CN209181784U - A video measuring device applied to automatic parking system - Google Patents

Abstract

The utility model provides a video measurement device applied to an automatic parking system, which comprises a plurality of cameras arranged at equal intervals parallel to the driving direction of the vehicle to be measured, and is vertically downward at a certain height with a bird's-eye view angle, and the video is recorded Measure the plane motion of the vehicle in the parking test scene; use panoramic stitching technology to stitch and fuse each frame recorded by different cameras into a high-definition panoramic video; establish a benchmark scale according to the reference objects in the video, and use motion analysis software to analyze the experimental video images Analyze and establish a kinematic model of the vehicle under test. The video measurement method applied to the automatic parking system described in the utility model has high test accuracy, is suitable for a large number of test verifications, and provides high-precision measurement for the function and performance test of the automatic parking system of the tested vehicle data support.

Description

A video measuring device applied to automatic parking system

technical field

The utility model belongs to the technical field of automobiles, in particular to a video measuring device applied to an automatic parking system.

Background technique

With the rapid development of science and technology, people's means and methods of travel are becoming more and more convenient, and as the most widely used means of transportation, the number of cars is constantly increasing, which brings traffic problems such as road congestion. With professionalization, the risk factor of driving a vehicle has also greatly increased. On the other hand, intelligent networked vehicles are a comprehensive manifestation of industrial transformation, integration of industrialization and industrialization, smart cities and national competitiveness. Governments of various countries also attach great importance to and actively deploy the technology chain and industrial chain of intelligent networked vehicles. The mainstream practice in the industry is to use the research and development of advanced driver assistance systems (ADAS) as the starting point for the development of "autonomous" intelligent networked vehicles. Against this background, the key technologies of ADAS have been developed and applied rapidly. This technology detects objects in traffic scenes through environmental perception sensors such as lidar, millimeter-wave radar, and cameras. The control algorithm processes the data in real time and performs decision-making planning. Control the action of the vehicle actuator to realize the driving assistance function. At present, ADAS functions are divided into four categories according to horizontal, vertical, rear and parking assistance, which greatly improve road safety, driving comfort and traffic efficiency, and effectively improve the driving habits of drivers.

Automated Parking System (APS), as an ADAS system commonly installed on mid-to-high-end cars, brings great convenience to drivers in parking and has a broad market prospect. Automatic parking technology can park the car in a small space. After the system is started, it relies on sensors such as cameras and radars to identify information such as obstacles, parking spaces, and target parking spaces, and controls the steering wheel, accelerator, and brakes in a fully automatic or semi-automatic manner. , gear, handbrake, etc., can realize automatic parking into place. APS greatly improves the efficiency, comfort and safety of parking, and solves the problem of poor skills and difficult parking for novice drivers.

In order to support the R&D and test verification of automatic parking products, and evaluate the functions and performance of the automatic parking system, it is necessary to accurately measure the motion information of the whole vehicle during the automatic parking operation. At present, there are two main automatic parking measurement methods at home and abroad: one is to directly measure the position and angle of the measured vehicle relative to the target parking space after the vehicle stops at the end of parking. The evaluation results are not comprehensive enough to measure the dynamic changes of the vehicle’s position and attitude; the second is to measure the combined guidance scheme of the high-precision global positioning system (GPS) supplemented by the inertial navigation system (INS). The measurement accuracy in the low-speed creeping state is very low and the error is large, and it is not suitable for indoor or underground parking conditions. In addition, the cost of GPS/INS and other equipment is too high, the installation and calibration are difficult, and the test efficiency is low.

SUMMARY OF THE INVENTION

In view of this, the utility model aims to propose a video measurement method applied to the automatic parking system to solve the low measurement accuracy and large error of the existing vehicle in the low-speed creeping state, and it is not suitable for indoor or outdoor use. Problem with underground parking.

In order to achieve the above object, the technical solution of the utility model is achieved in that:

A video measurement method applied to an automatic parking system, comprising the following steps: using a plurality of cameras arranged at equal intervals parallel to the driving direction of the vehicle under test, and shooting the vehicle under test vertically downward at a certain height with a bird's-eye view Plane motion in the parking test scene; using panoramic stitching technology to stitch and fuse each frame recorded by different cameras into a high-definition panoramic video with a wide range of viewing angles, small image distortion, high frame synchronization rate, and no obvious color difference between light and dark; according to the video The reference object in the system establishes the benchmark scale, analyzes the experimental video image through motion analysis software, captures and tracks the pose information of the moving object, and establishes the kinematics model of the vehicle under test, so as to measure the parking process in a limited space. The motion trajectory, linear/angular velocity, and linear/angular acceleration of the measured vehicle in the global coordinate system and relative coordinate system.

Further, the specific implementation method of the panorama stitching technology is:

Assuming that the shooting height of the camera from the ground is L, and the size of the shooting scene is W×H, the specific values of W and H can be determined through calculation or actual measurement, W represents the width, and H represents the height;

It is known that the size of a single group of images is W×H. Since the cameras are arranged in parallel at equal intervals, there is a fixed image overlapping area between each two groups of images. C represents the width of the overlapping area. The total length × height of the stitched image can be Expressed as S×H; during the measurement process, 4 groups of parallel and equidistant D distributions are selected, the size of the photosensitive element is 1/2 inch, the focal length is f, the resolution of shooting height×width is 1024×768, and the refresh rate is 25 frames per second camera, where the unit of D is meter, the unit of focal length f is millimeter, and the unit of resolution is pixel,

According to the imaging principle, the picture aspect ratio R is:

The installation height is:

The total width S of the spliced image is:

S=4×W−3×C.

Further, the specific implementation steps of the motion analysis software in the step three are: importing the fused and spliced video material; setting the start frame, end frame, and video file refresh frequency; setting the correction bar and coordinate axis: on the video screen An adjustable correction bar will appear, move the mouse to both ends of the correction bar, and adjust the correction bar to the parameters in the movie by dragging the end position of the correction bar.

Compared with the prior art, the video measurement method applied to the automatic parking system described in the utility model has the following advantages:

(1) The video measurement method applied to the automatic parking system described in the utility model has high test accuracy, is suitable for a large number of test verifications, and provides high precision for the function and performance testing of the automatic parking system of the vehicle under test. Supported by measurement data.

(2) In the video measurement method applied to the automatic parking system described in the utility model, the computer extracts the parking measurement image by identifying features such as the geometric center point, edge point, geometric center line, and parking space line of the vehicle. Key information, analyze and calculate the position, velocity, acceleration and angle change relationship between feature points and point-to-point, point-to-line, calculate the measurement data of parking motion, and then evaluate the function and performance of the automatic parking system.

Another purpose of the present utility model is to propose a video measurement device applied to the automatic parking system to provide a video measurement device applied to the automatic parking system with simple structure, low cost, easy installation and high testing efficiency device.

In order to achieve the above object, the technical solution of the utility model is achieved in that:

A video measurement device applied to an automatic parking system, characterized in that it includes a bracket group, several cameras, POE network cables, a video signal acquisition module, a memory, and a mobile workstation, and the cameras are respectively connected to a power supply, a video camera through a POE network cable A signal acquisition module, the video signal acquisition module is connected to the memory for data storage, and connected to the mobile workstation for data processing. The bracket group includes a number of bracket monomers and a number of connecting rods. Rod, No. 1 turntable, outrigger cantilever, support rod, No. 2 turntable and connectors, the base is a triangular base, and the three corners of the base are respectively connected to the No. 1 turntable through a connecting rod. The connecting piece is fixedly installed above the No. 1 turntable, and the top of the connecting piece is respectively connected to the first end of the outrigger cantilever and the support rod, and the second end of the support rod is installed with the No. 2 turntable. The No. 2 turntable is a servo turntable, and the signal of the servo turntable is connected to the controller of the external electric control system to control the pitch movement of the No. 2 turntable. One camera is installed on each of the No. 2 turntables, and each bracket is a single unit. The support rods are parallel to each other and distributed at equal intervals, and two adjacent support rods are fixedly connected by connecting rods.

Further, the number of the bracket units is 4 groups, the number of the connecting rods is 3, and the linkage of the 4 bracket units is realized through the 3 connecting rods.

Further, pull ropes are provided at both ends of the outrigger cantilever.

Further, the video signal acquisition module is a model 7130 video acquisition card.

Further, the storage is a local hard disk or a USB flash memory.

Further, the mobile workstation is a computer, and multi-channel video acquisition software is installed on the computer.

Further, the power supply is 220V civilian AC power supply or DC battery inverter to AC power supply.

Compared with the prior art, the video measuring device applied to the automatic parking system described in the utility model has the following advantages:

(1) The video measurement device used in the automatic parking system described in the utility model has a simple structure, is easy to install and debug, and has simple calibration and high test efficiency.

(2) The video measurement device applied to the automatic parking system described in the utility model has a single structure of the bracket and has an automatic adjustment function, which eliminates errors caused by installation and layout, and effectively ensures the height of the camera from the ground and verticality are within the allowable range of error.

Description of drawings

The accompanying drawings that constitute a part of the present invention are used to provide further understanding of the present invention, and the schematic embodiments and descriptions of the present invention are used to explain the present invention and do not constitute an improper limitation of the present invention. In the attached image:

Fig. 1 is a schematic diagram of the horizontal parking working condition and the scene range of the embodiment of the present invention;

Figure 2 is a schematic diagram of vertical parking conditions and scene ranges according to an embodiment of the present invention;

FIG. 3 is a working principle diagram of an automatic parking video measuring device according to an embodiment of the present invention;

Fig. 4 is a working flow diagram of an automatic parking video measuring device according to an embodiment of the present invention;

Fig. 5 is a schematic diagram of the shooting height and scene size of a single camera according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of image splicing and fusion according to an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of a video measuring device applied to automatic parking according to an embodiment of the present invention.

Description of reference numbers:

1-Bracket unit; 11-Base; 12-Connecting rod; 13-No. 1 turntable; 14-Overhanging cantilever; 15-Bracket rod; 16-No.

Detailed ways

It should be noted that the embodiments of the present invention and the features of the embodiments may be combined with each other under the condition of no conflict.

In describing the present utility model, it should be understood that the terms "center", "longitudinal", "transverse", "upper", "lower", "front", "rear", "left", "right", The orientations or positional relationships indicated by "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationships shown in the drawings, and are only for the convenience of describing the present invention. Novel and simplified descriptions do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore should not be construed as limiting the utility model. In addition, the terms "first", "second", etc. are used for descriptive purposes only, and should not be construed as indicating or implying relative importance or implying the number of indicated technical features. Thus, a feature defined as "first", "second", etc. may expressly or implicitly include one or more of that feature. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

In the description of the present invention, it should be noted that, unless otherwise expressly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it may be a fixed connection or a connectable connection. Detachable connection, or integral connection; may be mechanical connection or electrical connection; may be direct connection, or indirect connection through an intermediate medium, or internal communication between two components. Those of ordinary skill in the art can understand the specific meanings of the above terms in the present invention through specific situations.

The present utility model will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

A video measurement method applied to an automatic parking system, as shown in FIGS. The bird's-eye view is vertically downward, and the plane movement of the tested vehicle in the parking test scene is recorded;

Step 2: Use panoramic stitching technology to stitch and fuse each frame of images recorded by different cameras into a high-definition panoramic video with a wide viewing angle range, small image distortion, high frame synchronization rate, and no obvious color difference between light and dark;

Step 3: Establish a reference scale based on the reference object in the video, capture and track the pose information of the moving object by analyzing the experimental video image, and establish the kinematic model of the vehicle under test, so as to measure parking in a limited space During the process, the motion track, linear/angular velocity, and linear/angular acceleration of the measured vehicle in the global coordinate system and relative coordinate system.

A video measurement device applied to an automatic parking system, comprising a bracket group, several cameras, POE network cables, a video signal acquisition module, a memory and a mobile workstation, the cameras are respectively connected to a power supply and a video signal acquisition module through a POE network cable, The video signal acquisition module is respectively signal-connected to the memory for data storage, and connected to the mobile workstation for data processing. The bracket group includes several bracket monomers 1 and several connecting rods 2 with the same structure, and each bracket is equipped with a Camera, the support unit 1 includes a base 11, a connecting rod 12, a No. 1 turntable 13, an overhanging cantilever 14, a support rod 15, a No. 2 turntable 16 and a connector 17, the base 11 is a triangular base, and the base 11 The three corners are respectively connected to the No. 1 turntable 13 through a connecting rod 12, and the connecting rod 12 can drive the base 11 to rotate around the Z-axis by holding the connecting rod 2 left and right. The connecting piece 17 is fixedly installed, and the top of the connecting piece 17 is respectively connected to the first end of the outrigger cantilever 14 and the support rod 15, and the second end of the support rod 15 is installed with the second turntable 16, The No. 2 turntable 16 is a servo turntable, and its model is TBR60L. The signal of the servo turntable is connected to the controller of the external electric control system to control the No. 2 turntable 16 to perform pitching motion. Each No. 2 turntable 16 is equipped with a The camera is set to realize the pitching motion of the camera. The support rods 15 of each of the support monomers 1 are parallel to each other and distributed at equal intervals. Two adjacent support rods 15 are fixedly connected by connecting rods 2, so that multiple The linkage of each bracket unit 1 under the action of the connecting rod 2 can ensure the accuracy and efficiency of the pose adjustment of the four cameras.

The stand units 1 are distributed in columns, the bases 11 are arranged outside the measurement area, and the camera is installed directly above the shooting screen.

The controller of the external electronic control system is a single-chip microcomputer or PLC. Through the pulse input of the external electronic control system, the precise and independent control of the pitch angles of multiple groups of cameras is realized, which effectively solves the problem of image splicing and fusion caused by differences in shooting angles and camera installations. The problem with inaccurate results.

The number of the bracket monomers 1 is 4 groups, the number of the connecting rods 2 is 3, and the linkage of the four bracket monomers 1 is realized through the three connecting rods 2 .

The base 11 is a triangular base with good stability.

Two ends of the overhanging cantilever 14 are provided with stay ropes for stabilizing the end of the connecting rod 2 .

The power supply is 220V civilian AC power supply or DC battery inverter to AC power supply.

The video signal acquisition module is a model 7130 video acquisition card.

The storage is a local hard disk or a USB flash memory.

The mobile workstation is a computer, and multi-channel video acquisition software is installed on the computer.

1) The test of the automatic parking system generally includes scenarios such as horizontal parking, vertical parking and oblique parking. In order to ensure that the system can accurately record the complete motion information of the tested vehicle in the whole process of parking, The vehicle video measurement device can shoot a test site with a range of 30×13 meters at a refresh rate of not less than 25 frames per second, and the position error is between ±0.02 meters;

2) The video measurement device described above can accurately measure the trajectory of any point of the vehicle under test in any direction within the shooting range, the measured speed ranges from 0 to 30 km/h, and the speed error is ±0.1 m/s , the body axis direction angle deviation is between ±0.5°;

3) The video measurement device described above is easy to install and debug, easy to calibrate and high in testing efficiency.

Fig. 1 and Fig. 2 are respectively schematic diagrams of horizontal parking and vertical parking working conditions and scene ranges according to the embodiment of the present invention.

The initial position of the vehicle under test is in a static state, and the longitudinal distance from the parking space is 0.5 to 1.5 meters. By default, the parking space is searched on the right side. The size of the parking space (length x width) is 6 x 2.5 meters.

When the driver activates the automatic parking system, the system starts to search for a parking space and controls the movement of the vehicle under test. The direction pointed by the arrow is the parking trajectory of the tested vehicle, and the dashed box is the position of the tested vehicle at a certain moment in the parking process.

When the measured vehicle leaves the boundary range of the parking measurement, the vehicle is allowed to continue to move for a certain distance along the driving direction, and this distance is an effective parking space search stroke.

The search distance for parallel parking does not exceed 15 meters, and the search distance for perpendicular parking does not exceed 10 meters. If the automatic parking system is still unable to detect a parking space after exceeding the effective parking space search distance, it is determined that the automatic parking system function is invalid, and the driver needs to control the vehicle under test to return to the initial position and restart the parking test action. The range of the horizontal parking scene is 30×8 meters, and the range of the vertical parking scene is 16×13 meters. In order to ensure that the video measurement system can take into account the two test scenarios without disassembly and assembly, the union of the two ranges is taken, namely 30 x 13 meters.

FIG. 3 is a compositional structure of an automatic parking video measurement device according to an embodiment of the present invention.

First, fix and install the four cameras directly above the parking test area at the same height through the bracket unit 1, and distribute them at equal intervals along the direction parallel to the driving direction of the tested vehicle. Each camera shoots a part vertically downward. Aerial view of a parking scene.

In order to eliminate errors caused by installation and layout, the single bracket 1 itself has an adjustable angle device to ensure that the height from the ground and verticality of the camera are within the allowable range of errors.

The video signal acquisition module is installed in the non-shooting area, synchronously collects the video streams shot by each camera, and outputs them to the mobile workstation and storage, the storage is a local hard disk or USB flash memory.

After the shooting was completed, the testers used the panoramic stitching software Autopano Video Pro to stitch and fuse each frame recorded by different cameras into a high-definition panoramic video with a wide viewing angle range, small image distortion, high frame synchronization rate, and no obvious color difference between light and dark.

Finally, the testers establish a reference scale based on the reference objects in the video, analyze the experimental video image through the motion analysis software Tracker, capture and track the pose information of the moving object, and establish the kinematic model of the vehicle under test, so that in a limited space range Internally measure the motion trajectory, linear/angular velocity, and linear/angular acceleration of the measured vehicle in the global coordinate system and relative coordinate system during the parking process.

FIG. 4 is a workflow of the video measuring device applied to the automatic parking system according to the embodiment of the present invention.

First of all, before the automatic parking video measurement starts, a series of preparatory work should be carried out, mainly including: Step 1: The software and hardware configuration of the video signal acquisition module and the mobile workstation. The specific configuration process is as follows:

1. Connect 4 POE network cables to the camera, and the camera is powered and signal transmitted by the POE network cable;

2. Connect power supply to the video signal acquisition system (220V civilian AC power supply or DC battery inverter to AC power supply);

3. Turn on the camera and pre-collect the video signal of the 4-way network camera, and store it as video material.

Mobile workstation configuration steps:

1. Start up and log in to the operating system;

2. Open the panoramic video fusion software;

3. Put the multi-channel video material (pre-acquisition) captured by the video signal acquisition system into the material folder;

4. Import and synchronize video materials in the panoramic video fusion software;

5. Configure multi-channel video image fusion parameters and preview the fusion effect.

Step 2: Adjust the position and angle of the camera fixed on the bracket 1, adjust the internal and external parameters of the camera lens, image preprocessing for scene fusion and calibration of overlapping areas, etc.

At the same time, in order to determine the position and size relationship of the feature points in the shooting picture, on-site measurement of the reference point should be carried out, and the reference size calibration of the shooting picture of a single group of cameras should be completed;

Step 3: Configuration of motion analysis software in the computer, the specific steps are:

1. Import the fused and spliced video material;

2. Set the start frame, end frame, and video file refresh frequency;

3. Set the correction rod and coordinate axis: the adjustable correction rod will appear on the video screen, move the mouse to both ends of the correction rod, and adjust the correction rod to the parameters in the video by dragging the end position of the correction rod.

Step 4: Before the automatic parking test starts, start the camera to record the parking process synchronously, and the image information is output to the mobile workstation through the video signal acquisition system for local storage. After the parking test is over, the workstation performs post-processing on the videos captured by the four cameras, eliminates overlapping areas and adjusts the imaging effect, completes the splicing and fusion of the videos, and obtains the plane parking measurement images of the entire test scene.

Step 5: The workstation extracts the key information of the parking measurement image through the identification of the vehicle's geometric center point, edge point, geometric center line, and parking space line, and analyzes and calculates the distance between the feature point and point-to-point and point-to-line. The position, velocity, acceleration and angle change relationship are calculated to obtain the measurement data of the parking movement, and then the function and performance of the automatic parking system are evaluated.

Fig. 5 is a schematic diagram of the shooting height of the camera and the size of the scene according to the embodiment of the present invention. Assuming that the shooting height of the camera from the ground is L, and the size (width * height) of the shooting scene is W * H, it can be determined by calculation or actual measurement that W, The specific value of H.

Figure 6 is a schematic diagram of image splicing and fusion according to an embodiment of the present invention. It is known that the size of a single group of images (width×height) is W×H, and since the cameras are arranged in parallel at equal intervals, there is a fixed image overlapping area between each group of images , C represents the width of the overlapping region, and the size of the stitched image (total length×height) can be expressed as S×H. In the measurement process, 4 groups of parallel and equidistant D (unit: meter) distributions are selected, the size of the photosensitive element is 1/2 inch, the focal length is f (unit: mm), and the shooting (height × width) resolution is 1024 × 768 (unit: pixels) with a refresh rate of 25 frames per second.

According to the imaging principle, the picture aspect ratio R is:

The installation height is:

Select a standard fixed-focus lens f=2.8 (mm) to shoot a picture with a height of H=13 (m), then the installation height of the camera L=5.72 (m), and the shooting width W=9.8 (m)

The total width S of the spliced image is:

S=4×W-3×C

In order to capture a picture with a total length of S=30(m), the width of the overlapping area of the picture is C=3.07(m), which accounts for 31.3% of the scene area shot by a single camera, ensuring sufficient picture overlap, thereby ensuring the effect of visual fusion. The distance D=6.73(m) between each camera and the midpoint of the shooting picture and the midpoint of the adjacent picture.

The measurement accuracy of the video analysis method depends on the display accuracy of the image after video fusion. Its resolution is 2363×1024 (unit: pixel), and the diagonal line of each pixel corresponds to the size of the actual scene is 1.8 cm, that is, the position error guarantee Between ±0.02 meters. The video refresh rate is 25 frames per second, and the time interval between two frames is 0.04 seconds. Taking the position of the reference point every 5 frames to calculate the (average) motion speed, the maximum speed error (absolute value) caused by the position error is 0.09 m/s, that is, the speed error is guaranteed to be between ±0.1 m/s. Generally speaking, the width of the central axis of the vehicle body under test is not less than 4.5 meters, calculated according to the distance between the reference points at both ends of the central axis is equal to 4.5 meters, and the angular error (absolute value) caused by the position error of the two ends is at most 0.46 °, that is, the deviation of the direction angle of the axis of the vehicle body is guaranteed to be within ±0.5°.

The vehicle under test must be equipped with a fully automatic or semi-automatic parking system, preferably equipped with a fully automatic parking system, that is, no manual control is required during parking, and the automatic parking system automatically completes steering, gear shifting, braking, accelerator and parking. handbrake etc. The light intensity of the parking site should exceed 100 lux, and the camera is fixed on the bracket. In order to ensure the effect of video splicing and fusion and the accuracy of tracking measurement, the distance error of the bracket placement position should not exceed ±0.02 meters, and the vertical angle error should be within ±0.02 meters. Within 0.5°, the brightness and color difference of images between different groups of cameras is less than 10%. In addition, the mobile workstation should support large-flow data transmission work, and the hard disk should have storage space for writing more than 2 hours of video length. The results of image splicing and fusion need to be displayed on a high-resolution screen synchronously, which is convenient for the debugging of the camera installation position in the early stage and the playback and processing of the parking video in the later stage.

The above descriptions are only preferred embodiments of the present utility model, and are not intended to limit the present utility model. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present utility model shall be included in the Within the protection scope of the present utility model.

Claims (7)

1. a kind of video grammetry device applied to automated parking system, it is characterised in that: including bracket group, several video cameras, POE cable, video signal collection module, memory and mobile workstation, the video camera are respectively connected to electricity by POE cable Source, video signal collection module, the video signal collection module are connected separately to memory and carry out data storage, connection Data processing is carried out to mobile workstation, it is described if the bracket group includes the identical single support of stem structure and several connecting rods Single support includes that pedestal, connecting rod, No.1 turntable, overhanging cantilever, cradling piece, No. two turntables and connector, the pedestal are Triangle base, three angles of pedestal pass through the connecting rod respectively and are connected to the No.1 turntable, the No.1 turntable The connector is fixedly mounted in top, and the first end of the overhanging cantilever, cradling piece is respectively connected to above the connector, The second end of the cradling piece installs No. two turntables, and No. two turntables are servo turntable, and the servo turntable signal connects It is connected to the controller of external electric-control system, No. two turntables is controlled and does pitching movement, an institute is installed on each No. two turntables Video camera is stated, the cradling piece of each single support is parallel to each other, and equidistantly distributed, passes through company between two adjacent cradling pieces Bar is fixedly connected.

2. a kind of video grammetry device applied to automated parking system according to claim 1, it is characterised in that: described The quantity of single support is 4 groups, and the quantity of connecting rod is 3, and the linkage of 4 single supports is realized by 3 connecting rods.

3. a kind of video grammetry device applied to automated parking system according to claim 1, it is characterised in that: described The both ends of overhanging cantilever are equipped with drawstring.

4. a kind of video grammetry device applied to automated parking system according to claim 1, it is characterised in that: described Video signal collection module is 7130 video frequency collection card of model.

5. a kind of video grammetry device applied to automated parking system according to claim 1, it is characterised in that: described Memory is local hard drive or USB flash memory.

6. a kind of video grammetry device applied to automated parking system according to claim 1, it is characterised in that: described Mobile workstation is computer, and multi-channel video capturing software is installed on the computer.

7. a kind of video grammetry device applied to automated parking system according to claim 1, it is characterised in that: described Power supply is that the civilian Alternating Current Power Supply of 220V or dc-battery inversion turn Alternating Current Power Supply.