CN108693532A - Wearable barrier-avoiding method and device based on enhanced binocular camera Yu 3D millimetre-wave radars - Google Patents
Wearable barrier-avoiding method and device based on enhanced binocular camera Yu 3D millimetre-wave radars Download PDFInfo
- Publication number
- CN108693532A CN108693532A CN201810272405.9A CN201810272405A CN108693532A CN 108693532 A CN108693532 A CN 108693532A CN 201810272405 A CN201810272405 A CN 201810272405A CN 108693532 A CN108693532 A CN 108693532A
- Authority
- CN
- China
- Prior art keywords
- barrier
- information
- millimetre
- distance
- sensor
- 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 abstract description 31
- 230000004888 barrier function Effects 0.000 claims abstract description 120
- 230000004927 fusion Effects 0.000 claims abstract description 29
- 238000003384 imaging method Methods 0.000 claims abstract description 27
- 230000003993 interaction Effects 0.000 claims abstract description 5
- 238000013459 approach Methods 0.000 claims abstract description 4
- 238000001514 detection method Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 5
- 230000002452 interceptive effect Effects 0.000 claims description 5
- 230000033001 locomotion Effects 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000005286 illumination Methods 0.000 claims description 3
- 210000000988 bone and bone Anatomy 0.000 claims description 2
- 238000013507 mapping Methods 0.000 claims description 2
- 206010047571 Visual impairment Diseases 0.000 abstract description 5
- 238000005259 measurement Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000010146 3D printing Methods 0.000 description 1
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000002513 implantation Methods 0.000 description 1
- 239000000155 melt Substances 0.000 description 1
- 239000011664 nicotinic acid Substances 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
- H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
- H04B7/0413—MIMO systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/90—Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/30—Transforming light or analogous information into electric information
- H04N5/33—Transforming infrared radiation
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- General Physics & Mathematics (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The present invention relates to a kind of wearable barrier-avoiding method and device based on enhanced binocular image sensor Yu 3D millimetre-wave radars, belongs to wearable device field, includes the following steps:Step 1, distance, the data of speed and orientation that barrier is acquired by 3D millimetre-wave radars and enhanced binocular image sensor;Step 2 merges the information that 3D millimetre-wave radars and imaging sensor acquire;Step 3, by the distance, speed and azimuth information of the barrier after fusion with the information interaction approach annunciator wearer of acoustic coding.The device includes imaging sensor, radar sensor, information Fusion Module and information exchange module, the method of the present invention has merged the information of 3D millimetre-wave radars and enhanced binocular image sensor, the reliability of measurement is improved, can preferably help dysopia personage to hide existing barrier.
Description
Technical field
The present invention relates to wearable device fields, more particularly to one kind is based on enhanced binocular image sensor and 3D millimeters
The wearable barrier-avoiding method and device of wave radar.
Background technology
Eyes are that the mankind obtain the most organ of external information, and there are the people of dysopia, it is difficult to cope in daily life
The barrier often occurred.The help that simple blind man's stick provides is limited, the case where often will appear missing inspection;Seeing-eye dog then needs to grow
It is not allowed access into up to the professional training of several years, and in the occasion having;Bionic eye implantation has wound to human body, and high takes
With, be not appropriate for Normal visual impedient people use.And traditional electronic visual auxiliary tool includes mainly binocular vision auxiliary
System, active light depth camera auxiliary system, laser ranging system etc..
Vision ancillary technique based on binocular camera can provide a certain range of depth image, be dysopia personage
Avoiding barrier is capable of providing certain help, but list covers binocular camera system, there is very high requirement for images match, right
It is be easy to cause missing inspection in the inapparent place of texture, and the matching algorithm needed is complicated, what is needed is computationally intensive, be easy to cause
Handling result postpones.
Active light depth camera is to obtain dense exact depth image in real time compared to binocular camera advantage, but
Outdoor is affected by daylight, and distant place barrier is caused not detect accurately.And camera has fixed field angle, cannot
Environmental aspect other than accurate detective field of view angle.And laser ranging or ultrasonic ranging system can only be directed to single-point object and survey
Away from, cannot limited detection barrier whole pattern, also easily cause the erroneous judgement of barrier and fail to judge.
With the development of technology, it is integrated with the enhanced binocular image sensor of biocular systems and active light depth camera
The drawbacks of through occurring, binocular camera and active light depth camera can be solved to a certain extent.Meanwhile minimizing low-power consumption
3D millimetre-wave radar systems have occurred, and start large-scale application.By the 3D of enhanced binocular image sensor and low-power consumption
Millimetre-wave radar, which melts, to be used in combination, and dysopia personage can be helped to hide existing barrier.The spy of small volume low watt consumption
Point also makes its sports equipment field for focusing on volume and power consumption in unmanned plane etc. have wide application.
Invention content
It being based on enhanced binocular image sensor and 3D millimeter waves in view of the deficiencies of the prior art, the present invention provides a kind of
The wearable barrier-avoiding method and device of radar.
The technical solution adopted in the present invention is as follows:One kind is based on enhanced binocular image sensor and 3D millimetre-wave radars
Wearable barrier-avoiding method, include the following steps:
Step 1, distance, speed and the side that barrier is acquired by 3D millimetre-wave radars and enhanced binocular image sensor
The data of position;
Step 2 merges the information that 3D millimetre-wave radars and imaging sensor acquire;
Step 3 accuses the distance, speed and azimuth information of the barrier after fusion with the information interaction approach of acoustic coding
Know equipment wearer.
Further, the step 1 is specially:
Distance, speed and the direction of motion letter of step 1.1,3D millimetre-wave radars detection barrier in three dimensions
Breath;
The depth information and colour information of step 1.2, enhanced binocular image sensor detection barrier.
Further, the step 2 is specially:
The quantity and range information of step 2.1, the barrier detected according to 3D millimetre-wave radars, by different distance
Barrier is divided into different groups, the threshold value divided;
The depth information and colour information of imaging sensor output is further processed in step 2.2, uses depth
The method of habit determines the exterior contour of barrier in colour information, and the profile is mapped in depth map, to be hindered
Hinder the range information of object, while barrier is tracked using Mean Shift methods, and calculates velocity information;
Step 2.3, the threshold information obtained according to step 2.1, the depth information of image is layered, in different layers
In to image detection to barrier and radar detection to barrier merge;
It will be according to distance different residing for barrier to imaging sensor and radar sensor difference when step 2.4, fusion
Confidence level;
Step 2.5, according to different confidence levels, calculated using the method for Kalman filtering determining barrier distance,
Speed and azimuth information.
Further, the step 3 is specially:
Step 3.1, distance, speed and the azimuth information that barrier is finally determined according to the information after fusion, pass through sound
The range information of barrier, i.e., be mapped in the loudness of sound, the orientation of barrier be mapped to sound by the mode of sound coding
Tone color on, the movement velocity of barrier and its direction are mapped in the frequency of sound, barrier will be detected according to this rule
Hinder the information coding of object at voice signal.
The non-semantic voice signal that coding generates is passed to equipment wearer by step 3.2.
Further, in the step 3.2, non-semantic voice signal passes through wired earphone, bluetooth headset or osteoacusis ear
Machine passes to equipment wearer.
The present invention also provides a kind of wearable avoidances based on enhanced binocular image sensor and 3D millimetre-wave radars to fill
It sets, including imaging sensor, radar sensor, information Fusion Module and information exchange module, imaging sensor and radar is passed
Sensor is fixed together by a rigid connection frame, ensures two sensors in a plane;
Described image sensor is the enhanced binocular image system with depth information, which includes actively to project
Device, infrared binocular camera, colored monocular camera and image processor, infrared binocular camera and colour monocular camera at image
It manages device to be connected, the active projector projects infrared speckle outward;It is main in the case that ambient light illumination is less than 500lx indoors
Dynamic light projector projects infrared speckle outward, and the speckle is beaten through ovennodulation on barrier, and reflected light is connect by infrared camera
It receives, barrier changes the state of speckle, and the state by calculating speckle just can know that the depth information of barrier;Work as sensor
In the case where outdoor environment illuminance is more than 500lx, infrared binocular camera calculates obstacle by way of pure binocular camera
The depth information of object, in addition colored monocular camera obtain common colour information;The method for reusing deep learning is believed in colour
The exterior contour of barrier is determined in breath, and the profile is mapped in depth map, to obtain the range information of barrier, together
Shi Liyong Mean Shift methods track barrier, and calculate velocity information;
The radar sensor is 3D millimetre-wave radar sensors, for obtaining the distance and speed of barrier in space
Three-dimensional coordinate;
The barrier that imaging sensor and radar sensor detect is passed through data fusion by described information Fusion Module
Mode finally determines distance, speed and the azimuth information of barrier;
Described information interactive module informs the distance, speed and azimuth information of barrier by way of acoustic coding
Equipment wearer.
Further, the barrier that described information Fusion Module detects during data fusion according to 3D millimetre-wave radars
The barrier of different distance, is divided into different groups by the quantity and range information for hindering object, the threshold value divided;According to
The depth information of image is layered by threshold information, the barrier arrived to image detection in different layers and radar detection
To barrier merged;When fusion will according to distance different residing for barrier to imaging sensor and radar sensor not
Same confidence level;According to different confidence levels, calculated using the method for Kalman filtering the distance of determining barrier, speed and
Azimuth information.
Further, described information interactive system is reflected the range information of barrier by the way of stereo sound mapping
It is mapped in the loudness of sound, the velocity information of barrier is mapped in the frequency of sound, the orientation of barrier is mapped to sound
In the tone color of sound.
The beneficial effects of the invention are as follows:The present invention has merged the letter of 3D millimetre-wave radars and enhanced binocular image sensor
Breath, can solve the problems such as single equipment measurement result is unreliable, improve the precision and reliability of measurement, help dysopsia people
Scholar hides existing barrier.
Description of the drawings
Fig. 1 is present system flow chart;
Fig. 2 is the configuration schematic diagram of apparatus of the present invention;
Fig. 3 is the enhanced binocular image sensor structure schematic diagram of the present invention;
Fig. 4 is the 3D millimetre-wave radar antenna distribution schematic diagrams of the present invention.
Specific implementation mode
The present invention will be further described below with reference to the drawings.
The present invention proposes a kind of wearable avoidance dress based on enhanced binocular image sensor and 3D millimetre-wave radars
It sets, it is intended to dysopia personage be helped to hide existing barrier.By enhanced binocular image sensor and 3D millimetre-wave radars
System combines, to improve the stability and robustness of whole system.Fig. 2 is the configuration schematic diagram of apparatus of the present invention,
The device includes enhanced binocular image sensor, low-power consumption 3D millimetre-wave radars, information Fusion Module and information exchange module.
The basic structure of the enhanced binocular image sensor as shown in figure 3, the imaging sensor includes there are one
The infrared active projector 1;One color camera 2 receives external signal, and exports the colour information in space.Ambient light indoors
In the case that illumination is less than 500lx, active light projector projects infrared speckle outward, and the speckle is beaten and hindered through ovennodulation
Hinder on object, reflected light is received by infrared camera, and barrier changes the state of speckle, and the state by calculating speckle just can know that
The depth information of barrier;One infrared binocular camera, it is made of two infrared cameras 3, forms biocular systems, can utilize double
Purpose principle calculates the distance of barrier.One image processor 4 mainly calculates and exports the depth and color letter of barrier
Breath.In the case where outdoor environment illuminance is more than 500lx, infrared binocular camera is calculated by way of pure binocular camera
The depth information of barrier, in addition colored monocular camera obtain common colour information;The method of deep learning is reused in coloured silk
The exterior contour of barrier is determined in color information, and the profile is mapped in depth map, to obtain the distance letter of barrier
Breath, while barrier is tracked using Mean Shift methods, and calculate velocity information;The imaging sensor is integrated with active light
Depth camera and binocular camera, make no matter it has good table indoors or in the case that outdoor environment light is more complicated
It is existing.Since the position of these cameras is kept fixed, so by the way that the internal reference of binocular camera and all write-ins of outer ginseng are schemed after calibration
Picture processor can be used, without being demarcated during use below again.In addition the sensor also has low in energy consumption etc.
Feature directly can meet the needs of power supply and data transmission simultaneously using USB3.0 interfaces.
The antenna distribution basic structure of the 3D millimetre-wave radar system sensors is as shown in figure 4, marshalling in figure
Small rectangle be radar antenna.With common 2D millimetre-wave radars sensor can only obtain barrier in a plane away from
From speed can obtain the three-dimensional coordinate of the distance and speed of barrier in space with orientation difference, the radar, compare 2D thunders
For reaching, the result of calculation of barrier is more accurate.The radar sensor uses MIMO technology, using multipair dual-mode antenna,
The phase difference that different reception antennas are reached by calculating barrier goes to calculate the azimuth information of barrier.With common 2D millimeter waves thunder
Situation up to the multiple reception antennas of single horizontal distribution of antenna is different, and 3D millimetre-wave radar antennas are used in horizontal and vertical side
To multiple reception antennas are all placed, in this way, the millimetre-wave radar can not only distinguish the angle of horizontal direction barrier, can also calculate
Go out the angle of barrier vertical direction.The 3D millimetre-wave radars have small, low in energy consumption feature, and being highly suitable for can
Wearable device field uses.
Imaging sensor and radar sensor are fixed together by the rigid connection frame of a 3D printing, ensure two
Sensor is in a plane.Due to knowing the relative position of the two sensors, and it is angle-resolved with imaging sensor
Rate is compared, and the angular resolution of 3D radars is relatively low, so need not be demarcated to the two sensors.
The barrier that imaging sensor and radar sensor detect is passed through data fusion by described information Fusion Module
Mode finally determines distance, speed and the azimuth information of barrier;
Described information interactive module informs the distance, speed and azimuth information of barrier by way of acoustic coding
Equipment wearer.
As shown in Figure 1, the barrier-avoiding method of wearable obstacle avoidance apparatus includes the following steps:
Distance in step 1, respectively acquisition millimetre-wave radar and imaging sensor about barrier, the number of speed and direction
According to;
Step 2 merges the information of millimetre-wave radar and imaging sensor;
Step 3, by the distance about barrier after fusion, speed and azimuth information are by information interaction system with sound
The information interaction approach annunciator wearer of coding.
Further, the step 1 is specially:
Step 1.1, the data for acquiring 3D millimetre-wave radars, i.e., the barrier that millimetre-wave radar detects is in three dimensions
The information such as distance, speed and orientation, be stored in information Fusion Module;
The data of step 1.2, the enhanced binocular image sensor of acquisition, i.e., the depth for the barrier that imaging sensor detects
Information and colour information are spent, is stored in information Fusion Module;
The step 2 is specially:
Step 2.1, the data for analyzing 3D millimetre-wave radars, according to the letters such as the quantity of the barrier detected and distance
The barrier of different distance, is divided into different groups, the threshold value divided by breath.
The depth information and colour information of imaging sensor output is further processed in step 2.2, uses depth
The method of habit determines the exterior contour of barrier in colour information, and the profile is mapped in depth map, to be hindered
Hinder the range information of object, while barrier is tracked using Mean Shift methods, and calculates velocity information.
Step 2.3, the threshold information obtained according to step 2.1, the depth information of image is layered, in different layers
In to image detection to barrier and radar detection to barrier merge.
It will be according to distance different residing for barrier to imaging sensor and radar sensor difference when step 2.4, fusion
Confidence level, for example, giving imaging sensor higher confidence level within the scope of 3 meters, and given between 3 meters to 5 meters ranges
The identical confidence level of the two is given, and gives radar higher confidence level except 5 meters of ranges.It simultaneously also will be according to the information of fusion
Type gives different detectors different confidence levels, such as when merging speed, gives radar sensor higher confidence always
Degree.
Step 2.5, according to different confidence levels, calculated using the method for Kalman filtering determining barrier distance,
The information such as speed and orientation.
The step 3 is specially:
The information such as step 3.1, distance, speed and the orientation that barrier is finally determined according to the information after fusion, pass through
The range information of barrier is mapped in the loudness of sound by the mode of acoustic coding, the orientation of barrier is mapped to sound
In the tone color of sound, the movement velocity of barrier and its direction are mapped in the frequency of sound, will be detected according to this rule
The information coding of barrier is at voice signal.
Step 3.2, the non-semantic voice signal for generating coding are by including but not limited to common wireline earphone, normal blue
The devices such as tooth earphone and bone conduction earphone pass to equipment wearer.
Equipment wearer executes the behavior of avoiding barrier according to prompt after receiving voice signal.
Claims (8)
1. a kind of wearable barrier-avoiding method based on enhanced binocular image sensor Yu 3D millimetre-wave radars, which is characterized in that
Include the following steps:
Step 1 passes through the distance of 3D millimetre-wave radars and enhanced binocular image sensor acquisition barrier, speed and orientation
Data;
Step 2 merges the information that 3D millimetre-wave radars and imaging sensor acquire;
The distance, speed and azimuth information of barrier after fusion are informed with the information interaction approach of acoustic coding and are set by step 3
Standby wearer.
2. according to the method described in claim 1, it is characterized in that, the step 1 is specially:
Step 1.1, distance, speed and the direction of motion information of 3D millimetre-wave radars detection barrier in three dimensions;
The depth information and colour information of step 1.2, enhanced binocular image sensor detection barrier.
3. according to the method described in claim 1, it is characterized in that, the step 2 is specially:
The quantity and range information of step 2.1, the barrier detected according to 3D millimetre-wave radars, by the obstacle of different distance
Object is divided into different groups, the threshold value divided;
The depth information and colour information of imaging sensor output is further processed in step 2.2, uses deep learning
Method determines the exterior contour of barrier in colour information, and the profile is mapped in depth map, to obtain barrier
Range information, while tracking barrier using Mean Shift methods, and calculate velocity information;
Step 2.3, the threshold information obtained according to step 2.1, the depth information of image is layered, right in different layers
Image detection to barrier and radar detection to barrier merged;
It to be set according to distance different residing for barrier to imaging sensor is different with radar sensor when step 2.4, fusion
Reliability;
Step 2.5, according to different confidence levels, distance, the speed of determining barrier are calculated using the method for Kalman filtering
And azimuth information.
4. according to the method described in claim 1, it is characterized in that, the step 3 is specially:
Step 3.1, distance, speed and the azimuth information that barrier is finally determined according to the information after fusion, are compiled by sound
The range information of barrier, i.e., be mapped in the loudness of sound, the orientation of barrier be mapped to the sound of sound by the mode of code
On color, the movement velocity of barrier and its direction are mapped in the frequency of sound, barrier will be detected according to this rule
Information coding at voice signal.
The non-semantic voice signal that coding generates is passed to equipment wearer by step 3.2.
5. according to the method described in claim 4, it is characterized in that, in the step 3.2, non-semantic voice signal passes through wired
Earphone, bluetooth headset or bone conduction earphone pass to equipment wearer.
6. a kind of wearable obstacle avoidance apparatus based on enhanced binocular image sensor Yu 3D millimetre-wave radars, which is characterized in that
Including imaging sensor, radar sensor, information Fusion Module and information exchange module, by imaging sensor and radar sensor
It is fixed together by a rigid connection frame, ensures two sensors in a plane;
Described image sensor be the enhanced binocular image system with depth information, the system include the active projector,
Infrared binocular camera, colored monocular camera and image processor, infrared binocular camera and colour monocular camera are and image procossing
Device is connected, and the active projector projects infrared speckle outward;In the case that ambient light illumination is less than 500lx indoors, actively
Light projector projects infrared speckle outward, and the speckle is beaten through ovennodulation on barrier, and reflected light is connect by infrared camera
It receives, barrier changes the state of speckle, and the state that speckle is calculated by image processor just can know that the depth of barrier is believed
Breath;In the case where outdoor environment illuminance is more than 500lx, infrared binocular camera is calculated by way of pure binocular camera
The depth information of barrier, in addition colored monocular camera obtain common colour information;The method of deep learning is reused in coloured silk
The exterior contour of barrier is determined in color information, and the profile is mapped in depth map, to obtain the distance letter of barrier
Breath, while barrier is tracked using Mean Shift methods, and calculate velocity information;
The radar sensor is 3D millimetre-wave radar sensors, three for obtaining barrier distance in space and speed
Dimension coordinate;
The barrier that described information Fusion Module detects imaging sensor and radar sensor is by way of data fusion
Final distance, speed and the azimuth information for determining barrier;
Described information interactive module is by the distance, speed and azimuth information of barrier, by way of acoustic coding, annunciator
Wearer.
It a kind of is kept away with the wearable of 3D millimetre-wave radars based on enhanced binocular image sensor 7. according to claim 6
Fault device, which is characterized in that described information Fusion Module detected during data fusion according to 3D millimetre-wave radars
The barrier of different distance, is divided into different groups by the quantity and range information of barrier, the threshold value divided;Root
According to threshold information, the depth information of image is layered, the barrier and radar arrived to image detection in different layers is visited
The barrier measured is merged;It will be according to distance different residing for barrier to imaging sensor and radar sensor when fusion
Different confidence levels;According to different confidence levels, distance, the speed of determining barrier are calculated using the method for Kalman filtering
And azimuth information.
It a kind of is kept away with the wearable of 3D millimetre-wave radars based on enhanced binocular image sensor 8. according to claim 7
Fault device, which is characterized in that described information interactive system is reflected the range information of barrier by the way of stereo sound mapping
It is mapped in the loudness of sound, the velocity information of barrier is mapped in the frequency of sound, the orientation of barrier is mapped to sound
In the tone color of sound.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810272405.9A CN108693532A (en) | 2018-03-29 | 2018-03-29 | Wearable barrier-avoiding method and device based on enhanced binocular camera Yu 3D millimetre-wave radars |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810272405.9A CN108693532A (en) | 2018-03-29 | 2018-03-29 | Wearable barrier-avoiding method and device based on enhanced binocular camera Yu 3D millimetre-wave radars |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108693532A true CN108693532A (en) | 2018-10-23 |
Family
ID=63844397
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810272405.9A Pending CN108693532A (en) | 2018-03-29 | 2018-03-29 | Wearable barrier-avoiding method and device based on enhanced binocular camera Yu 3D millimetre-wave radars |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108693532A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109472831A (en) * | 2018-11-19 | 2019-03-15 | 东南大学 | Obstacle recognition range-measurement system and method towards road roller work progress |
CN109636837A (en) * | 2018-12-21 | 2019-04-16 | 浙江大学 | A kind of evaluation method of monocular camera and ginseng calibration accuracy outside millimetre-wave radar |
CN109670409A (en) * | 2018-11-28 | 2019-04-23 | 浙江大学 | A kind of scene expression system and method for the rodlike pixel of semanteme |
CN110579764A (en) * | 2019-08-08 | 2019-12-17 | 北京三快在线科技有限公司 | Registration method and device for depth camera and millimeter wave radar, and electronic equipment |
CN111208581A (en) * | 2019-12-16 | 2020-05-29 | 长春理工大学 | Unmanned aerial vehicle multi-dimensional identification system and method |
CN111223139A (en) * | 2018-11-26 | 2020-06-02 | 深圳市优必选科技有限公司 | Target positioning method and terminal equipment |
CN111324115A (en) * | 2020-01-23 | 2020-06-23 | 北京百度网讯科技有限公司 | Obstacle position detection fusion method and device, electronic equipment and storage medium |
CN112924972A (en) * | 2021-01-28 | 2021-06-08 | 四川写正智能科技有限公司 | Device and method for intelligent distance measurement and obstacle avoidance reminding based on millimeter waves |
CN114047787A (en) * | 2021-12-23 | 2022-02-15 | 普宙科技(深圳)有限公司 | Unmanned aerial vehicle obstacle avoidance system, method, equipment and storage medium |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102609941A (en) * | 2012-01-31 | 2012-07-25 | 北京航空航天大学 | Three-dimensional registering method based on ToF (Time-of-Flight) depth camera |
CN103021186A (en) * | 2012-12-28 | 2013-04-03 | 中国科学技术大学 | Vehicle monitoring method and vehicle monitoring system |
CN104359461A (en) * | 2014-11-06 | 2015-02-18 | 中国人民解放军装备学院 | Binocular vision measuring system having variable structure and parameter determining method |
CN105866779A (en) * | 2016-04-06 | 2016-08-17 | 浙江大学 | Wearable barrier avoiding apparatus and barrier avoiding method based on binocular camera and millimeter-wave radar |
CN106546981A (en) * | 2016-10-24 | 2017-03-29 | 复旦大学 | Movement human safety check imaging system and method |
CN106817577A (en) * | 2016-11-23 | 2017-06-09 | 杭州视氪科技有限公司 | One kind is based on RGB D cameras and stereosonic visually impaired people's barrier early warning glasses |
US20170246070A1 (en) * | 2016-02-29 | 2017-08-31 | Osterhout Group, Inc. | Radar imagery in head-worn computing |
CN107132913A (en) * | 2017-03-31 | 2017-09-05 | 南京理工大学 | A kind of multi-user's man-machine interaction method based on millimeter wave |
CN107202983A (en) * | 2017-05-19 | 2017-09-26 | 深圳佑驾创新科技有限公司 | The self-actuating brake method and system merged based on image recognition and millimetre-wave radar |
-
2018
- 2018-03-29 CN CN201810272405.9A patent/CN108693532A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102609941A (en) * | 2012-01-31 | 2012-07-25 | 北京航空航天大学 | Three-dimensional registering method based on ToF (Time-of-Flight) depth camera |
CN103021186A (en) * | 2012-12-28 | 2013-04-03 | 中国科学技术大学 | Vehicle monitoring method and vehicle monitoring system |
CN104359461A (en) * | 2014-11-06 | 2015-02-18 | 中国人民解放军装备学院 | Binocular vision measuring system having variable structure and parameter determining method |
US20170246070A1 (en) * | 2016-02-29 | 2017-08-31 | Osterhout Group, Inc. | Radar imagery in head-worn computing |
CN105866779A (en) * | 2016-04-06 | 2016-08-17 | 浙江大学 | Wearable barrier avoiding apparatus and barrier avoiding method based on binocular camera and millimeter-wave radar |
CN106546981A (en) * | 2016-10-24 | 2017-03-29 | 复旦大学 | Movement human safety check imaging system and method |
CN106817577A (en) * | 2016-11-23 | 2017-06-09 | 杭州视氪科技有限公司 | One kind is based on RGB D cameras and stereosonic visually impaired people's barrier early warning glasses |
CN107132913A (en) * | 2017-03-31 | 2017-09-05 | 南京理工大学 | A kind of multi-user's man-machine interaction method based on millimeter wave |
CN107202983A (en) * | 2017-05-19 | 2017-09-26 | 深圳佑驾创新科技有限公司 | The self-actuating brake method and system merged based on image recognition and millimetre-wave radar |
Non-Patent Citations (1)
Title |
---|
SHUAI ZHENG等: "Conditional Random Fields as Recurrent Neural Networks", 《2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION(ICCV)》 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109472831A (en) * | 2018-11-19 | 2019-03-15 | 东南大学 | Obstacle recognition range-measurement system and method towards road roller work progress |
CN111223139A (en) * | 2018-11-26 | 2020-06-02 | 深圳市优必选科技有限公司 | Target positioning method and terminal equipment |
CN111223139B (en) * | 2018-11-26 | 2024-02-13 | 深圳市优必选科技有限公司 | Target positioning method and terminal equipment |
CN109670409A (en) * | 2018-11-28 | 2019-04-23 | 浙江大学 | A kind of scene expression system and method for the rodlike pixel of semanteme |
CN109670409B (en) * | 2018-11-28 | 2022-10-21 | 浙江大学 | Scene representation system and method of semantic rod-shaped pixels |
CN109636837A (en) * | 2018-12-21 | 2019-04-16 | 浙江大学 | A kind of evaluation method of monocular camera and ginseng calibration accuracy outside millimetre-wave radar |
CN109636837B (en) * | 2018-12-21 | 2023-04-28 | 浙江大学 | Method for evaluating calibration accuracy of external parameters of monocular camera and millimeter wave radar |
CN110579764A (en) * | 2019-08-08 | 2019-12-17 | 北京三快在线科技有限公司 | Registration method and device for depth camera and millimeter wave radar, and electronic equipment |
CN110579764B (en) * | 2019-08-08 | 2021-03-09 | 北京三快在线科技有限公司 | Registration method and device for depth camera and millimeter wave radar, and electronic equipment |
CN111208581A (en) * | 2019-12-16 | 2020-05-29 | 长春理工大学 | Unmanned aerial vehicle multi-dimensional identification system and method |
CN111324115B (en) * | 2020-01-23 | 2023-09-19 | 北京百度网讯科技有限公司 | Obstacle position detection fusion method, obstacle position detection fusion device, electronic equipment and storage medium |
CN111324115A (en) * | 2020-01-23 | 2020-06-23 | 北京百度网讯科技有限公司 | Obstacle position detection fusion method and device, electronic equipment and storage medium |
CN112924972A (en) * | 2021-01-28 | 2021-06-08 | 四川写正智能科技有限公司 | Device and method for intelligent distance measurement and obstacle avoidance reminding based on millimeter waves |
CN112924972B (en) * | 2021-01-28 | 2023-05-16 | 四川写正智能科技有限公司 | Device and method for intelligent distance measurement and obstacle avoidance reminding based on millimeter waves |
CN114047787A (en) * | 2021-12-23 | 2022-02-15 | 普宙科技(深圳)有限公司 | Unmanned aerial vehicle obstacle avoidance system, method, equipment and storage medium |
CN114047787B (en) * | 2021-12-23 | 2024-04-05 | 普宙科技有限公司 | Unmanned aerial vehicle obstacle avoidance system, unmanned aerial vehicle obstacle avoidance method, unmanned aerial vehicle obstacle avoidance equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108693532A (en) | Wearable barrier-avoiding method and device based on enhanced binocular camera Yu 3D millimetre-wave radars | |
CN106772431B (en) | A kind of Depth Information Acquistion devices and methods therefor of combination TOF technology and binocular vision | |
CN106203390B (en) | A kind of intelligent blind auxiliary system | |
CN106980368B (en) | Virtual reality interaction equipment based on vision calculation and inertia measurement unit | |
CN109634279A (en) | Object positioning method based on laser radar and monocular vision | |
CN106383596B (en) | Virtual reality anti-dizzy system and method based on space positioning | |
CN106275410B (en) | A kind of wind disturbance resistant unmanned plane | |
CN105279750B (en) | It is a kind of that guide system is shown based on the equipment of IR-UWB and image moment | |
CN104217439B (en) | Indoor visual positioning system and method | |
CN105866779A (en) | Wearable barrier avoiding apparatus and barrier avoiding method based on binocular camera and millimeter-wave radar | |
CN107110953A (en) | Underwater positioning system | |
US20070098250A1 (en) | Man-machine interface based on 3-D positions of the human body | |
CN106384353A (en) | Target positioning method based on RGBD | |
CN106687850A (en) | Scanning laser planarity detection | |
CN104685541A (en) | Method and an apparatus for determining a gaze point on a three-dimensional object | |
CN105354825B (en) | The intelligent apparatus of reading matter position and its application in automatic identification read-write scene | |
CN207965645U (en) | A kind of robot autonomous navigation system | |
KR20130013015A (en) | Method and apparatus for estimating 3d position and orientation by means of sensor fusion | |
CN114488164B (en) | Synchronous positioning and mapping method for underwater vehicle and underwater vehicle | |
KR102298643B1 (en) | 3D modeling method of underwater surfaces using infrared thermal imaging camera and drone | |
KR102298645B1 (en) | 3D modeling system of underwater surfaces using infrared thermal imaging camera and drone | |
CN105354822A (en) | Intelligent apparatus for automatically identifying position of read-write element in read-write scene and application | |
WO2018119403A1 (en) | Head mounted sensor system | |
CN105335699A (en) | Intelligent determination method for reading and writing element three-dimensional coordinates in reading and writing scene and application thereof | |
US20200330003A1 (en) | An apparatus and a method for passive scanning of an object or a scene |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181023 |