CN109753840A - A method of parking stall line angle point is determined based on response - Google Patents
A method of parking stall line angle point is determined based on response Download PDFInfo
- Publication number
- CN109753840A CN109753840A CN201710679309.1A CN201710679309A CN109753840A CN 109753840 A CN109753840 A CN 109753840A CN 201710679309 A CN201710679309 A CN 201710679309A CN 109753840 A CN109753840 A CN 109753840A
- Authority
- CN
- China
- Prior art keywords
- pixel
- parking stall
- angle point
- response
- luminance contrast
- 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.)
- Granted
Links
Landscapes
- Traffic Control Systems (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of method for determining parking stall line angle point based on response, comprising the following steps: obtains capture image, obtains the brightness value of each pixel on capture image by pretreatment；Will each pixel is using the coordinate points where its pixel as origin on capture image, along origin to the parking stall vertical direction pixel group of parking stall principal direction and parking stall principal direction vertical direction successively pick-up position principal direction pixel group and two mutually opposing extensions.The luminance contrast response of obtained each pixel arranges the angle point luminance contrast response image to form capture image with coordinate points where its pixel；The maximum parking stall line angle point of confidence level in capture image is determined by the distribution situation of the luminance contrast response of each coordinate points in angle point luminance contrast response image and then determines that the maximum luminance contrast response point of confidence level is parking stall line angle point.
Description
Technical field
The present invention relates to vehicle electronics technical fields, more particularly to a kind of side for determining parking stall line angle point based on response
Method.
Background technique
The increase of car ownership promotes the development of large parking lot, and since marching toward 21st century, ours is big
Type parking lot is more and more, and being growing for parking lot scale, brings a series of the problem of parking with picking up the car, has become
The social concern that each large- and-medium size cities generally face in world wide.
During autonomous parking, how according to environment sensing information, detect accurate parking stall and detecting
Reduce equipment calculation amount in journey, quickly, accurately identifies parking stall line angle point as current urgent problem to be solved.
The existing method for calculating parking stall line angle point is to identify line segment according to pixel intensity difference on capture image, lead to
It crosses line segment and finds out qualified horizontal brightness item and vertical bright line item, find out the middle line of two sides of horizontal brightness item and hang down
The intersection point of two side middle lines of straight bright line item, is determined as the angle point of parking stall line.This identification parking stall line angle point by this method, it is right
The accuracy requirement for finding qualified horizontal brightness item and vertical bright line step is high, if the horizontal brightness item found out and
There is reflective " the vertical bright line item " or " horizontal brightness item " for waiting other interference to generate in vertical bright line item, then can make the vehicle identified
Bit line angle point is inaccurate.
Summary of the invention
In order to solve above-mentioned and other potential technical problems, the present invention provides one kind to determine vehicle based on response
The method of bit line angle point solves the problems, such as parking stall line corner recognition inaccuracy, by calculating each pixel in capture image
The judgement factor in the principal direction of parking stall and in the vertical direction of parking stall, to determine the pixel position for T-type parking stall line angle point and L
The luminance contrast response X of type parking stall line angle point, and then angle point luminance contrast response image is obtained, pass through angle point brightness pair
Brightness contrast more maximum than the distribution situation of the luminance contrast response of coordinate points each in degree response image judgement confidence level
Degree response point is parking stall line angle point.
A method of parking stall line angle point is determined based on response, comprising the following steps:
S01: obtaining capture image, obtains the brightness value of each pixel on capture image by pretreatment；
S02: will each pixel is using the coordinate points where its pixel as origin on capture image, along origin to parking stall
Successively the parking stall of pick-up position principal direction pixel group and two mutually opposing extensions is hung down for principal direction and parking stall principal direction vertical direction
Histogram is to pixel group；
By in principal direction pixel group each pixel Plx be located at principal direction pixel group two sides and with the pixel
Put the brightness pair that two pixels Pd1x and Pd2x on same straight line take the average value of luminance difference to mark pixel Pl
Than angle value, seek asking after the luminance contrast value of all pixels point Plx in principal direction pixel group its average mark based on side
Factor a is determined to angle point；
The formula of the luminance contrast value for seeking pixel Plx: Px=(Plx*2-Pd1x-Pd2x)/2；X=1,2,
3,4,5,6…n；
The principal direction angle point determines the calculation formula of factor a: a=(P1+P2+P3 ... Pn)/n；
By each pixel Pc in each parking stall vertical direction pixel group and it is located at parking stall vertical direction pixel
It organizes two sides and two pixels Pd1y and Pd2y being on same straight line with pixel Pl takes the average value of luminance difference to mark
The luminance contrast value of pixel Ply seeks the luminance contrast of all pixels point Pl in the vertical direction pixel group of parking stall
Its average is asked to determine that factor b and vertical direction angle point determine factor c labeled as vertical direction angle point after value；
The formula of the luminance contrast value for seeking pixel Ply: Py=(Ply*2-Pd1y-Pd2y)/2；Y=1,2,
3,4,5,6…m；
The vertical direction angle point determines the calculation formula of factor b: b=(P1+P2+P3 ... Pm)/m；
The vertical direction angle point determines the calculation formula of factor c: b=(P1+P2+P3 ... Pm)/m；
According to logical formula: X=MIN (MAX (a, b), c) show that the luminance contrast of each pixel in capture image is rung
It should value X；
S03: by the luminance contrast response X of each pixel obtained in step S02 with coordinate where its pixel
Point arrangement forms the angle point luminance contrast response image of capture image；
S04: by the distribution feelings of the luminance contrast response of each coordinate points in angle point luminance contrast response image
Condition determines the maximum parking stall line angle point of confidence level in capture image.
Further, the method for parking stall principal direction is obtained in step S02 are as follows: obtain capture image and detect in capture image
Line segment, will test out line segment and be grouped according to angle, the positional relationship the line segment in each group is analyzed, root
It gives a mark according to certain rule, most believable angle group is chosen according to score, and extract the line segment in most believable angle group,
The average angle for calculating line segment, is defined as principal direction angle, θ.
Further, the pixel number extended in the principal direction pixel group obtained in step S02 along parking stall principal direction
It is at least 6~8, the pixel number in the parking stall vertical direction pixel group along the extension of parking stall vertical direction is at least 6
~8.
Further, at least two column extend in the principal direction pixel group obtained in step S02 along parking stall principal direction
Pixel.
Such as: the pixel for having two column to extend along parking stall principal direction is labeled as pixel point range n1, n2；In pixel point range n1
The brightness value of pixel be labeled as (Pl1, Pl2, Pl3, Pl4 ...), the brightness value of the pixel in pixel point range n2 is labeled as
(pl1,pl2,pl3,pl4)；When taking the luminance contrast value of this pixel in principal direction pixel group, by pixel point range n1, n2
In in identical principal direction position pixel extract be averaged using formula (Pl1+pl1)/2 as step S02
Virtual representation vegetarian refreshments on straight line corresponding to middle Pl1 and pl1 as when calculating luminance contrast value in principal direction pixel group
Brightness value.
Further, logical formula: it includes the T-type parking stall parking stall Xian HeLXing that X=MIN (MAX (a, b), c), which can detecte out,
The angle point of line, if in the detection process, occurring the more than one luminance contrast higher than threshold value at adjacent pixel and ringing
When should be worth, the luminance contrast response and its coordinate points record of threshold value will be above, and weighted average is taken to obtain to the end
The response of luminance contrast.
As described above, of the invention has the advantages that
First, by calculating judgement of each pixel in the principal direction of parking stall and in the vertical direction of parking stall in capture image
The factor, come determine the pixel position for the luminance contrast response X of T-type parking stall line angle point and L-type parking stall line angle point, in turn
Angle point luminance contrast response image is obtained, the luminance contrast of each coordinate points in angle point luminance contrast response image is passed through
The distribution situation of response determines that the maximum luminance contrast response point of confidence level is parking stall line angle point.
Second, when calculating the luminance contrast value for determining the factor, principal direction pixel group or parking stall Vertical Square in parking stall
Take multiple row pixel in same direction into pixel group, the pixel on same position in the direction in the pixel of different lines
Brightness value be averaged after take the average value of difference with the pixel of two sides except the pixel group where it again, it is such
Luminance contrast value out is with a high credibility, and the confidence level of the judgement factor obtained is also higher.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is shown as flow diagram of the invention.
Fig. 2 is shown as the parking stall vertical directions of parking stall principal direction pixel group and two mutually opposing extensions of the invention
The schematic diagram of vegetarian refreshments group.
Fig. 3 is shown as the pixel schematic diagram that parking stall principal direction pixel group seeks Plx luminance contrast value.
Fig. 4 is shown as the pixel schematic diagram that parking stall vertical direction pixel group seeks Ply luminance contrast value.
Fig. 5 is shown as seeking Ply luminance contrast value's when having two column pixel point ranges in the vertical direction pixel group of parking stall
Pixel schematic diagram.
Fig. 6 is shown as capture image of the invention.
Fig. 7 be shown as left side be the present invention capture image right side be angle point luminance contrast response image of the invention.
In figure: 1- origin；The parking stall 2- principal direction；The parking stall 3- principal direction vertical direction；21- principal direction pixel group；31-
Parking stall vertical direction pixel group；4- pixel.
Specific embodiment
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification
Other advantages and efficacy of the present invention can be easily understood for disclosed content.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from
Various modifications or alterations are carried out under spirit of the invention.It should be noted that in the absence of conflict, following embodiment and implementation
Feature in example can be combined with each other.
It should be clear that this specification structure depicted in this specification institute accompanying drawings, ratio, size etc., only to cooperate specification to be taken off
The content shown is not intended to limit the invention enforceable qualifications so that those skilled in the art understands and reads, therefore
Do not have technical essential meaning, the modification of any structure, the change of proportionate relationship or the adjustment of size are not influencing the present invention
Under the effect of can be generated and the purpose that can reach, it should all still fall in disclosed technology contents and obtain the model that can cover
In enclosing.Meanwhile cited such as "upper" in this specification, "lower", "left", "right", " centre " and " one " term, be also only
Convenient for being illustrated for narration, rather than to limit the scope of the invention, relativeness is altered or modified, in no essence
It changes under technology contents, when being also considered as the enforceable scope of the present invention.
Referring to FIG. 1 to FIG. 7, a method of parking stall line angle point is determined based on response, comprising the following steps:
S01: obtaining capture image, obtains the brightness value of each pixel on capture image by pretreatment；
S02: will each pixel is using the coordinate points where its pixel as origin on capture image, along origin to parking stall
Successively the parking stall of pick-up position principal direction pixel group and two mutually opposing extensions is hung down for principal direction and parking stall principal direction vertical direction
Histogram is to pixel group；
By in principal direction pixel group each pixel Plx be located at principal direction pixel group two sides and with the pixel
Put the brightness pair that two pixels Pd1x and Pd2x on same straight line take the average value of luminance difference to mark pixel Pl
Than angle value, seek asking after the luminance contrast value of all pixels point Plx in principal direction pixel group its average mark based on side
Factor a is determined to angle point；
The formula of the luminance contrast value for seeking pixel Plx: Px=(Plx*2-Pd1x-Pd2x)/2；X=1,2,
3,4,5,6…n；
The principal direction angle point determines the calculation formula of factor a: a=(P1+P2+P3 ... Pn)/n；
By each pixel Ply in each parking stall vertical direction pixel group and it is located at parking stall vertical direction pixel
It organizes two sides and two pixels Pd1y and Pd2y being on same straight line with pixel Pl takes the average value of luminance difference to mark
The luminance contrast value of pixel Ply seeks the luminance contrast of all pixels point Ply in the vertical direction pixel group of parking stall
Its average is asked to determine that factor b and vertical direction angle point determine factor c labeled as vertical direction angle point after value；
The formula of the luminance contrast value for seeking pixel Ply: Py=(Ply*2-Pd1y-Pd2y)/2；Y=1,2,
3,4,5,6…m；
The vertical direction angle point determines the calculation formula of factor b: b=(P1+P2+P3 ... Pm)/m；
The vertical direction angle point determines the calculation formula of factor c: b=(P1+P2+P3 ... Pm)/m；
According to logical formula: X=MIN (MAX (a, b), c) obtains the luminance contrast of each pixel Pl in capture image
Response；
S03: by the luminance contrast response of each pixel obtained in step S02 with coordinate points where its pixel
Arrangement forms the angle point luminance contrast response image of capture image；By each coordinate in angle point luminance contrast response image
The distribution situation of the luminance contrast response of point determines the maximum parking stall line angle point of confidence level in capture image.
As a preferred embodiment, the method for parking stall principal direction is obtained in step S02 are as follows: obtain capture image and detect capture
Line segment in image will test out line segment and be grouped according to angle, carry out between the positional relationship the line segment in each group
Analysis, gives a mark according to certain rule, chooses most believable angle group according to score, and extract in most believable angle group
Line segment, calculate the average angle of line segment, be defined as principal direction angle, θ.
As a preferred embodiment, the pixel extended in the principal direction pixel group obtained in step S02 along parking stall principal direction
Point number is at least 6~8, is along the pixel number that parking stall vertical direction extends in the parking stall vertical direction pixel group
At least 6~8.
As a preferred embodiment, there are at least two column along parking stall principal direction in the principal direction pixel group obtained in step S02
The pixel of extension.
Such as: the pixel for having two column to extend along parking stall principal direction is labeled as pixel point range n1, n2；In pixel point range n1
The brightness value of pixel be labeled as (Pl1, Pl2, Pl3, Pl4 ...), the brightness value of the pixel in pixel point range n2 is labeled as
(pl1,pl2,pl3,pl4)；When taking the luminance contrast value of this pixel in principal direction pixel group, by pixel point range n1, n2
In in identical principal direction position pixel extract be averaged using formula (Pl1+pl1)/2 as step S02
Virtual representation vegetarian refreshments on straight line corresponding to middle Pl1 and pl1 as when calculating luminance contrast value in principal direction pixel group
Brightness value.
As a preferred embodiment, logical formula: it includes T-type parking stall line and L that X=MIN (MAX (a, b), c), which can detecte out,
The angle point of type parking stall line, if in the detection process, occurring the more than one brightness pair higher than threshold value at adjacent pixel
When than degree response, the luminance contrast response and its coordinate points record of threshold value will be above, and weighted average is taken to obtain
The response of last luminance contrast.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.It is any ripe
The personage for knowing this technology all without departing from the spirit and scope of the present invention, carries out modifications and changes to above-described embodiment.Cause
This, includes that institute is complete without departing from the spirit and technical ideas disclosed in the present invention for usual skill in technical field such as
At all equivalent modifications or change, should be covered by the claims of the present invention.
Claims (8)
1. a kind of method for determining parking stall line angle point based on response, comprising the following steps:
S01: obtaining capture image, obtains the brightness value of each pixel on capture image by pretreatment；
S02: will each pixel is using the coordinate points where its pixel as origin on capture image, along origin to the main side in parking stall
To the parking stall Vertical Square with parking stall principal direction vertical direction successively pick-up position principal direction pixel group and two mutually opposing extensions
To pixel group；
By in principal direction pixel group each pixel Plx be located at principal direction pixel group two sides and at the pixel
The average value of luminance difference is taken to mark the luminance contrast of pixel Pl in two pixels Pd1x and Pd2x on same straight line
Value is sought asking its average labeled as principal stresses angle in principal direction pixel group after the luminance contrast value of all pixels point Plx
Point determines factor a；
The formula of the luminance contrast value for seeking pixel Plx: Px=(Plx*2-Pd1x-Pd2x)/2；X=1,2,3,4,
5,6…n；
The principal direction angle point determines the calculation formula of factor a: a=(P1+P2+P3 ... Pn)/n；
By each pixel Ply in each parking stall vertical direction pixel group and it is located at parking stall vertical direction pixel group two
Side and two pixels Pd1y and Pd2y being on same straight line with pixel Ply take the average value of luminance difference to mark the picture
The luminance contrast value of vegetarian refreshments Ply seeks in the vertical direction pixel group of parking stall after the luminance contrast value of all pixels point Ply
Its average is asked to determine that factor b and vertical direction angle point determine factor c labeled as vertical direction angle point；
The formula of the luminance contrast value for seeking pixel Ply: Py=(Ply*2-Pd1y-Pd2y)/2；Y=1,2,3,4,
5,6…m；
The vertical direction angle point determines the calculation formula of factor b: b=(P1+P2+P3 ... Pm)/m；
The vertical direction angle point determines the calculation formula of factor c: b=(P1+P2+P3 ... Pm)/m；
According to logical formula: X=MIN (MAX (a, b), c) obtains the luminance contrast response of each pixel Pl in capture image
Value；
S03: the luminance contrast response of each pixel obtained in step S02 is arranged with coordinate points where its pixel
Form the angle point luminance contrast response image of capture image；By each coordinate points in angle point luminance contrast response image
The distribution situation of luminance contrast response determines the maximum parking stall line angle point of confidence level in capture image.
2. the method according to claim 1 for determining parking stall line angle point based on response, which is characterized in that in step S02
Obtain parking stall principal direction method are as follows: obtain capture image simultaneously detect capture image in line segment, will test out line segment according to
Angle is grouped, and is analyzed the positional relationship the line segment in each group, is given a mark according to certain rule, according to
Score chooses most believable angle group, and extracts the line segment in most believable angle group, calculates the average angle of line segment, is defined as
Principal direction angle, θ.
3. the method according to claim 2 for determining parking stall line angle point based on response, which is characterized in that in step S02
Pixel number in the principal direction pixel group of acquisition along the extension of parking stall principal direction is at least 6~8, the parking stall Vertical Square
Pixel number into pixel group along the extension of parking stall vertical direction is at least 6~8.
4. the method according to claim 3 for determining parking stall line angle point based on response, which is characterized in that in step S02
The pixel for thering are at least two column to extend in the principal direction pixel group of acquisition along parking stall principal direction.
5. the method according to claim 4 for determining parking stall line angle point based on response, which is characterized in that the logic is public
Formula: X=MIN (MAX (a, b), c) can detecte out the angle point including the T-type parking stall parking stall Xian HeLXing line, if in the detection process,
When occurring the more than one luminance contrast response higher than threshold value at adjacent pixel, the brightness pair of threshold value will be above
It is recorded than degree response and its coordinate points, and the response for the luminance contrast for taking weighted average to obtain to the end.
6. a kind of system for determining parking stall line angle point based on response characterized by comprising
Image collection module is captured, for obtaining capture image；
Pixel group generation module, for generating parking stall principal direction pixel group and parking stall vertical direction pixel group；
Principal direction angle point determines factor generation module, determines factor a for generating principal direction angle point；
Vertical direction angle point determines factor generation module, determines factor b and vertical direction angle point for generating vertical direction angle point
Determine factor c；
Angle point luminance contrast response image generation module, for passing through logical formula: X=MIN (MAX (a, b), c) generation is caught
The luminance contrast response of each pixel in image is obtained, and then obtains angle point luminance contrast response image.
7. the system according to claim 6 for determining parking stall line angle point in response, which is characterized in that further include parking stall master
Direction determining module, the parking stall principal direction determination module are used to examine from capturing image and detecting the line segment in capture image
It measures and carrys out line segment and be grouped according to angle, the positional relationship the line segment in each group is analyzed, according to certain rule
It then gives a mark, most believable angle group is chosen according to score, and extract the line segment in most believable angle group, calculate line segment
Average angle is defined as principal direction angle, θ.
8. a kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that: the program is held by processor
The step in method according to any one of claims 1 to 5 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710679309.1A CN109753840B (en) | 2017-11-06 | 2017-11-06 | Method, system and storage medium for determining parking space line corner points based on response values |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710679309.1A CN109753840B (en) | 2017-11-06 | 2017-11-06 | Method, system and storage medium for determining parking space line corner points based on response values |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109753840A true CN109753840A (en) | 2019-05-14 |
| CN109753840B CN109753840B (en) | 2023-09-01 |
Family
ID=66397498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710679309.1A Active CN109753840B (en) | 2017-11-06 | 2017-11-06 | Method, system and storage medium for determining parking space line corner points based on response values |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109753840B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112767425A (en) * | 2020-12-30 | 2021-05-07 | 智车优行科技（北京）有限公司 | Parking space detection method and device based on vision |
| CN115206130A (en) * | 2022-07-12 | 2022-10-18 | 合众新能源汽车有限公司 | Parking space detection method, system, terminal and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103600707A (en) * | 2013-11-06 | 2014-02-26 | 同济大学 | Parking position detecting device and method of intelligent parking system |
| WO2014063373A1 (en) * | 2012-10-23 | 2014-05-01 | 青岛海信信芯科技有限公司 | Methods for extracting depth map, judging video scenario switching and optimizing edge of depth map |
| 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 |
-
2017
- 2017-11-06 CN CN201710679309.1A patent/CN109753840B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014063373A1 (en) * | 2012-10-23 | 2014-05-01 | 青岛海信信芯科技有限公司 | Methods for extracting depth map, judging video scenario switching and optimizing edge of depth map |
| CN103600707A (en) * | 2013-11-06 | 2014-02-26 | 同济大学 | Parking position detecting device and method of intelligent parking system |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 刘阳等: "黑白棋盘格角点检测算法", 《东北大学学报(自然科学版)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112767425A (en) * | 2020-12-30 | 2021-05-07 | 智车优行科技（北京）有限公司 | Parking space detection method and device based on vision |
| CN115206130A (en) * | 2022-07-12 | 2022-10-18 | 合众新能源汽车有限公司 | Parking space detection method, system, terminal and storage medium |
| CN115206130B (en) * | 2022-07-12 | 2023-07-18 | 合众新能源汽车股份有限公司 | Parking space detection method, system, terminal and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109753840B (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104112269B (en) | A kind of solar battery laser groove parameter detection method and system based on machine vision | |
| CN105654067A (en) | Vehicle detection method and device | |
| WO2021253245A1 (en) | Method and device for identifying vehicle lane changing tendency | |
| CN110232379A (en) | A kind of vehicle attitude detection method and system | |
| CN113326735B (en) | YOLOv 5-based multi-mode small target detection method | |
| WO2021017211A1 (en) | Vehicle positioning method and device employing visual sensing, and vehicle-mounted terminal | |
| CN115797736B (en) | Training method, device, equipment and medium for target detection model and target detection method, device, equipment and medium | |
| CN115063579B (en) | Train positioning pin looseness detection method based on two-dimensional image and three-dimensional point cloud projection | |
| CN109086803A (en) | A kind of haze visibility detection system and method based on deep learning and the personalized factor | |
| CN103778411A (en) | Circle detection method and device based on raster image division | |
| CN110349186A (en) | Optical flow computation method is moved based on the matched big displacement of depth | |
| CN104463240A (en) | Method and device for controlling list interface | |
| CN114581744A (en) | Image target detection method, system, equipment and storage medium | |
| CN109753840A (en) | A method of parking stall line angle point is determined based on response | |
| CN109086781A (en) | A kind of cabinet lamp state identification method based on deep learning | |
| CN113221659B (en) | Double-light vehicle detection method and device based on uncertain sensing network | |
| CN109389013A (en) | Parking stall combinational algorithm and medium based on parking stall principal direction and template response point | |
| CN109389644A (en) | Parking stall line detecting method based on direction gradient enhancing | |
| CN109523530A (en) | A kind of micro strip circular pad detection method and system | |
| CN115457130A (en) | Electric vehicle charging port detection and positioning method based on depth key point regression | |
| CN114283199A (en) | Dynamic scene-oriented dotted line fusion semantic SLAM method | |
| CN112630736B (en) | Parameter determination method, device, equipment and storage medium of road side radar | |
| CN114663344A (en) | Train wheel set tread defect identification method and device based on image fusion | |
| CN105930813A (en) | Method for detecting line text under any natural scene | |
| Fang et al. | SLAM algorithm based on bounding box and deep continuity in dynamic scene |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |