CN107229931A - A kind of high Unmanned Systems of automaticity - Google Patents
A kind of high Unmanned Systems of automaticity Download PDFInfo
- Publication number
- CN107229931A CN107229931A CN201710400385.4A CN201710400385A CN107229931A CN 107229931 A CN107229931 A CN 107229931A CN 201710400385 A CN201710400385 A CN 201710400385A CN 107229931 A CN107229931 A CN 107229931A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msup
- image
- mfrac
- subsystem
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Abstract
The invention provides a kind of high Unmanned Systems of automaticity, including perceiving subsystem, task subsystem, decision-making subsystem, control subsystem and virtual reality subsystem, the perception subsystem is used to perceive vehicle drive environment, including panoramic shooting equipment and interesting image regions extraction element, the panoramic shooting equipment is used to obtain vehicle periphery panoramic information, described image region of interesting extraction device is used for the area-of-interest for obtaining surrounding environment, the task subsystem assigns a task according to vehicle drive environment, the decision-making subsystem is used to receive assigning for task, and make a policy, the control subsystem is used to the decision-making received being converted into the actual instruction for being controlled car, the virtual reality subsystem and the perception subsystem wireless connection, for showing vehicle drive environment information.Beneficial effects of the present invention are:There is provided a kind of high Unmanned Systems of automaticity.
Description
Technical field
The present invention relates to unmanned technical field, and in particular to a kind of high Unmanned Systems of automaticity.
Background technology
With the development of artificial intelligence technology, automatic driving vehicle turns into the developing direction of future automobile, with security
High, efficient easily advantage, helps to make up the defect of manned automobile, effectively reduces traffic accident.
Observer only can carry out selective analysis when watching image to the information in region interested in image, without
The global information of image is all analyzed.The method of traditional graphical analysis is that the global information of image is analyzed mostly
Processing, this does not meet the processing procedure to image information, and this global analysis's method adds point for many times wanting information
Analysis and processing, cause the waste in many unnecessary calculating.
The content of the invention
In view of the above-mentioned problems, a kind of the present invention is intended to provide high Unmanned Systems of automaticity.
The purpose of the present invention is realized using following technical scheme:
There is provided a kind of high Unmanned Systems of automaticity, including perceive subsystem, task subsystem, decision-making
System, control subsystem and virtual reality subsystem, the perception subsystem are used to perceive vehicle drive environment, including panorama is taken the photograph
As equipment and interesting image regions extraction element, the panoramic shooting equipment is used to obtain vehicle periphery panoramic information, described
Interesting image regions extraction element is used for the area-of-interest for obtaining surrounding environment, and the task subsystem is according to vehicle drive
Environment assigns a task, and the decision-making subsystem is used to receive assigning for task, and makes a policy, and the control subsystem is used for will
The decision-making received is converted into the actual instruction being controlled to car, the virtual reality subsystem and the perception subsystem without
Line is connected, for showing vehicle drive environment information.
Beneficial effects of the present invention are:There is provided a kind of high Unmanned Systems of automaticity.
Brief description of the drawings
Using accompanying drawing, the invention will be further described, but the embodiment in accompanying drawing does not constitute any limit to the present invention
System, for one of ordinary skill in the art, on the premise of not paying creative work, can also be obtained according to the following drawings
Other accompanying drawings.
Fig. 1 is the structural representation of the present invention;
Reference:
Perceive subsystem 1, task subsystem 2, decision-making subsystem 3, control subsystem 4, virtual reality subsystem 5.
Embodiment
The invention will be further described with the following Examples.
Referring to Fig. 1, a kind of high Unmanned Systems of automaticity of the present embodiment, including perceive subsystem 1, task
Subsystem 2, decision-making subsystem 3, control subsystem 4 and virtual reality subsystem 5, the perception subsystem 1 are used to perceive vehicle
Driving environment, including panoramic shooting equipment and interesting image regions extraction element, the panoramic shooting equipment are used to obtain car
Surrounding panoramic information, described image region of interesting extraction device is used for the area-of-interest for obtaining surrounding environment, described
Business subsystem 2 assigns a task according to vehicle drive environment, and the decision-making subsystem 3 is used to receive assigning for task, and makes certainly
Plan, the control subsystem 4 is used to the decision-making received being converted into the actual instruction for being controlled car, the virtual reality
Subsystem 5 and the perception wireless connection of subsystem 1, for showing vehicle drive environment information.
Present embodiments provide a kind of high Unmanned Systems of automaticity.
It is preferred that, the virtual reality subsystem 5 includes communication module and panorama display end, and the communication module is used to feel
Know that subsystem 1 transmits vehicle driving-environment information to virtual reality subsystem 5, the panorama display end is used to show vehicle drive
Environmental information.
The virtual reality that this preferred embodiment realizes vehicle drive information is shown.
It is preferred that, after the reception task of decision-making subsystem 3, task reasonability is judged, if task rationally, is done
Go out decision-making and be transmitted to control subsystem 4, if task is unreasonable, return to task subsystem 2.
This preferred embodiment improves the decision-making capability of decision-making subsystem.
It is preferred that, described image region of interesting extraction device includes eye and moves generation module, feature generation module and evaluation
Module, the eye moves the first area-of-interest that generation module is used to obtain image, and the feature generation module, which is used to obtain, schemes
Second area-of-interest of picture, the evaluation module is used to comment the second area-of-interest according to the first area-of-interest
Valency.
First area-of-interest of described image is tested tester using eye tracker;
The feature generation module includes feature extraction unit, notable figure generation unit and area-of-interest generation unit,
The feature extraction unit is used for the color characteristic and textural characteristics for extracting image, and the notable figure generation unit is used for according to figure
The feature of picture generates the characteristic remarkable picture of image, and the area-of-interest generation unit is used to generate image according to characteristic remarkable picture
The second area-of-interest.
The color characteristic is extracted in the following ways:
A, convert the image into HSV patterns;Color characteristic is extracted by following formula:
In formula, f (x, y) represents the color characteristic of image, and bhd (x, y) represents that image is located at the saturation of pixel (x, y)
Degree, bhd represents image saturation average, and ld (x, y) represents that image is located at the brightness of pixel (x, y), and ld represents brightness of image
Average;
B, the scope of pixel value is normalized to [0,255], obtains the color characteristic figure of image;
The textural characteristics are extracted in the following ways:
A, the textural characteristics on the yardstick 8 of image 5 direction are extracted using Gabor filter group, obtain 40 width of image
Texture maps;
B, the 40 width texture maps to image are normalized, and then equal weight is superimposed, and obtains final textural characteristics
Figure.
This preferred embodiment interesting image regions extraction element sets feature extraction unit to extract characteristics of image,
It when being extracted to color of image feature, will can only reflect the rgb value of color characteristic, be converted to the tone of reflection multiple features, satisfy
With degree and monochrome information, more accurate color characteristic figure is obtained, when being extracted to image texture characteristic, 40 width lines are chosen
Reason figure is handled, and has obtained more careful texture information.
It is preferred that, the characteristic remarkable picture of the generation image is in the following ways:
A, according to color characteristic figure and textural characteristics figure, corresponding color notable figure is obtained using ITTI human perceptual models
With texture notable figure;
B, the characteristic remarkable picture for determining using following formula image:
In formula, X represents the characteristic remarkable picture of image, and Y represents the color notable figure of image, and W represents that the texture of image is notable
Figure;
The second area-of-interest of described image is generated in the following ways:The scope of pixel value is normalized to [0,
255], given threshold T, extracts the pixel that pixel value is more than T, obtains the second area-of-interest DE of image.
This preferred embodiment is based on characteristics of the underlying image and extracts area-of-interest, reflects that image overall is special by color characteristic
Levy, textural characteristics reflect the local feature of image, the characteristic remarkable picture of more accurate image are obtained, second obtained from
Area-of-interest is more accurate.
It is preferred that, the evaluation module includes the first evaluation unit, the second evaluation unit, overall merit unit, described the
One evaluation unit is once evaluated the second area-of-interest, obtains the first evaluation of estimate, second evaluation unit is to second
Area-of-interest carries out second evaluation, obtains the second evaluation of estimate, and the overall merit unit is commented according to the first evaluation of estimate and second
Value carries out overall merit to the second area-of-interest, obtains comprehensive evaluation value;
It is described that second area-of-interest is carried out once to evaluate using the progress of the first evaluation of estimate, the first evaluation of estimate P1Under
Formula is calculated:
In formula, DY represents the first area-of-interest, deiAnd dyiThe second area-of-interest and the first region of interest are represented respectively
The corresponding pixel value of domain ith pixel point, M represents the number of pixels included in image;
The second evaluation that carried out to the second area-of-interest is using the progress of the second evaluation of estimate, the second evaluation of estimate P2Under
Formula is calculated:
In formula, w and h represent respectively be image width and height;
The overall merit that carried out to the second area-of-interest is using comprehensive evaluation value progress, comprehensive evaluation value PcUnder
Formula is calculated:
Comprehensive evaluation value is bigger, shows that the second region of interesting extraction is more accurate.
This preferred embodiment interesting image regions extraction element using the first area-of-interest as evaluation criterion, by asking
Take the second area-of-interest comprehensive evaluation value to reflect the accuracy and validity of the second area-of-interest, it is ensured that the second sense is emerging
The accuracy in interesting region, improves the environment sensing performance of Unmanned Systems, so as to improve the safety of Unmanned Systems
Property.
Using automaticity of the present invention, high Unmanned Systems carry out automatic Pilot, right when driving distance difference
Drive safety and driving efficiency are counted, compared with other Unmanned Systems, and generation is had the beneficial effect that shown in table:
Drive distance/km | Drive safety is improved | Driving efficiency is improved |
100 | 10% | 18% |
110 | 12% | 23% |
120 | 13% | 25% |
130 | 15% | 28% |
140 | 17% | 32% |
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than to present invention guarantor
The limitation of scope is protected, although being explained with reference to preferred embodiment to the present invention, one of ordinary skill in the art should
Work as understanding, technical scheme can be modified or equivalent substitution, without departing from the reality of technical solution of the present invention
Matter and scope.
Claims (8)
1. the high Unmanned Systems of a kind of automaticity, it is characterised in that including perceiving subsystem, task subsystem, determining
Plan subsystem, control subsystem and virtual reality subsystem, the perception subsystem are used to perceive vehicle drive environment, including complete
Scape picture pick-up device and interesting image regions extraction element, the panoramic shooting equipment are used to obtain vehicle periphery panoramic information,
Described image region of interesting extraction device is used for the area-of-interest for obtaining surrounding environment, and the task subsystem is according to vehicle
Driving environment assigns a task, and the decision-making subsystem is used to receive assigning for task, and makes a policy, and the control subsystem is used
In the instruction for being converted into actually being controlled car by the decision-making received, the virtual reality subsystem and the perception subsystem
System wireless connection, for showing vehicle drive environment information.
2. the high Unmanned Systems of automaticity according to claim 1, it is characterised in that virtual reality
System includes communication module and panorama display end, and the communication module is used to perceive subsystem to virtual reality subsystem transmission vehicle
Driving-environment information, the panorama display end is used to show vehicle drive environment information.
3. the high Unmanned Systems of automaticity according to claim 2, it is characterised in that the decision-making subsystem
After reception task, task reasonability is judged, if task rationally, makes a policy and is transmitted to control subsystem, if task is not
Rationally, then task subsystem is returned.
4. the high Unmanned Systems of automaticity according to claim 3, it is characterised in that described image is interested
Region extracting device includes eye and moves generation module, feature generation module and evaluation module, and the eye, which moves generation module, to be used to obtain
First area-of-interest of image, the feature generation module is used for the second area-of-interest for obtaining image, the evaluation mould
Block is used to evaluate the second area-of-interest according to the first area-of-interest.
5. the high Unmanned Systems of automaticity according to claim 4, it is characterised in that the first of described image
Area-of-interest is tested tester using eye tracker;
The feature generation module includes feature extraction unit, notable figure generation unit and area-of-interest generation unit, described
Feature extraction unit is used for the color characteristic and textural characteristics for extracting image, and the notable figure generation unit is used for according to image
Feature generates the characteristic remarkable picture of image, and the area-of-interest generation unit is used to generate the of image according to characteristic remarkable picture
Two area-of-interests.
6. the high Unmanned Systems of automaticity according to claim 5, it is characterised in that the color characteristic is adopted
Extract with the following methods:
A, convert the image into HSV patterns;Color characteristic is extracted by following formula:
<mrow>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>4</mn>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>+</mo>
<mn>2</mn>
<msup>
<mi>e</mi>
<mrow>
<mo>-</mo>
<mfrac>
<mrow>
<mi>b</mi>
<mi>h</mi>
<mi>d</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
</mrow>
<msqrt>
<mrow>
<msup>
<mi>bhd</mi>
<mn>2</mn>
</msup>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msqrt>
</mfrac>
</mrow>
</msup>
<mo>)</mo>
<mo>(</mo>
<mn>1</mn>
<mo>+</mo>
<mn>2</mn>
<msup>
<mi>e</mi>
<mrow>
<mo>-</mo>
<mfrac>
<mrow>
<mi>l</mi>
<mi>d</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
</mrow>
<msqrt>
<mrow>
<msup>
<mi>ld</mi>
<mn>2</mn>
</msup>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msqrt>
</mfrac>
</mrow>
</msup>
<mo>)</mo>
</mrow>
</mfrac>
</mrow>
In formula, f (x, y) represents the color characteristic of image, and bhd (x, y) represents that image is located at the saturation degree of pixel (x, y), bhd
Image saturation average is represented, ld (x, y) represents that image is located at the brightness of pixel (x, y), and ld represents brightness of image average;
B, the scope of pixel value is normalized to [0,255], obtains the color characteristic figure of image;
The textural characteristics are extracted in the following ways:
A, the textural characteristics on the yardstick 8 of image 5 direction are extracted using Gabor filter group, obtain 40 width textures of image
Figure;
B, the 40 width texture maps to image are normalized, and then equal weight is superimposed, and obtains final textural characteristics figure.
7. the high Unmanned Systems of automaticity according to claim 6, it is characterised in that the generation image
Characteristic remarkable picture is in the following ways:
A, according to color characteristic figure and textural characteristics figure, corresponding color notable figure and line are obtained using ITTI human perceptual models
Manage notable figure;
B, the characteristic remarkable picture for determining using following formula image:
<mrow>
<mi>X</mi>
<mo>=</mo>
<mn>0.7</mn>
<mrow>
<mo>(</mo>
<mfrac>
<msup>
<mi>Y</mi>
<mn>3</mn>
</msup>
<mrow>
<msup>
<mi>Y</mi>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mi>W</mi>
<mn>2</mn>
</msup>
</mrow>
</mfrac>
<mo>+</mo>
<mfrac>
<msup>
<mi>W</mi>
<mn>3</mn>
</msup>
<mrow>
<msup>
<mi>Y</mi>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mi>W</mi>
<mn>2</mn>
</msup>
</mrow>
</mfrac>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mn>0.3</mn>
<mrow>
<mo>(</mo>
<mfrac>
<msup>
<mi>Y</mi>
<mn>2</mn>
</msup>
<mrow>
<mi>Y</mi>
<mo>+</mo>
<mi>W</mi>
</mrow>
</mfrac>
<mo>+</mo>
<mfrac>
<msup>
<mi>W</mi>
<mn>2</mn>
</msup>
<mrow>
<mi>Y</mi>
<mo>+</mo>
<mi>W</mi>
</mrow>
</mfrac>
<mo>)</mo>
</mrow>
</mrow>
In formula, X represents the characteristic remarkable picture of image, and Y represents the color notable figure of image, and W represents the texture notable figure of image;
The second area-of-interest of described image is generated in the following ways:The scope of pixel value is normalized to [0,255], if
Determine threshold value T, extract the pixel that pixel value is more than T, obtain the second area-of-interest DE of image.
8. the high Unmanned Systems of automaticity according to claim 7, it is characterised in that the evaluation module bag
The first evaluation unit, the second evaluation unit, overall merit unit are included, first evaluation unit is carried out to the second area-of-interest
Once evaluate, obtain the first evaluation of estimate, second evaluation unit carries out second evaluation to the second area-of-interest, obtains second
Evaluation of estimate, the overall merit unit to the second area-of-interest integrate commenting according to the first evaluation of estimate and the second evaluation of estimate
Valency, obtains comprehensive evaluation value;
It is described that second area-of-interest is carried out once to evaluate using the progress of the first evaluation of estimate, the first evaluation of estimate P1Using following formula meter
Calculate:
<mrow>
<msub>
<mi>P</mi>
<mn>1</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>D</mi>
<mi>E</mi>
<mo>,</mo>
<mi>D</mi>
<mi>Y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msup>
<mi>e</mi>
<mrow>
<mo>-</mo>
<mfrac>
<mn>1</mn>
<mi>M</mi>
</mfrac>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>0</mn>
</mrow>
<mrow>
<mi>M</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<mfrac>
<mrow>
<mo>|</mo>
<msub>
<mi>de</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msub>
<mi>dy</mi>
<mi>i</mi>
</msub>
<mo>|</mo>
</mrow>
<mn>255</mn>
</mfrac>
</mrow>
</msup>
</mrow>
In formula, DY represents the first area-of-interest, deiAnd dyiThe second area-of-interest and the first area-of-interest are represented respectively
The corresponding pixel value of i pixel, M represents the number of pixels included in image;
The second evaluation that carried out to the second area-of-interest is using the progress of the second evaluation of estimate, the second evaluation of estimate P2Using following formula meter
Calculate:
<mrow>
<msub>
<mi>P</mi>
<mn>2</mn>
</msub>
<mrow>
<mo>(</mo>
<mi>D</mi>
<mi>E</mi>
<mo>,</mo>
<mi>D</mi>
<mi>Y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mo>-</mo>
<mi>lg</mi>
<mfrac>
<msqrt>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>0</mn>
</mrow>
<mrow>
<mi>M</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<mfrac>
<mrow>
<msub>
<mi>de</mi>
<mi>i</mi>
</msub>
</mrow>
<mi>M</mi>
</mfrac>
<mo>-</mo>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>0</mn>
</mrow>
<mrow>
<mi>M</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msubsup>
<mfrac>
<mrow>
<msub>
<mi>dy</mi>
<mi>i</mi>
</msub>
</mrow>
<mi>M</mi>
</mfrac>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msqrt>
<msqrt>
<mrow>
<msup>
<mi>w</mi>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mi>h</mi>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
</mfrac>
</mrow>
In formula, w and h represent respectively be image width and height;
The overall merit that carried out to the second area-of-interest is using comprehensive evaluation value progress, comprehensive evaluation value PcUsing following formula meter
Calculate:
<mrow>
<msub>
<mi>P</mi>
<mi>c</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>D</mi>
<mi>E</mi>
<mo>,</mo>
<mi>D</mi>
<mi>Y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>P</mi>
<mn>1</mn>
</msub>
<mo>&times;</mo>
<msub>
<mi>P</mi>
<mn>2</mn>
</msub>
<mo>+</mo>
<msqrt>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>P</mi>
<mn>1</mn>
</msub>
<mo>+</mo>
<msub>
<mi>P</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<mn>1</mn>
</mrow>
</msqrt>
</mrow>
<msup>
<mi>e</mi>
<mfrac>
<mn>1</mn>
<mrow>
<msub>
<mi>P</mi>
<mn>1</mn>
</msub>
<mo>+</mo>
<msub>
<mi>P</mi>
<mn>2</mn>
</msub>
</mrow>
</mfrac>
</msup>
</mfrac>
</mrow>
Comprehensive evaluation value is bigger, shows that the second region of interesting extraction is more accurate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710400385.4A CN107229931A (en) | 2017-05-31 | 2017-05-31 | A kind of high Unmanned Systems of automaticity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710400385.4A CN107229931A (en) | 2017-05-31 | 2017-05-31 | A kind of high Unmanned Systems of automaticity |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107229931A true CN107229931A (en) | 2017-10-03 |
Family
ID=59933606
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710400385.4A Pending CN107229931A (en) | 2017-05-31 | 2017-05-31 | A kind of high Unmanned Systems of automaticity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107229931A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107895147A (en) * | 2017-11-07 | 2018-04-10 | 龚土婷 | A kind of safe pilotless automobile system |
CN108036787A (en) * | 2017-12-07 | 2018-05-15 | 梁金凤 | The accurate unmanned measurement car of one kind measurement |
CN108098769A (en) * | 2017-12-07 | 2018-06-01 | 梁金凤 | A kind of robot for hazardous area measurement |
CN108986481A (en) * | 2018-07-17 | 2018-12-11 | 太仓远见科技咨询服务有限公司 | A kind of increasingly automated vehicular traffic |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102521595A (en) * | 2011-12-07 | 2012-06-27 | 中南大学 | Method for extracting image region of interest based on eye movement data and bottom-layer features |
CN105480224A (en) * | 2014-09-19 | 2016-04-13 | 任丘市永基建筑安装工程有限公司 | Unmanned vehicle system |
CN106394545A (en) * | 2016-10-09 | 2017-02-15 | 北京汽车集团有限公司 | Driving system, unmanned vehicle and vehicle remote control terminal |
CN206021074U (en) * | 2016-06-14 | 2017-03-15 | 北京汽车研究总院有限公司 | A kind of Unmanned Systems |
-
2017
- 2017-05-31 CN CN201710400385.4A patent/CN107229931A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102521595A (en) * | 2011-12-07 | 2012-06-27 | 中南大学 | Method for extracting image region of interest based on eye movement data and bottom-layer features |
CN105480224A (en) * | 2014-09-19 | 2016-04-13 | 任丘市永基建筑安装工程有限公司 | Unmanned vehicle system |
CN206021074U (en) * | 2016-06-14 | 2017-03-15 | 北京汽车研究总院有限公司 | A kind of Unmanned Systems |
CN106394545A (en) * | 2016-10-09 | 2017-02-15 | 北京汽车集团有限公司 | Driving system, unmanned vehicle and vehicle remote control terminal |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107895147A (en) * | 2017-11-07 | 2018-04-10 | 龚土婷 | A kind of safe pilotless automobile system |
CN108036787A (en) * | 2017-12-07 | 2018-05-15 | 梁金凤 | The accurate unmanned measurement car of one kind measurement |
CN108098769A (en) * | 2017-12-07 | 2018-06-01 | 梁金凤 | A kind of robot for hazardous area measurement |
CN108986481A (en) * | 2018-07-17 | 2018-12-11 | 太仓远见科技咨询服务有限公司 | A kind of increasingly automated vehicular traffic |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110501018B (en) | Traffic sign information acquisition method for high-precision map production | |
CN112912920B (en) | Point cloud data conversion method and system for 2D convolutional neural network | |
CN102682292B (en) | Method based on monocular vision for detecting and roughly positioning edge of road | |
CN106919915B (en) | Map road marking and road quality acquisition device and method based on ADAS system | |
WO2022141910A1 (en) | Vehicle-road laser radar point cloud dynamic segmentation and fusion method based on driving safety risk field | |
CN107229931A (en) | A kind of high Unmanned Systems of automaticity | |
DE102020131323A1 (en) | CAMERA-TO-LIDAR CALIBRATION AND VALIDATION | |
CN110738121A (en) | front vehicle detection method and detection system | |
CN111209780A (en) | Lane line attribute detection method and device, electronic device and readable storage medium | |
CN107084727A (en) | A kind of vision positioning system and method based on high-precision three-dimensional map | |
CN109344804A (en) | A kind of recognition methods of laser point cloud data, device, equipment and medium | |
US11455806B2 (en) | System and method for free space estimation | |
CN105654732A (en) | Road monitoring system and method based on depth image | |
DE102020200843A1 (en) | Localization with neural network based on image registration of sensor data and map data | |
CN106803073B (en) | Auxiliary driving system and method based on stereoscopic vision target | |
CN114419605B (en) | Visual enhancement method and system based on multi-network vehicle-connected space alignment feature fusion | |
CN113029187A (en) | Lane-level navigation method and system fusing ADAS fine perception data | |
CN110472508B (en) | Lane line distance measurement method based on deep learning and binocular vision | |
CN117111085A (en) | Automatic driving automobile road cloud fusion sensing method | |
CN116258756B (en) | Self-supervision monocular depth estimation method and system | |
CN112509321A (en) | Unmanned aerial vehicle-based driving control method and system for urban complex traffic situation and readable storage medium | |
CN112115737B (en) | Vehicle orientation determining method and device and vehicle-mounted terminal | |
CN115618602A (en) | Lane-level scene simulation method and system | |
CN114708565A (en) | Intelligent driving scene recognition model creating method, device, equipment and storage medium | |
CN113221756A (en) | Traffic sign detection method and related equipment |
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: 20171003 |