CN106289159B - Vehicle distance measurement method and device based on distance measurement compensation - Google Patents
Vehicle distance measurement method and device based on distance measurement compensation Download PDFInfo
- Publication number
- CN106289159B CN106289159B CN201610608255.5A CN201610608255A CN106289159B CN 106289159 B CN106289159 B CN 106289159B CN 201610608255 A CN201610608255 A CN 201610608255A CN 106289159 B CN106289159 B CN 106289159B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- distance
- camera
- estimated
- calculating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C3/00—Measuring distances in line of sight; Optical rangefinders
-
- 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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
- G01S17/08—Systems determining position data of a target for measuring distance only
Abstract
The invention provides a vehicle distance measurement method based on distance measurement compensation, which comprises the following steps: calculating the internal reference of the vehicle-mounted camera by adopting a camera internal reference calibration algorithm; measuring the pitch angle of the vehicle-mounted camera by using a gyroscope, and measuring the real height of the vehicle-mounted camera from the ground by using a ruler; respectively parking reference vehicles at N different positions, respectively acquiring a real distance set and a pre-estimated distance set of the reference vehicles parked at the N different positions by using a laser range finder and a monocular vision vehicle ranging method, and acquiring a distance difference set; acquiring a video image, and detecting a target vehicle from the video image by adopting a vehicle detection algorithm; acquiring an estimated vehicle distance of a target vehicle by using a monocular vision vehicle distance measurement method, and acquiring a distance compensation value corresponding to the estimated vehicle distance; and calculating and outputting the vehicle distance of the target vehicle according to the estimated vehicle distance and the distance compensation value. Compared with the prior art, the vehicle ranging method improves the accuracy of vehicle ranging through ranging compensation and is high in ranging speed.
Description
Technical Field
The invention relates to image processing, video monitoring and intelligent traffic, in particular to a vehicle distance measuring method and device.
Background
Ensuring the automaticity, comfort and safety of automobile driving is a constantly sought-after goal of intelligent vehicles, and among them, the safety of vehicles has been more emphasized in recent years. The safety performance of the present vehicles is mainly embodied in safety systems, danger early warning systems, collision avoidance systems, and the like. Under the control of a computer, the vehicle-mounted equipment provides auxiliary driving information to a driver in a mode of voice, images and the like, and can automatically or semi-automatically control the vehicle, thereby effectively preventing accidents. The vehicle distance measurement technology is one of the key points of the automobile anti-collision technology.
At present, the vehicle distance measurement methods mainly include ultrasonic distance measurement, millimeter wave radar distance measurement, distance measurement compensation, visual distance measurement and the like. Ultrasonic ranging is only suitable for short distances, since the ultrasonic energy decays in proportion to the square of the distance. Radar rangefinders are susceptible to electromagnetic interference, which can lead to mishandling of the vehicle. Although the distance measuring compensator has a fast measuring speed, the measuring precision is not high. The visual ranging is a measuring method which takes an image as a means or a carrier for detecting and transmitting information to be utilized, and has the characteristics of good stability, non-contact measurement and the like, so that the visual-based ranging method is greatly concerned.
The chinese patent application with publication number CN104392629A discloses a method for detecting a vehicle distance, which comprises the following steps: collecting images of tail lamps of the front vehicle; determining position information of the tail lamp of the front vehicle in the image; and calculating the distance between the vehicle and the front vehicle according to the position information. However, the above method is less accurate. The Chinese patent application with the publication number of CN105488454A discloses a monocular vision-based front vehicle detection and distance measurement method, which comprises the steps of preliminarily obtaining a rectangular area of vehicle information by methods of histogram equalization, a classifier and the like, removing false detection by using priori knowledge, determining the accurate position of a vehicle by using a shadow at the bottom of the vehicle, and performing vehicle distance measurement by using the detection result of the vehicle position and a lane line as the priori information. However, the above method has a large amount of calculation and a long running time.
In summary, there is a need to provide a method and a device for measuring distance of a vehicle with high speed and high accuracy.
Disclosure of Invention
In view of the above, the main objective of the present invention is to achieve fast vehicle ranging with high ranging accuracy.
To achieve the above object, according to a first aspect of the present invention, there is provided a vehicle ranging method based on ranging compensation, the method including:
The method comprises the following steps that firstly, internal parameters of a vehicle-mounted camera are calculated by adopting a camera internal parameter calibration algorithm;
the second step, the pitch angle of the vehicle-mounted camera is measured by using a gyroscope, and the real height of the vehicle-mounted camera from the ground is measured by using a scale;
Step three, respectively parking the reference vehicles at N different positions, respectively acquiring real distance sets and estimated distance sets of the reference vehicles parked at the N different positions by using a laser range finder and a monocular vision vehicle distance measurement method, and acquiring distance difference sets;
The fourth step, collecting video images, and detecting a target vehicle from the video images by adopting a vehicle detection algorithm;
fifthly, acquiring the estimated vehicle distance of the target vehicle by using a monocular vision vehicle distance measurement method, and acquiring a distance compensation value corresponding to the estimated vehicle distance; and
and a sixth step of calculating a sum of the estimated vehicle distance and the distance compensation value, and outputting the sum as the vehicle distance of the target vehicle.
The third step further comprises:
Selecting different distances, namely respectively parking the reference vehicle at N different positions within the visual range of the vehicle-mounted camera;
A step of acquiring a real distance set, in which a laser range finder is used to measure the real distance set L ═ L of the reference vehicles at N different positions respectively1，l2，…，lN}；
and calculating an estimated distance set, namely respectively acquiring estimated distance sets D-D of reference vehicles at N different positions by adopting a monocular vision vehicle ranging method1，d2，…，dN}；
A distance difference value set obtaining step of calculating a real distance set L ═ L1，l2，…，lND and the set of estimated distances D ═ D1，d2，…，dNdistance difference set Δ D ═ Δ D } ═ Δ D1，Δd２，…，ΔdNWhere Δ d isi＝li-di，i＝1，2，…，N。
The fifth step further includes:
an estimated vehicle distance calculation step, namely calculating the estimated vehicle distance d of the target vehicle by adopting a monocular vision vehicle distance measurement method S330E；
A distance compensation value obtaining step, wherein in the estimated distance set D ═ D1，d2，…，dNsearch and estimate vehicle distance dENearest diFrom the distance difference set Δ D ═ Δ D1，Δd2，…，ΔdNGet in and diCorresponding distance difference Δ diAnd will be Δ diAs a distance compensation value dCI.e. dC＝Δdi。
The monocular vision vehicle ranging method further includes:
a camera focal length obtaining step of calculating a camera focal length by using a focal length f in internal reference of the camera and a physical dimension dy in the y-axis direction
A vanishing ordinate calculating step of calculating an ordinate y of a vanishing line in the imageh＝v0-Fcam*tanθ，v0the vertical coordinate of the central point of the image is shown, and theta is the pitch angle of the camera;
Calculating the vertical coordinate of the intersection line of the vehicle, detecting the rectangular area of the vehicle from the image by using a vehicle detection algorithm, and acquiring the value y of the lower boundary of the rectangular areabWill y isbSetting the longitudinal coordinate of the intersection line of the vehicle and the ground;
a predicted distance calculating step of calculating a predicted distance of the vehicleHcamIs the true height of the camera from the ground.
According to another aspect of the present invention, there is provided a vehicle ranging apparatus based on ranging compensation, the apparatus including:
The camera internal reference calculation module (1) is used for calculating the internal reference of the vehicle-mounted camera by adopting a camera internal reference calibration algorithm;
The camera external reference acquisition module (2) comprises a gyroscope (21) and a scale (22);
the distance difference set acquisition module (3) is used for respectively parking the reference vehicle at N different positions, respectively acquiring a real distance set and a pre-estimated distance set of the reference vehicle parked at the N different positions by using a laser range finder and a monocular vision vehicle ranging method, and acquiring a distance difference set;
the target vehicle detection module (4) is used for acquiring a video image and detecting a target vehicle from the video image by adopting a vehicle detection algorithm;
The distance compensation value acquisition module (5) is used for acquiring the estimated vehicle distance of the target vehicle by utilizing a monocular vision vehicle distance measurement method and acquiring a distance compensation value corresponding to the estimated vehicle distance; and
And the vehicle distance calculation module (6) of the target vehicle is used for calculating the sum of the estimated vehicle distance and the distance compensation value, and outputting the sum as the vehicle distance of the target vehicle.
The gyroscope (21) is used for measuring the pitch angle of the vehicle-mounted camera; the scale (22) is used for measuring the real height of the vehicle-mounted camera from the ground.
the distance difference set obtaining module (3) further comprises:
A different distance selection module (31) for respectively parking the reference vehicle at N different positions within the visual range of the vehicle-mounted camera;
A true distance set acquisition module (32) for measuring the true distance sets L ═ L of the reference vehicles at the N different positions respectively by using the laser range finders1，l2，…，lN}；
An estimated distance set calculation module (33) for respectively acquiring estimated distance sets D-D of reference vehicles at N different positions by adopting a monocular vision vehicle ranging module (330)1，d2，…，dN}；
A distance difference set acquisition module (34) for calculating a true distance set L ═ L1，l2，…，lND and the set of estimated distances D ═ D1，d2，…，dNDistance difference set Δ D ═ Δ D } ═ Δ D1，Δd2，…，ΔdNWhere Δ d isi＝li-di，i＝1，2，…，N。
The target vehicle ranging module (5) further comprises:
The estimated vehicle distance calculation module (51) is used for calculating the estimated vehicle distance d of the target vehicle by adopting a monocular vision vehicle distance measurement method S330E；
A distance compensation value acquisition module (52) for estimating a distance set D ═ D1，d2，…，dNsearch and estimate vehicle distance dEnearest diFrom the distance difference set Δ D ═ Δ D1，Δd2，…，ΔdNGet in and diCorresponding distance difference Δ diAnd will be Δ diAs a distance compensation value dCI.e. dC＝Δdi。
The monocular vision vehicle ranging module (330) further comprises:
A camera focal length acquisition module (331) for calculating a camera focal length using a focal length f in the internal reference of the camera and a physical dimension dy in the y-axis direction
a vanishing ordinate calculation module (332) for calculating the ordinate y of the vanishing line in the imageh＝v0-Fcam*tanθ，v0The vertical coordinate of the central point of the image is shown, and theta is the pitch angle of the camera;
A vehicle intersection line ordinate calculation module (333) for detecting a rectangular region of the vehicle from the image by using a vehicle detection algorithm and obtaining a value y of a lower boundary of the rectangular regionbWill y isbSetting the longitudinal coordinate of the intersection line of the vehicle and the ground;
A predicted distance calculation module (334) for calculating a predicted distance of the vehicleHcamis the true height of the camera from the ground.
compared with the existing vehicle distance measuring technology, the vehicle distance measuring method and device based on distance measuring compensation can rapidly measure the distance of the target vehicle by adopting the distance measuring compensation method combining laser distance measuring and visual distance measuring, and the accuracy is higher.
Drawings
Fig. 1 shows a flow chart of a ranging compensation based vehicle ranging method according to the present invention.
Fig. 2 shows a block diagram of a vehicle distance measuring device based on distance measuring compensation according to the invention.
Detailed Description
To further clarify the structure, features and other objects of the present invention, a detailed description of the preferred embodiments will be given below with reference to the accompanying drawings, which are provided for illustration of the technical solution of the present invention and are not intended to limit the present invention.
Fig. 1 shows a flow chart of a vehicle ranging method based on ranging compensation according to the present invention. As shown in fig. 1, the ranging compensation-based vehicle ranging method according to the present invention includes:
The first step S1, calculating the internal reference of the vehicle-mounted camera by adopting a camera internal reference calibration algorithm;
A second step S2, measuring the pitch angle of the vehicle-mounted camera by using a gyroscope, and measuring the real height of the vehicle-mounted camera from the ground by using a ruler;
A third step S3, respectively parking the reference vehicles at N different positions, respectively acquiring real distance sets and estimated distance sets of the reference vehicles parked at the N different positions by using a laser range finder and a monocular vision vehicle distance measurement method, and acquiring distance difference sets;
A fourth step S4, collecting video images, and detecting a target vehicle from the video images by adopting a vehicle detection algorithm;
A fifth step S5, acquiring the estimated vehicle distance of the target vehicle by using a monocular vision vehicle distance measurement method, and acquiring a distance compensation value corresponding to the estimated vehicle distance; and
In the sixth step S6, the sum of the estimated vehicle distance and the distance compensation value is calculated and output as the vehicle distance of the target vehicle.
the camera internal reference calibration algorithm in the first step S1 is a prior art, and may be implemented by a calibration method for a zhangyou or an improved algorithm for calibration, such as "liuyan, li tengyo" improved research on the camera calibration method for zhangyou, "optical technology", 2014(6): 565-. The acquired internal parameters comprise focal length f and central point coordinates (u) of the image0,v0)。
In the second step S2, the pitch angle of the camera mounted on the vehicle is measured as θ by an existing gyro angle measurement method. The scale is a common scale capable of measuring height, and the true height of the measuring camera from the ground is Hcam。
the third step S3 further includes:
A different distance selecting step S31, wherein the reference vehicle is respectively parked at N different positions in the visual range of the vehicle-mounted camera;
A true distance set acquisition step S32 of measuring, with the laser range finder, true distance sets L ═ L of reference vehicles at N different positions, respectively1，l2，…，lN}；
an estimated distance set calculation step S33, obtaining estimated distance sets D ═ D of reference vehicles at N different positions respectively by using a monocular vision vehicle ranging method1，d2，…，dN}；
The distance difference set obtaining step S34 calculates a true distance set L ═ L1，l2，…，lND and the set of estimated distances D ═ D1，d2，…，dNdistance difference set Δ D ═ Δ D } ═ Δ D1，Δd2，…，ΔdNWhere Δ d isi＝li-di，i＝1，2，…，N。
wherein, the laser range finder is prior art.
the different distance selecting step S31 is further to park the reference vehicle at N different positions within a range of 10-100 m from the vehicle-mounted camera, respectively.
The N belongs to [5,50 ]. Preferably, N ∈ [10,20 ]. For example, N is chosen to be 15.
The method of one-eye vehicle ranging S330 in the estimated distance calculation step S33 further includes:
A camera focal length obtaining step S331 of calculating a camera focal length using a focal length f in the internal reference of the camera and a physical dimension dy in the y-axis direction
vanishing ordinate calculating step S332 of calculating ordinate y of vanishing line in imageh＝v0-Fcam*tanθ，v0The vertical coordinate of the central point of the image is shown, and theta is the pitch angle of the camera;
A vehicle intersection ordinate calculation step S333 of detecting a rectangular region of the vehicle from the image by using a vehicle detection algorithm and acquiring a value y of a lower boundary of the rectangular regionbwill y isbSetting the longitudinal coordinate of the intersection line of the vehicle and the ground;
A predicted distance calculating step S334 of calculating the predicted distance of the vehicleHcamIs the true height of the camera from the ground.
in step S331, the physical size dy in the y-axis direction is the intrinsic size of the camera photosensitive element.
The vehicle cross line and ordinate calculation step S333 is performed by using the existing vehicle detection algorithm based on vision. For example, "Xianfeng, Yangyan. a HOG-LBP-based efficient vehicle detection method," computer engineering, 2014,40(09): 210-.
In the fourth step S4, a video image is captured by the vehicle-mounted camera.
The vehicle detection algorithm in the fourth step S4 is an existing vision-based vehicle detection method, and may adopt a vehicle detection algorithm similar to that in the vehicle intersection ordinate calculation step S333.
The fifth step S5 further includes:
An estimated vehicle distance calculation step S51, which is to calculate the estimated vehicle distance d of the target vehicle by adopting a monocular vision vehicle distance measurement method S330E；
A distance compensation value obtaining step S52, where D is { D } in the estimated distance set1，d2，…，dNSearch and estimate vehicle distance dEnearest diFrom the distance difference set Δ D ═ Δ D1，Δd2，…，ΔdNGet in and diCorresponding distance difference Δ diand will be Δ diAs a distance compensation value dCi.e. dC＝Δdi。
The monocular vision vehicle ranging method in the estimated vehicle distance calculating step S51 employs the same monocular vision vehicle ranging method S330 as in the estimated distance calculating step S33.
In the distance compensation value obtaining step S52, the estimated distance set D ═ D1，d2，…，dNsearch and estimate vehicle distance dENearest diThe method specifically comprises the following steps: respectively calculating estimated distance set D ═ D1，d2，…，dNEvery estimated distance d iniAnd dEIs d is the absolute difference ofi-dE|，|di-dED with the smallest | valueiis the estimated vehicle distance dEnearest di。
The sixth step S6 is further to calculate the estimated vehicle distance dEand a distance compensation value dCSum of (d)T＝dE+dCWill sum up the value dTAnd the distance is used as the distance of the target vehicle and is output.
Fig. 2 is a block diagram of a camera calibration apparatus based on range compensation according to the present invention. As shown in fig. 2, the camera calibration apparatus based on ranging compensation according to the present invention includes:
The camera internal reference calculation module 1 is used for calculating the internal reference of the vehicle-mounted camera by adopting a camera internal reference calibration algorithm;
the camera external reference acquisition module 2 comprises a gyroscope 21 and a scale 22;
The distance difference set acquisition module 3 is used for respectively parking the reference vehicle at N different positions, respectively acquiring a real distance set and a pre-estimated distance set of the reference vehicle parked at the N different positions by using a laser range finder and a monocular vision vehicle ranging method, and acquiring a distance difference set;
the target vehicle detection module 4 is used for acquiring video images and detecting a target vehicle from the video images by adopting a vehicle detection algorithm;
The distance compensation value acquisition module 5 is used for acquiring the estimated vehicle distance of the target vehicle by utilizing a monocular vision vehicle distance measurement method and acquiring a distance compensation value corresponding to the estimated vehicle distance; and
and the vehicle distance calculation module 6 of the target vehicle is used for calculating the sum of the estimated vehicle distance and the distance compensation value, and outputting the sum as the vehicle distance of the target vehicle.
The gyroscope 21 is used for measuring the pitch angle of the vehicle-mounted camera; the scale 22 is used to measure the true height of the vehicle camera from the ground.
The camera internal reference calibration algorithm in the camera internal reference calculation module 1 is the prior art, and can be realized by a calibration method or an improved calibration algorithm, such as "liuyan, li tengyo" improvement research on the calibration method of a zhangnyu camera, "optical technology", 2014(6): 565-. The acquired internal parameters comprise focal length f and central point coordinates (u) of the image0,v0)。
The method for measuring the angle of the gyroscope 21 in the camera external parameter acquisition module 2 is the prior art, and the pitch angle of the camera loaded on the vehicle is measured to be theta. The scale 22 is a common scale capable of measuring height, and the true height of the measuring camera from the ground is Hcam。
The distance compensation value obtaining module 3 further includes:
A different distance selection module 31, configured to park the reference vehicle at N different positions within a visual range of the vehicle-mounted camera;
A real distance set acquiring module 32, configured to measure, by using the laser range finder, real distance sets L ═ L of the reference vehicles at N different positions respectively1，l2，…，lN}；
An estimated distance set calculation module 33, configured to obtain estimated distance sets D ═ D { D } of the reference vehicles at the N different positions by using the monocular vision vehicle ranging module 330, respectively1，d2，…，dN}；
A distance difference value set obtaining module 34 for calculating a real distance set L ═ L1，l2，…，lND and the set of estimated distances D ═ D1，d2，…，dNDistance difference set Δ D ═ Δ D } ═ Δ D1，Δd2，…，ΔdNWhere Δ d isi＝li-di，i＝1，2，＝，N。
Wherein, the laser range finder is prior art.
The different distance selecting module 31 further stops the reference vehicle at N different positions within a range of 10-100 m from the vehicle-mounted camera.
the N belongs to [5,50 ]. Preferably, N ∈ [10,20 ]. For example, N is chosen to be 15.
The single-eye vehicle ranging module 330 in the pre-estimated distance calculation module 33 further comprises:
A camera focal length obtaining module 331 for calculating a camera focal length by using a focal length f in the internal reference of the camera and a physical size dy in the y-axis direction
A vanishing ordinate calculating module 332 for calculating the ordinate y of the vanishing line in the imageh＝v0-Fcam*tanθ，v0The vertical coordinate of the central point of the image is shown, and theta is the pitch angle of the camera;
A vehicle intersection line ordinate calculation module 333, configured to detect a rectangular region of the vehicle from the image by using a vehicle detection algorithm, and obtain a value y of a lower boundary of the rectangular regionbwill y isbsetting the longitudinal coordinate of the intersection line of the vehicle and the ground;
A predicted distance calculation module 334 for calculating the predicted distance of the vehicleHcamIs the true height of the camera from the ground.
The physical size dy in the y-axis direction in the camera focal length acquiring module 331 is an intrinsic size of the camera photosensitive element.
The vehicle detection algorithm is an existing vision-based vehicle detection method. For example, "Xianfeng, Yangyan. a HOG-LBP-based efficient vehicle detection method," computer engineering, 2014,40(09): 210-.
and the target vehicle detection module 4 acquires video images through a vehicle-mounted camera.
The vehicle detection algorithm in the target vehicle detection module 4 is an existing vehicle detection method based on vision, and can adopt a vehicle detection algorithm similar to that in the vehicle intersection line ordinate calculation module 333.
The distance compensation value obtaining module 5 further includes:
The estimated vehicle distance calculation module 51 is used for calculating the estimated vehicle distance d of the target vehicle by adopting the monocular vision vehicle distance measurement method S330E；
A distance compensation value obtaining module 52, configured to obtain a distance between the estimated distance set D ═ D1，d2，…，dNSearch and estimate vehicle distance dENearest difrom the distance difference set D ═ Δ D ═ D1，Δd2，…，ΔdNGet in and diCorresponding distance difference Δ diAnd will be Δ dias a distance compensation value dCi.e. dC＝Δdi。
the monocular vision vehicle distance measuring module in the estimated vehicle distance calculating module 51 adopts the same monocular vision vehicle distance measuring module 330 as that in the estimated distance calculating module 33.
The distance compensation value obtaining module 52 estimates the distance set D ═ D1，d2，…，dNSearch and estimate vehicle distance dENearest diThe method specifically comprises the following steps: respectively calculating estimated distance set D ═ D1，d2，…，dNEvery estimated distance d iniAnd dEabsolute difference value | d ofi-dE|，|di-dEd with the smallest | valueiis the estimated vehicle distance dENearest di。
the vehicle distance calculation module 6 of the target vehicle further calculates the estimated vehicle distance dEand a distance compensation value dCSum of (d)T＝dE+dCwill sum up the value dTAnd the distance is used as the distance of the target vehicle and is output.
Compared with the existing vehicle distance measuring technology, the vehicle distance measuring method and device based on distance measuring compensation can rapidly measure the distance of the target vehicle by adopting the distance measuring compensation method combining laser distance measuring and visual distance measuring, and the accuracy is higher.
While the foregoing is directed to the preferred embodiment of the present invention, and is not intended to limit the scope of the invention, it will be understood that the invention is not limited to the embodiments described herein, which are described to assist those skilled in the art in practicing the invention. Further modifications and improvements may readily occur to those skilled in the art without departing from the spirit and scope of the invention, and it is intended that the invention be limited only by the terms and scope of the appended claims, as including all alternatives and equivalents which may be included within the spirit and scope of the invention as defined by the appended claims.
Claims (6)
1. The vehicle distance measurement method based on distance measurement compensation is characterized by comprising the following steps:
the method comprises the following steps that firstly, internal parameters of a vehicle-mounted camera are calculated by adopting a camera internal parameter calibration algorithm;
The second step, the pitch angle of the vehicle-mounted camera is measured by using a gyroscope, and the real height of the vehicle-mounted camera from the ground is measured by using a scale;
step three, respectively parking the reference vehicles at N different positions, respectively acquiring real distance sets and estimated distance sets of the reference vehicles parked at the N different positions by using a laser range finder and a monocular vision vehicle distance measurement method, and acquiring distance difference sets;
The fourth step, collecting video images, and detecting a target vehicle from the video images by adopting a vehicle detection algorithm;
fifthly, acquiring the estimated vehicle distance of the target vehicle by using a monocular vision vehicle distance measurement method, and acquiring a distance compensation value corresponding to the estimated vehicle distance; and
a sixth step of calculating a sum of the estimated vehicle distance and the distance compensation value, and outputting the sum as the vehicle distance of the target vehicle;
the camera internal reference calibration algorithm comprises the following steps: zhangyingyou calibration; the internal reference of the vehicle-mounted camera comprises: focal length f, center point coordinate of image (u)0,v0) The physical dimension dy in the y-axis direction;
wherein the third step comprises:
Selecting different distances, namely respectively parking the reference vehicle at N different positions within the visual range of the vehicle-mounted camera;
a step of acquiring a real distance set, in which a laser range finder is used to measure the real distance set L ═ L of the reference vehicles at N different positions respectively1，l2，…，lN}；
And calculating an estimated distance set, namely respectively acquiring estimated distance sets D-D of reference vehicles at N different positions by adopting a monocular vision vehicle ranging method1，d2，…，dN}；
A distance difference value set obtaining step of calculating a real distance set L ═ L1，l2，…，lND and the set of estimated distances D ═ D1，d2，…，dNDistance difference set Δ D ═ Δ D } ═ Δ D1，Δd2，…，ΔdNWhere Δ d isi＝li-di，i＝1，2，…，N；
The fifth step includes:
A step of calculating the estimated vehicle distance, namely calculating the estimated vehicle distance d of the target vehicle by adopting a monocular vision vehicle distance measurement methodE；
a distance compensation value obtaining step, wherein in the estimated distance set D ═ D1，d2，…，dNsearch and estimate vehicle distance dENearest difrom the distance difference set Δ D ═ Δ D1，Δd2，…，ΔdNGet in and diCorresponding distance difference Δ diAnd will be Δ diAs a distance compensation value dCi.e. dC＝Δdi。
2. The method of claim 1, wherein the monocular visual vehicle ranging method comprises: a camera focal length obtaining step of calculating a camera focal length by using a focal length f in internal reference of the camera and a physical dimension dy in the y-axis directionA vanishing ordinate calculating step of calculating an ordinate y of a vanishing line in the imageh＝v0-Fcam*tanθ，v0The vertical coordinate of the central point of the image is shown, and theta is the pitch angle of the camera;
Calculating the vertical coordinate of the intersection line of the vehicle, detecting the rectangular area of the vehicle from the image by using a vehicle detection algorithm, and acquiring the value y of the lower boundary of the rectangular areabWill y isbSetting the longitudinal coordinate of the intersection line of the vehicle and the ground;
a predicted distance calculating step of calculating a predicted distance of the vehicleHcamThe true height of the camera from the ground;
Wherein, the focal length F of the cameracamRepresenting the pixel representation of the focal length f in the y-axis direction.
3. The method of claim 1, wherein N e [5,50 ].
4. Vehicle range unit based on range compensation, its characterized in that, the device includes:
The camera internal reference calculation module (1) is used for calculating the internal reference of the vehicle-mounted camera by adopting a camera internal reference calibration algorithm;
the camera external reference acquisition module (2) comprises a gyroscope (21) and a scale (22);
The distance difference set acquisition module (3) is used for respectively parking the reference vehicle at N different positions, respectively acquiring a real distance set and a pre-estimated distance set of the reference vehicle parked at the N different positions by using a laser range finder and a monocular vision vehicle ranging method, and acquiring a distance difference set;
the target vehicle detection module (4) is used for acquiring a video image and detecting a target vehicle from the video image by adopting a vehicle detection algorithm;
The distance compensation value acquisition module (5) is used for acquiring the estimated vehicle distance of the target vehicle by utilizing a monocular vision vehicle distance measurement method and acquiring a distance compensation value corresponding to the estimated vehicle distance; and
The vehicle distance calculation module (6) of the target vehicle is used for calculating the sum of the estimated vehicle distance and the distance compensation value, and outputting the sum as the vehicle distance of the target vehicle;
The camera internal reference calibration algorithm comprises the following steps: zhangyingyou calibration; the internal reference of the vehicle-mounted camera comprises: focal length f, center point coordinate of image (u)0,v0) The physical dimension dy in the y-axis direction; wherein the gyroscope (21) is used for measuring the pitch angle of the vehicle-mounted camera; the scale (22) is used for measuring the real height of the vehicle-mounted camera from the ground;
Wherein the distance difference set obtaining module (3) comprises:
a different distance selection module (31) for respectively parking the reference vehicle at N different positions within the visual range of the vehicle-mounted camera;
A true distance set acquisition module (32) for measuring the true distance sets L ═ L of the reference vehicles at the N different positions respectively by using the laser range finders1，l2，…，lN}；
An estimated distance set calculation module (33) for respectively acquiring estimated distance sets D-D of reference vehicles at N different positions by adopting a monocular vision vehicle ranging module (330)1，d2，…，dN}；
A distance difference set acquisition module (34) for calculating a true distance set L ═ L1，l2，…，lNd and the set of estimated distances D ═ D1，d2，…，dNdistance difference set Δ D ═ Δ D } ═ Δ D1，Δd2，…，ΔdNwhere Δ d isi＝li-di，i＝1，2，…，N；
The target vehicle ranging module (5) comprises:
The estimated vehicle distance calculation module (51) is used for calculating the estimated vehicle distance d of the target vehicle by adopting a monocular vision vehicle distance measurement method S330E；
A distance compensation value acquisition module (52) for estimating a distance set D{d1，d2，…，dNsearch and estimate vehicle distance dEnearest diFrom the distance difference set Δ D ═ Δ D1，Δd2，…，ΔdNget in and diCorresponding distance difference Δ diand will be Δ diAs a distance compensation value dCi.e. dC＝Δdi。
5. The apparatus of claim 4, wherein the monocular vision vehicle ranging module (330) further comprises:
A camera focal length acquisition module (331) for calculating a camera focal length using a focal length f in the internal reference of the camera and a physical dimension dy in the y-axis direction
A vanishing ordinate calculation module (332) for calculating the ordinate y of the vanishing line in the imageh＝v0-Fcam*tanθ，v0The vertical coordinate of the central point of the image is shown, and theta is the pitch angle of the camera;
A vehicle intersection line ordinate calculation module (333) for detecting a rectangular region of the vehicle from the image by using a vehicle detection algorithm and obtaining a value y of a lower boundary of the rectangular regionbWill y isbsetting the longitudinal coordinate of the intersection line of the vehicle and the ground;
A predicted distance calculation module (334) for calculating a predicted distance of the vehicleHcamThe true height of the camera from the ground;
Wherein, the focal length F of the cameracamRepresenting the pixel representation of the focal length f in the y-axis direction.
6. The apparatus of claim 5, said N e [5,50 ].
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610608255.5A CN106289159B (en) | 2016-07-28 | 2016-07-28 | Vehicle distance measurement method and device based on distance measurement compensation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610608255.5A CN106289159B (en) | 2016-07-28 | 2016-07-28 | Vehicle distance measurement method and device based on distance measurement compensation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106289159A CN106289159A (en) | 2017-01-04 |
| CN106289159B true CN106289159B (en) | 2019-12-10 |
Family
ID=57663132
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610608255.5A Active CN106289159B (en) | 2016-07-28 | 2016-07-28 | Vehicle distance measurement method and device based on distance measurement compensation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106289159B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107389026B (en) * | 2017-06-12 | 2019-10-01 | 江苏大学 | A kind of monocular vision distance measuring method based on fixed point projective transformation |
| CN109141347A (en) | 2017-06-28 | 2019-01-04 | 京东方科技集团股份有限公司 | Vehicle-mounted vidicon distance measuring method and device, storage medium and electronic equipment |
| CN110966982A (en) * | 2018-09-28 | 2020-04-07 | 成都家有为力机器人技术有限公司 | Monocular camera ranging system and method for cleaning robot |
| CN110031829B (en) * | 2019-04-18 | 2021-07-09 | 北京联合大学 | Target accurate distance measurement method based on monocular vision |
| CN113643355B (en) * | 2020-04-24 | 2024-03-29 | 广州汽车集团股份有限公司 | Target vehicle position and orientation detection method, system and storage medium |
| CN111829484B (en) * | 2020-06-03 | 2022-05-03 | 江西江铃集团新能源汽车有限公司 | Target distance measuring and calculating method based on vision |
| CN111623776B (en) * | 2020-06-08 | 2022-12-02 | 昆山星际舟智能科技有限公司 | Method for measuring distance of target by using near infrared vision sensor and gyroscope |
| CN112254821B (en) * | 2020-10-16 | 2021-12-14 | 盈合(深圳)机器人与自动化科技有限公司 | Method and device for compensating body temperature detection precision through visual ranging |
| CN113178005A (en) * | 2021-05-26 | 2021-07-27 | 国网河南省电力公司南阳供电公司 | Efficient photographing modeling method and device for power equipment |
| CN114295099B (en) * | 2021-12-28 | 2024-01-30 | 合肥英睿系统技术有限公司 | Ranging method based on monocular camera, vehicle-mounted ranging equipment and storage medium |
| CN116363623B (en) * | 2023-01-28 | 2023-10-20 | 苏州飞搜科技有限公司 | Vehicle detection method based on millimeter wave radar and vision fusion |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8164628B2 (en) * | 2006-01-04 | 2012-04-24 | Mobileye Technologies Ltd. | Estimating distance to an object using a sequence of images recorded by a monocular camera |
| US9561804B2 (en) * | 2014-06-19 | 2017-02-07 | Ford Global Technologies, Llc | Distance to empty prediction with short term distance compensation |
| KR101646495B1 (en) * | 2014-11-18 | 2016-08-08 | 한밭대학교 산학협력단 | Road distance estimation method using image information of black box camera |
| KR101597771B1 (en) * | 2014-12-09 | 2016-02-25 | 주식회사 만도 | apparatuses and methods for steering torque compensation |
| CN104792302A (en) * | 2015-04-29 | 2015-07-22 | 深圳市保千里电子有限公司 | Modeling method for measuring car distance |
-
2016
- 2016-07-28 CN CN201610608255.5A patent/CN106289159B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106289159A (en) | 2017-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106289159B (en) | Vehicle distance measurement method and device based on distance measurement compensation | |
| CN107272021B (en) | Object detection using radar and visually defined image detection areas | |
| EP3792660B1 (en) | Method, apparatus and system for measuring distance | |
| US10909395B2 (en) | Object detection apparatus | |
| EP3306429B1 (en) | Position estimation device and position estimation method | |
| US9740942B2 (en) | Moving object location/attitude angle estimation device and moving object location/attitude angle estimation method | |
| WO2018105179A1 (en) | Vehicle-mounted image processing device | |
| US20090122136A1 (en) | Object detection device | |
| KR102441075B1 (en) | Apparatus and method for estmating position of vehicle base on road surface display | |
| US11302020B2 (en) | Stereo camera device | |
| CN108645375B (en) | Rapid vehicle distance measurement optimization method for vehicle-mounted binocular system | |
| CN106546257A (en) | Vehicle distance measurement method and device, vehicle relative velocity measuring method and device | |
| JP2018048949A (en) | Object recognition device | |
| JP2017181476A (en) | Vehicle location detection device, vehicle location detection method and vehicle location detection-purpose computer program | |
| CN105300390B (en) | The determination method and device of obstructing objects movement locus | |
| JP6834401B2 (en) | Self-position estimation method and self-position estimation device | |
| KR20160125803A (en) | Apparatus for defining an area in interest, apparatus for detecting object in an area in interest and method for defining an area in interest | |
| CN111998780B (en) | Target ranging method, device and system | |
| JP2001101420A (en) | Device and method for detecting obstacle | |
| CN110488320A (en) | A method of vehicle distances are detected using stereoscopic vision | |
| JP6604052B2 (en) | Runway boundary estimation device and runway boundary estimation method | |
| CN115320603A (en) | Shooting elevation angle correction method and device and vehicle | |
| CN113658252A (en) | Method, medium, apparatus for estimating elevation angle of camera, and camera | |
| Chiang et al. | Driver assistance system based on monocular vision | |
| CN116309694A (en) | Tracking device, tracking method, and tracking computer program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |