CN111754574A - Distance testing method, device and system based on binocular camera and storage medium - Google Patents
Distance testing method, device and system based on binocular camera and storage medium Download PDFInfo
- Publication number
- CN111754574A CN111754574A CN202010466128.2A CN202010466128A CN111754574A CN 111754574 A CN111754574 A CN 111754574A CN 202010466128 A CN202010466128 A CN 202010466128A CN 111754574 A CN111754574 A CN 111754574A
- Authority
- CN
- China
- Prior art keywords
- target
- binocular
- distance measurement
- monocular
- measured
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Measurement Of Optical Distance (AREA)
Abstract
The invention discloses a distance testing method, a device, a system and a storage medium based on a binocular camera, wherein the method comprises the steps of firstly, acquiring a blind area position of the binocular camera in a preset image range, adopting monocular distance measurement to a target to be measured when the target to be measured is judged to be in the blind area position, and outputting a distance measurement result obtained by the monocular distance measurement; and when the target to be measured is judged not to be in the blind area position, the monocular distance measurement and the binocular distance measurement are adopted to respectively measure the distance of the target to be measured, and after the weight calculation is carried out on the obtained monocular distance measurement result and the obtained binocular distance measurement result, a comprehensive distance measurement result is obtained and output. The method integrates the advantages of a binocular parallax distance measurement principle and a monocular distance measurement principle, and improves the distance measurement precision by combining monocular and binocular distance measurement, so that the technical problem that the distance measurement precision is low due to the fact that a traditional binocular camera is limited by a blind area during obstacle distance measurement is solved.
Description
Technical Field
The invention relates to the technical field of binocular camera imaging, in particular to a distance testing method, device and system based on a binocular camera and a storage medium.
Background
With the development of sensor technology and machine vision technology, barrier testing technology based on a binocular camera is increasingly widely applied to the fields of robots, intelligent automobiles and the like. However, in the prior art, target distance detection is performed by analyzing binocular parallax, and the target distance detection is easily limited by environments, binocular matching blind areas and the like, and has the defects of low distance measurement precision, incapability of measuring distance of the blind areas, poor robustness and the like.
Disclosure of Invention
Therefore, the embodiment of the invention provides a distance testing method, a distance testing device, a distance testing system and a storage medium based on a binocular camera, so as to at least partially solve the technical problem that the traditional binocular camera is limited by a blind area during obstacle distance detection and is low in distance measurement accuracy.
In order to achieve the above object, the embodiments of the present invention provide the following technical solutions:
a binocular camera-based distance testing method is characterized by comprising the following steps:
acquiring the position of a blind area of a binocular camera within a preset image range;
if the target to be measured is judged to be in the blind area position, the monocular distance measurement is carried out on the target to be measured, and a distance measurement result obtained by the monocular distance measurement is output;
and if the target to be measured is not in the blind area position, the monocular and binocular distance measurement is adopted to respectively measure the distance of the target to be measured, and after the weight calculation is carried out on the obtained monocular distance measurement result and the obtained binocular distance measurement result, a comprehensive distance measurement result is obtained and output.
Further, the method further comprises:
acquiring a binocular image of a target to be detected, extracting position information of the target to be detected in the binocular image, and marking the position information through a feature extraction frame;
obtaining the effective parallax proportion of the target to be detected in the range of the feature extraction frame;
judging that the effective parallax ratio is lower than a set threshold value and the target to be measured is in a blind area position, measuring the distance of the target to be measured by adopting monocular vision, and outputting a distance measurement result obtained by monocular distance measurement;
and if the effective parallax ratio is judged to be higher than the set threshold value and the target to be measured is not positioned in the blind area position, the monocular and binocular distance measurement is adopted to respectively measure the distance of the target to be measured, and after the weight calculation is carried out on the obtained monocular distance measurement result and the obtained binocular distance measurement result, a comprehensive distance measurement result is obtained and output.
Further, the acquiring of the binocular image of the target to be detected, the extracting of the position information of the target to be detected in the binocular image, and the labeling of the position information through the feature extraction frame specifically include:
acquiring a left eye image and a right eye image of the same frame of image containing the target to be detected, and acquiring a disparity map;
extracting the position information of the target to be detected in the disparity map through machine learning or feature detection;
and selecting the position information by using a rectangular frame.
Further, the integrated ranging result is obtained by the formula Dz ═ w × dist1+ (1-w) × dist 2;
wherein w is a weight, w is a parameter positively correlated with the effective parallax ratio, dist1 is a binocular ranging result, and dist2 is a monocular ranging result.
Further, the functional relationship of the weight to the effective disparity ratio comprises:
wherein η is the effective parallax ratio, ηmaxIs the maximum value of the set threshold.
Further, acquiring the blind area position of the binocular camera within the preset image range specifically includes:
acquiring internal and external parameters and an angle of view of a binocular camera;
and acquiring the blind area position according to the internal and external parameters and the field angle.
The invention also provides a binocular camera-based distance testing device for implementing the method, the device comprising:
the blind area acquisition unit is used for acquiring the position of a blind area of the binocular camera within a preset image range;
the first ranging result output unit is used for ranging the target to be measured by adopting a monocular mode and outputting a ranging result obtained by monocular ranging when the target to be measured is judged to be in the blind area position;
and the second ranging result output unit is used for respectively ranging the target to be measured by adopting monocular and binocular when judging that the target to be measured is not positioned in the blind area position, and obtaining and outputting a comprehensive ranging result after performing weight calculation on the obtained monocular ranging result and the obtained binocular ranging result.
Further, the apparatus further comprises:
the position acquisition unit is used for acquiring a binocular image of a target to be detected, extracting position information of the target to be detected in the binocular image and marking the position information through a feature extraction frame;
the parallax ratio acquisition unit is used for acquiring the effective parallax ratio of the target to be detected in the range of the feature extraction frame;
the first ranging result output unit is further configured to, when it is determined that the effective parallax ratio is lower than a set threshold and the target to be measured is located in the blind area, perform monocular ranging on the target to be measured, and output a ranging result obtained by monocular ranging;
and the second ranging result output unit is also used for judging that the effective parallax ratio is higher than a set threshold value and the target to be measured is not positioned in the blind area, respectively ranging the target to be measured by adopting monocular and binocular pairs, and obtaining and outputting a comprehensive ranging result after carrying out weight calculation on the obtained monocular ranging result and the obtained binocular ranging result.
The invention also provides a distance testing system based on the binocular camera, which comprises: a processor and a memory;
the memory is to store one or more program instructions;
the processor is configured to execute one or more program instructions to perform the method as described above.
The present invention also provides a computer storage medium having one or more program instructions embodied therein for executing the method as described above by a binocular camera based distance testing system.
The invention provides a distance testing method, a device, a system and a storage medium based on a binocular camera, wherein the method comprises the steps of firstly obtaining the blind area position of the binocular camera in a preset image range, adopting monocular distance measurement to a target to be measured when the target to be measured is judged to be in the blind area position, and outputting the distance measurement result obtained by the monocular distance measurement; and when the target to be measured is judged not to be in the blind area position, the monocular distance measurement and the binocular distance measurement are adopted to respectively measure the distance of the target to be measured, and after the weight calculation is carried out on the obtained monocular distance measurement result and the obtained binocular distance measurement result, a comprehensive distance measurement result is obtained and output. The method solves the problem that target distance detection is carried out through binocular parallax only and is easily limited by environments, binocular matching blind areas and the like, integrates the advantages of a binocular parallax distance measurement principle and a monocular distance measurement principle, improves distance measurement accuracy by combining monocular and binocular distance measurement, and solves the technical problem that the traditional binocular camera is limited by the blind areas during obstacle distance detection and is low in distance measurement accuracy.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
The structures, ratios, sizes, and the like shown in the present specification are only used for matching with the contents disclosed in the specification, so as to be understood and read by those skilled in the art, and are not used to limit the conditions that the present invention can be implemented, so that the present invention has no technical significance, and any structural modifications, changes in the ratio relationship, or adjustments of the sizes, without affecting the effects and the achievable by the present invention, should still fall within the range that the technical contents disclosed in the present invention can cover.
FIG. 1 is a flow chart of one embodiment of a distance testing method provided by the present invention;
FIG. 2 is a binocular range finding schematic diagram of a binocular stereo camera;
FIG. 3 is a schematic diagram of a ranging blind area based on the binocular ranging of FIG. 2;
FIG. 4 is a schematic diagram of monocular distance measurement of a binocular stereo camera;
FIG. 5 is a flowchart illustrating an implementation of the distance testing method shown in FIG. 1 in a real-time scenario;
FIG. 6 is a block diagram of a distance measuring device according to an embodiment of the present invention;
FIG. 7 is a block diagram of a distance testing system according to an embodiment of the present invention.
Description of reference numerals:
100-blind area acquisition unit 200-first ranging result output unit
300-second ranging result output unit 400-position acquisition unit 500-parallax ratio acquisition unit
Detailed Description
The present invention is described in terms of particular embodiments, other advantages and features of the invention will become apparent to those skilled in the art from the following disclosure, and it is to be understood that the described embodiments are merely exemplary of the invention and that it is not intended to limit the invention to the particular embodiments disclosed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
According to the distance testing method based on the binocular camera, the blind spot problem existing in binocular distance measurement is avoided by using a method of combining the monocular camera and the binocular camera for testing, and therefore the problem that the traditional binocular camera is limited by the blind spot in obstacle distance detection and is low in distance measurement accuracy is solved. In one embodiment, as shown in FIG. 1, the method comprises:
s1: acquiring the position of a blind area of a binocular camera within a preset image range; the blind area position acquisition specifically comprises the steps of acquiring internal and external parameters and a field angle of a binocular camera, and acquiring the blind area position according to the internal and external parameters and the field angle.
In practical operation, according to the principle of binocular distance measurement as shown in fig. 2, the following formula can be obtained from the triangular geometric relationship in fig. 2:
where f denotes the focal length of the camera, B denotes the distance between the centers of the two cameras, and D is Xleft-XrightThen, the z-direction distance can be obtained as:
therefore, the distance can be calculated only by finding a certain point in the space and imaging positions of the point in the left camera and the right camera at the same time in binocular ranging, and if the point can only appear on the imaging surface of one camera, the corresponding parallax cannot be obtained, and distance information cannot be obtained, so that a ranging blind area as shown in fig. 3 is formed.
S2: and when the target to be measured is judged to be in the blind area position, the distance of the target to be measured is measured by adopting the monocular pair, and the distance measurement result obtained by the monocular distance measurement is output, namely, when the target to be measured is judged to just go out of the blind point area of the camera, the binocular measurement cannot be detected, at the moment, the left eye camera or the right eye camera is required to be used for measurement, and the relatively accurate distance measurement result is output through the monocular pair.
As shown in fig. 4, parameter information of the target to be measured at the blind area position may be obtained by a monocular distance measuring method according to a principle of monocular distance measurement, where in fig. 4, θ e represents an included angle between a camera main optical axis and a horizontal ground, OE represents a camera main optical axis, OB represents a straight line where an intersection point of the target to be measured and the ground and a camera optical center are located, f represents a camera focal length, Hcam represents an installation height of the camera from the ground, and θ b represents an included angle between the OB straight line and the OE straight line. In general, the point V projected by OZ onto the imaging plane is called the vanishing point, which can be obtained by calibrating the camera pose. In an image coordinate system, ye represents the y-direction coordinate of the vanishing point, y0 represents the y-direction coordinate of the optical center point, the parameter can be obtained by calibrating camera internal parameters, and yb represents the y-direction coordinate of the intersection point B of the target to be measured and the ground.
Obtaining the Z-direction distance of the target to be measured through the geometrical relationship as follows:
s3: and when the target to be detected is judged not to be in the blind area position, respectively collecting binocular and monocular data, and carrying out weight calculation on the obtained data to output a more accurate final result.
Specifically, in a specific embodiment, as shown in fig. 5, the implementation process of the method includes:
acquiring a left eye image and a right eye image of the same frame of image containing the target to be detected, and acquiring a disparity map;
extracting the position information of the target to be detected in the disparity map through machine learning or feature detection;
selecting the position information by using a rectangular frame;
obtaining the effective parallax proportion of the target to be detected in the range of the feature extraction frame;
judging that the effective parallax ratio is lower than a set threshold value and the target to be measured is in a blind area position, measuring the distance of the target to be measured by adopting monocular vision, and outputting a distance measurement result obtained by monocular distance measurement;
and if the effective parallax ratio is judged to be higher than the set threshold value and the target to be measured is not positioned in the blind area position, the monocular and binocular distance measurement is adopted to respectively measure the distance of the target to be measured, and after the weight calculation is carried out on the obtained monocular distance measurement result and the obtained binocular distance measurement result, a comprehensive distance measurement result is obtained and output.
The comprehensive ranging result is obtained through a formula Dz w dist1+ (1-w) dist 2;
wherein w is a weight, w is a parameter positively correlated with the effective parallax ratio, dist1 is a binocular ranging result, and dist2 is a monocular ranging result.
Further, the functional relationship of the weight to the effective disparity ratio comprises:
wherein η is the effective parallax ratio, ηmaxIs the maximum value of the set threshold.
In the above embodiment, the distance testing method based on the binocular camera provided by the invention first obtains the blind area position of the binocular camera within the preset image range, and when the target to be tested is judged to be in the blind area position, the monocular distance measurement is adopted to measure the distance of the target to be tested, and the distance measurement result obtained by the monocular distance measurement is output; and when the target to be measured is judged not to be in the blind area position, the monocular distance measurement and the binocular distance measurement are adopted to respectively measure the distance of the target to be measured, and after the weight calculation is carried out on the obtained monocular distance measurement result and the obtained binocular distance measurement result, a comprehensive distance measurement result is obtained and output. The method solves the problem that target distance detection is carried out through binocular parallax only and is easily limited by environments, binocular matching blind areas and the like, integrates the advantages of a binocular parallax distance measurement principle and a monocular distance measurement principle, improves distance measurement accuracy by combining monocular and binocular distance measurement, and solves the technical problem that the traditional binocular camera is limited by the blind areas during obstacle distance detection and is low in distance measurement accuracy.
In addition to the above distance measuring method, the present invention also provides a distance measuring device based on a binocular camera for implementing the method as described above, and in a specific embodiment, as shown in fig. 6, the device includes:
a blind area obtaining unit 100, configured to obtain a blind area position of the binocular camera within a preset image range; the blind area position acquisition specifically comprises the steps of acquiring internal and external parameters and a field angle of a binocular camera, and acquiring the blind area position according to the internal and external parameters and the field angle.
First range finding result output unit 200 for when judging that the target that awaits measuring is in the blind area position, then adopt the monocular right the target that awaits measuring range to the range finding result that the range finding of output monocular range finding obtained, that is to say, when judging that the target that awaits measuring just goes out in the blind spot region of camera, binocular measurement can't detect, need adopt left eye camera or right eye camera measurement this moment, through the comparatively accurate range finding result of monocular output.
And a second ranging result output unit 300, configured to determine that the target to be measured is not located in the blind area position, respectively range the target to be measured using monocular and binocular pairs, and perform weight calculation on the obtained monocular ranging result and the obtained binocular ranging result to obtain and output a comprehensive ranging result, that is, when it is determined that the target to be measured is not located in the blind area position, respectively collect data of the binocular and the monocular, and perform weight calculation on the obtained data to output a relatively accurate final result.
In order to obtain an accurate blind spot position, the apparatus further includes:
the position acquisition unit 400 is used for acquiring a binocular image of a target to be detected, extracting position information of the target to be detected in the binocular image, and marking the position information through a feature extraction frame;
a parallax ratio obtaining unit 500, configured to obtain an effective parallax ratio of the target to be detected within the range of the feature extraction frame;
at this time, the first ranging result output unit is further configured to determine that the effective parallax ratio is lower than a set threshold and the target to be measured is located in the blind area, perform monocular ranging on the target to be measured, and output a ranging result obtained by monocular ranging;
and the second ranging result output unit is also used for judging that the effective parallax ratio is higher than a set threshold value and the target to be measured is not positioned in the blind area, respectively ranging the target to be measured by adopting monocular and binocular pairs, and obtaining and outputting a comprehensive ranging result after carrying out weight calculation on the obtained monocular ranging result and the obtained binocular ranging result.
In the above embodiment, the distance testing device based on the binocular camera provided by the invention first obtains the blind area position of the binocular camera within the preset image range, and when the target to be tested is judged to be in the blind area position, the monocular distance measurement is performed on the target to be tested, and the distance measurement result obtained by the monocular distance measurement is output; and when the target to be measured is judged not to be in the blind area position, the monocular distance measurement and the binocular distance measurement are adopted to respectively measure the distance of the target to be measured, and after the weight calculation is carried out on the obtained monocular distance measurement result and the obtained binocular distance measurement result, a comprehensive distance measurement result is obtained and output. The method solves the problem that target distance detection is carried out through binocular parallax only and is easily limited by environments, binocular matching blind areas and the like, integrates the advantages of a binocular parallax distance measurement principle and a monocular distance measurement principle, improves distance measurement accuracy by combining monocular and binocular distance measurement, and solves the technical problem that the traditional binocular camera is limited by the blind areas during obstacle distance detection and is low in distance measurement accuracy.
According to a third aspect of the embodiments of the present invention, the present invention further provides a distance testing system based on a binocular camera, as shown in fig. 7, the system including: a processor 201 and a memory 202;
the memory is to store one or more program instructions;
the processor is configured to execute one or more program instructions to perform the method as described above.
In correspondence with the above embodiments, embodiments of the present invention also provide a computer storage medium containing one or more program instructions therein. Wherein the one or more program instructions are for executing the method as described above by a distance testing system.
In an embodiment of the invention, the processor may be an integrated circuit chip having signal processing capability. The Processor may be a general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete Gate or transistor logic device, discrete hardware component.
The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The processor reads the information in the storage medium and completes the steps of the method in combination with the hardware.
The storage medium may be a memory, for example, which may be volatile memory or nonvolatile memory, or which may include both volatile and nonvolatile memory.
The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory.
The volatile Memory may be a Random Access Memory (RAM) which serves as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), SLDRAM (SLDRAM), and Direct Rambus RAM (DRRAM).
The storage media described in connection with the embodiments of the invention are intended to comprise, without being limited to, these and any other suitable types of memory.
Those skilled in the art will appreciate that the functionality described in the present invention may be implemented in a combination of hardware and software in one or more of the examples described above. When software is applied, the corresponding functionality may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
The above embodiments are only for illustrating the embodiments of the present invention and are not to be construed as limiting the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made on the basis of the embodiments of the present invention shall be included in the scope of the present invention.
Claims (10)
1. A binocular camera-based distance testing method is characterized by comprising the following steps:
acquiring the position of a blind area of a binocular camera within a preset image range;
if the target to be measured is judged to be in the blind area position, the monocular distance measurement is carried out on the target to be measured, and a distance measurement result obtained by the monocular distance measurement is output;
and if the target to be measured is not in the blind area position, the monocular and binocular distance measurement is adopted to respectively measure the distance of the target to be measured, and after the weight calculation is carried out on the obtained monocular distance measurement result and the obtained binocular distance measurement result, a comprehensive distance measurement result is obtained and output.
2. The distance testing method according to claim 1, characterized in that the method further comprises:
acquiring a binocular image of a target to be detected, extracting position information of the target to be detected in the binocular image, and marking the position information through a feature extraction frame;
obtaining the effective parallax proportion of the target to be detected in the range of the feature extraction frame;
judging that the effective parallax ratio is lower than a set threshold value and the target to be measured is in a blind area position, measuring the distance of the target to be measured by adopting monocular vision, and outputting a distance measurement result obtained by monocular distance measurement;
and if the effective parallax ratio is judged to be higher than the set threshold value and the target to be measured is not positioned in the blind area position, the monocular and binocular distance measurement is adopted to respectively measure the distance of the target to be measured, and after the weight calculation is carried out on the obtained monocular distance measurement result and the obtained binocular distance measurement result, a comprehensive distance measurement result is obtained and output.
3. The distance testing method according to claim 2, wherein the acquiring of the binocular image of the target to be tested, the extracting of the position information of the target to be tested in the binocular image, and the labeling of the position information through the feature extraction frame specifically include:
acquiring a left eye image and a right eye image of the same frame of image containing the target to be detected, and acquiring a disparity map;
extracting the position information of the target to be detected in the disparity map through machine learning or feature detection;
and selecting the position information by using a rectangular frame.
4. The distance testing method according to claim 3, wherein said integrated ranging result is obtained by the formula Dz w dist1+ (1-w) dist 2;
wherein w is a weight, w is a parameter positively correlated with the effective parallax ratio, dist1 is a binocular ranging result, and dist2 is a monocular ranging result.
5. The distance testing method of claim 4, wherein the functional relationship of the weight to the effective disparity ratio comprises:
wherein η is the effective parallax ratio, ηmaxIs the maximum value of the set threshold.
6. The distance testing method according to any one of claims 1 to 5, wherein the acquiring of the blind area position of the binocular camera within the preset image range specifically comprises:
acquiring internal and external parameters and an angle of view of a binocular camera;
and acquiring the blind area position according to the internal and external parameters and the field angle.
7. A binocular camera based distance testing apparatus for implementing the method of claims 1-6, the apparatus comprising:
the blind area acquisition unit is used for acquiring the position of a blind area of the binocular camera within a preset image range;
the first ranging result output unit is used for ranging the target to be measured by adopting a monocular mode and outputting a ranging result obtained by monocular ranging when the target to be measured is judged to be in the blind area position;
and the second ranging result output unit is used for respectively ranging the target to be measured by adopting monocular and binocular when judging that the target to be measured is not positioned in the blind area position, and obtaining and outputting a comprehensive ranging result after performing weight calculation on the obtained monocular ranging result and the obtained binocular ranging result.
8. The distance test device of claim 7, wherein the device further comprises:
the position acquisition unit is used for acquiring a binocular image of a target to be detected, extracting position information of the target to be detected in the binocular image and marking the position information through a feature extraction frame;
the parallax ratio acquisition unit is used for acquiring the effective parallax ratio of the target to be detected in the range of the feature extraction frame;
the first ranging result output unit is further configured to, when it is determined that the effective parallax ratio is lower than a set threshold and the target to be measured is located in the blind area, perform monocular ranging on the target to be measured, and output a ranging result obtained by monocular ranging;
and the second ranging result output unit is also used for judging that the effective parallax ratio is higher than a set threshold value and the target to be measured is not positioned in the blind area, respectively ranging the target to be measured by adopting monocular and binocular pairs, and obtaining and outputting a comprehensive ranging result after carrying out weight calculation on the obtained monocular ranging result and the obtained binocular ranging result.
9. A binocular camera based distance testing system, the system comprising: a processor and a memory;
the memory is to store one or more program instructions;
the processor, configured to execute one or more program instructions to perform the method of any of claims 1-6.
10. A computer storage medium containing one or more program instructions for performing the method of any of claims 1-6 by a binocular camera based distance testing system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010466128.2A CN111754574A (en) | 2020-05-28 | 2020-05-28 | Distance testing method, device and system based on binocular camera and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010466128.2A CN111754574A (en) | 2020-05-28 | 2020-05-28 | Distance testing method, device and system based on binocular camera and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111754574A true CN111754574A (en) | 2020-10-09 |
Family
ID=72673643
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010466128.2A Pending CN111754574A (en) | 2020-05-28 | 2020-05-28 | Distance testing method, device and system based on binocular camera and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111754574A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113959398A (en) * | 2021-10-09 | 2022-01-21 | 广东汇天航空航天科技有限公司 | Vision-based distance measurement method and device, travelable equipment and storage medium |
| CN114463388A (en) * | 2022-04-13 | 2022-05-10 | 北京中科慧眼科技有限公司 | Binocular camera-based height limiting device detection method and system and intelligent terminal |
| CN117372494A (en) * | 2023-08-07 | 2024-01-09 | 合肥工业大学 | Power grid operator parallax estimation and positioning method based on single-binocular vision cooperation |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102298818A (en) * | 2011-08-18 | 2011-12-28 | 中国科学技术大学 | Binocular shooting fire detecting and positioning device and fire positioning method thereof |
| US20150279022A1 (en) * | 2014-03-31 | 2015-10-01 | Empire Technology Development Llc | Visualization of Spatial and Other Relationships |
| CN110926408A (en) * | 2019-12-04 | 2020-03-27 | 北京中科慧眼科技有限公司 | Short-distance measuring method, device and system based on characteristic object and storage medium |
-
2020
- 2020-05-28 CN CN202010466128.2A patent/CN111754574A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102298818A (en) * | 2011-08-18 | 2011-12-28 | 中国科学技术大学 | Binocular shooting fire detecting and positioning device and fire positioning method thereof |
| US20150279022A1 (en) * | 2014-03-31 | 2015-10-01 | Empire Technology Development Llc | Visualization of Spatial and Other Relationships |
| CN110926408A (en) * | 2019-12-04 | 2020-03-27 | 北京中科慧眼科技有限公司 | Short-distance measuring method, device and system based on characteristic object and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 曹文君 等: "一种单双目结合的全景避障测距方法", 现代电子技术, vol. 40, no. 5, pages 38 - 41 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113959398A (en) * | 2021-10-09 | 2022-01-21 | 广东汇天航空航天科技有限公司 | Vision-based distance measurement method and device, travelable equipment and storage medium |
| CN113959398B (en) * | 2021-10-09 | 2024-04-12 | 广东汇天航空航天科技有限公司 | Distance measurement method and device based on vision, drivable equipment and storage medium |
| CN114463388A (en) * | 2022-04-13 | 2022-05-10 | 北京中科慧眼科技有限公司 | Binocular camera-based height limiting device detection method and system and intelligent terminal |
| CN117372494A (en) * | 2023-08-07 | 2024-01-09 | 合肥工业大学 | Power grid operator parallax estimation and positioning method based on single-binocular vision cooperation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111754574A (en) | Distance testing method, device and system based on binocular camera and storage medium | |
| US10909395B2 (en) | Object detection apparatus | |
| CN111179356A (en) | Binocular camera calibration method, device and system based on Aruco code and calibration board | |
| CN113792707A (en) | Terrain environment detection method and system based on binocular stereo camera and intelligent terminal | |
| WO2022183685A1 (en) | Target detection method, electronic medium and computer storage medium | |
| JP6515650B2 (en) | Calibration apparatus, distance measuring apparatus and calibration method | |
| CN110779491A (en) | Method, device and equipment for measuring distance of target on horizontal plane and storage medium | |
| US20220277470A1 (en) | Method and system for detecting long-distance target through binocular camera, and intelligent terminal | |
| CN114509045A (en) | Wheel area elevation detection method and system | |
| CN110926408A (en) | Short-distance measuring method, device and system based on characteristic object and storage medium | |
| CN111105465B (en) | Camera device calibration method, device, system electronic equipment and storage medium | |
| CN113240632A (en) | Road surface detection method and system based on semantic segmentation network and intelligent terminal | |
| CN110969666B (en) | Binocular camera depth calibration method, device, system and storage medium | |
| CN113140002B (en) | Road condition detection method and system based on binocular stereo camera and intelligent terminal | |
| CN114495043B (en) | Method and system for detecting up-and-down slope road conditions based on binocular vision system and intelligent terminal | |
| CN113965742B (en) | Dense disparity map extraction method and system based on multi-sensor fusion and intelligent terminal | |
| CN112465831A (en) | Curve scene perception method, system and device based on binocular stereo camera | |
| CN115100621A (en) | Ground scene detection method and system based on deep learning network | |
| CN111382591A (en) | Binocular camera ranging correction method and vehicle-mounted equipment | |
| CN112364793A (en) | Target detection and fusion method based on long-focus and short-focus multi-camera vehicle environment | |
| CN115205809B (en) | Method and system for detecting roughness of road surface | |
| CN112767498A (en) | Camera calibration method and device and electronic equipment | |
| US20230037072A1 (en) | Method and system for calculating a focusing parameter of a binocular stereo camera, and intelligent terminal | |
| CN113592934B (en) | Target depth and height measuring method and device based on monocular camera | |
| CN113689565B (en) | Road flatness grade detection method and system based on binocular stereo vision and intelligent terminal |
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 |