CN110307791A - Vehicle length and speed calculation method based on three-dimensional vehicle bounding box - Google Patents
Vehicle length and speed calculation method based on three-dimensional vehicle bounding box Download PDFInfo
- Publication number
- CN110307791A CN110307791A CN201910509507.2A CN201910509507A CN110307791A CN 110307791 A CN110307791 A CN 110307791A CN 201910509507 A CN201910509507 A CN 201910509507A CN 110307791 A CN110307791 A CN 110307791A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- bounding box
- dimensional
- detection zone
- length
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/04—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness specially adapted for measuring length or width of objects while moving
- G01B11/043—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness specially adapted for measuring length or width of objects while moving for measuring length
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P5/00—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft
- G01P5/18—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft by measuring the time taken to traverse a fixed distance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of Vehicle length and speed calculation method based on three-dimensional vehicle bounding box.This method comprises: (1), which is based on Mask R-CNN network, generates vehicle exposure mask；(2) make tangent line to the vehicle exposure mask of generation from three end points in scene and then construct three-dimensional vehicle bounding box；(3) it establishes vehicle virtual detection zone, and whether judges vehicle whether in detection zone in detection zone according to the bottom surface front midpoint of three-dimensional vehicle bounding box；(4) pixel coordinate that road surface reference point is determined using lane phantom line segments and scene end point solves the homography matrix between road plane world coordinates and respective pixel coordinate further according to known lane dotted line segment length, lane width；(5) vehicle physical length is calculated using homography matrix and three-dimensional vehicle bounding box；(6) car speed is calculated using homography matrix, three-dimensional vehicle bounding box and virtual detection area.Computational accuracy of the present invention is high and equipment cost is low, can be effectively applied in wisdom traffic system.
Description
Technical field
The present invention relates to a kind of Vehicle length and speed calculation method based on three-dimensional vehicle bounding box belongs to computer view
Feel technology and wisdom traffic field.
Background technique
Vehicle length and speed are parameters important in vehicular traffic information.Car speed usually passes through under embedment road surface
Sensor is obtained by arranging radar on road.However equipment manufacturing cost is higher in this way, and when between vehicle
Apart from it is close when, can bring larger detection error even result in detection failure.A kind of detection skill of the video technique as low cost
Art is widely studied at present, but its detection accuracy is still undesirable.And Vehicle length is the important indicator as vehicle classification,
Effective and inexpensive calculation method is still relatively short of at present.How effectively, high-precision and be achieved at low cost Vehicle length and speed
The calculating of degree is the problem of Current traffic field face.
Summary of the invention
To solve the above problems, the invention discloses a kind of Vehicle length based on three-dimensional vehicle bounding box and
Speed calculation method, computational accuracy is high and equipment cost is low.
Above-mentioned purpose is achieved through the following technical solutions:
A kind of Vehicle length and speed calculation method based on three-dimensional vehicle bounding box, this method comprises:
(1) vehicle exposure mask is generated based on Mask R-CNN network；
(2) make tangent line to the vehicle exposure mask of generation from three end points in scene and then construct three-dimensional vehicle bounding box；
(3) vehicle virtual detection zone is established, and according to the bottom surface front midpoint of three-dimensional vehicle bounding box whether in detection zone
Inside judge the vehicle whether in detection zone；
(4) road pavement is demarcated, and obtains the homography matrix between road plane world coordinates and respective pixel coordinate；
(5) physical length of vehicle is calculated using homography matrix and three-dimensional vehicle bounding box；
(6) car speed is calculated using homography matrix, three-dimensional vehicle bounding box and virtual detection area.
The Vehicle length and speed calculation method based on three-dimensional vehicle bounding box, building described in (2) are three-dimensional
Vehicle bounding box specifically determines scene first, the according to the lane line in traffic scene, vehicle texture, street lamp position respectively
Two and the orthogonal end point of third, and make tangent line structure to the vehicle exposure mask generated by Mask R-CNN based on these three orthogonal end points
Build three-dimensional vehicle bounding box.
The Vehicle length and speed calculation method based on three-dimensional vehicle bounding box, establishes vehicle described in (3)
Virtual detection area is to establish vehicle virtual detection zone within sweep of the eye in camera lens, and according to the bottom surface front of three-dimensional vehicle bounding box
Whether whether midpoint in detection zone judge the vehicle in detection zone.
The Vehicle length and speed calculation method based on three-dimensional vehicle bounding box, road surface calibration described in (4)
And then the homography matrix H between road plane world coordinates and respective pixel coordinate is obtained,
The pixel coordinate for specifically determining lane phantom line segments endpoint first, disappears further according to lane phantom line segments endpoint and scene second
It loses point and establishes straight line, then obtain the pixel coordinate of these straight lines Yu lane two sides solid line intersection point；By these above-mentioned known pixels
The point of coordinate is as road surface calibration reference point；Utilize known lane phantom line segments physical length and lane width, it can obtain
The world coordinates of these reference points；The pixel coordinate of reference point and world coordinates are brought into formula (2), by utilizing least square method
Or singular value decomposition can acquire eight independent parameters in homography matrix, to be the Vehicle length based on three-dimensional vehicle bounding box
And the calculating of speed provides basis.
(x in formulai,yi) and (Xi,Yi) world coordinates and pixel coordinate of reference point i are respectively represented, m is in homography matrix H
Independent parameter.
The Vehicle length and speed calculation method based on three-dimensional vehicle bounding box, Vehicle length described in (5)
In calculating, the midpoint world seat on both sides before and after three-dimensional vehicle bounding box bottom surface is calculated according to the homography matrix that road surface calibration obtains
Mark, the difference of the two o'clock world coordinates is the physical length of vehicle.
The Vehicle length and speed calculation method based on three-dimensional vehicle bounding box, car speed described in (6)
In calculating, the distance that is travelled in virtual detection area using vehicle and time calculate car speed, wherein operating range according to
World coordinates difference between the vehicle three-dimensional vehicle bounding box bottom surface front midpoint corresponding when ingressing and egressing out detection zone is counted
It calculates, and running time is then determined according to video frame rate, speed calculation formula is as follows:
In formula: V is speed, and L and T are operating range and time of the vehicle in virtual detection area, N respectivelyfIt is that vehicle exists
Totalframes corresponding in driving process, F in detection zonerIt is the frame per second of video,WithRespectively
It is the bottom surface front midpoint world coordinates of three-dimensional boundaries frame corresponding to the into and out detection zone of vehicle.
Compared with prior art, the beneficial effects of the present invention are:
(1) road plane scaling method proposed by the present invention is compared with the calculating side using three orthogonal end points and camera lens height
Method precision is higher.
(2) present invention is compared with tradition is based on the scheme that tests the speed of embedded-type sensor or radar, and required equipment cost is substantially
It reduces.
(3) the invention proposes the Vehicle length calculation methods based on monocular camera, provide for vehicular traffic classification new
Mode.
Detailed description of the invention
Fig. 1 is the building of three-dimensional vehicle bounding box；
Fig. 2 is road surface calibration reference point locations and verifying target；
Fig. 3 is that vehicle commander calculates schematic diagram；
Fig. 4 is that speed calculates schematic diagram.
Specific embodiment
The present invention will be further explained With reference to embodiment.
By taking certain bridge deck traffic scene as an example, detected in camera lens by the length of vehicle and speed.Specific includes such as
Lower content:
1. determining scene first, second and third respectively according to the lane line in traffic scene, vehicle texture, street lamp position
End point determines the intersection point i.e. end point of same direction difference straight line in scene according to least square method.And it is based on these three
Orthogonal end point makees tangent line to the vehicle exposure mask generated by Mask R-CNN and then constructs three-dimensional vehicle bounding box, as shown in Figure 1,
The 1 of three-dimensional boundaries frame can be directly determined according to intersection point between tangent line first, 2,3,4 angle points then can be true using this four angle points
Determine three-dimensional boundaries frame four additional angle point 5,6,7,8.Eight angle points can construct three-dimensional vehicle bounding box after all determining.
2. establishing vehicle virtual detection zone within sweep of the eye in camera lens, and utilize three-dimensional vehicle boundary to calculate speed
Whether whether the bottom surface front midpoint of frame in detection zone judge vehicle in detection zone.
3. because homography matrix has 8 independent unknown parameters in formula (1), it is therefore desirable to which at least four is not in straight line
On reference point solve homography matrix H.The pixel coordinate for determining lane phantom line segments endpoint first, further according to lane phantom line segments end
Point and the second end point establish straight line, then obtain the pixel coordinate of these straight lines Yu lane two sides solid line intersection point.By these
Know the point of pixel coordinate as calibration reference point, as shown in Figure 2.It is wide using known lane phantom line segments physical length and lane
Degree, can obtain the world coordinates of these reference points.The pixel coordinate of reference point and world coordinates are brought into formula (2), by most
Small square law or singular value decomposition can acquire homography matrix H.In order to verify the reliability of the proposed scaling method of the present invention, 15 sections
The lane phantom line segments of known length are taken as verifying target to examine calibration result of the invention, and verifying target is as shown in Figure 2.
It the verifying target length that is calculated according to three orthogonal end points and camera heights and is calculated according to this patent method
Verifying target length is listed in Table 1.This patent proposes that the calculating error of method is both less than 5% as can be seen from the table, substantially
More than conventional method.
4. the homography matrix of acquisition is inverted to obtain H-1, then according to the midpoint picture on both sides before and after three-dimensional vehicle bounding box bottom surface
The homogeneous form of plain coordinate is multiplied by H-1Corresponding homogeneous world coordinates is obtained, then homogeneous world coordinates is carried out with third component
Normalization obtains corresponding two-dimensional world coordinate, and the distance of the midpoint two-dimensional world coordinate on both sides is before and after vehicle bounding box bottom surface
For the physical length of vehicle, it is as shown in Figure 3 that vehicle commander calculates schematic diagram.
5. the distance travelled in virtual detection area using vehicle calculates car speed with the time, as shown in figure 4, wherein
Operating range utilizes the generation between the vehicle three-dimensional vehicle bounding box bottom surface front midpoint corresponding when ingressing and egressing out detection zone
Boundary's coordinate difference calculates, and running time is then determined according to video frame rate, and speed is calculated as follows by formula (3):
To sum up, the Vehicle length based on three-dimensional vehicle bounding box and speed calculation method proposed according to the present invention can be effective
In wisdom traffic system.
Target length calculated result is verified on 1 road surface of table
Claims (6)
1. a kind of Vehicle length and speed calculation method based on three-dimensional vehicle bounding box, it is characterised in that this method comprises:
(1) vehicle exposure mask is generated based on Mask R-CNN network；
(2) make tangent line to the vehicle exposure mask of generation from three end points in scene and then construct three-dimensional vehicle bounding box；
(3) establish vehicle virtual detection zone, and according to the bottom surface front midpoint of three-dimensional vehicle bounding box whether in detection zone come
Judge vehicle whether in detection zone；
(4) road pavement is demarcated, and obtains the homography matrix between road plane world coordinates and respective pixel coordinate；
(5) physical length of vehicle is calculated using homography matrix and three-dimensional vehicle bounding box；
(6) car speed is calculated using homography matrix, three-dimensional vehicle bounding box and virtual detection area.
2. the Vehicle length and speed calculation method according to claim 1 based on three-dimensional vehicle bounding box, feature exist
In: building three-dimensional vehicle bounding box described in (2), specifically according to the lane line in traffic scene, vehicle texture, street lamp position
It sets and determines the orthogonal end point of scene first, second and third respectively, and based on these three orthogonal end points to by Mask R-CNN
The vehicle exposure mask of generation makees tangent line building three-dimensional vehicle bounding box.
3. the Vehicle length and speed calculation method according to claim 1 based on three-dimensional vehicle bounding box, feature exist
In: it is to establish vehicle virtual detection zone within sweep of the eye in camera lens that vehicle virtual detection zone is established described in (3), and according to three
Whether whether the bottom surface front midpoint for tieing up vehicle bounding box in detection zone judge the vehicle in detection zone.
4. the Vehicle length and speed calculation method according to claim 1 based on three-dimensional vehicle bounding box, feature exist
In: the homography matrix H between road surface calibration described in (4) and then acquisition road plane world coordinates and respective pixel coordinate,
The pixel coordinate for determining lane phantom line segments endpoint first, is established further according to lane phantom line segments endpoint and the second end point of scene
Then straight line obtains the pixel coordinate of these straight lines Yu lane two sides solid line intersection point；By the point of these above-mentioned known pixels coordinates
As road surface calibration reference point；Utilize known lane phantom line segments physical length and lane width, it can obtain these references
The world coordinates of point；The pixel coordinate of reference point and world coordinates are brought into formula (2), by utilizing least square method or singular value
Decomposition can acquire eight independent parameters in homography matrix, to be Vehicle length and speed based on three-dimensional vehicle bounding box
It calculates and basis is provided；
(x in formulai,yi) and (Xi,Yi) world coordinates and pixel coordinate of reference point i are respectively represented, m is only in homography matrix H
Vertical parameter.
5. the Vehicle length and speed calculation method according to claim 1 based on three-dimensional vehicle bounding box, feature exist
In: during Vehicle length described in (5) calculates, three-dimensional vehicle bounding box bottom surface is calculated according to the homography matrix that road surface calibration obtains
The difference of the midpoint world coordinates on front and back both sides, the two o'clock world coordinates is the physical length of vehicle.
6. the Vehicle length and speed calculation method according to claim 1 based on three-dimensional vehicle bounding box, feature exist
In: during car speed described in (6) calculates, the distance travelled in virtual detection area using vehicle calculates vehicle with the time
Speed, wherein operating range is according in the vehicle three-dimensional vehicle bounding box bottom surface front corresponding when ingressing and egressing out detection zone
World coordinates difference between point calculates, and running time is then determined according to video frame rate, and speed calculation formula is as follows:
In formula: V is speed, and L and T are operating range and time of the vehicle in virtual detection area, N respectivelyfIt is vehicle in detection zone
Corresponding totalframes, F in interior driving processrIt is the frame per second of video,WithIt is vehicle respectively
The bottom surface front midpoint world coordinates of three-dimensional boundaries frame corresponding into and out detection zone.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910509507.2A CN110307791B (en) | 2019-06-13 | 2019-06-13 | Vehicle length and speed calculation method based on three-dimensional vehicle boundary frame |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910509507.2A CN110307791B (en) | 2019-06-13 | 2019-06-13 | Vehicle length and speed calculation method based on three-dimensional vehicle boundary frame |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110307791A true CN110307791A (en) | 2019-10-08 |
| CN110307791B CN110307791B (en) | 2020-12-29 |
Family
ID=68076628
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910509507.2A Active CN110307791B (en) | 2019-06-13 | 2019-06-13 | Vehicle length and speed calculation method based on three-dimensional vehicle boundary frame |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110307791B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909620A (en) * | 2019-10-30 | 2020-03-24 | 北京迈格威科技有限公司 | Vehicle detection method and device, electronic equipment and storage medium |
| CN112489106A (en) * | 2020-12-08 | 2021-03-12 | 深圳市哈工交通电子有限公司 | Video-based vehicle size measuring method and device, terminal and storage medium |
| CN112798811A (en) * | 2020-12-30 | 2021-05-14 | 杭州海康威视数字技术股份有限公司 | Speed measurement method, device and equipment |
| CN113011388A (en) * | 2021-04-23 | 2021-06-22 | 吉林大学 | Vehicle outer contour size detection method based on license plate and lane line |
| CN113689713A (en) * | 2020-05-19 | 2021-11-23 | 昆山研达电脑科技有限公司 | Vehicle speed monitoring method based on automobile data recorder |
| WO2021237750A1 (en) * | 2020-05-29 | 2021-12-02 | Siemens Ltd., China | Method and apparatus for vehicle length estimation |
| CN114863025A (en) * | 2022-05-18 | 2022-08-05 | 禾多科技（北京）有限公司 | Three-dimensional lane line generation method and device, electronic device and computer readable medium |
| CN115019557A (en) * | 2022-06-09 | 2022-09-06 | 杭州电子科技大学 | TUIO protocol-based lane virtual boundary construction and boundary crossing detection method |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010214258A (en) * | 2009-03-13 | 2010-09-30 | Toyota Motor Corp | Masking jig |
| CN102410836A (en) * | 2011-07-26 | 2012-04-11 | 清华大学 | Space six-freedom degrees article locating system based on two-dimensional sensitive sensor |
| US20130128064A1 (en) * | 2011-04-08 | 2013-05-23 | Hailin Jin | Methods and Apparatus for Robust Video Stabilization |
| CN104200483A (en) * | 2014-06-16 | 2014-12-10 | 南京邮电大学 | Human body central line based target detection method under multi-camera environment |
| CN105573047A (en) * | 2014-10-10 | 2016-05-11 | 中芯国际集成电路制造(上海)有限公司 | System and method for detecting mask figure fidelity |
| CN105718870A (en) * | 2016-01-15 | 2016-06-29 | 武汉光庭科技有限公司 | Road marking line extracting method based on forward camera head in automatic driving |
| CN106408589A (en) * | 2016-07-14 | 2017-02-15 | 浙江零跑科技有限公司 | Vehicle-mounted overlooking camera based vehicle movement measurement method |
| CN107122792A (en) * | 2017-03-15 | 2017-09-01 | 山东大学 | Indoor arrangement method of estimation and system based on study prediction |
| US10055853B1 (en) * | 2017-08-07 | 2018-08-21 | Standard Cognition, Corp | Subject identification and tracking using image recognition |
| CN108550143A (en) * | 2018-04-03 | 2018-09-18 | 长安大学 | A kind of measurement method of the vehicle length, width and height size based on RGB-D cameras |
| CN108759667A (en) * | 2018-05-29 | 2018-11-06 | 福州大学 | Front truck distance measuring method based on monocular vision and image segmentation under vehicle-mounted camera |
| US20190103026A1 (en) * | 2017-09-29 | 2019-04-04 | Uber Technologies, Inc. | Image Processing for Vehicle Collision Avoidance System |
| WO2019097456A1 (en) * | 2017-11-17 | 2019-05-23 | C 3 Limited | Object measurement system |
-
2019
- 2019-06-13 CN CN201910509507.2A patent/CN110307791B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010214258A (en) * | 2009-03-13 | 2010-09-30 | Toyota Motor Corp | Masking jig |
| US20130128064A1 (en) * | 2011-04-08 | 2013-05-23 | Hailin Jin | Methods and Apparatus for Robust Video Stabilization |
| CN102410836A (en) * | 2011-07-26 | 2012-04-11 | 清华大学 | Space six-freedom degrees article locating system based on two-dimensional sensitive sensor |
| CN104200483A (en) * | 2014-06-16 | 2014-12-10 | 南京邮电大学 | Human body central line based target detection method under multi-camera environment |
| CN105573047A (en) * | 2014-10-10 | 2016-05-11 | 中芯国际集成电路制造(上海)有限公司 | System and method for detecting mask figure fidelity |
| CN105718870A (en) * | 2016-01-15 | 2016-06-29 | 武汉光庭科技有限公司 | Road marking line extracting method based on forward camera head in automatic driving |
| CN106408589A (en) * | 2016-07-14 | 2017-02-15 | 浙江零跑科技有限公司 | Vehicle-mounted overlooking camera based vehicle movement measurement method |
| CN107122792A (en) * | 2017-03-15 | 2017-09-01 | 山东大学 | Indoor arrangement method of estimation and system based on study prediction |
| US10055853B1 (en) * | 2017-08-07 | 2018-08-21 | Standard Cognition, Corp | Subject identification and tracking using image recognition |
| US20190103026A1 (en) * | 2017-09-29 | 2019-04-04 | Uber Technologies, Inc. | Image Processing for Vehicle Collision Avoidance System |
| WO2019097456A1 (en) * | 2017-11-17 | 2019-05-23 | C 3 Limited | Object measurement system |
| CN108550143A (en) * | 2018-04-03 | 2018-09-18 | 长安大学 | A kind of measurement method of the vehicle length, width and height size based on RGB-D cameras |
| CN108759667A (en) * | 2018-05-29 | 2018-11-06 | 福州大学 | Front truck distance measuring method based on monocular vision and image segmentation under vehicle-mounted camera |
Non-Patent Citations (3)
| Title |
|---|
| BENJAMIN COIFMAN等: "Speed estimation and length based vehicle classification from freeway single-loop detectors", 《TRANSPORTATION RESEARCH PART C》 * |
| 张利平等: "基于光流旳运动车辆检测和跟踪技术的研究", 《车辆与动力技术》 * |
| 赵俊梅等: "交通视频中运动车辆检测和跟踪技术的研究", 《车辆与动力技术》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909620A (en) * | 2019-10-30 | 2020-03-24 | 北京迈格威科技有限公司 | Vehicle detection method and device, electronic equipment and storage medium |
| CN113689713A (en) * | 2020-05-19 | 2021-11-23 | 昆山研达电脑科技有限公司 | Vehicle speed monitoring method based on automobile data recorder |
| WO2021237750A1 (en) * | 2020-05-29 | 2021-12-02 | Siemens Ltd., China | Method and apparatus for vehicle length estimation |
| CN112489106A (en) * | 2020-12-08 | 2021-03-12 | 深圳市哈工交通电子有限公司 | Video-based vehicle size measuring method and device, terminal and storage medium |
| CN112798811A (en) * | 2020-12-30 | 2021-05-14 | 杭州海康威视数字技术股份有限公司 | Speed measurement method, device and equipment |
| CN113011388A (en) * | 2021-04-23 | 2021-06-22 | 吉林大学 | Vehicle outer contour size detection method based on license plate and lane line |
| CN113011388B (en) * | 2021-04-23 | 2022-05-06 | 吉林大学 | Vehicle outer contour size detection method based on license plate and lane line |
| CN114863025A (en) * | 2022-05-18 | 2022-08-05 | 禾多科技（北京）有限公司 | Three-dimensional lane line generation method and device, electronic device and computer readable medium |
| CN114863025B (en) * | 2022-05-18 | 2023-03-10 | 禾多科技（北京）有限公司 | Three-dimensional lane line generation method and device, electronic device and computer readable medium |
| CN115019557A (en) * | 2022-06-09 | 2022-09-06 | 杭州电子科技大学 | TUIO protocol-based lane virtual boundary construction and boundary crossing detection method |
| CN115019557B (en) * | 2022-06-09 | 2024-05-14 | 杭州电子科技大学 | Lane virtual boundary construction and boundary crossing detection method based on TUIO protocol |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110307791B (en) | 2020-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110307791A (en) | Vehicle length and speed calculation method based on three-dimensional vehicle bounding box | |
| CN107705331B (en) | Vehicle video speed measurement method based on multi-viewpoint camera | |
| CN110567469B (en) | Visual positioning method and device, electronic equipment and system | |
| US6985619B1 (en) | Distance correcting apparatus of surroundings monitoring system and vanishing point correcting apparatus thereof | |
| CN107389026B (en) | A kind of monocular vision distance measuring method based on fixed point projective transformation | |
| CN105955259B (en) | The accurate positioning method of monocular vision AGV based on multiwindow real time distance | |
| CN105157608B (en) | A kind of detection method of overrun vehicle, apparatus and system | |
| CN107884767A (en) | A kind of method of binocular vision system measurement ship distance and height | |
| CN106156723B (en) | A kind of crossing fine positioning method of view-based access control model | |
| CN105551020B (en) | A kind of method and device detecting object size | |
| CN109409311A (en) | A kind of limit for height method for early warning based on binocular stereo vision | |
| CN109074490A (en) | Path detection method, related device and computer readable storage medium | |
| US10482615B2 (en) | Image processing device and image processing method | |
| CN112529966B (en) | On-line calibration method of vehicle-mounted looking-around system and vehicle-mounted looking-around system thereof | |
| CA2967872C (en) | Double stereoscopic sensor | |
| CN109410264A (en) | A kind of front vehicles distance measurement method based on laser point cloud and image co-registration | |
| CN200990147Y (en) | Intelligent video traffic monitoring system based on multi-view point | |
| CN105163065A (en) | Traffic speed detecting method based on camera front-end processing | |
| CN108180888A (en) | A kind of distance detection method based on rotating pick-up head | |
| CN110415299B (en) | Vehicle position estimation method based on set guideboard under motion constraint | |
| CN110097591A (en) | The detection method of bow net state | |
| CN107492123A (en) | A kind of road monitoring camera self-calibrating method using information of road surface | |
| CN110415298A (en) | A kind of calculation method for deviation | |
| JP6171849B2 (en) | Moving body position / posture angle estimation apparatus and moving body position / posture angle estimation method | |
| CN110220500A (en) | A kind of unmanned based on binocular camera uses distance measuring method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |