CN1713696A - Environmental identification from image process and outputtig device for end - Google Patents
Environmental identification from image process and outputtig device for end Download PDFInfo
- Publication number
- CN1713696A CN1713696A CNA2004100499815A CN200410049981A CN1713696A CN 1713696 A CN1713696 A CN 1713696A CN A2004100499815 A CNA2004100499815 A CN A2004100499815A CN 200410049981 A CN200410049981 A CN 200410049981A CN 1713696 A CN1713696 A CN 1713696A
- Authority
- CN
- China
- Prior art keywords
- treatment element
- input element
- image
- analysis
- information
- 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
- 238000000034 method Methods 0.000 title claims description 6
- 230000007613 environmental effect Effects 0.000 title description 2
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 230000004888 barrier function Effects 0.000 claims description 18
- 238000005516 engineering process Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 7
- 230000004069 differentiation Effects 0.000 claims description 4
- 238000009434 installation Methods 0.000 claims description 3
- 239000003550 marker Substances 0.000 claims description 3
- 239000011449 brick Substances 0.000 claims description 2
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 239000002352 surface water Substances 0.000 claims description 2
- 238000010191 image analysis Methods 0.000 claims 1
- 238000001228 spectrum Methods 0.000 claims 1
- 208000029257 vision disease Diseases 0.000 abstract 1
- 239000003086 colorant Substances 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 235000014698 Brassica juncea var multisecta Nutrition 0.000 description 1
- 241000283070 Equus zebra Species 0.000 description 1
- 241000251184 Rajiformes Species 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
- Rehabilitation Tools (AREA)
Abstract
The invention can be used by visual disorder persons or unmanned vehicles. It consists of at least a CCD or CMOS component used to acquire image, a processor used to MCU and an output unit that can be sound prompt earphone. The processor uses tone analysis and geometry analysis to distinguish traffic light and mark lines.
Description
Technical field
The relevant a kind of electronic installation of the present invention specifically, about a kind of electronic installation of image processing to differentiate surrounding environment and the differentiation result can be exported that use, uses for visually impaired person.
Background technology
One is marched toward modern society, will spend more mental and physical efforts and go to look after handicapped person.The person is an example to look the barrier, from traditional blind-guiding stick, and seeing-eye dog, the visible modulating signal sound in street corner caution till now, facility is not few to make the person that looks the barrier take action more, but it all has different shortcomings.Traditional blind-guiding stick can only find out before the body nearby that there is clear on ground, then knows nothing for situation at a distance.Seeing-eye dog then can't with the person's interaction of looking the barrier, it is done some preparations to the place ahead situation, and the seeing-eye dog training is very high with feeding cost, non-common people can bear.Build terrestrial reference (for example modulating signal sound at crossing caution, or phonetic guiding etc.) in advance and need do existing avenue and overhaul comprehensively, its cost is too high.
Because the progress of electronic motor science and technology, there are many relevant patents to do prospective improvement at traditional guide equipment, No. the 563525th, Taiwan patent announcement " traffic blind-guide device " for example, it makes improvement to traditional blind-guide brick, make it when red light, have magnetic, can hold special blind-guiding stick or specially look the barrier person uses footwear, but its shortcoming is that the person must use described special blind-guiding stick or look the barrier person with the footwear except all look the barrier, it still needs existing avenue is done comprehensive renewal, otherwise only not too big meaning is installed at the minority crossing.
No. the 518965th, Taiwan notification number " voice guide glasses " for another example, this patent is a kind of glasses that are provided with checkout gear and output earphone, two kinds of functions of this checkout gear tool, but the color of first kind of traffic signals sign such as function sensing traffic lights is with the color of earphone notice person the place ahead modulating signal of looking the barrier; Second kind of function can be launched infrared light beam, learns the place ahead barrier situation by the infrared light beam of detection of reflected, and how the person moves to look the barrier with the earphone indication.This invention conception is more ingenious at first sight, but discussible place is more after going into seriously:
1. this case adopts RGB beam split filter to handle traffic lights light, but need know that all luminous raies all can be decomposed into the RGB three primary colors.If carry out the traffic lights real time discriminating by the image information of carrying out after the RGB three primary colors decompose, conceivable is that the data volume that is produced will be very huge, so the method that this case adopted not is the preferred plan on the engineering.
2. even computer technology has had significant progress, these huge data of energy real-time operation, but RGB three primary colors decomposing system has visibly different filter result under the light environment that power does not wait, thus cause the erroneous judgement situation on the high side.
3. this invention only can be differentiated traffic lights and barrier situation in front, and is just powerless for the indication of planes such as graticule, yet in daily life, it is many providing the situation of walking along the street information with plane landmark.
The present inventor is the present post professor of university, and special smart image recognition and computer vision at the shortcoming of above known technology, propose the real feasible solution of a cover.
Summary of the invention
Apparatus of the present invention mainly are made of three parts, shown in the 1st figure in the accompanying drawing, first is an input element, it mainly can be by one or more CMOS (Complementary Metal-OxideSemiconductor, complementary metal oxide semiconductors (CMOS)) or CCD (Charge-Coupled Device, charge coupled device) member constitute; Second portion is a treatment element, and it can be made of the mobile arithmetic system an of PDA (personal digital assistant) or notebook computer and so on, and the image recognition technology of its use will be in describing in detail after a while; Third part is an output element, and it can be an instantaneous speech power or a sense of touch output device.
This input element mainly comprises CMOS or CCD shooting member, and it absorbs coloured image and sends this treatment element to does image discriminating.This input element can contain the active sensor component just like infrared ray or radar and so in addition, to promote the function of total system.
This treatment element is after receiving the coloured image that comes from input element, earlier transfer it to HSV form (hue/saturation/brightness), to adapt to the Different Light environment, demarcate hue information in the image after conversion then near traffic lights signal and the main block that closely links.This kind is converted to known technology, and common on the market softwares such as Photoshop have just included similar functions at present.
After as above changing, can in image, calibrate and to be traffic lights signal place, assist a ruler in governing a country again with other criterions, for example whether the traffic lights signal changes by the rational time interval, whether have other assist a ruler in governing a country modulating signal (as expression stop red humanoid) exist, whether modulating signal be circle (or the possible shape of any modulating signal; This kind Figure recognition is a known technology).
Except the existence of identification traffic lights signal, this treatment element also can according to input element take the photograph image find out whether there is graticule on the road surface.Because graticule (for example zebra stripes on crosswalk road) is the figure that rule is extended, therefore can pick out its length, width and direction easily with tone and how much detection techniques.
This treatment element except above-mentioned basic function, can also adopt known technologies such as stereoscopic vision analytical technology or error image analytical technology be identified in this input element take the photograph image in whether have barrier fixing or that move to exist.Also can utilize the obtained data of active sensor component that contain in addition such as texture analysis, spectrum analysis or input unit that environment is had more accurate understanding.Wherein with error image analyze mobile platform taken the photograph in the image technology of barrier be found in European patent EP 1391845, " Image Based0bject Detection Apparatus and Method ".
This treatment element also can be analyzed how much on line segment and the tone in the input element acquisition video, finds out surface water horizontal line information, adjusts the elevation angle voluntarily and drive this input element; Or drive this output element and export a prompting, notify user's manual adjustment this input element elevation angle.
At last, this treatment element can have a default pattern, in this pattern, except basic system's adjustment, can also carry out " education " to this device, and the accuracy that this device is in use discerned is more and more higher.Enter the default pattern or in this default pattern method of operating, except this treatment element of direct control, can also for example before this shooting member, make the gesture of appointment etc. by giving this input element input specified message realization.
The ambient environmental conditions that this output element is then differentiated according to this treatment element is sent suitable voice or haptic message in good time and is looked the barrier with guiding the person advances.
By last sight it, advantage of the present invention is as follows:
1. before based on the blind-guide device conception of active detection means, except power consumption was big, lack of resolution cost an arm and a leg, and can't differentiate graticule all is shortcoming.The present invention has solved the problems referred to above with image processing method.
2. the image of taking the photograph except the passive type analysis is to differentiate the surrounding environment, and this device can also add joins active detection means to satisfy under the special status more strict demand.
3. this input element can comprise a recording function, and this recording function also can provide the usefulness of this device self-teaching except can increasing the overall understanding to environment.
4. with low cost.
5. this device also can be applicable to the self-Navigation Control of unmanned delivery vehicle except guiding function, and especially at environment in the single and complete controllable factory, this device is applied in and has best effect on the unmanned delivery vehicle.
Description of drawings
Fig. 1 is a device schematic diagram of the present invention;
Fig. 2 is the outward appearance explanation of the present invention's one specific embodiment;
Fig. 3 is the action flow chart of the present invention's one specific embodiment.
Embodiment
Relevant concrete implementation step of the present invention and apparatus structure are asked for an interview the 2nd and the 3rd figure in the accompanying drawing.These embodiment only illustrate the simplest and easy execution mode of the present invention so that the easier quilt of the present invention is understood, but it is not in order to the restriction embodiments of the present invention, the those skilled in the art can make an amendment to execution mode, but still does not break away from spirit of the present invention and category.
This embodiment comprises a microcam 1, and it is made up of CCD or CMOS member, a microprocessor system 2 (as notebook computer or PDA), and a voice suggestion earphone 3.Wherein this microcam 1 is worn on the person front of looking the barrier or the stable place of head, 2 of microprocessor systems wear on one's body, as shown in Figure 2.
Ask for an interview Fig. 3, after this blind-guide device started, this microcam 1 began pickup image immediately, and sends the image that is absorbed to microprocessor system 2, and is converted to the HSV form.If summary is described, can be earlier be after 0～1 with the luminance standardization (normalize) of R, G, B (Red Green Blue) in the coloured image, with following formula calculate and tone (H) value:
H=H
1If B≤G
H=360 °-H
1If B＞G
Then demarcate hue information near traffic lights signal part:
When 0＜H＜0.125 is the red colored lamp signal, and 0.125＜H＜0.22 o'clock is the amber light signal, and 0.25＜H＜0.45 o'clock is the green light signal.
Whether this microprocessor is differentiated microcam 1 angle simultaneously correct, and revise in good time.
As Fig. 3, when microprocessor system 2 is found doubtful traffic lights signal, promptly demarcate, and with other supplementary analysis-by-synthesis, geometry as modulating signal, whether auxiliary signal sign (red humanoid marker that stops as expression etc.) is arranged on every side, whether have the crosswalk road in addition, information such as the width on crosswalk road and length, direction.After the comprehensive distinguishing, if be defined as modulating signal, but then can be according to the traffic status of modulating signal this moment, with judged result by the earphone 3 notices person that looks the barrier.If can pass through, then except information such as width that the crosswalk road is provided by earphone 3 and length, direction, this blind-guide device also can be with methods such as error image detection of obstacles calculation rules, and whether detect the place ahead has barrier, and by the earphone 3 notices person that looks the barrier.
Claims (15)
1. a sensing and judge the electronic installation of surrounding environment, it comprises:
One input element, it comprises at least one CCD or CMOS member, in order to captured image;
One treatment element, it can move arithmetic system by one and form; And
One output element, it can be a voice suggestion element or sense of touch output element etc.,
This input element sensing ambient condition information also is sent to this treatment element to differentiate, again by the data output of this output element with surrounding environment.
2. device according to claim 1, wherein said input element also can comprise an active sensor component in addition, and it is a radar member or a ultrasonic waves member etc.
3. device according to claim 1, the light frequency that wherein said input element absorbed can not only be visible light.
4. device according to claim 1, wherein said treatment element can carry out the differentiation of traffic lights signal and various marker and graticule by the data that described input element obtains.
5. device according to claim 1, wherein said treatment element can carry out barrier in the surrounding environment, other mobile objects or navigation information (as the warning of road surface fluctuating by the data that described input element obtains, the tracking of blind-guide brick, identification of pavement edge etc.) differentiation.
6. device according to claim 4, wherein said treatment element utilize tone analysis and geometrical analysis that traffic lights signal and various marker and graticule are differentiated.
7. device according to claim 6, the operation that wherein said treatment element is differentiated the traffic lights signal is:
The coloured image of described input element picked-up is converted to the HSV form;
Hue information is similar to modulating signal and tight connectionist in the selection image;
It is carried out geometrical analysis to determine whether the being modulating signal shape; And
Check whether there is other aid identification information, as modulating signal whether can red, green, yellow, red according to rational time interval conversion, whether contiguous have an auxiliary lamp signal etc.
8. device according to claim 6, wherein said treatment element can utilize the straight-line detection technology to search the crosswalk marking lines, and differentiate information such as its direction, width, length.
9. according to claim 4 or 5 described devices, wherein said treatment element also can utilize such as methods such as error image analysis, stereoscopic vision analysis, object texture analysis or spectrum analyses to differentiate surrounding environment.
10. device according to claim 1, wherein said treatment element can obtain line segment geometry and tone data in the image by analyzing via described input element, finds out surface water horizontal line information, learns the elevation angle of present input element with this.
11. device according to claim 10, wherein said treatment element can drive described input element and adjust the elevation angle voluntarily, or drives described output element and export a prompting, notifies the elevation angle of the described input element of user's manual adjustment.
12. device according to claim 1, wherein said treatment element can comprise a default pattern.
13. device according to claim 12, the operation of wherein said default pattern can be finished input equipment input information specific by the described treatment element of direct control or according to the user.
14. according to claim 12 or 13 described devices, wherein said default pattern can comprise a self-teaching set-up function.
15. device according to claim 1, wherein said treatment element can be according to the data of the described input element video recording basis as self-teaching.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2004100499815A CN1713696A (en) | 2004-06-24 | 2004-06-24 | Environmental identification from image process and outputtig device for end |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2004100499815A CN1713696A (en) | 2004-06-24 | 2004-06-24 | Environmental identification from image process and outputtig device for end |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN1713696A true CN1713696A (en) | 2005-12-28 |
Family
ID=35719107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2004100499815A Pending CN1713696A (en) | 2004-06-24 | 2004-06-24 | Environmental identification from image process and outputtig device for end |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1713696A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102114840A (en) * | 2011-01-20 | 2011-07-06 | 浙江吉利汽车研究院有限公司 | Driving safety control device on road surface change |
| CN102254078A (en) * | 2010-05-17 | 2011-11-23 | 上海杰远环保科技有限公司 | Multifunctional carbon footprint calculation terminal and implementation method thereof |
| CN102095207B (en) * | 2009-12-14 | 2012-08-22 | 财团法人工业技术研究院 | Combustion process monitoring and diagnosing method based on image |
| CN103854503A (en) * | 2012-12-06 | 2014-06-11 | 通用汽车环球科技运作有限责任公司 | A traffic light detection system |
| CN104739622A (en) * | 2015-02-04 | 2015-07-01 | 覃泳睿 | Novel wearable blind guiding equipment and working method thereof |
-
2004
- 2004-06-24 CN CNA2004100499815A patent/CN1713696A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102095207B (en) * | 2009-12-14 | 2012-08-22 | 财团法人工业技术研究院 | Combustion process monitoring and diagnosing method based on image |
| CN102254078A (en) * | 2010-05-17 | 2011-11-23 | 上海杰远环保科技有限公司 | Multifunctional carbon footprint calculation terminal and implementation method thereof |
| CN102254078B (en) * | 2010-05-17 | 2016-03-23 | 上海杰远环保科技有限公司 | A kind of Multifunctional carbon footprint calculation terminal and its implementation |
| CN102114840A (en) * | 2011-01-20 | 2011-07-06 | 浙江吉利汽车研究院有限公司 | Driving safety control device on road surface change |
| CN103854503A (en) * | 2012-12-06 | 2014-06-11 | 通用汽车环球科技运作有限责任公司 | A traffic light detection system |
| CN104739622A (en) * | 2015-02-04 | 2015-07-01 | 覃泳睿 | Novel wearable blind guiding equipment and working method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102509089B (en) | Method for recognizing zebra crossing and measuring zebra crossing distance based on line-by-line scanning | |
| CN102389361B (en) | Blindman outdoor support system based on computer vision | |
| CN103065470B (en) | Detection device for behaviors of running red light of vehicle based on machine vision with single eye and multiple detection faces | |
| Wu et al. | Applying a functional neurofuzzy network to real-time lane detection and front-vehicle distance measurement | |
| CN102048612A (en) | Blind-guidance robot based on machine vision | |
| CN103778786A (en) | Traffic violation detection method based on significant vehicle part model | |
| CN101231786A (en) | Vehicle checking method based on video image characteristic | |
| CN109325390B (en) | Positioning method and system based on combination of map and multi-sensor detection | |
| CN102354457A (en) | General Hough transformation-based method for detecting position of traffic signal lamp | |
| CN108876805A (en) | The end-to-end unsupervised scene of one kind can traffic areas cognition and understanding method | |
| CN115223019B (en) | All-day parking space detection method based on fusion of camera and laser radar | |
| CN113903008A (en) | Ramp exit vehicle violation identification method based on deep learning and trajectory tracking | |
| CN1713696A (en) | Environmental identification from image process and outputtig device for end | |
| CN209479649U (en) | A kind of night intelligence DAS (Driver Assistant System) | |
| CN111310651A (en) | Water surface detection method based on polarization camera and RGB-D sensor | |
| CN106960193A (en) | A kind of lane detection apparatus and method | |
| CN109815836A (en) | A kind of urban road surfaces guiding arrow detection recognition method | |
| CN110070724A (en) | A kind of video monitoring method, device, video camera and image information supervisory systems | |
| CN112274399A (en) | Intelligent sensing machine blind guiding control method, storage medium, system and device | |
| CN103680148B (en) | A kind of taxi recognition methods | |
| CN110942024A (en) | Unmanned vehicle curb detection method based on deep learning | |
| CN1243333C (en) | A two-way radar speed-measuring video capture equipment | |
| CN111985418B (en) | Vehicle-mounted highway traffic safety facility risk source intelligent identification device and method | |
| CN209734484U (en) | Intelligent blind guiding device | |
| CN206593670U (en) | The device of lane detection is carried out using gyro sensor |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |