CN103049918A - Method for accurately calculating size of actual target in video frequency monitoring - Google Patents
Method for accurately calculating size of actual target in video frequency monitoring Download PDFInfo
- Publication number
- CN103049918A CN103049918A CN2011103152958A CN201110315295A CN103049918A CN 103049918 A CN103049918 A CN 103049918A CN 2011103152958 A CN2011103152958 A CN 2011103152958A CN 201110315295 A CN201110315295 A CN 201110315295A CN 103049918 A CN103049918 A CN 103049918A
- Authority
- CN
- China
- Prior art keywords
- target
- straight line
- video camera
- line segment
- size
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a method for accurately calculating the size of an actual target in video frequency monitoring. Firstly, according to an actual monitoring scene, building a plane and right angle coordinate system passing by the shooting direction of a camera and perpendicular to the ground; secondly, building a straight line equation of the relationship between camera imaging and the actual target in the plane and right angle coordinate system; and finally by utilizing the relationship of a straight line position, calculating the size of the actual target, and carrying out the identification the classification of a target. By the adoption of the principle of the straight line equation in the plane and right angle coordinate system, the relationship between the size of a two-dimensional target obtained in a video frequency monitoring picture and the size of the actual target is established, so that the actual size of a target is determined, and the determined actual size can be taken as the reference data of classification of the target in intelligent analysis and can be used for application of the actual size of other targets needed to be calculated in a picture. The method has the advantages of low complexity, easiness in realization, and an extremely wide application scope.
Description
Technical field
The present invention relates to accurately calculate in a kind of video monitoring the method for realistic objective size, belong to the security precautions technology field.
Background technology
In recent years, full-fledged along with technology such as computer vision, image processing, pattern-recognition, artificial intelligence, digital signal processing, Video Supervision Technique has also had significant progress, and wherein intelligent video monitoring receives increasing concern as a new generation based on the supervisory system of video content analysis.Intelligent video monitoring is based on computer vision technique the video image content of monitoring scene is analyzed, and extracts the key message in the scene, and forms the monitor mode of corresponding event and alarm.At present, the intelligent video analysis system mainly is identification, classification and tracking to moving target in the application of video monitoring direction, and wherein the classification of moving target and tracking are accurately to carry out on the basis of identification at moving target.
Moving target identification can be by the textural characteristics of moving target, the shape of moving target, and the color of moving target and the methods such as size of moving target are identified.The size of moving target can be described as a most basic attribute of moving target, and determining of target sizes can directly be carried out clear and definite division to the classification of target.For example, height is less than 2 meters, and width is less than 1 meter target, and certainly not motor vehicles according to the monitoring micro-judgment, are likely the people.But intelligent video analysis, the target sizes that gets access to is the size of the two dimension in the monitor video picture just, and the relation between the size of this size and realistic objective is to be difficult to directly obtain.Magnitude relationship between the two and the setting height(from bottom) of video camera, shooting angle, the model of video camera, there is relation camera lens zoom position etc., how both is carried out accurately association, becomes a gordian technique of moving object classification, identification.The current technology that much addresses this problem all is to cooperate for how much the video camera imaging principle to carry out by space multistory, owing to relating to a plurality of space coordinates, complexity is very high.And because calculation of complex, (for example video camera setting height(from bottom), camera lens focal length etc.) is very large on the result of calculation impact so that a lot of on-the-spot calibrating parameters.To intelligent analysis system require highly, simultaneously accuracy rate also easily is affected.
Usually in the actual video monitoring is used, all be that video camera is installed on the position of certain altitude, overlook the monitoring scene scene is monitored.The equipment that monitoring is adopted may comprise gunlock and monopod video camera etc., and the position of installation, depression angle, lens parameters, monitoring range etc. vary.Use for intelligent video analysis etc., how the target found in the video pictures and the target sizes in the actual field are carried out relatedly, very large difficulty just occurred.The actual size of target, for the classification of target, for example people or vehicle have very large booster action.In order to address this problem, need to demarcate a lot of parameters of video monitoring equipment, comprise lens parameters, equipment installation site etc.Calculate common needs by these parameters and carry out three-dimensional space and demarcate, and by image-forming principle, space scale and picture imaging are carried out related, the final size of calculating the acquisition realistic objective.But this algorithm complex is very high, and requires very high to the calibrating parameters accuracy rate.In actual applications, often the impact of a lot of relation factors all is very little, how can adopt a kind of relatively simple method to calculate, and computational solution precision can guarantee in certain limit simultaneously, is the active demand of practical application.
Summary of the invention
The invention provides the method for accurately calculating the target actual size in a kind of video monitoring of simple, applied range.
For reaching above purpose, the present invention adopts following technical proposals.
Accurately calculate the method for realistic objective size in a kind of video monitoring, may further comprise the steps:
(1) according to the actual monitored scene, set up through video camera and take direction, and perpendicular to the plane right-angle coordinate on ground;
(2) in plane right-angle coordinate, set up the straight-line equation of video camera imaging and realistic objective relation, calculate the realistic objective size.
In the step (1), in the described plane right-angle coordinate take the installation site of video camera as true origin O, take perpendicular to the prone direction of Horizon as Y-axis, take in the plane that direction becomes at Y-axis and video camera, cross initial point and do straight line perpendicular to Y-axis, this straight line is the x axle.
In described plane right-angle coordinate, corresponding the first line segment of the center line of shooting picture, target is projected as the second line segment on the first line segment, and the top of target and bottom be the first end points and second end points of corresponding the second line segment respectively;
The second end points of connection coordinate initial point O and the second line segment, the corresponding straight line of the line segment that obtains and ground level intersects at the first intersection point, cross the first intersection point and do the straight line that is parallel to Y-axis and hand over the first line segment in the second intersection point, then the true altitude of the corresponding target of distance between the first intersection point and the second intersection point.
In the step (2), in described plane right-angle coordinate, setting up the straight-line equation of video camera imaging and realistic objective relation, be the relation of setting up video camera imaging and realistic objective according to image-forming principle, and this relation obtains by setting up straight-line equation.
Utilize each the linear position relation in the plane right-angle coordinate, calculating realistic objective size is according in the plane geometry, crossing, the parallel position relationship of straight line, utilize intersecting lens to obtain intersecting point coordinate, and calculate the actual size of target according to the distance between two points formula.
In the step (2), concrete calculation procedure is as follows:
A) setting height(from bottom), video camera shooting direction and the angle of surface level, the vertical field of view angle of video camera according to video camera draws two endpoint locations of described the first line segment;
B) according to the lens imaging principle, obtain two endpoint locations of described the second line segment;
C) obtain distance between described the first intersection point and the second intersection point, the i.e. true altitude of target according to geometric relationship;
D) actual aspect ratio according to target equals target the ratio of width to height in image, obtains the developed width of target.
Beneficial effect of the present invention is:
1, the present invention adopts and to carry out straight-line equation calculate in plane right-angle coordinate, obtains the corresponding relation of target and realistic objective size in the video pictures, and computing method are very simple, can be applied in the middle of various device or the software, and range of application is very extensive.
2, computing method of the present invention are simple, and needed actual calibrating parameters (such as video camera setting height(from bottom), field angle etc.) is less, for practical application provides a great convenience.
Description of drawings
Fig. 1 is the process flow diagram of the inventive method;
Fig. 2 is actual monitored scene graph in the present embodiment;
Fig. 3 is the present embodiment mathematical model figure abstract to the actual monitored scene;
Fig. 4 is that the present embodiment is according to the mathematical model figure of further abstract foundation on Fig. 3 basis;
Fig. 5 is the location drawing of target in image that the based on motion detection algorithm obtains in the present embodiment.
Embodiment
In the present embodiment, video camera is installed on position apart from 14 meters on ground, the angle of taking direction and surface level is 36 to spend.Video camera adopts the tight shot of 6mm, can obtain by consulting the video camera handbook, and its horizontal field of view angle is 40 degree, and the vertical field of view angle is 30 degree.By the software client of Internet Transmission to the rear end, software client carries the intelligent video analysis function to video camera, can carry out mobile detection to monitor video, extracts moving target with the picture taken.This method is built in the software client, can get access to the analysis result of mobile detection, i.e. the position of moving target in picture in the video pictures, with and size in picture.This method is calculated in real time according to the analysis result of mobile detection, calculates the actual size of moving target, and this value is exported to follow-up intellectual analysis function use, and target is carried out type divide, such as people or vehicle.
Describe the present invention below in conjunction with accompanying drawing.
Step (1) such as Fig. 1, according to the actual monitored scene, is set up the plane right-angle coordinate perpendicular to ground level.Such as Fig. 4, set up plane right-angle coordinate, take the installation site of video camera as true origin, take perpendicular to the prone direction of Horizon as Y-axis.Take in the plane that direction becomes at Y-axis and video camera, cross initial point and do straight line perpendicular to Y-axis, this straight line is the x axle.Fig. 4 cathetus OF is that video camera is taken direction, straight line BL is that ground level is (in the present embodiment, ground is level) with the intersection of XOY plane, line segment OL is the setting height(from bottom) of monopod video camera, ∠ FOX is the angle that video camera is taken direction and surface level, ∠ IOB is the vertical field of view angle of video camera, gives an I and puts B with straight line BL.Straight line AB is perpendicular to straight line OF, and gives a C with straight line OF, gives a B with straight line OB, gives an A with straight line OI.If line segment AB is mapped directly in the shooting picture of video camera, line segment AB just is the center line of shooting picture, the vertical line that runs through picture that picture center line span equates from shooting picture left and right sides frontier distance.Just be in the screen centerline position if the based on motion detection algorithm obtains moving target, its crown accounts for approximately 1/6 of picture overall height apart from the distance on picture top, and the height of target in picture accounts for approximately 1/8 of picture overall height.Can be according to height and the position of target on screen centerline, equal proportion is mapped to it on line segment AB, such as Fig. 4, can obtain line segment DE.Line segment DE is according to image-forming principle, and one section line segment on the picture center line is carried out equal proportion mapping, the projection of the target that obtains on line segment AB.Connect OE and hand over BL in a H, connect OD, cross H point do be parallel to Y-axis straight line friendship OD in a J.At this moment, the true altitude of the corresponding moving target of line segment JH.
Step (2) such as Fig. 1,4, in plane right-angle coordinate, is set up the straight-line equation of video camera imaging and realistic objective relation, utilizes the linear position relation, calculates the realistic objective size, specifically comprises following content:
Integrating step 1 can obtain each parameter value as follows:
∠ FOX=36 degree;
∠ IOB=30 degree;
BL=14 rice;
Below be to carry out detailed computation process according to as above technical parameter:
A, ask a B with the some A coordinate
Because O is true origin, while ∠ FOX=36
The slope k of straight line OC
OC=tan (∠ FOX)=tan36=0.727
Vertical with straight line OF because of straight line AB simultaneously, thus obtain,
k
AB＝-1/k
OC＝-1.376
According to, straight line BL is parallel to X-axis, OL=14
Can get, straight line BL equation is: y=OL=14
Straight line OB crosses initial point, simultaneously k
OB=tan (∠ FOX-∠ AOB/2)=tan (36-30/2)=0.384
Can get, straight line OB equation is: y=k
OB* x=0.384*x
Simultaneous straight line BL equation and straight line OB equation
Thereby obtaining the coordinate that B orders is (B
x, B
y)
Wherein, B
x=OL/k
OB=36.458, B
y=OL=14
By k
ABReach the B point coordinate and get, the equation of straight line AB is:
y＝k
AB(x-OL/k
OB)+OL＝-1.376*x+64.166
Straight line OA crosses initial point, simultaneously k
OA=tan (∠ FOX+ ∠ AOB/2)=tan (36+30/2)=1.23
Can get, straight line OA equation is: y=k
OA* x=1.23*x
Simultaneous straight line AB equation and straight line OA equation
Thereby obtaining the coordinate that A orders is (A
x, A
y)
Wherein, A
x=OL* (k
OB-k
AB)/(k
OB* (k
OA-k
AB))=24.622
A
y＝k
OA*OL*(k
OB-k
AB)/(k
OB*(k
OA-k
AB))＝30.286
B, ask a D and the some E coordinate
According to the lens imaging principle,
(lu is object distance, and lv is image distance, and hu is object height, and hv is image height)
Thereby can get BE/BA=0.4, BD/BA=0.177
Utilize the proportional principle of similar triangles corresponding sides
Can get, the coordinate that E is ordered is (E
x, E
y)
Wherein, E
x=BL-(E
y-OL)/k
AB=B
x-(E
y-OL)/k
AB
＝36.458-(20.514-14)/(-1.376)＝41.192
E
y＝OL+BE/BA*(k
OA*OL*(k
OB-k
AB)/(k
OB*(k
OA-k
AB))-OL)
＝OL+BE/BA*(A
y-OL)
＝14+0.4*(30.286-14)
＝20.514
The coordinate that D is ordered is (D
x, D
y)
Wherein, D
x=BL-(D
y-OL)/k
AB
＝36.458-(17.192-14)/(-1.376)
＝38.778
D
y＝OL+BD/BA*(k
OA*OL*(k
OB-k
AB)/(k
OB*(k
OA-k
AB))-OL)
＝OL+BD/BA*(A
y-OL)
＝14+0.177*(30.286-14)
＝16.882
C, ask the coordinate of a H and some J, and the length of JH
OE crosses initial point according to straight line, can obtain,
The slope of straight line OE is:
k
OE＝(OL+BE/BA*(OL*k
OA(k
OB-k
AB)/(k
OB*(k
OA-k
AB))-OL))/(BL-(E
y-OL)/k
AB)
＝E
y/E
x
＝20.514/41.192
＝0.498
Thereby the equation of straight line OE is: y=k
OE* x=0.498*x
Simultaneous straight line BL equation and straight line OE equation
Obtaining the coordinate that H orders is (OL/k
OE, OL)=(28.112,14)
Because straight line JH is parallel to the y axle, and the known H coordinate of ordering, thereby,
The equation of straight line JH is: x=OL/k
OE=28.112
OD crosses initial point according to straight line, can obtain,
The slope of straight line OD is:
k
OD＝(OL+BD/BA*(OL*k
OA(k
OB-k
AB)/(k
OB*(k
OA-k
AB))-OL))/(BL-(E
y-OL)/k
AB)
＝D
y/D
x
＝16.882/38.778
＝0.435
Thereby the equation of straight line OD is: y=k
OD* x=0.435*x
Simultaneous straight line JH equation and straight line OD equation
Obtain J point coordinate (J
x, J
y)
J wherein
y=OL*k
OD/ k
OE=14*0.435/0.498=12.21
J
x＝OL/k
OE＝14/0.498＝28.112
By a H with the length that the coordinate of putting J gets line segment JH be:
D, according to the true altitude of target, calculate the developed width of target, computing formula is as follows:
Developed width=the 1.77*35/133=0.47 of target (m)
Can see according to field observation, the target that occurs in the picture is the people, and the height that calculates is 1.77 meters, and developed width is 0.47 meter, and the result is very accurate.Obviously this advanced to be used for follow-up Intelligent Target classification, had very important reference significance, can also be used for simultaneously other various application that need to obtain the shot object actual size.
In above-described embodiment, calculating is the explanation of carrying out as example at the shooting picture center line take target, on the picture center line feeling the pulse with the finger-tip be marked in the picture the position in the horizontal direction, equate with picture left and right sides frontier distance.The distortion factor of camera lens has been ignored in this calculating, except the lens distortion factor, if target is not on center line, calculate this moment in the manner described above, other deviation will appear in the result, the size of deviation and video camera are apart from floor level, and the field angle of video camera is big or small, and there is relation target position in picture etc.If these factors are consideration all, meeting is so that computation complexity is very high, and several factors can't obtain by calculating.Pass through in practice actual measurement, in the situation that the camera field of view angle is no more than 50 degree, this error can not surpass 5%, and the impact of considering this error obviously is less, therefore can not ignore this error in accuracy requirement is not very high application.
Claims (4)
1. accurately calculate the method for realistic objective size in the video monitoring, it is characterized in that, may further comprise the steps:
(1) according to the actual monitored scene, set up through video camera and take direction, and perpendicular to the plane right-angle coordinate on ground;
(2) in plane right-angle coordinate, set up the straight-line equation of video camera imaging and realistic objective relation, calculate the realistic objective size.
2. accurately calculate the method for realistic objective size in the video monitoring as claimed in claim 1, it is characterized in that, in the step (1), in the described plane right-angle coordinate take the installation site of video camera as true origin O, take perpendicular to the prone direction of Horizon as Y-axis, take in the plane that direction becomes at Y-axis and video camera, cross initial point and do straight line perpendicular to Y-axis, this straight line is the x axle.
3. accurately calculate the method for realistic objective size in the video monitoring as claimed in claim 2, it is characterized in that, in described plane right-angle coordinate, corresponding the first line segment of the center line of shooting picture, target is projected as the second line segment on the first line segment, the top of target and bottom be the first end points and second end points of corresponding the second line segment respectively;
The second end points of connection coordinate initial point O and the second line segment, the corresponding straight line of the line segment that obtains and ground level intersects at the first intersection point, cross the first intersection point and do the straight line that is parallel to Y-axis and hand over the first line segment in the second intersection point, then the true altitude of the corresponding target of distance between the first intersection point and the second intersection point.
4. accurately calculate the method for realistic objective size in the video monitoring as claimed in claim 3, it is characterized in that, in the step (2), concrete calculation procedure is as follows:
A) setting height(from bottom), video camera shooting direction and the angle of surface level, the vertical field of view angle of video camera according to video camera draws two endpoint locations of described the first line segment;
B) according to the lens imaging principle, obtain two endpoint locations of described the second line segment;
C) obtain distance between described the first intersection point and the second intersection point, the i.e. true altitude of target according to geometric relationship;
D) actual aspect ratio according to target equals target the ratio of width to height in image, obtains the developed width of target.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011103152958A CN103049918A (en) | 2011-10-17 | 2011-10-17 | Method for accurately calculating size of actual target in video frequency monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011103152958A CN103049918A (en) | 2011-10-17 | 2011-10-17 | Method for accurately calculating size of actual target in video frequency monitoring |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103049918A true CN103049918A (en) | 2013-04-17 |
Family
ID=48062547
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011103152958A Pending CN103049918A (en) | 2011-10-17 | 2011-10-17 | Method for accurately calculating size of actual target in video frequency monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103049918A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104378539A (en) * | 2014-11-28 | 2015-02-25 | 华中科技大学 | Scene-adaptive video structuring semantic extraction camera and method thereof |
| CN105333818A (en) * | 2014-07-16 | 2016-02-17 | 浙江宇视科技有限公司 | 3D space measurement method based on monocular camera |
| CN108234932A (en) * | 2016-12-21 | 2018-06-29 | 腾讯科技（深圳）有限公司 | Personnel's form extracting method and device in video monitoring image |
| CN110660186A (en) * | 2018-06-29 | 2020-01-07 | 杭州海康威视数字技术股份有限公司 | Method and device for identifying target object in video image based on radar signal |
| CN110879386A (en) * | 2019-12-02 | 2020-03-13 | 山东科技大学 | Target size estimation method based on broadband shallow profile data |
| CN111402344A (en) * | 2020-04-23 | 2020-07-10 | Oppo广东移动通信有限公司 | Calibration method, calibration device and non-volatile computer-readable storage medium |
| CN111504269A (en) * | 2020-05-26 | 2020-08-07 | 南方电网调峰调频发电有限公司 | Underwater scale measuring method and device |
| CN113674312A (en) * | 2021-06-30 | 2021-11-19 | 浙江大华技术股份有限公司 | Target tracking close-up method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101033944A (en) * | 2007-04-20 | 2007-09-12 | 北京工业大学 | Measurement instrument and method suitable for remotely monitoring crack width of concrete |
| CN101661619A (en) * | 2009-09-25 | 2010-03-03 | 天津大学 | Image manipulation detection method based on single view measurement |
-
2011
- 2011-10-17 CN CN2011103152958A patent/CN103049918A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101033944A (en) * | 2007-04-20 | 2007-09-12 | 北京工业大学 | Measurement instrument and method suitable for remotely monitoring crack width of concrete |
| CN101661619A (en) * | 2009-09-25 | 2010-03-03 | 天津大学 | Image manipulation detection method based on single view measurement |
Non-Patent Citations (1)
| Title |
|---|
| 陈大海等: "《固定摄像头图像中测算目标距离和尺寸的算法》", 《大众科技》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105333818A (en) * | 2014-07-16 | 2016-02-17 | 浙江宇视科技有限公司 | 3D space measurement method based on monocular camera |
| CN104378539A (en) * | 2014-11-28 | 2015-02-25 | 华中科技大学 | Scene-adaptive video structuring semantic extraction camera and method thereof |
| CN104378539B (en) * | 2014-11-28 | 2017-08-08 | 华中科技大学 | The video structural extraction of semantics video camera and its method of scene adaptive |
| CN108234932A (en) * | 2016-12-21 | 2018-06-29 | 腾讯科技（深圳）有限公司 | Personnel's form extracting method and device in video monitoring image |
| CN110660186A (en) * | 2018-06-29 | 2020-01-07 | 杭州海康威视数字技术股份有限公司 | Method and device for identifying target object in video image based on radar signal |
| CN110660186B (en) * | 2018-06-29 | 2022-03-01 | 杭州海康威视数字技术股份有限公司 | Method and device for identifying target object in video image based on radar signal |
| CN110879386A (en) * | 2019-12-02 | 2020-03-13 | 山东科技大学 | Target size estimation method based on broadband shallow profile data |
| CN110879386B (en) * | 2019-12-02 | 2022-08-30 | 山东科技大学 | Target size estimation method based on broadband shallow profile data |
| CN111402344A (en) * | 2020-04-23 | 2020-07-10 | Oppo广东移动通信有限公司 | Calibration method, calibration device and non-volatile computer-readable storage medium |
| CN111504269A (en) * | 2020-05-26 | 2020-08-07 | 南方电网调峰调频发电有限公司 | Underwater scale measuring method and device |
| CN111504269B (en) * | 2020-05-26 | 2024-04-19 | 南方电网调峰调频发电有限公司 | Underwater scale measurement method and device thereof |
| CN113674312A (en) * | 2021-06-30 | 2021-11-19 | 浙江大华技术股份有限公司 | Target tracking close-up method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103049918A (en) | Method for accurately calculating size of actual target in video frequency monitoring | |
| Li et al. | Optimal extrinsic calibration between a stereoscopic system and a LIDAR | |
| US9678210B2 (en) | Error estimation in real-time visual odometry system | |
| CN105021124A (en) | Planar component three-dimensional position and normal vector calculation method based on depth map | |
| Bryson et al. | Airborne smoothing and mapping using vision and inertial sensors | |
| CN104574393A (en) | Three-dimensional pavement crack image generation system and method | |
| Li et al. | 3D triangulation based extrinsic calibration between a stereo vision system and a LIDAR | |
| Pinggera et al. | High-performance long range obstacle detection using stereo vision | |
| Moemen et al. | 3-D reconstruction and measurement system based on multimobile robot machine vision | |
| CN108335325A (en) | A kind of cube method for fast measuring based on depth camera data | |
| Abanay et al. | A calibration method of 2D LIDAR-Visual sensors embedded on an agricultural robot | |
| CN112446915A (en) | Picture-establishing method and device based on image group | |
| Wang et al. | Micro aerial vehicle navigation with visual-inertial integration aided by structured light | |
| CN115700760A (en) | Multi-mode data-based total-space laser radar scattering cross section calculation method | |
| CN115393537A (en) | Precision evaluation system and method for three-dimensional visual modeling of power transmission channel | |
| CN115222815A (en) | Obstacle distance detection method, obstacle distance detection device, computer device, and storage medium | |
| Mardiati et al. | The derivation of matrix transformation from pixel coordinates to real-world coordinates for vehicle trajectory tracking | |
| CN114863031A (en) | Method, device and equipment for calculating overlapping degree of three-dimensional model and storage medium | |
| CN114565669A (en) | Method for fusion positioning of field-end multi-camera | |
| CN113870367A (en) | Method, apparatus, device, storage medium and program product for generating camera external parameters | |
| Aliakbarpour et al. | Geometric exploration of virtual planes in a fusion-based 3D data registration framework | |
| Förstner et al. | Automatic orientation and recognition in highly structured scenes | |
| Gu et al. | Research on SLAM of indoor mobile robot assisted by AR code landmark | |
| Bao et al. | Global principal planes aided LiDAR-based mobile mapping method in artificial environments | |
| Wu et al. | Retrieval of siltation 3D properties in artificially created water conveyance tunnels using image-based 3D reconstruction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130417 |