video acquisition ability, and centimetre rank is fixed
The GPS of position, the wireless transmission rate of stable 100Mbps.Traditional drive recorder general record running car overall process
Video image and sound, do not have other expanded functions;Traditional car navigation device typically uses built-in or network map side
Formula combines GPS location technology, and the method using map denotation and path to indicate carries out auto navigation, is not bound with drive recorder
The image gathered carries out real scene navigation;The mode having some automobile real scene navigation equipment to have collection outdoor scene video combines map and shows
Show and method that path indicates, or calculate the traffic flow in a plurality of road track, but cannot in conjunction with image recognition technology,
How prompting and prompting user select turning roadway or Through Lane when close to crossing, it is impossible to judge the traffic mark of changeable driveway
Show board, it is impossible to remind user to travel or parking according to actual traffic RST.
Summary of the invention
The invention solves the problems that technical problem is to provide automobile real scene navigation apparatus and the method for a kind of image recognition, use existing
Some Video Analysis Technologies, image recognition technology, GPS location technology, Path Planning Technique etc., by information-based means and hardware
The design of equipment, it is achieved automobile real scene navigation function.
In order to solve above-mentioned technical problem, concrete technical scheme of the present invention is as follows:
A kind of automobile real scene navigation apparatus of image recognition, including: analysis module, picture recognition module, GPS positions
Module, path planning module, management map module, real scene navigation management module;
Described analysis module is connected with picture recognition module;
Described real scene navigation management module respectively with picture recognition module, GPS locating module, management map module, road
Footpath planning module connects;
Described management map module is for providing the related roads information in running car region;
Described real scene navigation management module for integrated real scene image identification information, latitude and longitude information, routing information and
Road information, and showing that interface shows in real time;
The automobile real scene navigation method of a kind of image recognition is as follows:
Real scene navigation management Module cycle performs following steps
Step S1, GPS locating module extracts the latitude and longitude information of running car;
Step S2, management map module is for providing the related roads information in running car region;
Step S3, path planning module is according to latitude and longitude information, the related roads information of running car and arrives at
The routing information needed, it is provided that automobile is to turn around, turn left, keep straight on or the track selecting party such as right-hand bend at previous crossing
Formula;
Step S4, analysis module gathers the real-time video information of automobilism, analyzes and extract key frame of video,
It is stored as key frame images file;
Step S5, picture recognition module analysis of key two field picture file, analyze the current moment, if mould on daytime
Formula, proceeds to step S6, is otherwise night mode, proceeds to step S7;
Step S6, arranges day mode parameter, proceeds to step S8;
Step S7, arranges night mode parameter, proceeds to step S8;
Step S8, picture recognition module analysis of key two field picture file, traffic marking board information, road traffic marking information
With traffic light information, and store information;
Step S9, it is judged that whether road traffic marking information is that road junction roadway indicates, if it is, proceed to step S10, if
No, proceed to step 12;
Step S10, it is judged that within time threshold T1, if having traffic marking board information, if it is, proceed to step
S11, if it does not, proceed to step 12;
Step S11, it is judged that turning around, turn left, keep straight on or turning right in traffic marking board information, maps that to
Road traffic marking information turns around, turns left, keeps straight on or turns right, the choosing lane mode provided according to path planning module,
Determine choosing lane information;
Step S12, it may be judged whether have traffic light information, if it has, proceed to step S13, if it does not, proceed to step
16;
Step S13, it is judged that within time threshold T2, if having choosing lane information, if it is, proceed to step S14,
If it does not, proceed to step 15;
Step S14, judges the track clearance sign situation in traffic light information according to choosing lane information: travel or
Person's parking, proceeds to step S16;
Step S15, directly judges the track clearance sign situation in traffic light information: travel or parking;
Step S16, real scene navigation management module integrated real scene image identification information, latitude and longitude information, routing information and road
Road information, and showing that interface outdoor scene shows, it is provided that to driver's choosing lane, travel or parking prompting;
The present invention has beneficial effect: the invention provides the new method of the automobile real scene navigation of a kind of image recognition, logical
Crossing car navigation device and provide map denotation, path indicates, and the image in conjunction with drive recorder collection carries out image recognition, especially
The identification of the traffic marking board for changeable driveway, point out and remind user how to select when close to crossing turning roadway or
Through Lane, reminds user to travel or parking according to actual traffic RST, it is achieved real scene navigation.Add auto navigation
New function, adds Consumer's Experience impression.
The concrete beneficial effect of patent of the present invention can be embodied in following aspect:
Analysis module uses keyframe techniques, can remove major part in outdoor scene video information and repeat frame of video, subtract
The data amount of calculation of few coupling, improves treatment effeciency;
Picture recognition module uses medium filtering and Morphological scale-space method to eliminate the noise in key frame images file, fall
The error rate of low coupling, uses the method identification zone boundary of structure Polygonal Boundary, improves objectives discrimination, uses not
Bending moment feature all has invariance for translation, rotation and the proportional zoom of objectives, makes objectives have higher knowledge
Not rate;
By analysis of key two field picture file in the automobile real scene navigation method of a kind of image recognition, when analyzing current
Carving is daytime or night mode, can use the different parameters being adapted to daytime or night mode, for daytime or night
Evening, different scene, made objectives have higher discrimination;
By collecting and judging in the automobile real scene navigation method of a kind of image recognition: ground road traffic marking is believed
Whether breath is that road junction roadway indicates, the shape that turns around, turns left, keeps straight on or turn right in the traffic marking board information that roadside is set up
State, crossing is set up the many-sided integrated informations relevant to real scene navigation such as traffic light information, many information sources, is made
Driver's choosing lane, travels or the decision information calculating of parking has higher accuracy rate;
Accompanying drawing explanation
Fig. 1 is the population structure schematic diagram of the automobile real scene navigation apparatus of a kind of image recognition.
Fig. 2 is the flow chart of the automobile real scene navigation method of a kind of image recognition.
Fig. 3 is correlation map road information and the path planning schematic diagram in running car region.
Fig. 4 is the key frame of traffic marking board information in scene on daytime.
Fig. 5 be daytime scene extract the schematic diagram of traffic marking board information.
Fig. 6 is the key frame of road traffic marking information in scene on daytime.
Fig. 7 be daytime scene extract the schematic diagram of road traffic marking information.
Fig. 8 is the key frame of traffic light red light information in scene on daytime.
Fig. 9 be daytime scene extract the schematic diagram of traffic light red light information.
Figure 10 is the key frame of traffic light green light information in scene on daytime.
Figure 11 be daytime scene extract the schematic diagram of traffic light green light information.
Figure 12 is the key frame of traffic marking board information in changeable driveway scene.
Figure 13 is the schematic diagram that changeable driveway scene extracts traffic marking board information.
Figure 14 is the key frame of road traffic marking information in changeable driveway scene.
Figure 15 is the schematic diagram that changeable driveway scene extracts road traffic marking information.
Figure 16 is the key frame of traffic marking board information in scene that turns around.
Figure 17 is that the scene that turns around extracts the schematic diagram of traffic marking board information.
Figure 18 is the key frame of road traffic marking information in scene that turns around.
Figure 19 is that the scene that turns around extracts the schematic diagram of road traffic marking information.
Figure 20 is the key frame of traffic marking board information in night-time scene.
Figure 21 is the schematic diagram that night-time scene extracts traffic marking board information.
Figure 22 is the key frame of road traffic marking information in night-time scene.
Figure 23 is the schematic diagram that night-time scene extracts road traffic marking information.
Label declaration: 1-analysis module, 2-picture recognition module, 3-GPS locating module, 4-path planning module,
5-management map module, 6-real scene navigation management module.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Describe wholely.
The population structure schematic diagram of the automobile real scene navigation apparatus of a kind of image recognition as shown in Figure 1 understands, and it includes
1-analysis module, 2-picture recognition module, 3-GPS locating module, 4-path planning module, 5-management map module, 6-
Real scene navigation management module.
Described analysis module 1 is connected with picture recognition module 2;
Described real scene navigation management module 6 respectively with picture recognition module 2, GPS locating module 3, management map module
4, path planning module 5 connects;
The outdoor scene video information that described analysis module 1 gathers for analytical equipment, extracts key frame of video, storage
For key frame images file;
Described picture recognition module 2 is for identifying the traffic marking board information in key frame images file, and road is handed over
Logical graticule information, traffic light information;
Described GPS locating module 3 is for providing the latitude and longitude information of running car;
Described path planning module 4 is for providing the routing information arriving at needs;
Described management map module 5 is for providing the related roads information in running car region;
Described real scene navigation management module 6 for integrated real scene image identification information, latitude and longitude information, routing information and
Road information, and showing that interface shows in real time;
The outdoor scene video information that described analysis module gathers for analytical equipment;Extract key frame of video, storage
For key frame images file;Key frame is a frame or the combination of multiple image, the key frame of main contents in outdoor scene video information
Abstracting method be to judge similarity degree between all successive image frames in outdoor scene video information, use visual characteristic such as face
Color, motion etc. are criterion;
Described picture recognition module is for identifying the traffic marking board information in key frame images file, road traffic
Graticule information, traffic light information;Method particularly includes: initially with the medium filtering in image recognition and Morphological scale-space side
Method eliminates the noise in key frame images file, then the method identification region of the structure Polygonal Boundary in employing image recognition
Objectives are also identified in border, finally use and calculate objectives invariant moment features and traffic marking board, road traffic marking,
The distance of the invariant moment features of traffic light, it is judged that the actual information of objectives;
L1 carrier wave and the L2 that frequency is 1227.60MHz that described GPS locating module uses frequency to be 1575.42MHz carry
Ripple, for providing the latitude and longitude information of running car;
Described path planning module uses Dijkstra's algorithm, for providing the path letter arriving at needs
Breath.
The following is the embodiment that inventor provides:
Flow process is as shown in Figure 2.
Embodiment 1: automobile real scene navigation scene on daytime
Following steps are performed successively by vehicle running route
The process step of two field picture shown in Fig. 4:
GPS locating module 3 extracts the latitude and longitude information of running car;
Management map module 5 is according to the latitude and longitude information of running car, it is provided that the phase in running car region as shown in Figure 3
Close road information;
Path planning module 4 is according to latitude and longitude information, the related roads information of running car and arrives at needs
Routing information, it is provided that the prompting kept straight at previous crossing to automobile;
Analysis module 1 gathers the real-time video information of automobilism, analyzes and extracts key frame of video, being stored as
Key frame images file as shown in Figure 4;
Picture recognition module 2 analysis of key two field picture file, analyzing the current moment is day mode;
Day mode parameter is set, adjusts suitable brightness, contrast, denoising parameter;
Picture recognition module 2 analyzes key frame images file as shown in Figure 4, traffic marking board information, road traffic mark
Line information and traffic light information are as it is shown in figure 5, and store information;
Judge whether road traffic marking information is that road junction roadway indicates, no;
Determine whether traffic light information, no;
Real scene navigation management module 6 integrated real scene image identification information, latitude and longitude information, routing information and road information,
And showing that interface outdoor scene shows, it is provided that travel prompting to driver;
Two field picture shown in Fig. 6 processes step
Picture recognition module 2 analyzes key frame images file as shown in Figure 6, traffic marking board information, road traffic mark
Line information and traffic light information are as it is shown in fig. 7, and store information;
Judge whether road traffic marking information is that road junction roadway indicates, be;
Judge within time threshold T1, the T1=100 second, if having traffic marking board information, be;
Judge the traffic marking board information as shown in Figure 5 identified from Fig. 4, be followed successively by from left to right: craspedodrome 1, keep straight on
2, turn right;Map that to the road traffic marking information as shown in Figure 7 identified from Fig. 6, be followed successively by from left to right: keep straight on
1, craspedodrome 2, turn right;The prompting kept straight in the crossing provided according to path planning module 4, determines selection track craspedodrome 1 or craspedodrome 2;
Judge from whether Fig. 6 identifies traffic light information, as it is shown in fig. 7, no;
Real scene navigation management module 6 integrated real scene image identification information, latitude and longitude information, routing information and road information,
And showing that interface outdoor scene shows, it is provided that point out to driver's choosing lane;
Two field picture shown in Fig. 8 processes step
Picture recognition module 2 analyzes key frame images file as shown in Figure 8, traffic marking board information, road traffic mark
Line information and traffic light information are as it is shown in figure 9, and store information;
Judge whether road traffic marking information is that road junction roadway indicates, be;
Judge within time threshold T1, the T1=100 second, if having traffic marking board information, be;
Judge the traffic marking board information as shown in Figure 5 identified from Fig. 4, be followed successively by from left to right: keep straight on, keep straight on,
Turn right;Map that to the road traffic marking information as shown in Figure 7 identified from Fig. 6, be followed successively by from left to right: keep straight on,
Keep straight on, turn right;The prompting kept straight in the crossing provided according to path planning module 4, determines selection track craspedodrome 2;
Judge from whether Fig. 8 identifies traffic light information, as it is shown in figure 9, be;
Judge within time threshold T2, the T2=90 second, if having choosing lane information, be;
The track clearance sign situation in traffic light information is judged according to choosing lane information, owing to being red light, and
And have waiting time of 24 seconds, then parking;
Real scene navigation management module 6 integrated real scene image identification information, latitude and longitude information, routing information and road information,
And showing that interface outdoor scene shows, it is provided that point out to driver's parking;
Two field picture shown in Figure 10 processes step
Picture recognition module 2 analyzes key frame images file as shown in Figure 10, traffic marking board information, road traffic mark
Line information and traffic light information as shown in figure 11, and store information;
Judge from whether Figure 10 identifies traffic light information, as shown in figure 11, be;
Judge within time threshold T1, the T1=100 second, if having traffic marking board information, be;
Judge the traffic marking board information as shown in Figure 5 identified from Fig. 4, be followed successively by from left to right: keep straight on, keep straight on,
Turn right;Map that to the road traffic marking information as shown in Figure 7 identified from Fig. 6, be followed successively by from left to right: keep straight on,
Keep straight on, turn right;The prompting kept straight in the crossing provided according to path planning module 4, determines selection track craspedodrome 2;
Judge from whether Figure 10 identifies traffic light information, as shown in figure 11, be;
Judge within time threshold T2, the T2=90 second, if having choosing lane information, be;
The track clearance sign situation in traffic light information is judged, owing to being green light, then according to choosing lane information
Travel;
Real scene navigation management module 6 integrated real scene image identification information, latitude and longitude information, routing information and road information,
And showing that interface outdoor scene shows, it is provided that travel prompting to driver;
Embodiment 2: automobile real scene navigation changeable driveway scene;
Following steps are performed successively by vehicle running route;
The process step of two field picture shown in Figure 12:
GPS locating module 3 extracts the latitude and longitude information of running car;
Management map module 5 is according to the latitude and longitude information of running car, it is provided that the related roads information in running car region;
Path planning module 4 is according to latitude and longitude information, the related roads information of running car and arrives at needs
Routing information, it is provided that the prompting kept straight at previous crossing to automobile;
Analysis module 1 gathers the real-time video information of automobilism, analyzes and extracts key frame of video, being stored as
Key frame images file as shown in figure 12;
Picture recognition module 2 analysis of key two field picture file, analyzing the current moment is day mode;
Day mode parameter is set, adjusts suitable brightness, contrast, denoising parameter;
Picture recognition module 2 analyzes key frame images file as shown in figure 12, traffic marking board information, road traffic mark
Line information and traffic light information as shown in figure 13, and store information;
Judge whether road traffic marking information is that road junction roadway indicates, no;
Determine whether traffic light information, no;
Real scene navigation management module 6 integrated real scene image identification information, latitude and longitude information, routing information and road information,
And showing interface outdoor scene display changeable driveway, it is provided that travel prompting to driver;
Two field picture shown in Figure 14 processes step
Picture recognition module 2 analyzes key frame images file as shown in figure 14, traffic marking board information, road traffic mark
Line information and traffic light information are as it is shown in fig. 7, and store information;
Judge whether road traffic marking information is that road junction roadway indicates, be;
Judge within time threshold T1, the T1=100 second, if having traffic marking board information, be;
Judge the board information of traffic marking as shown in fig. 13 that identified from Figure 12, be followed successively by from left to right: turn left, keep straight on
1, craspedodrome 2, turn right;Map that to the road traffic marking information as shown in figure 15 identified from Figure 14, before mapping from
Left-to-right is followed successively by: turn left, and changeable driveway is kept straight on, changeable driveway;It is followed successively by from left to right after mapping: turn left, craspedodrome 1, directly
Row 2, turns right;The prompting kept straight in the crossing provided according to path planning module 4, determines selection track craspedodrome 2;
Judge from whether Figure 14 identifies traffic light information, as shown in figure 15, no;
Real scene navigation management module 6 integrated real scene image identification information, latitude and longitude information, routing information and road information,
And showing that interface outdoor scene shows, it is provided that point out to driver's choosing lane;
Embodiment 3: automobile real scene navigation turns around scene
Following steps are performed successively by vehicle running route
The process step of two field picture shown in Figure 16:
GPS locating module 3 extracts the latitude and longitude information of running car;
Management map module 5 is according to the latitude and longitude information of running car, it is provided that the related roads information in running car region;
Path planning module 4 is according to latitude and longitude information, the related roads information of running car and arrives at needs
Routing information, it is provided that the prompting kept straight at previous crossing to automobile;
Analysis module 1 gathers the real-time video information of automobilism, analyzes and extracts key frame of video, being stored as
Key frame images file as shown in figure 16;
Picture recognition module 2 analysis of key two field picture file, analyzing the current moment is day mode;
Day mode parameter is set, adjusts suitable brightness, contrast, denoising parameter;
Picture recognition module 2 analyzes key frame images file as shown in figure 16, traffic marking board information, road traffic mark
Line information and traffic light information as shown in figure 17, and store information;
Judge whether road traffic marking information is that road junction roadway indicates, no;
Determine whether traffic light information, no;
Real scene navigation management module 6 integrated real scene image identification information, latitude and longitude information, routing information and road information,
And showing that interface outdoor scene shows, it is provided that travel prompting to driver;
Two field picture shown in Figure 18 processes step
Picture recognition module 2 analyzes key frame images file as shown in figure 18, traffic marking board information, road traffic mark
Line information and traffic light information as shown in figure 19, and store information;
Judge whether road traffic marking information is that road junction roadway indicates, be;
Judge within time threshold T1, the T1=100 second, if having traffic marking board information, be;
Judge the traffic marking board information as shown in figure 17 identified from Figure 16, be followed successively by from left to right: turn around or left
Turn, turn left, turn right, turn right;Map that to the road traffic marking information as shown in figure 19 identified from Figure 18, from a left side to
The right side is followed successively by: turns around or turns left, and turns left, and turns right, and turns right;The prompting kept straight in the crossing provided according to path planning module 4, determines
Track is selected to turn around or turn left;
Judge from whether Figure 18 identifies traffic light information, as shown in figure 19, no;
Real scene navigation management module 6 integrated real scene image identification information, latitude and longitude information, routing information and road information,
And showing that interface outdoor scene shows, it is provided that point out to driver's choosing lane;
Embodiment 4: automobile real scene navigation night-time scene
Following steps are performed successively by vehicle running route
The process step of two field picture shown in Figure 20:
GPS locating module 3 extracts the latitude and longitude information of running car;
Management map module 5 is according to the latitude and longitude information of running car, it is provided that the related roads information in running car region;
Path planning module 4 is according to latitude and longitude information, the related roads information of running car and arrives at needs
Routing information, it is provided that the prompting kept straight at previous crossing to automobile;
Analysis module 1 gathers the real-time video information of automobilism, analyzes and extracts key frame of video, being stored as
Key frame images file as shown in figure 20;
Picture recognition module 2 analysis of key two field picture file, analyzing the current moment is night mode;
Night mode parameter is set, adjusts suitable brightness, contrast, denoising parameter;
Picture recognition module 2 analyzes key frame images file as shown in figure 20, traffic marking board information, road traffic mark
Line information and traffic light information as shown in figure 21, and store information;
Judge whether road traffic marking information is that road junction roadway indicates, no;
Determine whether traffic light information, no;
Real scene navigation management module 6 integrated real scene image identification information, latitude and longitude information, routing information and road information,
And showing that interface outdoor scene shows, it is provided that travel prompting to driver;
Two field picture shown in Figure 22 processes step
Picture recognition module 2 analyzes key frame images file as shown in figure 22, traffic marking board information, road traffic mark
Line information and traffic light information are as it is shown in fig. 7, and store information;
Judge whether road traffic marking information is that road junction roadway indicates, be;
Judge within time threshold T1, the T1=100 second, if having traffic marking board information, be;
Judge the traffic marking board information as shown in figure 21 identified from Figure 20, be followed successively by from left to right: craspedodrome 1, directly
Row 2, keeps straight on and turns right;Map that to the road traffic marking information as shown in figure 23 identified from Figure 22, depend on from left to right
Secondary it is: keep straight on 1 to keep straight on 2, keeps straight on and turn right;The prompting kept straight in the crossing provided according to path planning module 4, determines selection track
Keep straight on and turn right;
Judge from whether Figure 22 identifies traffic light information, as shown in figure 23, no;
Real scene navigation management module 6 integrated real scene image identification information, latitude and longitude information, routing information and road information,
And showing that interface outdoor scene shows, it is provided that point out to driver's choosing lane.
In the description of this specification, reference term " embodiment ", " some embodiments ", " illustrative examples ",
The description of " example ", " concrete example " or " some examples " etc. means to combine this embodiment or the specific features of example description, knot
Structure, material or feature are contained at least one embodiment or the example of the present invention.In this manual, to above-mentioned term
Schematic representation is not necessarily referring to identical embodiment or example.And, the specific features of description, structure, material or spy
Point can combine in any one or more embodiments or example in an appropriate manner.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that: not
These embodiments can be carried out multiple change in the case of departing from the principle of the present invention and objective, revise, replace and modification, this
The scope of invention is limited by claim and equivalent thereof.
Claims (4)
1. the automobile real scene navigation apparatus of an image recognition, it is characterised in that include analysis module, image recognition mould
Block, GPS locating module, path planning module, management map module, real scene navigation management module;
Described analysis module is connected with picture recognition module;
Described real scene navigation management module is advised with picture recognition module, GPS locating module, management map module, path respectively
Draw module to connect;
The outdoor scene video information that described analysis module gathers for analytical equipment, extracts key frame of video, is stored as closing
Key two field picture file;
Described picture recognition module is for identifying the traffic marking board information in key frame images file, road traffic marking
Information, traffic light information;
Described GPS locating module is for providing the latitude and longitude information of running car;
Described path planning module arrives at the routing information of needs for providing;
Described management map module is for providing the related roads information in running car region;
Described real scene navigation management module is for integrated real scene image identification information, latitude and longitude information, routing information and road
Information, and showing that interface shows in real time.
The automobile real scene navigation apparatus of a kind of image recognition the most according to claim 1, it is characterised in that described GPS
L1 carrier wave that locating module uses frequency to be 1575.42MHz and L2 carrier wave that frequency is 1227.60MHz.
3. the automobile real scene navigation method of an image recognition, it is characterised in that comprise the following steps:
Step S1, GPS locating module extracts the latitude and longitude information of running car;
Step S2, management map module is for providing the related roads information in running car region;
Step S3, path planning module is according to latitude and longitude information, the related roads information of running car and arrives at needs
Routing information, it is provided that automobile is to turn around, turn left, keep straight on or the track selection mode such as right-hand bend at previous crossing;
Step S4, analysis module gathers the real-time video information of automobilism, analyzes and extract key frame of video, storage
For key frame images file;
Step S5, picture recognition module analysis of key two field picture file, analyze the current moment, if day mode, turn
Enter step S6, be otherwise night mode, proceed to step S7;
Step S6, arranges day mode parameter, proceeds to step S8;
Step S7, arranges night mode parameter, proceeds to step S8;
Step S8, picture recognition module analysis of key two field picture file, traffic marking board information, road traffic marking information and friendship
Ventilating signal lamp information, and store information;
Step S9, it is judged that whether road traffic marking information is that road junction roadway indicates, if it is, proceed to step S10, if it does not,
Proceed to step 12;
Step S10, it is judged that within time threshold T1, if having traffic marking board information, if it is, proceed to step S11, as
The most no, proceed to step 12;
Step S11, it is judged that turning around, turn left, keep straight on or turning right in traffic marking board information, maps that to road and hands over
Logical graticule information turns around, turns left, keeps straight on or turns right, and the choosing lane mode provided according to path planning module determines
Choosing lane information;
Step S12, it may be judged whether have traffic light information, if it has, proceed to step S13, if it does not, proceed to step 16;
Step S13, it is judged that within time threshold T2, if having choosing lane information, if it is, proceed to step S14, if
No, proceed to step 15;
Step S14, judges the track clearance sign situation in traffic light information: travel or stay according to choosing lane information
Car, proceeds to step S16;
Step S15, directly judges the track clearance sign situation in traffic light information: travel or parking;
Step S16, real scene navigation management module integrated real scene image identification information, latitude and longitude information, routing information and road letter
Breath, and showing that interface outdoor scene shows, it is provided that to driver's choosing lane, travel or parking prompting.
The automobile real scene navigation method of a kind of image recognition the most according to claim 3, it is characterised in that described step S8
Method particularly includes: eliminate in key frame images file initially with the medium filtering in image recognition and Morphological scale-space method
Noise, then use the method identification zone boundary of the structure Polygonal Boundary in image recognition and identify objectives,
Finally using and calculate objectives invariant moment features and traffic marking board, road traffic marking, the not bending moment of traffic light is special
The distance levied, it is judged that the actual information of objectives.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610461454.8A CN106092114A (en) | 2016-06-22 | 2016-06-22 | The automobile real scene navigation apparatus of a kind of image recognition and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610461454.8A CN106092114A (en) | 2016-06-22 | 2016-06-22 | The automobile real scene navigation apparatus of a kind of image recognition and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106092114A true CN106092114A (en) | 2016-11-09 |
Family
ID=57253275
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610461454.8A Pending CN106092114A (en) | 2016-06-22 | 2016-06-22 | The automobile real scene navigation apparatus of a kind of image recognition and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106092114A (en) |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108109437A (en) * | 2018-01-24 | 2018-06-01 | 广东容祺智能科技有限公司 | It is a kind of that generation method is extracted from main shipping track based on the unmanned plane of map feature |
CN108417028A (en) * | 2017-02-09 | 2018-08-17 | 丰田自动车株式会社 | Image processing system and image processing method |
CN108871369A (en) * | 2018-06-27 | 2018-11-23 | 威马智慧出行科技(上海)有限公司 | Vehicular navigation map-indication method, electronic equipment, server and storage medium |
CN109029488A (en) * | 2018-06-29 | 2018-12-18 | 百度在线网络技术(北京)有限公司 | Navigating electronic map generating method, equipment and storage medium |
CN109540161A (en) * | 2018-11-08 | 2019-03-29 | 东软睿驰汽车技术(沈阳)有限公司 | A kind of air navigation aid and device of vehicle |
CN109712423A (en) * | 2018-12-21 | 2019-05-03 | 江苏大学 | A kind of valet parking parking system and vehicle go out warehousing control method |
WO2019119359A1 (en) * | 2017-12-21 | 2019-06-27 | Bayerische Motoren Werke Aktiengesellschaft | Method, device and system for displaying augmented reality navigation information |
CN110276971A (en) * | 2019-07-03 | 2019-09-24 | 广州小鹏汽车科技有限公司 | A kind of auxiliary control method of vehicle drive, system and vehicle |
CN110320899A (en) * | 2018-03-30 | 2019-10-11 | 比亚迪股份有限公司 | Automobile and its travel control method |
CN110481560A (en) * | 2018-05-15 | 2019-11-22 | Aptiv技术有限公司 | Device and method for the lane that search vehicle can travel |
CN110530385A (en) * | 2019-08-21 | 2019-12-03 | 西安华运天成通讯科技有限公司 | City navigation method and its system based on image recognition |
CN110567476A (en) * | 2019-09-23 | 2019-12-13 | 东软睿驰汽车技术(沈阳)有限公司 | Navigation method and device |
CN110715666A (en) * | 2018-07-13 | 2020-01-21 | 上海博泰悦臻网络技术服务有限公司 | High-precision navigation method, system, medium and vehicle-mounted terminal based on vehicle-mounted camera device |
CN110736475A (en) * | 2018-07-19 | 2020-01-31 | 上海博泰悦臻网络技术服务有限公司 | Positioning optimization method and system based on vehicle-mounted camera device, storage medium and vehicle-mounted terminal |
CN110979350A (en) * | 2019-12-18 | 2020-04-10 | 奇瑞汽车股份有限公司 | AR navigation based on automobile data recorder |
CN111024115A (en) * | 2019-12-27 | 2020-04-17 | 奇瑞汽车股份有限公司 | Live-action navigation method, device, equipment, storage medium and vehicle-mounted multimedia system |
CN111213031A (en) * | 2018-12-06 | 2020-05-29 | 深圳市大疆创新科技有限公司 | Navigation processing method and device and navigation processing equipment |
CN111833629A (en) * | 2019-04-23 | 2020-10-27 | 上海博泰悦臻网络技术服务有限公司 | Special lane prompting method and system and vehicle |
CN111968364A (en) * | 2020-07-07 | 2020-11-20 | 王斌 | Driving method based on road right distribution, electronic equipment and storage medium |
CN112560728A (en) * | 2020-12-22 | 2021-03-26 | 上海哔哩哔哩科技有限公司 | Target object identification method and device |
CN113237487A (en) * | 2021-04-09 | 2021-08-10 | 烟台杰瑞石油服务集团股份有限公司 | Vision-aided navigation method and device |
CN115366899A (en) * | 2022-10-25 | 2022-11-22 | 南京项尚车联网技术有限公司 | Long-range on-vehicle route identification system based on big dipper |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102519475A (en) * | 2011-12-12 | 2012-06-27 | 杨志远 | Intelligent navigation method and equipment based on augmented reality technology |
CN102889892A (en) * | 2012-09-13 | 2013-01-23 | 东莞宇龙通信科技有限公司 | Live-action navigation method and navigation terminal |
KR20130040361A (en) * | 2011-10-14 | 2013-04-24 | 주식회사 엘지유플러스 | Method, server, and recording medium for providing traffic information based on ar navigation |
CN103105174A (en) * | 2013-01-29 | 2013-05-15 | 四川长虹佳华信息产品有限责任公司 | AR (augmented reality)-based vehicle-mounted live-action safe navigation method |
CN105547319A (en) * | 2015-12-11 | 2016-05-04 | 上海卓易科技股份有限公司 | Route planning implementation method adopting image recognition for live-action navigation |
-
2016
- 2016-06-22 CN CN201610461454.8A patent/CN106092114A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20130040361A (en) * | 2011-10-14 | 2013-04-24 | 주식회사 엘지유플러스 | Method, server, and recording medium for providing traffic information based on ar navigation |
CN102519475A (en) * | 2011-12-12 | 2012-06-27 | 杨志远 | Intelligent navigation method and equipment based on augmented reality technology |
CN102889892A (en) * | 2012-09-13 | 2013-01-23 | 东莞宇龙通信科技有限公司 | Live-action navigation method and navigation terminal |
CN103105174A (en) * | 2013-01-29 | 2013-05-15 | 四川长虹佳华信息产品有限责任公司 | AR (augmented reality)-based vehicle-mounted live-action safe navigation method |
CN105547319A (en) * | 2015-12-11 | 2016-05-04 | 上海卓易科技股份有限公司 | Route planning implementation method adopting image recognition for live-action navigation |
Cited By (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108417028A (en) * | 2017-02-09 | 2018-08-17 | 丰田自动车株式会社 | Image processing system and image processing method |
WO2019119359A1 (en) * | 2017-12-21 | 2019-06-27 | Bayerische Motoren Werke Aktiengesellschaft | Method, device and system for displaying augmented reality navigation information |
US11761783B2 (en) | 2017-12-21 | 2023-09-19 | Bayerische Motoren Werke Aktiengesellschaft | Method, device and system for displaying augmented reality navigation information |
CN108109437B (en) * | 2018-01-24 | 2021-01-12 | 广东容祺智能科技有限公司 | Unmanned aerial vehicle autonomous route extraction and generation method based on map features |
CN108109437A (en) * | 2018-01-24 | 2018-06-01 | 广东容祺智能科技有限公司 | It is a kind of that generation method is extracted from main shipping track based on the unmanned plane of map feature |
CN110320899A (en) * | 2018-03-30 | 2019-10-11 | 比亚迪股份有限公司 | Automobile and its travel control method |
CN110481560B (en) * | 2018-05-15 | 2023-05-30 | Aptiv技术有限公司 | Device and method for searching for a lane on which a vehicle can travel |
CN110481560A (en) * | 2018-05-15 | 2019-11-22 | Aptiv技术有限公司 | Device and method for the lane that search vehicle can travel |
CN108871369A (en) * | 2018-06-27 | 2018-11-23 | 威马智慧出行科技(上海)有限公司 | Vehicular navigation map-indication method, electronic equipment, server and storage medium |
CN108871369B (en) * | 2018-06-27 | 2022-08-19 | 威马智慧出行科技(上海)有限公司 | Vehicle navigation map display method, electronic device, server and storage medium |
CN109029488A (en) * | 2018-06-29 | 2018-12-18 | 百度在线网络技术(北京)有限公司 | Navigating electronic map generating method, equipment and storage medium |
CN110715666A (en) * | 2018-07-13 | 2020-01-21 | 上海博泰悦臻网络技术服务有限公司 | High-precision navigation method, system, medium and vehicle-mounted terminal based on vehicle-mounted camera device |
CN110736475A (en) * | 2018-07-19 | 2020-01-31 | 上海博泰悦臻网络技术服务有限公司 | Positioning optimization method and system based on vehicle-mounted camera device, storage medium and vehicle-mounted terminal |
CN109540161A (en) * | 2018-11-08 | 2019-03-29 | 东软睿驰汽车技术(沈阳)有限公司 | A kind of air navigation aid and device of vehicle |
CN111213031A (en) * | 2018-12-06 | 2020-05-29 | 深圳市大疆创新科技有限公司 | Navigation processing method and device and navigation processing equipment |
CN109712423A (en) * | 2018-12-21 | 2019-05-03 | 江苏大学 | A kind of valet parking parking system and vehicle go out warehousing control method |
CN109712423B (en) * | 2018-12-21 | 2021-05-25 | 江苏大学 | Passenger-riding parking lot system and vehicle in-out control method |
CN111833629A (en) * | 2019-04-23 | 2020-10-27 | 上海博泰悦臻网络技术服务有限公司 | Special lane prompting method and system and vehicle |
CN110276971A (en) * | 2019-07-03 | 2019-09-24 | 广州小鹏汽车科技有限公司 | A kind of auxiliary control method of vehicle drive, system and vehicle |
CN110530385A (en) * | 2019-08-21 | 2019-12-03 | 西安华运天成通讯科技有限公司 | City navigation method and its system based on image recognition |
CN110567476A (en) * | 2019-09-23 | 2019-12-13 | 东软睿驰汽车技术(沈阳)有限公司 | Navigation method and device |
CN110979350A (en) * | 2019-12-18 | 2020-04-10 | 奇瑞汽车股份有限公司 | AR navigation based on automobile data recorder |
CN111024115A (en) * | 2019-12-27 | 2020-04-17 | 奇瑞汽车股份有限公司 | Live-action navigation method, device, equipment, storage medium and vehicle-mounted multimedia system |
CN111968364A (en) * | 2020-07-07 | 2020-11-20 | 王斌 | Driving method based on road right distribution, electronic equipment and storage medium |
CN112560728A (en) * | 2020-12-22 | 2021-03-26 | 上海哔哩哔哩科技有限公司 | Target object identification method and device |
CN112560728B (en) * | 2020-12-22 | 2023-07-11 | 上海幻电信息科技有限公司 | Target object identification method and device |
CN113237487A (en) * | 2021-04-09 | 2021-08-10 | 烟台杰瑞石油服务集团股份有限公司 | Vision-aided navigation method and device |
CN115366899A (en) * | 2022-10-25 | 2022-11-22 | 南京项尚车联网技术有限公司 | Long-range on-vehicle route identification system based on big dipper |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106092114A (en) | The automobile real scene navigation apparatus of a kind of image recognition and method | |
Bock et al. | The ind dataset: A drone dataset of naturalistic road user trajectories at german intersections | |
Krajewski et al. | The round dataset: A drone dataset of road user trajectories at roundabouts in germany | |
US10901416B2 (en) | Scene creation system for autonomous vehicles and methods thereof | |
US10296794B2 (en) | On-demand artificial intelligence and roadway stewardship system | |
US9652980B2 (en) | Enhanced clear path detection in the presence of traffic infrastructure indicator | |
AU2019235551B2 (en) | On-demand artificial intelligence and roadway stewardship system | |
CN110717433A (en) | Deep learning-based traffic violation analysis method and device | |
US20180301031A1 (en) | A method and system for automatically detecting and mapping points-of-interest and real-time navigation using the same | |
US20140314279A1 (en) | Clear path detection using an example-based approach | |
CN107122385A (en) | Mapping road lighting | |
KR20180046798A (en) | Method and apparatus for real time traffic information provision | |
CN102867417B (en) | Taxi anti-forgery system and taxi anti-forgery method | |
US20100098297A1 (en) | Clear path detection using segmentation-based method | |
CN106778548A (en) | Method and apparatus for detecting barrier | |
Cao et al. | Amateur: Augmented reality based vehicle navigation system | |
JP5522475B2 (en) | Navigation device | |
CN114518122A (en) | Driving navigation method, driving navigation device, computer equipment, storage medium and computer program product | |
CN112396000A (en) | Method for constructing multi-mode dense prediction depth information transmission model | |
WO2023017317A1 (en) | Environmentally aware prediction of human behaviors | |
Coronado et al. | Detection and classification of road signs for automatic inventory systems using computer vision | |
Chen et al. | Video-based on-road driving safety system with lane detection and vehicle detection | |
CN107577995A (en) | The processing method and processing device of view data | |
Panda et al. | RECENT DEVELOPMENTS IN LANE DEPARTURE WARNING SYSTEM: AN ANALYSIS | |
Vasudha et al. | Carriageway Edge Detection for Unmarked Urban Roads using Deep Learning Techniques |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161109 |
|
RJ01 | Rejection of invention patent application after publication |