CN109299686A - A kind of parking stall recognition methods, device, equipment and medium - Google Patents
A kind of parking stall recognition methods, device, equipment and medium Download PDFInfo
- Publication number
- CN109299686A CN109299686A CN201811075501.0A CN201811075501A CN109299686A CN 109299686 A CN109299686 A CN 109299686A CN 201811075501 A CN201811075501 A CN 201811075501A CN 109299686 A CN109299686 A CN 109299686A
- Authority
- CN
- China
- Prior art keywords
- parking stall
- division line
- horizontal division
- rule
- pair
- 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
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/586—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a kind of parking stall recognition methods, device, equipment and media, which comprises according to the parking stall identification request detected, unilateral overhead view image corresponding with parking stall identification request is extracted from current panorama image；The vertical cut-off rule at least one parking stall corresponding at least a pair of of parking stall horizontal division line and at least a pair of of parking stall horizontal division line is extracted from the unilateral overhead view image according to preset algorithm；The position of the parking stall is determined according at least a pair of of parking stall horizontal division line and the vertical cut-off rule in the parking stall.Parking stall recognition methods provided by the embodiment of the present invention identifies that request is chosen according to parking stall and is calculated with unilateral overhead view image, improves computational efficiency, and can calculate the specific location of parking stall.
Description
Technical field
The present embodiments relate to vehicle electric field more particularly to a kind of parking stall recognition methods, device, equipment and Jie
Matter.
Background technique
The panoramic looking-around system of view-based access control model technology can provide vehicle-surroundings situation for driver, assist driver safety
Traveling, therefore be widely used.At present in the automatic parking technology of panoramic looking-around system, the identification of parking stall has ultrasonic radar technology
And image procossing two ways.Automatic parking technology based on ultrasonic radar technology is mainly according to the inspection of ultrasonic obstacle object
It surveys, carries out the navigation of automatic parking.Parking stall identification in viewing system based on image processing techniques is mainly according to whole picture
Overhead view image is looked around, edge detection scheduling algorithm is carried out, determines the position on parking stall.
But parking stall cannot be recognized accurately in spacious scene based on the identification of the parking stall of ultrasonic radar technology, it is difficult
Accurately to determine the specific location on parking stall.In viewing system based on image processing techniques parking stall identification computational efficiency compared with
It is low, and stopping guide line present in parking lot and parking stall cut-off rule location similarity are very high, also do not accurately distinguish,
It is difficult to accurately determine the specific location on parking stall.
Summary of the invention
The embodiment of the invention provides a kind of parking stall recognition methods, device, equipment and media, improve parking stall identification to realize
Computational efficiency, the accurate specific location for determining parking stall.
In a first aspect, the embodiment of the invention provides a kind of parking stall recognition methods, comprising:
According to the parking stall identification request detected, extracted from current panorama image corresponding with parking stall identification request
Unilateral overhead view image；
Extracted from the unilateral overhead view image according to preset algorithm at least a pair of of parking stall horizontal division line and it is described to
The vertical cut-off rule at least one parking stall corresponding to the horizontal division line of few a pair of parking stall；
The position of the parking stall is determined according at least a pair of of parking stall horizontal division line and the vertical cut-off rule in the parking stall.
Second aspect, the embodiment of the invention also provides a kind of stall recognition devices, comprising:
Image determining module, for being extracted from current panorama image and institute according to the parking stall identification request detected
It states parking stall identification and requests corresponding unilateral overhead view image；
Cut-off rule determining module, for extracting at least a pair of of parking stall from the unilateral overhead view image according to preset algorithm
The vertical cut-off rule at least one parking stall corresponding to horizontal division line and at least a pair of of parking stall horizontal division line；
Position determination module, for true according at least a pair of of parking stall horizontal division line and the vertical cut-off rule in the parking stall
The position of the fixed parking stall.
The third aspect, the embodiment of the invention also provides a kind of computer equipment, the equipment includes:
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes such as parking stall recognition methods provided by any embodiment of the invention.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program realizes such as parking stall recognition methods provided by any embodiment of the invention when the program is executed by processor.
Method for detecting parking stalls provided by the embodiment of the present invention is according to the parking stall identification request detected, from current panorama figure
Unilateral overhead view image corresponding with parking stall identification request is extracted as in, identifies that request is chosen and unilateral vertical view according to parking stall
Image is calculated, and computational efficiency is improved；At least a pair of of vehicle is extracted from the unilateral overhead view image according to preset algorithm
The vertical cut-off rule at least one parking stall corresponding to position horizontal division line and at least a pair of of parking stall horizontal division line；According to institute
It states at least a pair of of parking stall horizontal division line and the vertical cut-off rule in the parking stall determines the position of the parking stall, define parking stall
Specific location.
Detailed description of the invention
Fig. 1 a is the flow chart of method for detecting parking stalls provided by the embodiment of the present invention one；
Fig. 1 b is that Vehicle Speed provided by the embodiment of the present invention one calculates schematic diagram；
Fig. 2 a is the flow chart of method for detecting parking stalls provided by the embodiment of the present invention two；
Fig. 2 b is that line search schematic diagram is divided on parking stall provided by the embodiment of the present invention two vertically；
Fig. 3 is the flow chart of method for detecting parking stalls provided by the embodiment of the present invention three；
Fig. 4 is the structural schematic diagram of stall testing apparatus provided by the embodiment of the present invention four；
Fig. 5 is the structural schematic diagram of computer equipment provided by the embodiment of the present invention five.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 a is the flow chart of method for detecting parking stalls provided by the embodiment of the present invention one, and the present embodiment is applicable to certainly
Situation when carrying out parking stall identification when parking is moved, is particularly suitable for carrying out parking stall identification when the automatic parking in spacious scene
When situation.This method can be executed by stall testing apparatus, which can use the side of software and/or hardware
Formula is realized, for example, the stall testing apparatus is configured in computer equipment.As shown in Figure 1a, this method specifically includes:
S110, it is requested according to the parking stall identification detected, extracts from current panorama image and asked with parking stall identification
Seek corresponding unilateral overhead view image.
Optionally, identification request in parking stall can be user's triggering, for requesting the instruction of progress parking stall identification.In this reality
It applies in example, parking stall identification request can be the parking stall identification instruction for including parking stall identification region.In general, when driver drives
Vehicle enter parking lot or can parking area when carrying out the searching on parking stall, parking stall be located at the left side of vehicle heading with/
Or right side.In the present embodiment, parking stall identification region is the left or right side of vehicle heading.
In the present embodiment, the identification of parking stall is carried out based on panoramic looking-around system.When detecting parking stall identification request, root
It is extracted from panoramic picture according to the parking stall identification region for including in the identification request of parking stall corresponding with parking stall identification region unilateral
Overhead view image.The identification that parking stall is carried out with unilateral overhead view image corresponding to the identification region of parking stall, energy are extracted from panoramic picture
Enough make wider field of view corresponding to the image obtained, the region for being used in parking stall identification is wider.
Optionally, it when detecting parking stall identification request, is requested on corresponding vehicle all around based on parking stall identification
Set camera carries out the acquisition of image, after carrying out image rectification to each image and carry out perspective transform, is spliced to form this
The panoramic picture of vehicle-surroundings.According to parking stall identification region included in the identification request of parking stall, from the panorama sketch being spliced to form
It is extracted and unilateral overhead view image corresponding to the identification region of parking stall as in.That is, (such as according to the parking stall demand of user
Parking stall search is carried out on the left side and/or the right), it extracts and unilateral overhead view image corresponding to the demand of parking stall.Citing comes
It says, if parking stall identification region included in the identification request of parking stall is to take in panoramic picture and be located on the left of vehicle heading
The image of the left area of the middle line parallel with y-axis is as unilateral overhead view image corresponding to the parking stall identification region.
S120, at least a pair of of parking stall horizontal division line and institute are extracted from the unilateral overhead view image according to preset algorithm
State the vertical cut-off rule at least one parking stall corresponding at least a pair of of parking stall horizontal division line.
In the present embodiment, first according to preset algorithm identify unilateral overhead view image included in parking stall horizontal segmentation
Line, then search and at least one parking stall corresponding to the parking stall horizontal division line are perpendicular on the parking stall horizontal division line identified
Straight cut-off rule.Optionally, parking stall horizontal division line is the parking stall cut-off rule vertical with vehicle heading, the vertical cut-off rule in parking stall
For the parking stall cut-off rule parallel with vehicle heading.Provided parking stall recognition methods carries out parking stall through the embodiment of the present invention
Identification do not need to identify all edge lines of parking stall, the specific position of parking stall can be identified from the identification region of parking stall
It sets, and can be avoided the influence that other lines included in parking stall guide line or parking stall identification region generate parking stall identification,
It avoids identifying the parking stall to make mistake because of pseudo- parking stall cut-off rule.
S130, the parking stall is determined according at least a pair of of parking stall horizontal division line and the vertical cut-off rule in the parking stall
Position.
In the present embodiment, parking stall horizontal division line is the edge line in parking stall horizontal direction to be identified, and parking stall is divided vertically
Secant is the edge line on parking stall vertical direction to be identified.It optionally, can be according to a pair in parking stall horizontal direction to be identified
At least one edge line on edge line and vertical direction determines the specific location of parking stall to be identified.For example, can be according to be identified
The linear equation of parking stall edge line calculates the corner location coordinate of parking stall to be identified.
Optionally, after determining parking stall position, path planning can be carried out according to the specific location of parking stall, guides driver
It stops.
The embodiment of the present invention extracts and the parking stall according to the parking stall identification request detected from current panorama image
Corresponding unilateral overhead view image is requested in identification, is identified that request is chosen according to parking stall and is calculated with unilateral overhead view image, is improved
Computational efficiency；Extracted from the unilateral overhead view image according to preset algorithm at least a pair of of parking stall horizontal division line and it is described to
The vertical cut-off rule at least one parking stall corresponding to the horizontal division line of few a pair of parking stall；According at least a pair of of parking stall level point
The vertical cut-off rule of secant and the parking stall determines the position of the parking stall, defines the specific location on parking stall.
On the basis of above scheme, if not extracting at least a pair of of parking stall horizontal segmentation from the unilateral overhead view image
The vertical cut-off rule at least one parking stall corresponding to line and at least a pair of of parking stall horizontal division line, then basis was currently stopped
History parking stall recognition result and running velocity in journey determine the position of the parking stall.
In the present embodiment, divide vertically if not extracting parking stall horizontal division line and/or parking stall from unilateral overhead view image
Secant, then using parking stall early period search parking space information, parking stall is accurately tracked, according to historical search to stop
Parking stall and running velocity determine historical search to position of the parking stall in present image, and by historical search to stop
Parking stall is as parking stall recognition result.Equal environment influence this method or other factors influence fails to recognize parking stall being illuminated by the light
When, using history parking stall tracking technique, the information on history parking stall is obtained from parking stall search result early period, largely
Improve the stability of parking stall identification.
Optionally, user is during the identification request of triggering parking stall goes forward side by side and drives a vehicle position identification, it is possible to exist and identify
Parking stall out, but user selects to continue to move forward the situation that do not stop on current recognized parking stall out.When user after
It is continuous move forward after when can not recognize parking stall, the parking stall that history identifies can be pushed to use as parking stall recognition result
Family.Optionally, if in the recognition result of history parking stall including multiple parking stalls, the last time is known according to the recognition time of each parking stall
Not Chu parking stall as parking stall recognition result.Family is can be used into as parking stall recognition result in the parking stall that the last time is identified
Operating range is shorter when being stopped, more convenient.
Optionally, when user trigger parking stall identification request when, persistently carried out in vehicle travel process parking stall identification and
Positioning, and the specific location of the time, vehicle location coordinate and parking stall when recording when identifying parking stall identified parking stall.When
When user's selection continues that parking stall can not be recognized after moving forward, according to the parking stall identified in this parking stall identification process
Time selects the last parking stall identified as parking stall recognition result.
Optionally, described in the history parking stall recognition result and running velocity according in current docking process determines
The position of parking stall, comprising:
Running velocity is calculated according to the parking stall alternate position spike identified in adjacent two field pictures in the identification of history parking stall；
The history parking stall is calculated in present image according to the running velocity and history parking stall recognition result
Position.
Optionally, running velocity can be according to the parking stall that two frame parking stalls of front and back are included in the identification process of history parking stall
Alternate position spike be calculated.When carrying out parking stall search, speed is lower and to drive at a constant speed, two frames of front and back when searching for parking stall
Obtained parking stall is same parking stall, and the change in location of obtained parking stall in the picture is the two field pictures time difference
Displacement goes out the speed of vehicle movement at this time by the time difference of two field pictures and the displacement calculation.Calculate vehicle fortune
After scanning frequency degree, in conjunction with the parking stall coordinate that the last time is identified, position of the parking stall in present image is calculated.
Fig. 1 b is that Vehicle Speed provided by the embodiment of the present invention one calculates schematic diagram.As shown in Figure 1 b, vehicle exists
It is travelled from the bottom to top on the left of guide line, vehicle forward direction is dotted arrow direction, and dotted line indicates in adjacent two frames identification warehouse compartment
Position of the same warehouse compartment in previous frame image, solid line indicate that same warehouse compartment is in a later frame image in adjacent two frames identification warehouse compartment
Position, the speed of service of vehicle can be calculated according to the change in location dy and adjacent two frame times difference of two frame warehouse compartment of front and back.
Embodiment two
Fig. 2 a is the flow chart of method for detecting parking stalls provided by the embodiment of the present invention two, and the present embodiment is in above-described embodiment
On the basis of further optimized.As shown in Figure 2 a, which comprises
S210, it is requested according to the parking stall identification detected, extracts from current panorama image and asked with parking stall identification
Seek corresponding unilateral overhead view image.
S220, at least a pair of of parking stall horizontal segmentation for meeting the first preset condition is extracted from the unilateral overhead view image
Line.
In the present embodiment, binaryzation is pre-processed and carried out to unilateral overhead view image first, by unilateral overhead view image
In parking stall cut-off rule candidate's straight line show.Optionally, preset threshold T can be set, by the picture in unilateral overhead view image
Plain value is divided into the pixel group greater than T and the pixel group less than T, and the pixel value that will be greater than the pixel group of T is set as white (or black
Color), the pixel value of the pixel group less than T is set as black (or white), by threshold value by the vehicle in unilateral overhead view image
Position cut-off rule candidate's straight line screens.
Optionally, after filtering out parking stall cut-off rule candidate's straight line in unilateral overhead view image, pre-set first is utilized
Preset condition screens parking stall cut-off rule candidate's straight line.Optionally, the first preset condition may include between straight line and x-axis
Angle within the scope of the first predetermined angle, between the straight line that occurs in pairs with other straight lines and occur in pairs with it at a distance from
Within the scope of pre-determined distance etc..In the present embodiment, by meet the first preset condition parking stall cut-off rule candidate straight line and and its
The parking stall cut-off rule candidate's straight line occurred in pairs is determined as a pair of of parking stall horizontal division line.
For example, can first determine whether the parking stall for each parking stall cut-off rule candidate's straight line in unilateral overhead view image
Whether the angle between cut-off rule candidate straight line and the x-axis of unilateral overhead view image is within the scope of the first predetermined angle.If the parking stall
Angle between cut-off rule candidate straight line and the x-axis of unilateral overhead view image then judges the vehicle not within the scope of the first predetermined angle
Position cut-off rule candidate straight line is not parking stall cut-off rule；If between the parking stall cut-off rule candidate straight line and the x-axis of unilateral overhead view image
Angle within the scope of the first predetermined angle, then whether continue to test in unilateral overhead view image has other parking stalls cut-off rules candidate straight
Line and parking stall cut-off rule candidate's straight line parallel.If there is no other parking stall cut-off rule candidate straight lines and being somebody's turn to do in unilateral overhead view image
Parking stall cut-off rule candidate's straight line parallel then judges that parking stall cut-off rule candidate straight line is not parking stall cut-off rule；If unilateral top view
There are other parking stall cut-off rule candidate straight lines and parking stall cut-off rule candidate's straight line parallel as in, then continue to judge that the parking stall is divided
Whether the distance between line candidate straight line and parking stall cut-off rule candidate in parallel are within the scope of pre-determined distance, if the distance is not
Within a preset range, then judge that parking stall cut-off rule candidate straight line is not parking stall cut-off rule；If the distance is within a preset range,
The parking stall cut-off rule candidate straight line and parking stall cut-off rule candidate's straight line in parallel are determined as a pair of of parking stall horizontal division line.
Optionally, the first predetermined angle may range from 0 °~5 °.Optionally, pre-determined distance may range from 2 meters -3 meters.
Optionally, pre-determined distance range can also be determined according to type of vehicle, be needed with can satisfy the parking area of current vehicle type
Subject to asking.For example, if vehicle be kart (such as car, jeep, minicar, light bus, light truck and
Small, dedicated automobile etc. is no more than 6 meters of automobiles below of 9 people or vehicle commander), then pre-determined distance may range from 2 meters -2.5 meters；If
Vehicle is medium-and-large-sized vehicle (for such as vehicle commander less than 6 meters, seating capacity is greater than the automobile of 9 people), then pre-determined distance may range from 2.5
- 3 meters of rice.The result for determining that pre-determined distance range can be such that parking stall identifies according to type of vehicle is more accurate.
S230, determine that at least a pair of of parking stall horizontal division line institute is right according at least a pair of of parking stall horizontal division line
The vertical cut-off rule at least one parking stall answered.
In the present embodiment, a pair of of parking stall horizontal division line is selected from determining parking stall horizontal division line, for determining
The vertical cut-off rule in parking stall corresponding to the horizontal division line of parking stall.Optionally, from determining at least a pair of of parking stall horizontal division line
A pair of of the parking stall horizontal division line nearest with vehicle distances is chosen as determining the parking stall level point of the vertical cut-off rule in parking stall
Secant.It chooses and determines the vertical cut-off rule in parking stall with the nearest parking stall horizontal division line of vehicle distances, make determined parking stall water
It is most short at a distance from vehicle to divide parking stall corresponding to the vertical cut-off rule of secant and parking stall equally, user is facilitated to stop.
Optionally, the parking stall horizontal division line at least a pair of of according to determines at least a pair of of parking stall horizontal segmentation
The vertical cut-off rule at least one parking stall corresponding to line, comprising:
It chooses a little to be used as from any bar parking stall horizontal division line at least a pair of of parking stall horizontal division line and search
Suo Qidian, and region of search is determined based on described search starting point.
It is scanned for along the parking stall horizontal division line from described search starting point, it is pre- by meeting second in described search region
If the straight line of condition is as the vertical cut-off rule in the parking stall.
In the present embodiment, any one parking stall level point can be chosen from identified a pair of of parking stall horizontal division line
The search of the secant progress vertical cut-off rule in parking stall.Optionally, will be located on selected parking stall horizontal division line, abscissa is
Coordinate points corresponding to the 1/2 of unilateral overhead view image maximum abscissa value are determined as search starting point, and centered on search starting point,
Establish the region of search for meeting preset shape.Optionally, preset shape can be rectangle, and the width of the rectangle is 20-25 picture
Vegetarian refreshments, length are 60-70 pixel.It will be located on selected parking stall horizontal division line, abscissa is unilateral top view
The coordinate points as corresponding to the 1/2 of maximum abscissa value are determined as search starting point, and the major part that may search near vehicle can
It identifies parking stall, and the interference straight line in image can be reduced, improve search efficiency.
In general, the vertical cut-off rule in parking stall is in the side close to vehicle.Therefore, in the present embodiment, the direction of search can
To be set as from search center to the direction close to vehicle location.
Optionally, after determining search center, region of search and the direction of search, using determining search starting point as starting point, with true
Fixed region of search size, with preset step-length, the direction of search on the horizontal division line of parking stall searches for the vertical cut-off rule in parking stall, will
The straight line of first the second preset condition of satisfaction searched is as the vertical cut-off rule in parking stall.Optionally, preset step-length can root
It is determined according to the width of region of search, each region to be searched is covered when scanning for.Optionally, step-length is region of search
The 1/3 of width.
Optionally, the second preset condition can for parking stall cut-off rule candidate straight line and selected parking stall horizontal division line it
Between it is vertical in admissible error range.Optionally, the second preset condition can be with are as follows: parking stall cut-off rule candidate straight line with it is selected
The angle between the horizontal division line of parking stall taken is within the scope of the second predetermined angle.Optionally, the second predetermined angle range can be with
It is 85 °~95 °.
Fig. 2 b is that line search schematic diagram is divided on parking stall provided by the embodiment of the present invention two vertically.As shown in Figure 2 b, vehicle
It is travelled from the bottom to top on the left of guide line, parking stall identification region is on the right side of vehicle heading, horizontal from the parking stall extracted
Search starting point, region of search (ROI) and the direction of search (dotted arrow direction) are determined on cut-off rule, since search starting point, with
Determining region of search size carries out the identification of the vertical cut-off rule in parking stall along the direction of search, will meet the straight of the second preset condition
Line is as the vertical cut-off rule in parking stall.
In the present embodiment, if not searching the straight line for meeting the second preset condition on the parking stall horizontal division line,
Search starting point is reset from another parking stall horizontal division line at least a pair of of parking stall horizontal division line to be searched
Rope.Optionally, the mode for the vertical cut-off rule in parking stall being re-searched on another parking stall horizontal division line can be detailed in above-mentioned implementation
Example, details are not described herein.
S240, the parking stall is determined according at least a pair of of parking stall horizontal division line and the vertical cut-off rule in the parking stall
Position.
The technical solution of the embodiment of the present invention embodies determining parking stall horizontal division line on the basis of the above embodiments
And the operation of the vertical cut-off rule in parking stall, at least a pair of of vehicle of the first preset condition is met by extracting from unilateral overhead view image
Position horizontal division line；It is determined corresponding at least a pair of parking stall horizontal division line at least according at least a pair of of parking stall horizontal division line
One vertical cut-off rule in parking stall so that the determination of the vertical cut-off rule of parking stall horizontal division line and parking stall is more accurate, and then makes vehicle
The position identification of position is more accurate.
Embodiment three
Fig. 3 is the flow chart of method for detecting parking stalls provided by the embodiment of the present invention three, and the present embodiment is in above-described embodiment
On the basis of further optimized.As shown in Figure 3, which comprises
S310, it is requested according to the parking stall identification detected, extracts from current panorama image and asked with parking stall identification
Seek corresponding unilateral overhead view image.
S320, at least a pair of of parking stall horizontal division line and institute are extracted from the unilateral overhead view image according to preset algorithm
State the vertical cut-off rule at least one parking stall corresponding at least a pair of of parking stall horizontal division line.
S330, using the intersecting point coordinate of the vertical cut-off rule of the parking stall horizontal division line and the parking stall as the vehicle
The corner location coordinate of position.
In the present embodiment, it is identified according to the vertical cut-off rule determination of parking stall horizontal division line and its corresponding parking stall
The corner location coordinate of parking stall, calculates the accurate location of parking stall.Optionally, parking stall water is being extracted from unilateral overhead view image
When dividing secant and the vertical cut-off rule in parking stall equally, the slope and intercept of the vertical cut-off rule of parking stall horizontal division line and parking stall are had recorded.
Optionally, each parking stall level point can be calculated according to the slope and intercept of the vertical cut-off rule of each parking stall horizontal division line and parking stall
The linear equation of the vertical cut-off rule of secant and parking stall, the linear equation of calculated parking stall horizontal division line is divided vertically with parking stall
Corner location coordinate of the intersecting point coordinate of the linear equation of secant as parking stall.Illustratively, if parking stall horizontal division line
For straight line A and straight line B, the vertical cut-off rule in parking stall is straight line C, then by the intersecting point coordinate of straight line A and straight line C and straight line B with
Two corner location coordinates of the intersecting point coordinate of straight line C as parking stall.
S340, other corner locations that the parking stall is calculated according to preset parking stall depth and the corner location coordinate are sat
Mark.
Optionally, parking stall depth can be preset, according to preset parking stall depth and two angle point positions having determined that
Set other two corner location coordinates that coordinate calculates parking stall.Optionally, can preset parking stall depth and parking stall width it
Between mapping table, when two angles for determining parking stall according to the intersection point between the vertical cut-off rule of parking stall horizontal division line and parking stall
After point position coordinates, the distance between a pair of of parking stall horizontal division line is obtained, using the distance as parking stall width, and is set in advance
In the mapping table set search parking stall width corresponding to parking stall depth, finally according to the parking stall depth searched, determine
The linear equation of two corner location coordinates and parking stall horizontal division line out calculates other two corner location coordinates of parking stall.
It determines that parking stall depth can make the determination of parking stall depth more accurate according to parking stall width, and then identifies the position of parking stall more
Accurately.
Optionally, when parking stall width is within the scope of 2 meters -2.5 meters, its settable corresponding parking stall depth is 5 meters；Work as vehicle
When bit width range is within the scope of 2.5 meters -3 meters, its settable corresponding parking stall depth is 7 meters.
Illustratively, if parking stall horizontal division line is straight line A and straight line B, the vertical cut-off rule in parking stall is straight line C, according to straight
Parking stall angle point determined by line A, straight line C is angle point M, is angle point N according to parking stall angle point determined by straight line B, straight line C, according to
Parking stall width determined by the distance between parking stall horizontal division line be D1, then in pre-set mapping table search with
Depth D2 in parking stall corresponding to parking stall width D 1 will be located on straight line A, reverse along the direction of search and the distance between with angle point M
For D2 point as angle point P, will be located on straight line B, point conduct that is reverse along the direction of search and being D2 with the distance between angle point N
Angle point Q, using angle point M, angle point N, angle point P and angle point Q as four angle points of parking stall.
The technical solution of the embodiment of the present invention is embodied on the basis of the above embodiments according at least a pair of of parking stall water
Divide the operation that the vertical cut-off rule of secant and parking stall determines the position of parking stall equally, by dividing parking stall horizontal division line and parking stall vertically
Corner location coordinate of the intersecting point coordinate of secant as parking stall；It is calculated according to preset parking stall depth and corner location coordinate
Other corner location coordinates of parking stall, so that the corner location coordinate of parking stall is accurately calculated, so that the knowledge of parking stall
It is more inaccurate.
Example IV
Fig. 4 is the structural schematic diagram of stall recognition device provided by the embodiment of the present invention four.The stall recognition device can
It is realized in a manner of using software and/or hardware, such as the stall recognition device can be configured at computer equipment, such as Fig. 4 institute
Show, described device includes:
Image determining module 410, for according to detect parking stall identification request, extracted from current panorama image with
Corresponding unilateral overhead view image is requested in the parking stall identification；
Cut-off rule determining module 420, it is at least a pair of for being extracted from the unilateral overhead view image according to preset algorithm
The vertical cut-off rule at least one parking stall corresponding to parking stall horizontal division line and at least a pair of of parking stall horizontal division line；
Position determination module 430, for being divided vertically according at least a pair of of parking stall horizontal division line and the parking stall
Line determines the position of the parking stall.
Stall recognition device provided by the embodiment of the present invention is identified by image determining module according to the parking stall detected
Request extracts unilateral overhead view image corresponding with parking stall identification request from current panorama image, is identified according to parking stall
Request is chosen and is calculated with unilateral overhead view image, and computational efficiency is improved；Cut-off rule determining module is according to preset algorithm from institute
It states and extracts at least a pair of of parking stall horizontal division line in unilateral overhead view image and at least a pair of of parking stall horizontal division line institute is right
The vertical cut-off rule at least one parking stall answered；Position determination module is according at least a pair of of parking stall horizontal division line and the vehicle
The vertical cut-off rule in position determines the position of the parking stall, defines the specific location on parking stall.
On the basis of above scheme, the cut-off rule determining module 420 includes:
Horizontal division line determination unit, for extracted from the unilateral overhead view image meet the first preset condition to
Few a pair of parking stall horizontal division line；
Vertical cut-off rule determination unit, it is described at least a pair of for being determined according at least a pair of of parking stall horizontal division line
The vertical cut-off rule at least one parking stall corresponding to the horizontal division line of parking stall.
On the basis of above scheme, the vertical cut-off rule determination unit includes:
Region of search subelement, for from any bar parking stall horizontal segmentation at least a pair of of parking stall horizontal division line
It is chosen on line and is a little used as search starting point, and region of search is determined based on described search starting point；
Vertical cut-off rule subelement, for being scanned for along the parking stall horizontal division line from described search starting point, by institute
It states and meets the straight line of the second preset condition in region of search as the vertical cut-off rule in the parking stall.
On the basis of above scheme, the cut-off rule determining module 420 includes:
Unit is re-searched for, meets the straight of the second preset condition if not searching on the parking stall horizontal division line
Line, then reset from another parking stall horizontal division line at least a pair of of parking stall horizontal division line search starting point into
Row search.
On the basis of above scheme, the position determination module 430 includes:
Angular coordinate determination unit, for by the intersection point position of the vertical cut-off rule of the parking stall horizontal division line and the parking stall
Set corner location coordinate of the coordinate as the parking stall；
Angular coordinate computing unit, for calculating the parking stall according to preset parking stall depth and the corner location coordinate
Other corner location coordinates.
On the basis of above scheme, described device further include:
History parking stall tracing module, if for not extracting at least a pair of of parking stall level point from the unilateral overhead view image
The vertical cut-off rule at least one parking stall corresponding to secant and at least a pair of of parking stall horizontal division line, then according to current parking
History parking stall recognition result and running velocity in the process determines the position of the parking stall.
On the basis of above scheme, history parking stall tracing module includes:
Car speed computing unit, for according to the parking stall position identified in adjacent two field pictures in the identification of history parking stall
It sets difference and calculates running velocity；
History parking stall computing unit, for being gone through according to the running velocity and the calculating of history parking stall recognition result
Position of the history parking stall in present image.
Parking stall recognition methods provided by any embodiment can be performed in stall recognition device provided by the embodiment of the present invention,
Have the corresponding functional module of execution method and beneficial effect.
Embodiment five
Fig. 5 is the structural schematic diagram of computer equipment provided by the embodiment of the present invention five.Fig. 5, which is shown, to be suitable for being used in fact
The block diagram of the exemplary computer device 512 of existing embodiment of the present invention.The computer equipment 512 that Fig. 5 is shown is only one
Example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 5, computer equipment 512 is showed in the form of universal computing device.The component of computer equipment 512 can
To include but is not limited to: one or more processor 516, system storage 528 connect different system components (including system
Memory 528 and processor 516) bus 518.
Bus 518 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor 516 or total using the local of any bus structures in a variety of bus structures
Line.For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture
(MAC) bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) are total
Line.
Computer equipment 512 typically comprises a variety of computer system readable media.These media can be it is any can
The usable medium accessed by computer equipment 512, including volatile and non-volatile media, moveable and immovable Jie
Matter.
System storage 528 may include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 530 and/or cache memory 532.Computer equipment 512 may further include it is other it is removable/
Immovable, volatile/non-volatile computer system storage medium.Only as an example, storage device 534 can be used for reading
Write immovable, non-volatile magnetic media (Fig. 5 do not show, commonly referred to as " hard disk drive ").Although being not shown in Fig. 5,
The disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided, and non-easy to moving
The CD drive that the property lost CD (such as CD-ROM, DVD-ROM or other optical mediums) is read and write.In these cases, each
Driver can be connected by one or more data media interfaces with bus 518.Memory 528 may include at least one
Program product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform this
Invent the function of each embodiment.
Program/utility 540 with one group of (at least one) program module 542, can store in such as memory
In 528, such program module 542 includes but is not limited to operating system, one or more application program, other program modules
And program data, it may include the realization of network environment in each of these examples or certain combination.Program module 542
Usually execute the function and/or method in embodiment described in the invention.
Computer equipment 512 can also be with one or more external equipments 514 (such as keyboard, sensing equipment, display
524 etc.) it communicates, the equipment interacted with the computer equipment 512 communication can be also enabled a user to one or more, and/or
(such as network interface card is adjusted with any equipment for enabling the computer equipment 512 to be communicated with one or more of the other calculating equipment
Modulator-demodulator etc.) communication.This communication can be carried out by input/output (I/O) interface 522.Also, computer equipment
512 can also by network adapter 520 and one or more network (such as local area network (LAN), wide area network (WAN) and/or
Public network, such as internet) communication.As shown, network adapter 520 passes through its of bus 518 and computer equipment 512
The communication of its module.It should be understood that although not shown in the drawings, other hardware and/or software can be used in conjunction with computer equipment 512
Module, including but not limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, magnetic
Tape drive and data backup storage system etc..
Processor 516 by the program that is stored in system storage 528 of operation, thereby executing various function application and
Data processing, such as realize parking stall recognition methods provided by the embodiment of the present invention, this method comprises:
According to the parking stall identification request detected, extracted from current panorama image corresponding with parking stall identification request
Unilateral overhead view image；
Extracted from the unilateral overhead view image according to preset algorithm at least a pair of of parking stall horizontal division line and it is described to
The vertical cut-off rule at least one parking stall corresponding to the horizontal division line of few a pair of parking stall；
The position of the parking stall is determined according at least a pair of of parking stall horizontal division line and the vertical cut-off rule in the parking stall.
Certainly, it will be understood by those skilled in the art that processor can also realize it is provided by any embodiment of the invention
The technical solution of parking stall recognition methods.
Embodiment five
The embodiment of the present invention five additionally provides a kind of computer readable storage medium, is stored thereon with computer program, should
The parking stall recognition methods as provided by the embodiment of the present invention is realized when program is executed by processor, this method comprises:
According to the parking stall identification request detected, extracted from current panorama image corresponding with parking stall identification request
Unilateral overhead view image；
Extracted from the unilateral overhead view image according to preset algorithm at least a pair of of parking stall horizontal division line and it is described to
The vertical cut-off rule at least one parking stall corresponding to the horizontal division line of few a pair of parking stall；
The position of the parking stall is determined according at least a pair of of parking stall horizontal division line and the vertical cut-off rule in the parking stall.
Certainly, a kind of computer readable storage medium provided by the embodiment of the present invention, the computer program stored thereon
The method operation being not limited to the described above, can also be performed the phase in parking stall recognition methods provided by any embodiment of the invention
Close operation.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: tool
There are electrical connection, the portable computer diskette, hard disk, random access memory (RAM), read-only memory of one or more conducting wires
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
It further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of parking stall recognition methods characterized by comprising
According to the parking stall identification request detected, list corresponding with parking stall identification request is extracted from current panorama image
Side overhead view image；
At least a pair of of parking stall horizontal division line and described at least one is extracted from the unilateral overhead view image according to preset algorithm
To the vertical cut-off rule at least one parking stall corresponding to the horizontal division line of parking stall；
The position of the parking stall is determined according at least a pair of of parking stall horizontal division line and the vertical cut-off rule in the parking stall.
2. the method according to claim 1, wherein it is described according to preset algorithm from the unilateral overhead view image
Extract at least one parking stall corresponding at least a pair of of parking stall horizontal division line and at least a pair of of parking stall horizontal division line
Vertical cut-off rule, comprising:
At least a pair of of parking stall horizontal division line for meeting the first preset condition is extracted from the unilateral overhead view image；
According to corresponding at least a pair of of parking stall horizontal division line described at least a pair of of parking stall horizontal division line determination at least
One vertical cut-off rule in parking stall.
3. according to the method described in claim 2, it is characterized in that, the parking stall horizontal division line at least a pair of of according to is true
The vertical cut-off rule at least one parking stall corresponding to fixed at least a pair of of parking stall horizontal division line, comprising:
From being chosen on any bar parking stall horizontal division line at least a pair of of parking stall horizontal division line and being a little used as search
Point, and region of search is determined based on described search starting point；
It is scanned for along the parking stall horizontal division line from described search starting point, the second default item will be met in described search region
The straight line of part is as the vertical cut-off rule in the parking stall.
4. according to the method described in claim 3, it is characterized in that, if satisfaction is not searched on the parking stall horizontal division line
The straight line of two preset conditions, then from another parking stall horizontal division line at least a pair of of parking stall horizontal division line again
Setting search starting point scans for.
5. the method according to claim 1, wherein the parking stall horizontal division line at least a pair of of according to and
The vertical cut-off rule in parking stall determines the position of the parking stall, comprising:
Using the intersecting point coordinate of the vertical cut-off rule of the parking stall horizontal division line and the parking stall as the angle point of the parking stall
Position coordinates；
Other corner location coordinates of the parking stall are calculated according to preset parking stall depth and the corner location coordinate.
6. the method according to claim 1, wherein if not extracting at least one from the unilateral overhead view image
To the vertical cut-off rule at least one parking stall corresponding to parking stall horizontal division line and at least a pair of of parking stall horizontal division line, then
According in current docking process history parking stall recognition result and running velocity determine the position of the parking stall.
7. according to the method described in claim 6, it is characterized in that, the history parking stall in the current docking process of the basis identifies
As a result and running velocity determines the position of the parking stall, comprising:
Running velocity is calculated according to the parking stall alternate position spike identified in adjacent two field pictures in the identification of history parking stall；
Position of the history parking stall in present image is calculated according to the running velocity and history parking stall recognition result.
8. a kind of stall recognition device characterized by comprising
Image determining module, for being extracted from current panorama image and the vehicle according to the parking stall identification request detected
Corresponding unilateral overhead view image is requested in position identification；
Cut-off rule determining module, it is horizontal for extracting at least a pair of of parking stall from the unilateral overhead view image according to preset algorithm
The vertical cut-off rule at least one parking stall corresponding to cut-off rule and at least a pair of of parking stall horizontal division line；
Position determination module, for determining institute according at least a pair of of parking stall horizontal division line and the vertical cut-off rule in the parking stall
State the position of parking stall.
9. a kind of computer equipment, which is characterized in that the equipment includes:
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now parking stall recognition methods as described in any in claim 1-7.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The parking stall recognition methods as described in any in claim 1-7 is realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811075501.0A CN109299686A (en) | 2018-09-14 | 2018-09-14 | A kind of parking stall recognition methods, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811075501.0A CN109299686A (en) | 2018-09-14 | 2018-09-14 | A kind of parking stall recognition methods, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109299686A true CN109299686A (en) | 2019-02-01 |
Family
ID=65163137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811075501.0A Pending CN109299686A (en) | 2018-09-14 | 2018-09-14 | A kind of parking stall recognition methods, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109299686A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111428547A (en) * | 2019-06-24 | 2020-07-17 | 杭州海康威视数字技术股份有限公司 | Parking space determining method and device |
| CN112356831A (en) * | 2021-01-12 | 2021-02-12 | 天津天瞳威势电子科技有限公司 | Warehouse location tracking method and warehouse location tracking system |
| CN112455430A (en) * | 2020-12-02 | 2021-03-09 | 苏州优达斯汽车科技有限公司 | Method for detecting inclined parking spaces without parking space lines, parking method and parking system |
| CN113053164A (en) * | 2021-05-11 | 2021-06-29 | 吉林大学 | Parking space identification method using look-around image |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150130640A1 (en) * | 2013-11-14 | 2015-05-14 | Hyundai Motor Company | Parking area detecting apparatus and method thereof |
| CN104933409A (en) * | 2015-06-12 | 2015-09-23 | 北京理工大学 | Parking space identification method based on point and line features of panoramic image |
| WO2015186294A1 (en) * | 2014-06-02 | 2015-12-10 | 株式会社デンソー | Vehicle-mounted image-processing device |
| CN105539430A (en) * | 2015-12-29 | 2016-05-04 | 北京理工大学 | Intelligent man-car interaction parking method based on hand-held terminal |
| CN106585627A (en) * | 2016-11-07 | 2017-04-26 | 纵目科技（上海）股份有限公司 | Parking auxiliary system and automobile |
| CN107491738A (en) * | 2017-07-25 | 2017-12-19 | 纵目科技（上海）股份有限公司 | Parking space detection method and system, storage medium and electronic equipment |
| CN108431881A (en) * | 2015-10-22 | 2018-08-21 | 日产自动车株式会社 | The display methods and parking aid of parking assisting information |
-
2018
- 2018-09-14 CN CN201811075501.0A patent/CN109299686A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150130640A1 (en) * | 2013-11-14 | 2015-05-14 | Hyundai Motor Company | Parking area detecting apparatus and method thereof |
| WO2015186294A1 (en) * | 2014-06-02 | 2015-12-10 | 株式会社デンソー | Vehicle-mounted image-processing device |
| CN104933409A (en) * | 2015-06-12 | 2015-09-23 | 北京理工大学 | Parking space identification method based on point and line features of panoramic image |
| CN108431881A (en) * | 2015-10-22 | 2018-08-21 | 日产自动车株式会社 | The display methods and parking aid of parking assisting information |
| CN105539430A (en) * | 2015-12-29 | 2016-05-04 | 北京理工大学 | Intelligent man-car interaction parking method based on hand-held terminal |
| CN106585627A (en) * | 2016-11-07 | 2017-04-26 | 纵目科技（上海）股份有限公司 | Parking auxiliary system and automobile |
| CN107491738A (en) * | 2017-07-25 | 2017-12-19 | 纵目科技（上海）股份有限公司 | Parking space detection method and system, storage medium and electronic equipment |
Non-Patent Citations (4)
| Title |
|---|
| KHALED SHAABAN等: "Parking Space Detection System Using Video Images", 《TRANSPORTATION RESEARCH RECORD JOURNAL OF THE TRANSPORTATION RESEARCH BOARD》 * |
| WENHAO ZONG等: "A Robust Method for Detecting Parking Areas in Both Indoor and Outdoor Environment", 《SENSORS》 * |
| 廖梦龑: "2D全景环视的停车位识别算法及应用", 《信息与电脑(理论版)》 * |
| 沈浩斌等: "基于信息融合的自动泊车***车位智能识别", 《机械工程学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111428547A (en) * | 2019-06-24 | 2020-07-17 | 杭州海康威视数字技术股份有限公司 | Parking space determining method and device |
| CN111428547B (en) * | 2019-06-24 | 2024-03-01 | 杭州海康威视数字技术股份有限公司 | Parking space determining method and device |
| CN112455430A (en) * | 2020-12-02 | 2021-03-09 | 苏州优达斯汽车科技有限公司 | Method for detecting inclined parking spaces without parking space lines, parking method and parking system |
| CN112356831A (en) * | 2021-01-12 | 2021-02-12 | 天津天瞳威势电子科技有限公司 | Warehouse location tracking method and warehouse location tracking system |
| CN112356831B (en) * | 2021-01-12 | 2021-04-20 | 天津天瞳威势电子科技有限公司 | Warehouse location tracking method and warehouse location tracking system |
| CN113053164A (en) * | 2021-05-11 | 2021-06-29 | 吉林大学 | Parking space identification method using look-around image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11393219B2 (en) | Method and apparatus for detecting obstacle, electronic device, vehicle and storage medium | |
| CN109299686A (en) | A kind of parking stall recognition methods, device, equipment and medium | |
| US9076047B2 (en) | System and method for recognizing parking space line markings for vehicle | |
| US10331962B2 (en) | Detecting device, detecting method, and program | |
| US20220107647A1 (en) | Speed planning method and apparatus, electronic device and storage medium | |
| JP4600760B2 (en) | Obstacle detection device | |
| CN108473131A (en) | Parking assistance method and device | |
| JPH09319872A (en) | Road white line detector, curvature radium calculator, and navigation device | |
| US11935250B2 (en) | Method, device and computer-readable storage medium with instructions for processing sensor data | |
| JP4660569B2 (en) | Object detection apparatus and object detection method | |
| JP2010202017A (en) | Data analysis device and method, and program | |
| US20210326612A1 (en) | Vehicle detection method and device | |
| CN109883439A (en) | A kind of automobile navigation method, device, electronic equipment and storage medium | |
| US20130100281A1 (en) | Method, System and Computer Program Product for Detecting an Obstacle with a Camera | |
| US20210350142A1 (en) | In-train positioning and indoor positioning | |
| CN109300322B (en) | Guideline drawing method, apparatus, device, and medium | |
| CN114228703A (en) | Automatic parking method, system, vehicle and storage medium | |
| US20150168155A1 (en) | Method and system for measuring a vehicle position indoors | |
| CN113092079A (en) | Definition detection target plate and method and system, electronic equipment and detection platform | |
| EP4258078A1 (en) | Positioning method and apparatus, and vehicle | |
| JP2009229180A (en) | Navigation device | |
| CN111951328A (en) | Object position detection method, device, equipment and storage medium | |
| CN109919118A (en) | Barrier prompt method, apparatus, equipment and medium in AR navigation | |
| JP2004205527A (en) | Navigation system | |
| US20190354781A1 (en) | Method and system for determining an object location by using map information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190201 |