CN105043395B - A kind of real-time Dynamic Location method of aircraft menology soft landing - Google Patents
A kind of real-time Dynamic Location method of aircraft menology soft landing Download PDFInfo
- Publication number
- CN105043395B CN105043395B CN201510424070.4A CN201510424070A CN105043395B CN 105043395 B CN105043395 B CN 105043395B CN 201510424070 A CN201510424070 A CN 201510424070A CN 105043395 B CN105043395 B CN 105043395B
- Authority
- CN
- China
- Prior art keywords
- aircraft
- circle
- drop zone
- result
- picture
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000004888 barrier function Effects 0.000 claims abstract description 27
- 238000001514 detection method Methods 0.000 claims abstract description 14
- 238000005286 illumination Methods 0.000 claims abstract description 13
- 238000006243 chemical reaction Methods 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000000205 computational method Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000002045 lasting effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 4
- 230000007423 decrease Effects 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000011435 rock Substances 0.000 description 2
- 239000004575 stone Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/24—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for cosmonautical navigation
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Astronomy & Astrophysics (AREA)
- Automation & Control Theory (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
A kind of real-time Dynamic Location method of aircraft menology soft landing, comprises the following steps:1) landing scene selects;2) based on shade and highlighted detection of obstacles, the image captured is handled, if having barrier in the image captured, highlight regions are had in addition to shade near barrier;3) addressing based on shade and highlighted detection of obstacles;4) realization of Dynamic Location in real time.The present invention, which provides a kind of change to intensity of illumination, has robustness, the real-time Dynamic Location method for the aircraft menology soft landing that accuracy rate is higher, real-time is higher.
Description
Technical field
The present invention relates to safety zone identification addressing landing field, especially a kind of real-time Dynamic Location applied in menology
Method.
Background technology
Always the popular of moon contest is talked about since eighties of last century the fifties for the research and development of moon landing technology
Topic, this topic come to an end after the mankind in 1969 climb up the moon first.2004, China Lunar Exploration Program started.By
In the special environment of moonscape, landforms texture unobvious, the continuous change of intensity of illumination, traditional vision algorithm is caused
Through the process that can not be applied to menology landing.
At the time of aircraft menology soft landing refers to aircraft apart from menology 1-2km, aircraft captures according to video camera
Data, can utilize vision method, automatic avoiding barrier, in real time selection can drop zone.And under aircraft
During the entire process of drop, the data that video camera captures can be more and more clear, so occurring that some new volumes are smaller again
Barrier, therefore decline process needs and be modified according to the data obtained in real time, so as to reach high-precision requirement.
Land on the moon has the harsh requirement of comparison to the precision and security of landing, it is desirable to realizes precision landing, and evades and falling from the sky or outer space
The different obstacles such as stone pit, slope, valley, rock.After selected safe landing locations, guidance control system provides thrust, posture
Order carrys out talk down device and reaches desired target location from current location smooth transfer.In the obstacle avoidance stage, detector needs
The terrain information in touch-down zone is constantly obtained, terrain obstruction is therefrom identified, information is provided for control system.
The defects of existing recognition methods is present:More sensitive, accuracy rate and real-time are changed to external factor such as illumination
It is not high.
The content of the invention
It is accurate in order to overcome changing to external factor such as illumination for the recognition methods of existing aircraft menology soft landing more sensitive
The not high deficiency of true rate and real-time, the present invention provide a kind of higher, real with robustness, accuracy rate to intensity of illumination change
The real-time Dynamic Location method of the higher aircraft menology soft landing of when property.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of real-time Dynamic Location method of aircraft menology soft landing, comprises the following steps:
1) landing scene selects
When aircraft is apart from menology 1-2km, starts to analyze and handle by the picture of aircraft capture, use IDS
The instrument of wide visual field camera and IDS narrow visual fields camera as capture images, searching can drop zone, and repair in real time in the process
Positive result;
2) based on shade and highlighted detection of obstacles
The image captured is handled, if having barrier in the image captured, near barrier except
Highlight regions are had outside shade, process is as follows:
2.1), state initialization:State initialization is carried out, the angle parameter of the sun, aircraft and camera is set;
2.2), the segmentation of shade and highlight regions:Shadow region, the method are partitioned into using maximum entropy threshold partitioning algorithm
In by histogram analysis carry out shadow region segmentation;Then the gray value of original image arbitrfary point is set as p, and 255-p is made
For the new gray value at this point, i.e., highlight regions can be obtained by the method for reverse image gray value;
2.3), regional analysis:Using Ellipses Detection detect it is last in result, obtain the information of shadow region,
By the way that highlight regions are merged with shadow region information;
2.4), petrophysical model:Express profile information using approximate polygon, according to the angle alpha of profile and the sun,
Shooting angle beta, and barrier region is in direction of illumination long pl and wide pw, height h, width w and the position of disturbance in judgement thing
pos;The computational methods of height are:H=pl/tan (alpha);The computational methods of width are:W=pw;Position pos is to detect
The coordinate of the barrier arrived;
3) addressing based on shade and highlighted detection of obstacles
Addressing process is as follows::
3.1), gridding, image I is obtained;
3.2), range conversion:Image I range conversion result is calculated, obtains range conversion matrix M;
3.3) maximum, is asked for:Calculating matrix M maximum R, this value R be can drop zone maximum radius, it is maximum
Value institute position in the picture, as can drop zone circle the center of circle, be expressed as circle wherein justifying, the center of circle is expressed as
circle.first。
Further, the site selecting method also includes:4) realization of Dynamic Location, step are as follows in real time:
4.1), pre-process:Starting stage, the first frame that video is captured to aircraft do the processing of the 3) step, detected
The center of circle that domain of settling in an area can be justified and radius, as the reference coordinate subsequently addressed;
4.2), high-definition picture is cut:Based on the testing result in 4.1), picture sanction can carried out at drop zone
Cut, wherein clipping region is rectangle, rectangular centre for can the round heart in drop zone, cut picture length and it is wide be respectively w, h, and
And w, h be can be 2-4 times of drop zone radius of circle R;
4.3), address again:Addressed in the result picture that step 4.2) is cut using step 3), acquired results are new
Can drop zone circle the center of circle and radius, and with it is previous can computing compared with the result of drop zone, calculation position skew
Amount.With reference to offset and it is new can drop zone coordinate control aircraft to it is new can drop zone direction move, based on cutting
Zonule carry out computing can significantly improve arithmetic speed;
4.4), repeat step 4.2), 4.3), for video present frame is captured to aircraft, with reference to the calculating of former frame
As a result calculate present frame can drop zone coordinate information, and by it is new can drop zone information it is lasting to feed back to aircraft straight
To aircraft lands.
Beneficial effects of the present invention are mainly manifested in:To intensity of illumination change with robustness, accuracy rate is higher, real-time
It is higher.
Brief description of the drawings
Fig. 1 is the block flow diagram of whole Dynamic Location system.
Fig. 2 be based on shade and highlighted testing result, wherein, (a) (b) represents the result of detected barrier,
(a) barrier is white in, and barrier is black in (b).
Fig. 3 is the result of address procedures, wherein, (a) is represented according to obtained by the testing result of previous step does range conversion
Image, (b) represent according to range conversion result find out maximum can drop zone, represent can dropping zone for the circle in the lower right corner in figure
Domain.
Fig. 4 is the time whether the algorithm plan provided in dynamic address procedures using us is coughed up to compare figure.
Fig. 5 is to verify the result figure that this algorithm has to the insensitivity of illumination, wherein, (a), (b), (c), the light of (d)
Successively decrease successively according to intensity, but final result shows that this algorithm has the performance to illumination-insensitive.
Fig. 6 is the result figure tested using this method, wherein, (a), (b), (c) represent the experiment three times done, a (1), b
(1), c (1), which is represented, uses addressing results of this algorithm during decline, and a (2), b (2), c (2) are found when representing addressing every time
Arrive can drop zone radius.
Embodiment
The invention will be further described below in conjunction with the accompanying drawings.
1~Fig. 6 of reference picture, a kind of real-time Dynamic Location method of aircraft menology soft landing, comprises the following steps:
1) selection of landing scene and sensor
When aircraft is apart from menology 1-2km, starting to analyze and handling can be dropped by the picture of aircraft capture, searching
Settle in an area domain, and real-time correction result in the process.In order to reach required precision, we are narrow using IDS wide visual field cameras and IDS
Instrument of the visual field camera as capture images.But due to the limitation of condition, we can only be on the basis of existing data set
Emulation experiment is done, with the feasibility of detection algorithm.
2) based on shade and highlighted detection of obstacles algorithm
The image line captured is handled, if having barrier such as stone etc. in the image captured, in the attached of barrier
Closely in addition to shade, highlight regions are had certainly.Specific algorithm is following step by step rapid:
2.1), state initialization:State initialization is carried out, the parameters such as the angle of the sun, aircraft and camera are set.
2.2), the segmentation of shade and highlight regions:Shadow region, the method are partitioned into using maximum entropy threshold partitioning algorithm
In by histogram analysis carry out shadow region segmentation.Then the gray value of original image arbitrfary point is set as p, and 255-p is made
For the new gray value at this point, i.e., highlight regions can be obtained by the method for reverse image gray value.Shadow region is general
It is connected with barrier, but highlight regions typically belong to a part for barrier.
2.3), regional analysis:Using Ellipses Detection detect it is last in result, the letter of shadow region can be obtained
Breath, by the way that highlight regions are merged with shadow region information, can substantially reduce missing inspection region.
2.4), petrophysical model:Express profile information using approximate polygon, according to the angle alpha of profile and the sun,
Shooting angle beta, and barrier region is in direction of illumination long pl and wide pw, can easily disturbance in judgement thing height
H, width w and position pos.The computational methods of height are:H=pl/tan (alpha);The computational methods of width are:W=pw;Position
Put the coordinate that pos is the barrier detected.
3) addressing algorithm based on shade and highlighted detection of obstacles
According to the result of upper section, we can obtain the region of barrier.Before addressing algorithm is introduced.Must introduce away from
From scaling method is become, the range conversion of image is generally used for obtaining the position detected by property detector.Range conversion is calculated
Method has been applied to the coordinate points for calculating the safety zone that can land.Specific algorithm includes:
3.1), gridding, image I is obtained;
3.2), range conversion:Image I range conversion result is calculated, obtains range conversion matrix M;
3.3) maximum, is asked for:Calculating matrix M maximum R, this value R be can drop zone maximum radius, it is maximum
Value institute position in the picture, as can drop zone circle the center of circle, be expressed as circle wherein justifying, the center of circle is expressed as
circle.first;
4) realization of Dynamic Location in real time
, completely can be in the process of flight if directly using above step to each frame in the video of aircraft capture
In search out can drop zone, and meet requirement of real-time by test.But the contact between front and rear frame is so lost, and
And by the resolution ratio of captured video is of a relatively high, therefore the burden of aircraft operation board can be increased, therefore 1), 2), 3)
On the basis of step, a simple Dynamic Location strategy in real time is proposed, this strategy can effectively improve arithmetic speed and accurate
Degree, error detection can be removed to a certain extent by combining the contact between front and rear frame, be comprised the following steps that:
4.1), pre-process:Starting stage, the first frame that video is captured to aircraft do the processing of the 3) step, detected
The center of circle that domain of settling in an area can be justified and radius, as the reference coordinate subsequently addressed;
4.2), high-definition picture is cut:Based on the testing result in 4.1), picture sanction can carried out at drop zone
Cut, wherein clipping region is rectangle, rectangular centre for can the round heart in drop zone, cut picture length and it is wide be respectively w, h, and
And be generally can be 2-4 times of drop zone radius of circle R by w, h.
4.3), address again:Addressed in the result picture that step 4.2) is cut using step 3), acquired results are new
Can drop zone circle the center of circle and radius, and with it is previous can computing compared with the result of drop zone, calculation position skew
Amount.With reference to offset and it is new can drop zone coordinate control aircraft to it is new can drop zone direction move, based on cutting
Zonule carry out computing can significantly improve arithmetic speed;
4.4), repeat step 4.2), 4.3), for video present frame is captured to aircraft, with reference to the calculating of former frame
As a result calculate present frame can drop zone coordinate information, and by it is new can drop zone information it is lasting to feed back to aircraft straight
To aircraft lands.
Fig. 1 is the block flow diagram of whole Dynamic Location system, reads in a pictures first, using based on shade and highlighted
Detection of obstacles algorithm detected, detect the boundary position of barrier.Input using result as next step, performs choosing
Location algorithm, searching out can drop zone.With reference to last time circulation can drop zone result, search out most suitable dropping zone
Domain, this process are the places of the marrow of whole Dynamic Location.
Fig. 2 be based on shade and highlighted testing result, in (a) figure, black region represents it is safe can drop zone,
White represents detected barrier.In (b) figure, left result is embodied, black region represents the tool detected
The barrier of body, white portion is can drop zone.Wherein barrier includes massif, rock etc. and the object of some positions.
Fig. 3 is the result of address procedures, and (a) figure is the result of range conversion, and white portion is the maximum of range conversion
At value, as can drop zone results area.(b) figure is the gridding result that left figure negates, the white circular of right figure lower right
Circle represents the safety zone that can land.
Fig. 4 is to compare the time whether the algorithm plan provided in dynamic address procedures using us is coughed up, and strategy is to make
Result is coughed up with provided herein is algorithm plan, will be obvious that operation time at least reduces 10 times.
Fig. 5 be in order to detect provided herein is algorithm to intensity of illumination change there is robustness, from left to right, from top to bottom,
The intensity of illumination of picture slowly strengthens, but the result detected is basically unchanged, and illustrates change of this algorithm to intensity of illumination well
Change has good robustness.
Fig. 6 is the result using this algorithm experimental, and this experiment does three groups altogether, and left-half is that the coordinate of Dynamic Location becomes
Change, right side part be can drop zone radius.Because aircraft constantly declines, so the barrier that can be detected is more clear
It is clear, further diminish so radius can become.
Claims (1)
1. a kind of real-time Dynamic Location method of aircraft menology soft landing, it is characterised in that:Comprise the following steps:
1) landing scene selects
When aircraft is apart from menology 1-2km, starts to analyze and handle by the picture of aircraft capture, regarded using IDS is wide
The instrument of camera and IDS narrow visual fields camera as capture images, searching can drop zone, and amendment is tied in real time in the process
Fruit;
2) based on shade and highlighted detection of obstacles
The image captured is handled, if having barrier in the image captured, except shade near barrier
Outside have highlight regions, process is as follows:
2.1), state initialization:State initialization is carried out, the angle parameter of the sun, aircraft and camera is set;
2.2), the segmentation of shade and highlight regions:Shadow region is partitioned into using maximum entropy threshold partitioning algorithm, is led in the method
Cross the segmentation that histogram analysis carry out shadow region;Then the gray value of original image arbitrfary point is set as p, regard 255-p as this
New gray value at point, i.e., can obtain highlight regions by the method for reverse image gray value;
2.3), regional analysis:Using Ellipses Detection detect it is last in result, obtain the information of shadow region, pass through
Highlight regions are merged with shadow region information;
2.4), petrophysical model:Profile information is expressed using approximate polygon, according to the angle alpha of profile and the sun, shooting
Angle beta, and barrier region is in direction of illumination long pl and wide pw, height h, width w and the position pos of disturbance in judgement thing;
The computational methods of height are:H=pl/tan (alpha);The computational methods of width are:W=pw;Position pos is what is detected
The coordinate of barrier;
3) addressing based on shade and highlighted detection of obstacles
Addressing process is as follows:
3.1), gridding, image I is obtained;
3.2), range conversion:Image I range conversion result is calculated, obtains range conversion matrix M;
3.3) maximum, is asked for:Calculating matrix M maximum R, this value R be can drop zone maximum radius, maximum institute
Position in the picture, as can drop zone circle the center of circle, wherein circle be expressed as circle, the center of circle is expressed as
circle.first;
4) realization of Dynamic Location, step are as follows in real time:
4.1), pre-process:Starting stage, the first frame that video is captured to aircraft do the processing of the 3) step, and detecting can will
Settle in an area domain circle the center of circle and radius, as the reference coordinate subsequently addressed;
4.2), high-definition picture is cut:Based on the testing result in 4.1), picture cutting can be being carried out at drop zone, its
Middle clipping region is rectangle, rectangular centre for can the round heart in drop zone, cut picture length and it is wide be respectively w, h, and w, h
For can be 2-4 times of drop zone radius of circle R;
4.3), address again:Addressed in the result picture that step 4.2) is cut using step 3), acquired results are new drop
Settle in an area domain circle the center of circle and radius, and with it is previous can computing compared with the result of drop zone, calculation position offset, knot
Close offset and it is new can drop zone coordinate control aircraft to it is new can drop zone direction move, the cell based on cutting
Domain, which carries out computing, can significantly improve arithmetic speed;
4.4), repeat step 4.2), 4.3), for video present frame is captured to aircraft, with reference to the result of calculation of former frame
Calculate present frame can drop zone coordinate information, and by it is new can drop zone information it is lasting feed back to aircraft until flying
Row device lands.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510424070.4A CN105043395B (en) | 2015-07-17 | 2015-07-17 | A kind of real-time Dynamic Location method of aircraft menology soft landing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510424070.4A CN105043395B (en) | 2015-07-17 | 2015-07-17 | A kind of real-time Dynamic Location method of aircraft menology soft landing |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105043395A CN105043395A (en) | 2015-11-11 |
CN105043395B true CN105043395B (en) | 2017-12-05 |
Family
ID=54450129
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510424070.4A Active CN105043395B (en) | 2015-07-17 | 2015-07-17 | A kind of real-time Dynamic Location method of aircraft menology soft landing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105043395B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105468825B (en) * | 2015-11-18 | 2017-03-29 | 北京理工大学 | The dynamic (dynamical) parameter simulation method of recoverable capsule soft landing |
CN105787192B (en) * | 2016-03-15 | 2020-06-23 | 联想(北京)有限公司 | Information processing method and aircraft |
WO2018027338A1 (en) | 2016-08-06 | 2018-02-15 | SZ DJI Technology Co., Ltd. | Automatic terrain evaluation of landing surfaces, and associated systems and methods |
CN109598243B (en) * | 2018-12-06 | 2021-08-24 | 山东大学 | Moon surface safe landing area selection method and system |
CN111721302B (en) * | 2020-06-24 | 2021-11-09 | 北京理工大学 | Method for recognizing and sensing complex terrain features on surface of irregular asteroid |
CN113777590B (en) * | 2021-08-31 | 2024-01-26 | 同济大学 | Complex lunar surface simulation field for soft landing obstacle detection and verification method |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1847792A (en) * | 2006-05-12 | 2006-10-18 | 哈尔滨工业大学 | Simulation test device for visual navigation algorithm of soft landing of deep-space detector |
EP2339296A2 (en) * | 2009-12-22 | 2011-06-29 | General Electric Company | A method of determing range |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2746487B2 (en) * | 1991-07-25 | 1998-05-06 | 防衛庁技術研究本部長 | Aircraft position measurement method for vertical take-off and landing aircraft |
US8275193B2 (en) * | 2004-08-04 | 2012-09-25 | America Gnc Corporation | Miniaturized GPS/MEMS IMU integrated board |
-
2015
- 2015-07-17 CN CN201510424070.4A patent/CN105043395B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1847792A (en) * | 2006-05-12 | 2006-10-18 | 哈尔滨工业大学 | Simulation test device for visual navigation algorithm of soft landing of deep-space detector |
EP2339296A2 (en) * | 2009-12-22 | 2011-06-29 | General Electric Company | A method of determing range |
Non-Patent Citations (2)
Title |
---|
一种基于形态学的探测器安全着陆点选择方法;邵巍等;《宇航学报》;20080331;第659-663页 * |
基于降落图像的安全着陆点选择技术研究;王海涛等;《航天返回与遥感》;20120831;第33卷(第4期);第13-18页 * |
Also Published As
Publication number | Publication date |
---|---|
CN105043395A (en) | 2015-11-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105043395B (en) | A kind of real-time Dynamic Location method of aircraft menology soft landing | |
US11360571B2 (en) | Information processing device and method, program and recording medium for identifying a gesture of a person from captured image data | |
CN106650640B (en) | Negative obstacle detection method based on laser radar point cloud local structure characteristics | |
CN104282020B (en) | A kind of vehicle speed detection method based on target trajectory | |
CN110929566B (en) | Human face living body detection method based on visible light and near infrared binocular camera | |
CN104392468B (en) | Based on the moving target detecting method for improving visual background extraction | |
TWI670684B (en) | A method for detecting and tracing a moving target and a target detection device | |
CN105022990B (en) | A kind of waterborne target rapid detection method based on unmanned boat application | |
CN104835164B (en) | A kind of processing method and processing device of binocular camera depth image | |
CN109636771B (en) | Flight target detection method and system based on image processing | |
CN104408725B (en) | A kind of target reacquisition system and method based on TLD optimized algorithms | |
CN108960011B (en) | Partially-shielded citrus fruit image identification method | |
CN104751146B (en) | A kind of indoor human body detection method based on 3D point cloud image | |
US20230080178A1 (en) | Automated assessment of cracks using lidar and camera data | |
US10861172B2 (en) | Sensors and methods for monitoring flying objects | |
CN109559324A (en) | A kind of objective contour detection method in linear array images | |
CN109711256B (en) | Low-altitude complex background unmanned aerial vehicle target detection method | |
CN106650701A (en) | Binocular vision-based method and apparatus for detecting barrier in indoor shadow environment | |
CN106991418A (en) | Winged insect detection method, device and terminal | |
CN109949308A (en) | A kind of space Relative Navigation target rapid extracting method of anti-starlight interference | |
CN113344953A (en) | Unmanned aerial vehicle-based machine vision tidal bore flow velocity measurement method | |
CN112183361A (en) | Goal detection method and system combining target detection and dynamic difference | |
CN109978916B (en) | Vibe moving target detection method based on gray level image feature matching | |
CN105787912A (en) | Classification-based step type edge sub pixel localization method | |
CN106529441A (en) | Fuzzy boundary fragmentation-based depth motion map human body action recognition method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |