CN110542895A - monocular-based freespace distance measurement method - Google Patents
monocular-based freespace distance measurement method Download PDFInfo
- Publication number
- CN110542895A CN110542895A CN201810524658.0A CN201810524658A CN110542895A CN 110542895 A CN110542895 A CN 110542895A CN 201810524658 A CN201810524658 A CN 201810524658A CN 110542895 A CN110542895 A CN 110542895A
- Authority
- CN
- China
- Prior art keywords
- camera
- distance
- inverse perspective
- perspective projection
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S11/00—Systems for determining distance or velocity not using reflection or reradiation
- G01S11/12—Systems for determining distance or velocity not using reflection or reradiation using electromagnetic waves other than radio waves
Abstract
the utility model relates to a distance measurement technique and autopilot technical field provide a freespace range finding method based on monocular, include: calibrating a camera coordinate system, external parameters of the ground and internal parameters of the camera by a calibration plate which is placed in parallel on the ground right in front of the camera; carrying out inverse perspective transformation on an image which is shot by a camera and contains a calibration plate to obtain an inverse perspective projection image, and calculating the actual size K represented by a single pixel in the inverse perspective projection image; manually measuring the distance from the camera to a point actually represented by a point in the middle of the lower edge of the inverse perspective projection drawing to obtain a camera blind area distance M; and obtaining the distance L from the target point to the camera by the following monocular distance measuring formula: and L is M + k v, wherein v is the number of pixels of the target point from the lower edge of the inverse perspective projection image. The distance measuring method disclosed by the invention can overcome the defects of inaccurate measurement caused by height and angle problems in the prior art, and reduce the error of the measurement result. Meanwhile, the operation process can be simplified, the complex operation degree is reduced, the props are used strategically, and the freespace ranging effect is improved.
Description
Technical Field
The disclosure relates to the technical field of distance measurement and automatic driving, in particular to a monocular-based freespace distance measurement method.
Background
Freespace technology has become an integral part of the mainstream technology of automatic driving that is prevalent today. Freespace, the area where a car can travel, includes areas that avoid other cars, pedestrians, road edges. The technology not only uses an image recognition algorithm, but also relates to a geometric measurement algorithm in computer vision, namely, the distance of a target area under a camera coordinate system is obtained. Common means include monocular and binocular, wherein monocular distance measurement is simple and effective, does not need a large amount of calculation, and has low power consumption, and binocular distance measurement has the characteristics of complex structure and long matching time. In terms of the current vehicle condition, most low-end vehicles do not have a front-mounted ADAS (vehicle driving assistance) function, that is, a binocular ranging scheme with high maturity cannot be generally applied to the existing vehicles. The monocular-based freespace algorithm only needs one camera to acquire data, is easy to be embedded into vehicle-mounted equipment such as a vehicle data recorder and the like, has a wide application range, and becomes a research hotspot of technicians in the industry.
The existing monocular-based distance measurement method can estimate the distance of the target in the image area only by acquiring the installation height and angle information of the camera. Due to the height and angle information, manual measurement is needed, measurement errors are inevitably introduced, and the accuracy of the final measurement scheme is greatly influenced.
In addition, the existing technical method can cause the result error of monocular distance measurement to be too large to be applied due to the inaccuracy of height and angle measurement. And the operation is complicated and time-consuming.
Therefore, designing a new monocular-based ranging method is a technical problem to be solved urgently at present.
It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
It is an object of the present disclosure to provide a monocular-based freespace ranging method, thereby overcoming, at least to some extent, the problems caused by the limitations and disadvantages of the related art.
additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.
According to an example embodiment of the present disclosure, a monocular-based freespace ranging method is disclosed, which is characterized in that the method includes:
Calibrating a camera coordinate system, external parameters of the ground and internal parameters of the camera by a calibration plate which is placed in parallel on the ground right in front of the camera;
carrying out inverse perspective transformation on an image which is shot by a camera and contains a calibration plate to obtain an inverse perspective projection image, and calculating the actual size K represented by a single pixel in the inverse perspective projection image;
Measuring the distance from the camera to a point actually represented by a point in the middle of the lower edge of the inverse perspective projection drawing to obtain a camera blind area distance M; and
The distance L from the target point to the camera is obtained by the following monocular distance measuring formula:
L＝M+k*v，
And v is the number of pixels of the target point from the lower edge of the inverse perspective projection image.
According to an example embodiment of the present disclosure, the calibration is performed using a calibration toolkit of MATLAB.
According to an example embodiment of the present disclosure, wherein calculating the actual size K represented by a single pixel in the inverse perspective projection view comprises: the actual size K of the individual pixel representation is converted from the dimensions of the calibration plate.
According to an example embodiment of the present disclosure, the calibration plate has a rectangular upper surface, and the rectangle is divided into a plurality of uniformly distributed square lattices.
According to an example embodiment of the present disclosure, the plurality of uniformly distributed square lattices is a plurality of uniformly distributed square lattices which are alternate black and white.
according to an example embodiment of the present disclosure, wherein the calibration plate is a chessboard.
According to an example embodiment of the present disclosure, wherein the board is a chess board.
According to an example embodiment of the present disclosure, wherein calculating the actual size K represented by a single pixel in the inverse perspective projection view comprises: and dividing the side length of the checkerboard grid by the number of pixels corresponding to the side of the checkerboard grid to obtain K.
According to an example embodiment of the present disclosure, the method further comprises:
And converting the image recognition area of the actual freespace into the ground distance information of the freespace by utilizing a monocular distance measuring formula.
According to an example embodiment of the present disclosure, wherein measuring the distance from the camera to a point actually represented by a point in the middle of the lower edge of the inverse perspective projection view to obtain the camera blind zone distance M comprises: the distance of the camera to the point actually represented by the point in the middle of the lower edge of the inverse perspective projection view is manually measured to obtain the camera blind spot distance M.
According to some example embodiments of the present disclosure, the measurement inaccuracy caused by height and angle problems in the prior art can be overcome, and the error of the measurement result is reduced.
According to some example embodiments of this disclosure, can simplify the operation process, reduce the complex operation degree, promote the freespace range finding effect.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty.
FIG. 1 shows a flow diagram of a monocular based freespace ranging method according to an example embodiment of the present disclosure;
FIG. 2 shows an image taken by a camera containing a calibration plate;
FIG. 3 illustrates an inverse perspective transformation of the image shown in FIG. 2 to obtain an inverse perspective projection view;
Fig. 4 shows a flowchart of a monocular-based freespace ranging method according to another example embodiment of the present disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and the like. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
The disclosed monocular-based freespace distance measurement method comprises the following steps: calibrating a camera coordinate system, external parameters of the ground and internal parameters of the camera by a calibration plate which is placed in parallel on the ground right in front of the camera; carrying out inverse perspective transformation on an image which is shot by a camera and contains a calibration plate to obtain an inverse perspective projection image, and calculating the actual size K represented by a single pixel in the inverse perspective projection image; manually measuring the distance from the camera to a point actually represented by a point in the middle of the lower edge of the inverse perspective projection drawing to obtain a camera blind area distance M; and obtaining the distance L from the target point to the camera by the following monocular distance measuring formula: and L is M + k v, wherein v is the number of pixels of the target point from the lower edge of the inverse perspective projection image. The distance measuring method disclosed by the invention can overcome the defects of inaccurate measurement caused by height and angle problems in the prior art, and reduce the error of the measurement result. Meanwhile, the operation process can be simplified, the complex operation degree is reduced, the props are used strategically, and the freespace ranging effect is improved.
The monocular based freespace ranging method of the present disclosure is specifically described below with reference to fig. 1 to 4, where fig. 1 shows a flowchart of the monocular based freespace ranging method according to an example embodiment of the present disclosure; FIG. 2 shows an image taken by a camera containing a calibration plate; FIG. 3 illustrates an inverse perspective transformation of the image shown in FIG. 2 to obtain an inverse perspective projection view; fig. 4 shows a flowchart of a monocular-based freespace ranging method according to another example embodiment of the present disclosure.
fig. 1 shows a flowchart of a monocular-based freespace ranging method according to an example embodiment of the present disclosure.
At S101, a camera coordinate system, an external reference of the ground, and an internal reference of the camera are calibrated by a calibration plate placed in parallel on the ground directly in front of the camera.
The internal reference is divided into an internal reference matrix and a distortion parameter matrix, and because a camera coordinate system uses a millimeter unit and a pixel used by an image plane is a unit, the internal reference has the function of linearly changing between the two coordinate systems; the extrinsic parameters are a rotation matrix and a translation matrix, which together describe how to convert a point from the world coordinate system to the camera coordinate system. The calibration camera coordinate system is the mapping from the world coordinate to the pixel coordinate in a sentence, certainly the world coordinate is artificially defined, the calibration is that the world coordinate and the pixel coordinate of the known calibration control point are solved, once the mapping relation is solved, the world coordinate of the point can be reversely deduced from the pixel coordinate of the point, and certainly, other subsequent operations such as measurement and the like can be carried out by the world coordinate.
placing a checkerboard in parallel on the ground directly in front of the camera (or vehicle carrying the camera) requires: the ground is flat, the distance from the calibration plate to a camera coordinate system (or a vehicle body coordinate system) can be measured, and the checkerboard angular points in the image are clear and easy to extract. Can be placed with reference to fig. 2.
According to an example embodiment of the present disclosure, wherein the board is a chess board. But also go or Chinese chess board.
The present disclosure is not so limited and other calibration plates having a surface pattern resembling a checkerboard may be used.
according to an example embodiment of the present disclosure, the calibration plate has a rectangular upper surface, and the rectangle is divided into a plurality of uniformly distributed square lattices.
According to an example embodiment of the present disclosure, the plurality of uniformly distributed square lattices is a plurality of uniformly distributed square lattices which are alternate black and white.
according to an example embodiment of the present disclosure, the calibration is performed using a calibration toolkit of MATLAB.
In S102, an image including the calibration plate captured by the camera is subjected to inverse perspective transformation to obtain an inverse perspective projection image, and an actual size K represented by a single pixel in the inverse perspective projection image, that is, a side length of an actual square region represented by the single pixel, is calculated.
first, briefly describing the principle of inverse perspective transformation, formula (1) represents the coordinate transformation between an image pixel Q (u, v) and a spatial three-dimensional point Q (X, Y, Z), where w is a scale factor, and transition matrices P and T contain information such as camera internal reference and external reference. Q → Q can be calculated by equation (1).
the equation for calculating a two-dimensional space from three dimensions has a unique solution, however, if one point on an image is passed through, the situation of multiple solutions occurs when the three-dimensional space is calculated, that is, the real distance of the space point cannot be determined. Therefore, a plane is introduced, see formula (2), since the algorithm is applied to detect freespace on the ground, it is not assumed that the plane represents the ground,
∏:aX+bY+cZ+d＝0， (2)
The two formulas of (1) and (2) are combined to obtain (3),
Transferring d to the translation matrix yields (4),
Transforming the formula (4) by a term shift to obtain a formula (5), merging the formula (5) into a formula (6),
Exchanging the positions of the translation matrix and the spatial coordinates yields equation (7), i.e., from image pixel coordinates Q (X, Y) → spatial coordinates Q (X, Y, Z). On the basis of this principle, an inverse perspective projection of fig. 2 is obtained, as shown in fig. 3.
on the basis of the inverse perspective projection image, the real size (the real size of the calibration plate/the number of pixels corresponding to the calibration plate in the inverse perspective projection image) represented by each pixel in the inverse perspective projection image, namely the proportionality coefficient k, can be converted by combining the real distance of the real size of the calibration plate (the real size of the calibration plate is known or can be accurately measured by a simple method).
According to an example embodiment of the present disclosure, wherein calculating the actual size K represented by a single pixel in the inverse perspective projection view comprises: and dividing the side length of the checkerboard grid by the number of pixels corresponding to the side of the checkerboard grid to obtain K.
At S103, the distance of the camera to a point actually represented by a point in the middle of the lower edge of the inverse perspective projection view is measured to obtain a camera blind zone distance M.
According to an example embodiment of the present disclosure, wherein measuring the distance from the camera to a point actually represented by a point in the middle of the lower edge of the inverse perspective projection view to obtain the camera blind zone distance M comprises: the distance of the camera to the point actually represented by the point in the middle of the lower edge of the inverse perspective projection view is manually measured to obtain the camera blind spot distance M. Of course, other measurement methods may be used (e.g., laser ranging, etc., to further improve measurement accuracy).
At S104, by the monocular distance measuring formula: and obtaining the distance L from the target point to the camera by M + k v, wherein v is the number of pixels of the target point from the lower edge of the inverse perspective projection image.
specifically, the monocular distance measurement formula can be expressed as:
L＝M+k*v (8)
L represents the depth distance (unit: meter) of the target point in the camera coordinate system, M represents the blind area distance (unit: meter), k represents the proportionality coefficient (unit: meter/pix), and v represents the pixel number (unit: pix) of the target pixel from the lower boundary of the inverse perspective projection image.
Fig. 4 shows a flowchart of a monocular-based freespace ranging method according to another example embodiment of the present disclosure, where S401 to S404 are the same as S101 to S104, which are not described herein again, and only S405 is described below:
at S405, the image recognition area of the actual freespace is converted into ground distance information of the freespace using a monocular distance measuring formula.
Because the image identification area of the freespace is a two-dimensional curve on an image plane, each pixel point on the curve is brought into the formula (8), and the ground distance information of the freespace can be obtained.
one skilled in the art will readily appreciate from the foregoing detailed description that methods according to embodiments of the present disclosure have one or more of the following advantages.
According to some example embodiments of the present disclosure, the measurement inaccuracy caused by height and angle problems in the prior art can be overcome, and the error of the measurement result is reduced.
according to some example embodiments of this disclosure, can simplify the operation process, reduce the complex operation degree, promote the freespace range finding effect.
other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
Claims (10)
1. A monocular-based freespace distance measurement method is characterized by comprising the following steps:
Calibrating a camera coordinate system, external parameters of the ground and internal parameters of the camera by a calibration plate which is placed in parallel on the ground right in front of the camera;
Carrying out inverse perspective transformation on an image which is shot by a camera and contains a calibration plate to obtain an inverse perspective projection image, and calculating the actual size K represented by a single pixel in the inverse perspective projection image;
Measuring the distance from the camera to a point actually represented by a point in the middle of the lower edge of the inverse perspective projection drawing to obtain a camera blind area distance M; and
The distance L from the target point to the camera is obtained by the following monocular distance measuring formula:
L＝M+k*v，
And v is the number of pixels of the target point from the lower edge of the inverse perspective projection image.
2. The method of claim 1, wherein the calibration is performed using a calibration kit of MATLAB.
3. The method of claim 1, wherein calculating the actual size K represented by a single pixel in the inverse perspective projection view comprises: the actual size K of the individual pixel representation is converted from the dimensions of the calibration plate.
4. The method of claim 1, wherein the calibration plate has a rectangular upper surface, said rectangle being divided into a plurality of uniformly distributed square lattices.
5. The method of claim 4, wherein the plurality of evenly distributed square lattices are a plurality of evenly distributed black and white square lattices.
6. the method of claim 1, wherein the calibration plate is a checkerboard.
7. The method of claim 6, wherein the board is a chess board.
8. The method of claim 6, wherein calculating the actual size K represented by a single pixel in the inverse perspective projection view comprises: and dividing the side length of the checkerboard grid by the number of pixels corresponding to the side of the checkerboard grid to obtain K.
9. The method of claim 1, further comprising:
And converting the image recognition area of the actual freespace into the ground distance information of the freespace by utilizing a monocular distance measuring formula.
10. The method of claim 1, wherein measuring the distance from the camera to a point actually represented by a point in the middle of the lower edge of the inverse perspective projection view to obtain a camera blind spot distance M comprises: the distance of the camera to the point actually represented by the point in the middle of the lower edge of the inverse perspective projection view is manually measured to obtain the camera blind spot distance M.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810524658.0A CN110542895A (en) | 2018-05-28 | 2018-05-28 | monocular-based freespace distance measurement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810524658.0A CN110542895A (en) | 2018-05-28 | 2018-05-28 | monocular-based freespace distance measurement method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110542895A true CN110542895A (en) | 2019-12-06 |
Family
ID=68701107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810524658.0A Pending CN110542895A (en) | 2018-05-28 | 2018-05-28 | monocular-based freespace distance measurement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110542895A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023273108A1 (en) * | 2021-06-30 | 2023-01-05 | 深圳市优必选科技股份有限公司 | Monocular distance measurement method and apparatus, and intelligent apparatus |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504364A (en) * | 2014-11-23 | 2015-04-08 | 北京联合大学 | Real-time stop line recognition and distance measurement method based on temporal-spatial correlation |
| CN106156723A (en) * | 2016-05-23 | 2016-11-23 | 北京联合大学 | A kind of crossing fine positioning method of view-based access control model |
| US20170287112A1 (en) * | 2016-03-31 | 2017-10-05 | Sony Computer Entertainment Inc. | Selective peripheral vision filtering in a foveated rendering system |
| CN107389026A (en) * | 2017-06-12 | 2017-11-24 | 江苏大学 | A kind of monocular vision distance-finding method based on fixing point projective transformation |
-
2018
- 2018-05-28 CN CN201810524658.0A patent/CN110542895A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504364A (en) * | 2014-11-23 | 2015-04-08 | 北京联合大学 | Real-time stop line recognition and distance measurement method based on temporal-spatial correlation |
| US20170287112A1 (en) * | 2016-03-31 | 2017-10-05 | Sony Computer Entertainment Inc. | Selective peripheral vision filtering in a foveated rendering system |
| CN106156723A (en) * | 2016-05-23 | 2016-11-23 | 北京联合大学 | A kind of crossing fine positioning method of view-based access control model |
| CN107389026A (en) * | 2017-06-12 | 2017-11-24 | 江苏大学 | A kind of monocular vision distance-finding method based on fixing point projective transformation |
Non-Patent Citations (1)
| Title |
|---|
| 叶美松: "单目视觉的智能电动小车车道线识别与跟踪", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023273108A1 (en) * | 2021-06-30 | 2023-01-05 | 深圳市优必选科技股份有限公司 | Monocular distance measurement method and apparatus, and intelligent apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109767473B (en) | Panoramic parking device calibration method and device | |
| CN103927754B (en) | A kind of scaling method of vehicle-mounted vidicon | |
| CN112270713A (en) | Calibration method and device, storage medium and electronic device | |
| CN110031829B (en) | Target accurate distance measurement method based on monocular vision | |
| CN109902637A (en) | Method for detecting lane lines, device, computer equipment and storage medium | |
| CN104143192A (en) | Calibration method and device of lane departure early warning system | |
| CN106780590A (en) | The acquisition methods and system of a kind of depth map | |
| US20230215187A1 (en) | Target detection method based on monocular image | |
| CN102609941A (en) | Three-dimensional registering method based on ToF (Time-of-Flight) depth camera | |
| CN110555407B (en) | Pavement vehicle space identification method and electronic equipment | |
| CN111815713A (en) | Method and system for automatically calibrating external parameters of camera | |
| CN104021588A (en) | System and method for recovering three-dimensional true vehicle model in real time | |
| CN103278138A (en) | Method for measuring three-dimensional position and posture of thin component with complex structure | |
| CN111508027A (en) | Method and device for calibrating external parameters of camera | |
| CN112365545B (en) | Calibration method of laser radar and visible light camera based on large-plane composite target | |
| CN103852060A (en) | Visible light image distance measuring method based on monocular vision | |
| CN115079143B (en) | Multi-radar external parameter quick calibration method and device for double-bridge steering mine card | |
| CN113989766A (en) | Road edge detection method and road edge detection equipment applied to vehicle | |
| CN111382591B (en) | Binocular camera ranging correction method and vehicle-mounted equipment | |
| CN114119682A (en) | Laser point cloud and image registration method and registration system | |
| CN110542895A (en) | monocular-based freespace distance measurement method | |
| CN111380503B (en) | Monocular camera ranging method adopting laser-assisted calibration | |
| CN113034583A (en) | Vehicle parking distance measuring method and device based on deep learning and electronic equipment | |
| CN110543612B (en) | Card collection positioning method based on monocular vision measurement | |
| CN111627067B (en) | Calibration method of binocular camera and vehicle-mounted equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191206 |