CN108454553A - One kind realizing obstacle detection technology based on human eye vision identification technology - Google Patents
One kind realizing obstacle detection technology based on human eye vision identification technology Download PDFInfo
- Publication number
- CN108454553A CN108454553A CN201711382570.1A CN201711382570A CN108454553A CN 108454553 A CN108454553 A CN 108454553A CN 201711382570 A CN201711382570 A CN 201711382570A CN 108454553 A CN108454553 A CN 108454553A
- Authority
- CN
- China
- Prior art keywords
- human eye
- barrier
- image
- vehicle
- obstacle detection
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R21/00—Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks
- B60R21/01—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents
- B60R21/013—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents including means for detecting collisions, impending collisions or roll-over
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
- B60Q9/008—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling for anti-collision purposes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/193—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Health & Medical Sciences (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to driving safety system technical fields, disclose one kind and realizing obstacle detection technology based on human eye vision identification technology, include the following steps：1）It keeps driver head position constant, acquires the eye image of driver using positioning camera, 2）The position for converting positioning camera, obtains the eye image information of five kinds of different angles.Obstacle detection technology should be realized based on human eye vision identification technology, by using human eye vision identification technology, using moving window algorithm to the visible area of human eye into line trace, collect the image-region that human eye can not be observed, and the space coordinate of barrier is determined using obstacle sensor, and the position of barrier is determined on barrier display screen, relative position to barrier relative to vehicle carries out overlapping judgement, determine whether the range present in barrier overlaps with the existing range of vehicle, the using effect of obstacle detection technology is realized to substantially increase this based on human eye vision identification technology.
Description
Technical field
The present invention relates to driving safety system technical fields, specially a kind of to realize obstacle based on human eye vision identification technology
Quality testing survey technology.
Background technology
With the high speed development of science and technology, the security performance of vehicle also stepping up, and is needed in vehicle travel process pair
Vehicle-surroundings carry out viewed in projection, but shown in display screen it is most of be hash, i.e. human eye vision is observed that
Picture, be difficult to be detected for the blind area of some drivers, for this purpose, we have proposed one kind based on human eye vision know
Other technology realizes obstacle detection technology to solve the above problems.
Invention content
（One）The technical issues of solution
In view of the deficiencies of the prior art, the present invention provides one kind realizing detection of obstacles skill based on human eye vision identification technology
Art has the advantages of being detected with human eye vision identification technology, solves the problems, such as that existing equipment using effect is bad.
（Two）Technical solution
To realize that the above-mentioned purpose being detected with human eye vision identification technology, the present invention provide the following technical solutions：It is a kind of
Obstacle detection technology is realized based on human eye vision identification technology, is included the following steps：
1）It keeps driver head position constant, the eye image of driver is acquired using positioning camera；
2）The position for converting positioning camera, obtains the eye image information of five kinds of different angles；
3）The image coordinate of human eye alignment features point is carried out to image and obtains the space of characteristic point according to principle of computer vision
Coordinate carries out three-dimensional modeling to eye image using three-dimensional modeling unit, human eye is identified in established space coordinates
The first space coordinate（X1, Y1, Z1）, according to the eye image information detected, the spatial position of its iris is carried out true
It is fixed, identify the second space coordinate of iris（X2, Y2, Z2）；
4）According to step 3）In obtained space coordinate, obtain location information of the human eye relative to barrier display screen；
5）After obtaining location information of the human eye relative to barrier display screen display screen, using moving window algorithm to human eye can
Viewed area collects the image-region that human eye can not be observed into line trace；
6）In the image-region that human eye can not be observed, the sky of barrier is determined using the obstacle sensor of vehicle front
Between coordinate, and on barrier display screen determine barrier position；
7）The position for the barrier relative to vehicle that testing result of the position of barrier based on obstacle sensor is determined
It is stored in memory, is updated according to the position of the variable quantity of vehicle location, the barrier to being stored on memory, from
And relative position of the current barrier relative to vehicle is determined successively；
8）Overlapping judgement is carried out relative to the relative position of vehicle to the barrier determined, determines the range present in barrier
Whether overlap with the existing range of vehicle；
9）When the existing range of range and vehicle present in the barrier overlaps, alarm is judged to needing to implement alarm
In the case of, carry out alert process to driver.
Preferably, the step 2）There are five types of the adjusting position of middle positioning camera is total, it is that center adjusts position to take 90 ° of directions
It sets, 30 °, 60 °, 90 °, 120 ° and 150 ° directions is taken to determine that five adjusting positions, the adjusting radius are 30 centimetres respectively.Institute
State step 3）In three-dimensional modeling unit include that data acquisition module, data analysis module, data concatenation module and data are built
Mould module, the three-dimensional modeling unit on automobile-used airborne LIDAR based on being designed.
Preferably, the step 5）After middle barrier display screen collects next frame image, previous frame figure is preferably picked out
The image-region that does not identify as in, is collected the image area data of appearance, repeatedly, finally detect human eye without
The image-region that method is observed.
Preferably, the step 8）The existing range of range and vehicle present in middle determining barrier overlaps,
Then carry out alert process；If the existing range of the range and vehicle present in barrier does not overlap, without alarm
Processing.
Preferably, the step 9）In alert process can be light emitting diode alarm or buzzer warning.
（Three）Advantageous effect
Compared with prior art, the present invention provides one kind realizing obstacle detection technology, tool based on human eye vision identification technology
Standby following advantageous effect：
Obstacle detection technology should be realized based on human eye vision identification technology, by using human eye vision identification technology, use shifting
Dynamic window algorithm, into line trace, collects the image-region that human eye can not be observed, and use to the visible area of human eye
Obstacle sensor determines the space coordinate of barrier, and the position of barrier is determined on barrier display screen, to barrier
Relative position relative to vehicle carries out overlapping judgement, determine range present in barrier whether the existing range with vehicle
It overlaps, the using effect of obstacle detection technology is realized to substantially increase this based on human eye vision identification technology, is had
Help the popularization of the technology.
Specific implementation mode
Below in conjunction with the embodiment of the present invention, technical solution in the embodiment of the present invention is clearly and completely retouched
It states, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Based on the present invention
In embodiment, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
One kind realizing obstacle detection technology based on human eye vision identification technology, includes the following steps：
1）It keeps driver head position constant, the eye image of driver is acquired using positioning camera；
2）The position for converting positioning camera, obtains the eye image information of five kinds of different angles；
3）The image coordinate of human eye alignment features point is carried out to image and obtains the space of characteristic point according to principle of computer vision
Coordinate carries out three-dimensional modeling to eye image using three-dimensional modeling unit, human eye is identified in established space coordinates
The first space coordinate（X1, Y1, Z1）, according to the eye image information detected, the spatial position of its iris is carried out true
It is fixed, identify the second space coordinate of iris（X2, Y2, Z2）, three-dimensional modeling unit includes data acquisition module, data analysis mould
Block, data concatenation module and data modeling module, three-dimensional modeling unit on automobile-used airborne LIDAR based on being designed；
4）According to step 3）In obtained space coordinate, obtain location information of the human eye relative to barrier display screen；
5）After obtaining location information of the human eye relative to barrier display screen display screen, using moving window algorithm to human eye can
Viewed area collects the image-region that human eye can not be observed into line trace, and barrier display screen collects next frame image
Afterwards, the image-region not identified in previous frame image is preferably picked out, the image area data of appearance is collected, is repeated
Repeatedly, the image-region that human eye can not be observed finally is detected；
6）In the image-region that human eye can not be observed, the sky of barrier is determined using the obstacle sensor of vehicle front
Between coordinate, and on barrier display screen determine barrier position；
7）The position for the barrier relative to vehicle that testing result of the position of barrier based on obstacle sensor is determined
It is stored in memory, is updated according to the position of the variable quantity of vehicle location, the barrier to being stored on memory, from
And relative position of the current barrier relative to vehicle is determined successively；
8）Overlapping judgement is carried out relative to the relative position of vehicle to the barrier determined, determines the range present in barrier
Whether overlap with the existing range of vehicle, determines that weight occurs for the existing range of the range and vehicle present in barrier
It is folded, then carry out alert process；If the existing range of the range and vehicle present in barrier does not overlap, without report
Alert processing；
9）When the existing range of range and vehicle present in the barrier overlaps, alarm is judged to needing to implement alarm
In the case of, alert process is carried out to driver, alert process can be light emitting diode alarm or buzzer warning.
The beneficial effects of the invention are as follows：Obstacle detection technology should be realized based on human eye vision identification technology, pass through utilization
Human eye vision identification technology, using moving window algorithm to the visible area of human eye into line trace, collecting human eye can not carry out
The image-region of observation, and determine using obstacle sensor the space coordinate of barrier, and on barrier display screen really
The position for determining barrier, the relative position to barrier relative to vehicle carry out overlapping judgement, determine the model present in barrier
It encloses and whether overlaps with the existing range of vehicle, being based on human eye vision identification technology to substantially increasing this realizes obstacle
The using effect of quality testing survey technology contributes to the popularization of the technology.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
Understanding without departing from the principles and spirit of the present invention can carry out these embodiments a variety of variations, modification, replace
And modification, the scope of the present invention is defined by the appended.
Claims (6)
1. one kind realizing obstacle detection technology based on human eye vision identification technology, which is characterized in that include the following steps：
1）It keeps driver head position constant, the eye image of driver is acquired using positioning camera；
2）The position for converting positioning camera, obtains the eye image information of five kinds of different angles；
3）The image coordinate of human eye alignment features point is carried out to image and obtains the space of characteristic point according to principle of computer vision
Coordinate carries out three-dimensional modeling to eye image using three-dimensional modeling unit, human eye is identified in established space coordinates
The first space coordinate（X1, Y1, Z1）, according to the eye image information detected, the spatial position of its iris is carried out true
It is fixed, identify the second space coordinate of iris（X2, Y2, Z2）；
4）According to step 3）In obtained space coordinate, obtain location information of the human eye relative to barrier display screen；
5）After obtaining location information of the human eye relative to barrier display screen display screen, using moving window algorithm to human eye can
Viewed area collects the image-region that human eye can not be observed into line trace；
6）In the image-region that human eye can not be observed, the sky of barrier is determined using the obstacle sensor of vehicle front
Between coordinate, and on barrier display screen determine barrier position；
7）The position for the barrier relative to vehicle that testing result of the position of barrier based on obstacle sensor is determined
It is stored in memory, is updated according to the position of the variable quantity of vehicle location, the barrier to being stored on memory, from
And relative position of the current barrier relative to vehicle is determined successively；
8）Overlapping judgement is carried out relative to the relative position of vehicle to the barrier determined, determines the range present in barrier
Whether overlap with the existing range of vehicle；
9）When the existing range of range and vehicle present in the barrier overlaps, alarm is judged to needing to implement alarm
In the case of, carry out alert process to driver.
2. according to claim 1 a kind of based on human eye vision identification technology realization obstacle detection technology, feature exists
In：The step 2）The adjusting position of middle positioning camera altogether there are five types of, it is center adjusting position to take 90 ° of directions, take respectively 30 °,
60 °, 90 °, 120 ° and 150 ° directions determine that five adjusting positions, the adjusting radius are 30 centimetres.
3. according to claim 1 a kind of based on human eye vision identification technology realization obstacle detection technology, feature exists
In：The step 3）In three-dimensional modeling unit include data acquisition module, data analysis module, data concatenation module and number
According to modeling module, the three-dimensional modeling unit on automobile-used airborne LIDAR based on being designed.
4. according to claim 1 a kind of based on human eye vision identification technology realization obstacle detection technology, feature exists
In：The step 5）After middle barrier display screen collects next frame image, preferably picks out and do not identified in previous frame image
Image-region, the image area data of appearance is collected, repeatedly, finally detects what human eye can not be observed
Image-region.
5. according to claim 1 a kind of based on human eye vision identification technology realization obstacle detection technology, feature exists
In：The step 8）The existing range of range and vehicle present in middle determining barrier overlaps, then carries out at alarm
Reason；If the existing range of the range and vehicle present in barrier does not overlap, without alert process.
6. according to claim 1 a kind of based on human eye vision identification technology realization obstacle detection technology, feature exists
In：The step 9）In alert process can be light emitting diode alarm or buzzer warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711382570.1A CN108454553A (en) | 2017-12-20 | 2017-12-20 | One kind realizing obstacle detection technology based on human eye vision identification technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711382570.1A CN108454553A (en) | 2017-12-20 | 2017-12-20 | One kind realizing obstacle detection technology based on human eye vision identification technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108454553A true CN108454553A (en) | 2018-08-28 |
Family
ID=63221260
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711382570.1A Pending CN108454553A (en) | 2017-12-20 | 2017-12-20 | One kind realizing obstacle detection technology based on human eye vision identification technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108454553A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113850972A (en) * | 2021-09-22 | 2021-12-28 | 南京问度智能物联有限公司 | Intelligent early warning method for engineering mechanical equipment based on power grid safety |
| CN113911058A (en) * | 2021-09-27 | 2022-01-11 | 东风汽车集团股份有限公司 | Vehicle control method, device, system, terminal device and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101925930A (en) * | 2008-03-27 | 2010-12-22 | 松下电器产业株式会社 | Blind spot display device |
| CN102474596A (en) * | 2009-07-13 | 2012-05-23 | 歌乐牌株式会社 | Blind-spot image display system for vehicle, and blind-spot image display method for vehicle |
| CN102538766A (en) * | 2011-12-21 | 2012-07-04 | 武汉科技大学 | Obstacle test method for active intelligent vehicle |
| CN105930821A (en) * | 2016-05-10 | 2016-09-07 | 上海青研信息技术有限公司 | Method for identifying and tracking human eye and apparatus for applying same to naked eye 3D display |
| CN106796758A (en) * | 2014-10-22 | 2017-05-31 | 株式会社电装 | Obstacle alert device |
-
2017
- 2017-12-20 CN CN201711382570.1A patent/CN108454553A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101925930A (en) * | 2008-03-27 | 2010-12-22 | 松下电器产业株式会社 | Blind spot display device |
| CN102474596A (en) * | 2009-07-13 | 2012-05-23 | 歌乐牌株式会社 | Blind-spot image display system for vehicle, and blind-spot image display method for vehicle |
| CN102538766A (en) * | 2011-12-21 | 2012-07-04 | 武汉科技大学 | Obstacle test method for active intelligent vehicle |
| CN106796758A (en) * | 2014-10-22 | 2017-05-31 | 株式会社电装 | Obstacle alert device |
| CN105930821A (en) * | 2016-05-10 | 2016-09-07 | 上海青研信息技术有限公司 | Method for identifying and tracking human eye and apparatus for applying same to naked eye 3D display |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113850972A (en) * | 2021-09-22 | 2021-12-28 | 南京问度智能物联有限公司 | Intelligent early warning method for engineering mechanical equipment based on power grid safety |
| CN113911058A (en) * | 2021-09-27 | 2022-01-11 | 东风汽车集团股份有限公司 | Vehicle control method, device, system, terminal device and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107635129B (en) | Three-dimensional trinocular camera device and depth fusion method | |
| CN106650708B (en) | Automatic driving obstacle vision detection method and system | |
| CN102944224B (en) | Work method for automatic environmental perception systemfor remotely piloted vehicle | |
| CN102435174B (en) | Method and device for detecting barrier based on hybrid binocular vision | |
| CN110244282B (en) | Multi-camera system and laser radar combined system and combined calibration method thereof | |
| CN104902246A (en) | Video monitoring method and device | |
| CN110738150B (en) | Camera linkage snapshot method and device and computer storage medium | |
| CN112102409B (en) | Target detection method, device, equipment and storage medium | |
| CN112365549B (en) | Attitude correction method and device for vehicle-mounted camera, storage medium and electronic device | |
| CN111179345A (en) | Method and system for automatically detecting violation behaviors of crossing lines of front vehicle based on vehicle-mounted machine vision | |
| CN104902261B (en) | Apparatus and method for the road surface identification in low definition video flowing | |
| CN102496232B (en) | Transmission facility monitoring method and system | |
| CN110850413A (en) | Method and system for detecting front obstacle of automobile | |
| CN104374376A (en) | Vehicle-mounted three-dimensional measurement system device and application thereof | |
| CN104036488A (en) | Binocular vision-based human body posture and action research method | |
| CN106162144A (en) | A kind of visual pattern processing equipment, system and intelligent machine for overnight sight | |
| CN104966062A (en) | Video monitoring method and device | |
| CN104935893A (en) | Monitoring method and device | |
| CN105760846A (en) | Object detection and location method and system based on depth data | |
| CN110491060A (en) | A kind of robot and its method for safety monitoring, device and storage medium | |
| CN108021899A (en) | Vehicle intelligent front truck anti-collision early warning method based on binocular camera | |
| CN111222441B (en) | Point cloud target detection and blind area target detection method and system based on vehicle-road cooperation | |
| CN110083099B (en) | Automatic driving architecture system meeting automobile function safety standard and working method | |
| CN107145825A (en) | Ground level fitting, camera calibration method and system, car-mounted terminal | |
| CN106915303A (en) | Automobile A-column blind area perspective method based on depth data and fish eye images |
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: 20180828 |