CN110008918A - A kind of motorcycle simulator driver gestures recognition methods - Google Patents
A kind of motorcycle simulator driver gestures recognition methods Download PDFInfo
- Publication number
- CN110008918A CN110008918A CN201910291096.4A CN201910291096A CN110008918A CN 110008918 A CN110008918 A CN 110008918A CN 201910291096 A CN201910291096 A CN 201910291096A CN 110008918 A CN110008918 A CN 110008918A
- Authority
- CN
- China
- Prior art keywords
- image
- pattern
- driver
- recognition methods
- tilt angle
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/243—Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- 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
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B9/00—Simulators for teaching or training purposes
- G09B9/02—Simulators for teaching or training purposes for teaching control of vehicles or other craft
- G09B9/04—Simulators for teaching or training purposes for teaching control of vehicles or other craft for teaching control of land vehicles
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Aviation & Aerospace Engineering (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of motorcycle simulator driver gestures recognition methods, including acquisition image information, color identification, shape matching and angle correction and etc..The present invention passes through the specific pattern in driver's setting behind, its central axes are calculated by the identification to predetermined pattern, since the pattern is synchronous with the change in location of driver in driver's operating process, it therefore is tilt angle of the driver when driving vehicle travel process to the calculating of the pattern central axes tilt angle, and the practical tilt angle that drives is modified according to initial angle, to obtain the inclined exact value of driver.
Description
Technical field
The present invention relates to drive simulating technical field more particularly to a kind of motorcycle simulator driver gestures identification sides
Method.
Background technique
Due to the controling power to speed when motorcycle drives as a part important in China's communications and transportation, but new person
Deficiency usually will appear contingency, make many new persons daunting.And present driving analog system, user is provided
True driving condition is simulated, motor cycle rider's simulation system utilizes design similar with real motorcycle, and should by operation
Motor cycle rider's device, and generate operation signal and pass to system, and the corresponding anti-of motorcycle generation is shown by display device
It answers, generates the effect of drive simulating, it is therefore desirable to which a kind of motorcycle simulator driver gestures recognition methods is rubbed by identification
The posture of motorcycle jockey's upper body carrys out steering of the motorcycle simulator in virtual scene.
Summary of the invention
It is an object of the present invention in view of the above-mentioned problems, propose a kind of motorcycle simulator driver gestures recognition methods.
A kind of motorcycle simulator driver gestures recognition methods, includes the following steps:
S1: camera is installed in motorcycle tail, acquires driver gestures image information;
S2: color identification removes the background information in image according to color characteristic;
S3: noise present in image information is eliminated;
S4: shape matching and angle calculation;
S5: declining angle rectification is carried out according to the initial position of video camera.
Background information in the removal image be by the way that the rgb space of color of image is converted to HSV space, and according to
H, the pixel value range in tri- channels S, V screens pixel, removes the ambient noise area in image according to color characteristic
Domain.
The step S3 further includes following sub-step:
S31: image information is filtered by median filter;
S32: morphologic opening operation and closed operation are carried out to binary image.
The opening operation and closed operation include two sub-steps of image expansion and Image erosion;
Image erosion realize process are as follows: by the origin translation of B into A the position pixel (x, y), if B image picture elements (x,
Y) place is completely contained in the overlapping region of A, then 1 is exported at (x, y), otherwise exports 0, formula expression are as follows:
Image expansion realize process are as follows: by the origin translation of B into A the position pixel (x, y), if B image picture elements (x,
Y) intersection of place and A are not empty, then export the corresponding pixel (x, y) of image and be assigned a value of 1, be otherwise assigned a value of 0;
Wherein A is target image, B structure element.
The step S4 further includes following sub-step:
S41: pattern contour detection;
S42: polygonal segments, the polygon pattern of the rule obtained;
S43: shape matching is carried out according to the feature that default rectangle inside includes triangle, obtains the position letter of target pattern
Breath;
S44: according to location information, tilt angle calculating is carried out.
The process that the tilt angle calculates are as follows: the central axes that pattern is determined according to the location information of pattern record respectively
Rectangle central axes when initial time and pattern tilt, calculate the tilt angle of central axes.
The declining angle rectification is the mean value by calculating driver's tilt angle in 200ms, and according to this inclination angle
Degree corrects the tilt angle after 200ms.
Beneficial effects of the present invention: the present invention is by the specific pattern in driver's setting behind, by predetermined pattern
Identification its central axes are calculated, since the pattern is synchronous with the change in location of driver in driver's operating process
, therefore be tilt angle of the driver when driving vehicle travel process to the calculating of the pattern central axes tilt angle,
And the practical tilt angle that drives is modified according to initial angle, to obtain the inclined exact value of driver
Detailed description of the invention
Fig. 1 is a kind of flow chart of motorcycle simulator driver gestures recognition methods.
Fig. 2 is that pattern tilt angle calculates schematic diagram.
Specific embodiment
For a clearer understanding of the technical characteristics, objects and effects of the present invention, this reality of Detailed description of the invention is now compareed
With novel specific embodiment.
A kind of motorcycle simulator driver gestures recognition methods, includes the following steps:
S1: camera is installed in motorcycle tail, acquires driver gestures image information;
S2: color identification removes the background information in image according to color characteristic;
S3: noise present in image information is eliminated;
S4: shape matching and angle calculation;
S5: declining angle rectification is carried out according to the initial position of video camera.
In the present embodiment, camera is disposed in motorcycle tail, camera is with respect to ground keeping parallelism, riding position distance
Driver back 40cm to 60cm, the about 50cm highly above driving platform adjust camera focal length and guarantee image clearly, to taking the photograph
As the large percentage that head image is tested, and guarantee camera captured image driver occupies, external environment is reduced to the later period
The interference of image.
In driver gestures identification, it is necessary first to carry out pattern identification to driver gestures.
The identification of pattern is divided into two stages, and first stage identification process is positioned to pattern, and the method used is
The color of predetermined pattern is identified, the background information in image is removed according to color characteristic.The figure that camera captures
As the image that information is rgb format, in order to facilitate our processing to image information, the color space of image is carried out first
Conversion, is converted to HSV space by the space RGB.The cone that hsv color spatial model corresponds in cylindrical-coordinate system is sat
Mark system, describes color using tone, color saturation, brightness.
The conversion regime that rgb space is transformed into HSV space is as follows:
C max=max (R ', G ', B ')
C min=min (R ', G ', B ')
Δ=C max-C min
H is calculated:
S is calculated:
V is calculated:
V=C max
After image is switched to HSV space, pixel is screened according to the pixel value range in tri- channels H, S, V, is obtained
To the color value of target pattern, so as to efficiently orient in a complicated background and region similar in predetermined pattern, sieve
Most noise region is fallen in choosing.
The second stage of pattern identification is that the binarization pattern obtained to the upper stage carries out shape matching.Since camera is hard
The interference of background color in the limitation and color identification process of part condition inevitably exists in the image information of binaryzation and makes an uproar
Sound.It needs to be removed noise before outline identification.First pass around median filter filtering, then to binary image into
The morphologic opening operation of row and closed operation, expand image and are corroded, can smooth binary image by above two step
Boundary excludes noise interference, eliminates salt-pepper noise present in image.The realization principle of corrosion is as follows: setting A as target image, B
Structural element, as origin translation pixel (x, y) into A of B, if the overlay region for being completely contained in A at (x, y) of B
In domain, then 1 is exported at (x, y), otherwise exports 0.Formula expression are as follows:
The realization principle of expansion is as follows: A is expanded with structure B, by the origin translation of structural element B to target image A pixel
The position (x, y).If B is at image picture elements (x, y) and the intersection of A is not sky, exports the corresponding pixel (x, y) of image and assign
Value is 1, is otherwise assigned a value of 0.Formula expression are as follows:
Captured image information is carried out to carry out outline identification to pattern after eliminating noise, predetermined pattern is rectangle, line with
Horizontal angle also can be obtained by the tilt angle of driver.
Rectangle inside includes multiple triangles as detection feature.Polygon is carried out to the pattern contour that identification obtains to force
Closely, the polygon for obtaining rule includes that this feature of triangle carries out shape matching according to rectangle inside, removes and exist in background
Interference profile, obtain the location information of target pattern.As shown in Fig. 2, determining the axis of pattern according to the apex coordinate of rectangle
The calculation formula of rectangle axis tilt angle L can be calculated using trigonometric function in pattern inclination for line are as follows:A in figure, B, C, D are 4 vertex of pattern before tilting, A ', B ', C ', D ' it is 4 of pattern after tilting
A vertex, MN are the central axes of pattern before tilting, and M ' N ' is the central axes of pattern after inclination, intersection point of the O between MN and A ' B '.
It needs to carry out initial angle correction to tilt angle after obtaining tilt angle, in the operation of driver's simulator
In the process, the initial position of video camera keeps horizontality with simulator always, but not can guarantee driver in the preparation stage
The pattern and simulator of behind are horizontal, so if directly using the tilt angle being calculated as a result, inevitably
There can be error.In order to eliminate the error of original state, the method for use are as follows: after simulator start-up operation, driver's is first
After beginning position is fixed, the mean value of driver's tilt angle at this time is calculated according to the image captured in 200ms before video camera,
The angle that the value is corrected as needs, the obtained tilt angle after 200ms is corrected all in accordance with the value, thus
To the inclined exact value of driver.
Its is calculated by the identification to predetermined pattern by the specific pattern in driver's setting behind in the present invention
Central axes, due to the pattern be with the change in location of driver in driver's operating process it is synchronous, in the pattern
The calculating of shaft angle degree is tilt angle of the driver when driving vehicle travel process, and according to initial angle to reality
Border drives tilt angle and is modified, to obtain the inclined exact value of driver.
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (7)
1. a kind of motorcycle simulator driver gestures recognition methods, which comprises the steps of:
S1: camera is installed in motorcycle tail, acquires driver gestures image information;
S2: color identification removes the background information in image according to color characteristic;
S3: noise present in image information is eliminated;
S4: shape matching and angle calculation;
S5: declining angle rectification is carried out according to the initial position of video camera.
2. a kind of motorcycle simulator driver gestures recognition methods according to claim 1, which is characterized in that described to go
Except the background information in image is by the way that the rgb space of color of image is converted to HSV space, and according to tri- channels H, S, V
Pixel value range pixel is screened, according to color characteristic remove image in ambient noise region.
3. a kind of motorcycle simulator driver gestures recognition methods according to claim 1, which is characterized in that the step
Rapid S3 further includes following sub-step:
S31: image information is filtered by median filter;
S32: morphologic opening operation and closed operation are carried out to binary image.
4. a kind of motorcycle simulator driver gestures recognition methods according to claim 3, which is characterized in that described to open
Operation and closed operation include two sub-steps of image expansion and Image erosion;
Image erosion realize process are as follows: by the origin translation of B into A the position pixel (x, y), if B is at image picture elements (x, y)
It is completely contained in the overlapping region of A, then exports 1 at (x, y), otherwise export 0, formula expression are as follows:
Image expansion realize process are as follows: by the origin translation of B into A the position pixel (x, y), if B is at image picture elements (x, y)
Intersection with A is not sky, then exports the corresponding pixel (x, y) of image and be assigned a value of 1, be otherwise assigned a value of 0;
Wherein A is target image, B structure element.
5. a kind of motorcycle simulator driver gestures recognition methods according to claim 1, which is characterized in that the step
Rapid S4 further includes following sub-step:
S41: pattern contour detection;
S42: polygonal segments, the polygon pattern of the rule obtained;
S43: shape matching is carried out according to the feature that default rectangle inside includes triangle, obtains the location information of target pattern;
S44: according to location information, tilt angle calculating is carried out.
6. a kind of motorcycle simulator driver gestures recognition methods according to claim 5, which is characterized in that described to incline
The process that rake angle calculates are as follows: determine the central axes of pattern according to the location information of pattern, record initial time and pattern respectively
Rectangle central axes when inclination, calculate the tilt angle of central axes.
7. a kind of motorcycle simulator driver gestures recognition methods according to claim 1, which is characterized in that described to incline
Rake angle rectifys the mean value for being exactly based on and calculating driver's tilt angle in 200ms, and according to this tilt angle to inclining after 200ms
Rake angle is corrected.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910291096.4A CN110008918B (en) | 2019-04-11 | 2019-04-11 | Method for identifying posture of motorcycle simulator driver |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910291096.4A CN110008918B (en) | 2019-04-11 | 2019-04-11 | Method for identifying posture of motorcycle simulator driver |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110008918A true CN110008918A (en) | 2019-07-12 |
CN110008918B CN110008918B (en) | 2023-06-06 |
Family
ID=67171235
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910291096.4A Active CN110008918B (en) | 2019-04-11 | 2019-04-11 | Method for identifying posture of motorcycle simulator driver |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110008918B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113492850A (en) * | 2020-04-06 | 2021-10-12 | 丰田自动车株式会社 | Inclination angle detection device and control device |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101458763A (en) * | 2008-10-30 | 2009-06-17 | 中国人民解放军国防科学技术大学 | Automatic human face identification method based on image weighting average |
US20140168059A1 (en) * | 2012-12-18 | 2014-06-19 | Hyundai Motor Company | Method and system for recognizing gesture |
CN105809138A (en) * | 2016-03-15 | 2016-07-27 | 武汉大学 | Road warning mark detection and recognition method based on block recognition |
CN105807912A (en) * | 2015-01-21 | 2016-07-27 | 现代自动车株式会社 | Vehicle, method for controlling the same and gesture recognition apparatus therein |
CN106915302A (en) * | 2015-12-24 | 2017-07-04 | Lg电子株式会社 | For the display device and its control method of vehicle |
CN108890692A (en) * | 2018-07-05 | 2018-11-27 | 陕西大中科技发展有限公司 | A kind of material color identification method for industrial robot vision's sorting |
-
2019
- 2019-04-11 CN CN201910291096.4A patent/CN110008918B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101458763A (en) * | 2008-10-30 | 2009-06-17 | 中国人民解放军国防科学技术大学 | Automatic human face identification method based on image weighting average |
US20140168059A1 (en) * | 2012-12-18 | 2014-06-19 | Hyundai Motor Company | Method and system for recognizing gesture |
CN105807912A (en) * | 2015-01-21 | 2016-07-27 | 现代自动车株式会社 | Vehicle, method for controlling the same and gesture recognition apparatus therein |
CN106915302A (en) * | 2015-12-24 | 2017-07-04 | Lg电子株式会社 | For the display device and its control method of vehicle |
CN105809138A (en) * | 2016-03-15 | 2016-07-27 | 武汉大学 | Road warning mark detection and recognition method based on block recognition |
CN108890692A (en) * | 2018-07-05 | 2018-11-27 | 陕西大中科技发展有限公司 | A kind of material color identification method for industrial robot vision's sorting |
Non-Patent Citations (1)
Title |
---|
王晓婷: "基于深度学习的驾驶疲劳检测应用的设计与实现", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113492850A (en) * | 2020-04-06 | 2021-10-12 | 丰田自动车株式会社 | Inclination angle detection device and control device |
CN113492850B (en) * | 2020-04-06 | 2023-11-03 | 丰田自动车株式会社 | Inclination angle detection device and control device |
Also Published As
Publication number | Publication date |
---|---|
CN110008918B (en) | 2023-06-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110650368B (en) | Video processing method and device and electronic equipment | |
CN107292965B (en) | Virtual and real shielding processing method based on depth image data stream | |
US10178314B2 (en) | Moving object periphery image correction apparatus | |
JP5463866B2 (en) | Image processing apparatus, image processing method, and program | |
US10304164B2 (en) | Image processing apparatus, image processing method, and storage medium for performing lighting processing for image data | |
JP5016541B2 (en) | Image processing apparatus and method, and program | |
US11783443B2 (en) | Extraction of standardized images from a single view or multi-view capture | |
US8055016B2 (en) | Apparatus and method for normalizing face image used for detecting drowsy driving | |
CN103770708A (en) | Dynamic rearview mirror adaptive dimming overlay through scene brightness estimation | |
JP2000020728A (en) | Image processor and image processing method | |
WO2007074844A1 (en) | Detecting method and detecting system for positions of face parts | |
CN103597516A (en) | Controlling objects in a virtual environment | |
US20090245625A1 (en) | Image trimming device and program | |
CN110245199B (en) | Method for fusing large-dip-angle video and 2D map | |
CN110941996A (en) | Target and track augmented reality method and system based on generation of countermeasure network | |
CN113902965A (en) | Multi-spectral pedestrian detection method based on multi-layer feature fusion | |
CN109916415A (en) | Road type determines method, apparatus, equipment and storage medium | |
CN106682652A (en) | Structure surface disease inspection and analysis method based on augmented reality | |
JP2009205283A (en) | Image processing apparatus, method and program | |
CN110008918A (en) | A kind of motorcycle simulator driver gestures recognition methods | |
CN108961182B (en) | Vertical direction vanishing point detection method and video correction method for video image | |
JP5201184B2 (en) | Image processing apparatus and program | |
JP4496005B2 (en) | Image processing method and image processing apparatus | |
US9323981B2 (en) | Face component extraction apparatus, face component extraction method and recording medium in which program for face component extraction method is stored | |
CN112132753A (en) | Infrared image super-resolution method and system for multi-scale structure guide image |
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 |