CN112356831B - Warehouse location tracking method and warehouse location tracking system - Google Patents
Warehouse location tracking method and warehouse location tracking system Download PDFInfo
- Publication number
- CN112356831B CN112356831B CN202110035749.XA CN202110035749A CN112356831B CN 112356831 B CN112356831 B CN 112356831B CN 202110035749 A CN202110035749 A CN 202110035749A CN 112356831 B CN112356831 B CN 112356831B
- Authority
- CN
- China
- Prior art keywords
- library
- class
- information
- positions
- bin
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000007613 environmental effect Effects 0.000 claims abstract description 18
- 230000000007 visual effect Effects 0.000 claims description 13
- 238000001514 detection method Methods 0.000 description 7
- 238000013135 deep learning Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000008447 perception Effects 0.000 description 4
- 239000002131 composite material Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/06—Automatic manoeuvring for parking
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The application discloses a storehouse position tracking method and a storehouse position tracking system, wherein, the storehouse position tracking method divides the storehouse position in a storehouse position container into a first kind of storehouse position and a second kind of storehouse position based on the environmental image information of a current frame in the storehouse position tracking process, updates the first kind of storehouse position depending on the environmental image information, updates the second kind of storehouse position depending on the acquired wheel speed information, and realizes the purpose of continuous tracking when the storehouse position needing tracking is not in the environmental image information.
Description
Technical Field
The present disclosure relates to the field of vehicle engineering technologies, and in particular, to a parking space tracking method and a parking space tracking system.
Background
With the rapid development of the automatic driving technology in recent years, enterprises in the industry are trying to develop a car parking system for the valet to promote the commercialization of the automatic driving technology.
The existing commercial car parking systems (or called automatic parking systems) are all automatic parking systems, and belong to the field of ADAS (Advanced Driving Assistance System). In the automatic parking process, the garage (or parking space) needs to be continuously tracked, so that the automatic parking system can perform automatic parking operation according to the tracked garage information.
However, most of the existing warehouse location tracking methods perform warehouse location detection based on vision, and when a warehouse location to be tracked appears outside a picture, the warehouse location detection cannot be performed, so that automatic parking cannot be performed.
Disclosure of Invention
In order to solve the technical problem, the application provides a library position tracking method and a library position tracking system, so as to achieve the purpose of continuously tracking when a library position to be tracked is not in environment image information.
In order to achieve the technical purpose, the embodiment of the application provides the following technical scheme:
a depot tracking method for tracking a depot of an environment in which a motor vehicle is located during automatic parking, the motor vehicle including visual information acquisition means for acquiring environmental image information, the depot tracking method comprising:
when the automatic parking system of the motor vehicle is started, a storage space container is initialized, and storage space information of at least one storage space is stored in the storage space container;
acquiring wheel speed information of the motor vehicle;
analyzing the environment image information based on the current frame, and dividing the library positions in the library position container into a first class library position and a second class library position, wherein the first class library position comprises the library positions visible in the environment image information, and the second class library position comprises the library positions invisible in the environment image information;
and updating the first class of library positions based on the environment image information, and updating the second class of library positions based on the wheel speed information and the initial positions of the second class of library positions to obtain an updated library position container.
Optionally, the method further includes:
updating an initial position of a third class of bin bits based on the ambient image information of the current frame, the third class of bin bits including bin bits that are the first class of bin bits in the current frame ambient image information and that are the second class of bin bits in the history frame ambient image information.
Optionally, the initial position of the second-class library bit includes position information of the second-class library bit in the environment image information of a historical latest frame;
the initial position of the third class of bin bits includes position information of the third class of bin bits in the environmental image information of a historical last frame.
Optionally, the updating the second class library bits based on the wheel speed information and the initial position of the second class library bits includes:
acquiring initial coordinate information of the library position corner points of the second class library positions in a global coordinate system based on the initial positions of the second class library positions;
determining position information and attitude information of the motor vehicle in the environment image information of the current frame based on the wheel speed information;
and according to the position information and the attitude information of the motor vehicle in the environment image information of the current frame, converting the initial coordinate information of the library site corner points of the second class of library sites under a global coordinate system into the self-vehicle coordinate system, and converting the initial coordinate information of the library site corner points of the second class of library sites under the global coordinate system into the image coordinate system so as to update the second class of library sites.
Optionally, the obtaining of the initial coordinate information of the library site corner point of the second class of library sites in the global coordinate system based on the initial position of the second class of library sites includes:
acquiring coordinates of corner points of the second-class library positions in an image coordinate system based on the initial positions of the second-class library positions;
and converting the coordinates of the corner points of the second-class library positions under the image coordinate system to the self-vehicle coordinate system, and converting the coordinates of the corner points of the second-class library positions under the self-vehicle coordinate system to the global coordinate system to obtain the initial coordinate information of the library position corner points of the second-class library positions under the global coordinate system.
A depot tracking system for tracking a depot of an environment in which a motor vehicle is located during an automatic parking process, the motor vehicle including visual information acquisition means for acquiring environmental image information, the depot tracking system comprising:
the system comprises a storage space container establishing module, a storage space storage module and a storage space storage module, wherein the storage space container establishing module is used for initializing a storage space container when an automatic parking system of the motor vehicle is started, and the storage space container stores the storage space information of at least one storage space;
a wheel speed information acquisition module for acquiring wheel speed information of the motor vehicle;
a library position classification module, configured to analyze the environment image information based on the current frame, and classify library positions in the library position container into a first class library position and a second class library position, where the first class library position includes a library position visible in the environment image information, and the second class library position includes a library position invisible in the environment image information;
and the bin tracking module is used for updating the first type of bin based on the environment image information and updating the second type of bin based on the wheel speed information and the initial position of the second type of bin to obtain an updated bin container.
Optionally, the method further includes:
and the initial position updating module is used for updating the initial position of a third class of library positions based on the environment image information of the current frame, wherein the third class of library positions comprises the library positions which are the first class of library positions in the environment image information of the current frame and are the second class of library positions in the environment image information of the historical frame.
Optionally, the initial position of the second-class library bit includes position information of the second-class library bit in the environment image information of a historical latest frame;
the initial position of the third class of bin bits includes position information of the third class of bin bits in the environmental image information of a historical last frame.
Optionally, the process of updating the second class library position by the library position tracking module based on the wheel speed information and the initial position of the second class library position specifically includes:
acquiring initial coordinate information of the library position corner points of the second class library positions in a global coordinate system based on the initial positions of the second class library positions;
determining position information and attitude information of the motor vehicle in the environment image information of the current frame based on the wheel speed information;
and according to the position information and the attitude information of the motor vehicle in the environment image information of the current frame, converting the initial coordinate information of the library site corner points of the second class of library sites under a global coordinate system into the self-vehicle coordinate system, and converting the initial coordinate information of the library site corner points of the second class of library sites under the global coordinate system into the image coordinate system so as to update the second class of library sites.
Optionally, the process of the library position tracking module acquiring, based on the initial position of the second-class library position, initial coordinate information of the library position corner point of the second-class library position in the global coordinate system specifically includes:
acquiring coordinates of corner points of the second-class library positions in an image coordinate system based on the initial positions of the second-class library positions;
and converting the coordinates of the corner points of the second-class library positions under the image coordinate system to the self-vehicle coordinate system, and converting the coordinates of the corner points of the second-class library positions under the self-vehicle coordinate system to the global coordinate system to obtain the initial coordinate information of the library position corner points of the second-class library positions under the global coordinate system.
It can be seen from the foregoing technical solutions that the embodiments of the present application provide a library position tracking method and a library position tracking system, where in a library position tracking process, the library positions in a library position container are divided into first class library positions and second class library positions based on environmental image information of a current frame, the first class library positions are updated depending on the environmental image information, and the second class library positions are updated depending on acquired wheel speed information, so as to achieve a purpose of continuous tracking when the library positions to be tracked are not in the environmental image information.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flowchart of a method for tracking library bits according to an embodiment of the present application;
fig. 2 is a schematic diagram of a library bit and the environment image information according to an embodiment of the present application;
FIG. 3 is a schematic diagram illustrating a transformation of an image coordinate system to a host vehicle coordinate system according to an embodiment of the present application;
FIG. 4 is a schematic flow chart illustrating a method for tracking library bits according to another embodiment of the present application;
FIG. 5 is a flow chart illustrating a method for tracking library bits according to another embodiment of the present application;
FIG. 6 is a flowchart illustrating a method for bin tracking according to yet another embodiment of the present application;
fig. 7 and fig. 8 are schematic experimental diagrams of the library location tracking method provided in the embodiment of the present application.
Detailed Description
As described in the background art, the prior art library bit tracking method includes a conventional geometric library bit perception scheme, a library bit perception scheme based on deep learning, and a composite perception scheme combining the two schemes. However, various false detections and missed detections are more in the conventional geometric scheme, the library bit sensing scheme based on the deep learning causes the conditions of library bit jitter and library bit flicker, and the composite sensing scheme is better than the conventional and deep learning schemes, but still has the conditions of jitter and flicker.
In addition, in any scheme in the prior art, the perception of the library position requires that the library position appears in a spliced picture acquired by the motor vehicle as a premise, otherwise, the library position to be tracked cannot be detected in the current frame image, and if the library position is out of the picture, the vehicle cannot be automatically parked.
In order to solve the problem, an embodiment of the present application provides a parking space tracking method for tracking a parking space of an environment where a motor vehicle is located in an automatic parking process, where the motor vehicle includes a visual information acquisition device for acquiring environment image information, and the parking space tracking method includes:
when the automatic parking system of the motor vehicle is started, a storage space container is initialized, and storage space information of at least one storage space is stored in the storage space container;
acquiring wheel speed information of the motor vehicle;
analyzing the environment image information based on the current frame, and dividing the library positions in the library position container into a first class library position and a second class library position, wherein the first class library position comprises the library positions visible in the environment image information, and the second class library position comprises the library positions invisible in the environment image information;
and updating the first class of library positions based on the environment image information, and updating the second class of library positions based on the wheel speed information and the initial positions of the second class of library positions to obtain an updated library position container.
In the library position tracking method, the library positions in the library position container are divided into a first class library position and a second class library position based on the environment image information of the current frame, the first class library position is updated by depending on the environment image information, the second class library position is updated by depending on the acquired wheel speed information, and the aim of continuous tracking can be achieved when the library position to be tracked is not in the environment image information.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. 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 application.
The embodiment of the application provides a parking space tracking method, which is used for tracking a parking space of an environment where a motor vehicle is located in an automatic parking process, wherein the motor vehicle comprises a visual information acquisition device, the visual information acquisition device is used for acquiring environment image information, and as shown in fig. 1, the parking space tracking method comprises the following steps:
s101: when the automatic parking system of the motor vehicle is started, a storage space container is initialized, and storage space information of at least one storage space is stored in the storage space container;
s102: acquiring wheel speed information of the motor vehicle;
s103: analyzing the environment image information based on the current frame, and dividing the library positions in the library position container into a first class library position and a second class library position, wherein the first class library position comprises the library positions visible in the environment image information, and the second class library position comprises the library positions invisible in the environment image information;
s104: and updating the first class of library positions based on the environment image information, and updating the second class of library positions based on the wheel speed information and the initial positions of the second class of library positions to obtain an updated library position container.
In step S101, initializing the storage space container means that when the automatic parking system is started, the storage space is searched based on the visual information acquisition device, and the searched storage space information such as the corner coordinates of the storage space, the storage space ID, and the like is stored in the storage space container, so that the storage space container is initialized.
In step S102, the wheel speed information may be obtained by reading from various controllers of the motor vehicle, or by using a sensor, which is not limited in this application.
In step S103, the current frame is the current time or the latest frame acquired by the visual information acquiring apparatus. The method for analyzing the environmental image information of the current frame may be a relatively mature image processing technology or a deep learning detection method, so as to obtain information such as corner coordinates of the bin and a bin ID from the environmental image information.
In the library tracking process, a three-dimensional coordinate system, which is an image coordinate system, a self-vehicle coordinate system and a global coordinate system, is generally required.
Referring to fig. 2, fig. 2 shows a schematic diagram of a library site and the environment image information, and the visual information acquisition device of the motor vehicle generally comprises a plurality of cameras distributed on a vehicle body, and images acquired by the cameras are spliced to obtain the environment image information.
The image coordinate system takes pixels as units, the origin is the upper left corner of the environment image information, the right side of the image is a u-axis, and the downward side is a v-axis.
The self-vehicle coordinate system takes the center of the rear axle of the motor vehicle as an origin, and a right-hand coordinate system X-Y-Z, X, Y, Z established in the positive direction by taking the direction of the head of the motor vehicle as the Y axis respectively represents the horizontal axis, the vertical axis and the vertical axis of the right-hand coordinate system.
The global coordinate system is a self-vehicle coordinate system established by the position of the motor vehicle when the automatic parking system is started.
In the process of converting the image coordinate system to the host vehicle coordinate system, it is necessary to determine the coordinate according to the size and the magnification of the environment image information, and referring to fig. 3, it is described by taking an example that the size of the environment image information is 950 × 675 (width × height) and the magnification is 0.5 (one image coordinate is 2cm of the world coordinate), and when the motor vehicle is at the center position of the environment image information, the vehicle rear axle center coordinate can be obtained by the size and the magnification of the environment image information and actual measurement, and the coordinate in the image coordinate system can be converted into the coordinate in the host vehicle coordinate system by substituting the following formula.
X_w = u* 2 - rearCenter.x；
Y_w = rearCenter.y - v * 2；
Wherein X _ w and Y _ w respectively represent X-axis coordinates and Y-axis coordinates in the own vehicle coordinate system, u and v respectively represent u-axis coordinates and v-axis coordinates in the image coordinate system, and rearcenter. X and rearcenter. Y respectively represent u-axis coordinates and v-axis coordinates of the rear axle center of the motor vehicle in the image coordinate system.
In step S103, when the second-class library is updated based on the wheel speed information and the initial position of the second-class library, the wheel speed information generally serves to obtain the motion state of the motor vehicle in the global coordinate system based on the wheel speed information, obtain the motion state of the motor vehicle using the wheel speed, and indirectly calculate and update the position of the library in the screen.
On the basis of the foregoing embodiment, in an embodiment of the present application, as shown in fig. 4, the library bit tracking method further includes:
s105: updating an initial position of a third class of bin bits based on the ambient image information of the current frame, the third class of bin bits including bin bits that are the first class of bin bits in the current frame ambient image information and that are the second class of bin bits in the history frame ambient image information.
Optionally, the initial position of the second-class library bit includes position information of the second-class library bit in the environment image information of a historical latest frame;
the initial position of the third class of bin bits includes position information of the third class of bin bits in the environmental image information of a historical last frame.
In the embodiment, the original visual target detection method is adopted in consideration of the condition that the wheel speed tracking has accumulated errors and the library position is not shown (namely, the first type library position). And under the condition that the library position is displayed (namely, the library position of the second type), continuously obtaining the ID of the library position and the coordinates of the angular point of the library position by adopting wheel speed tracking. The purpose in step S105 is to eliminate the accumulated error caused by the third type library position when tracking is performed by means of wheel speed information.
On the basis of the above embodiment, in another embodiment of the present application, as shown in fig. 5, the updating the second class library bit based on the wheel speed information and the initial position of the second class library bit includes:
s1041: acquiring initial coordinate information of the library position corner points of the second class library positions in a global coordinate system based on the initial positions of the second class library positions;
s1042: determining position information and attitude information of the motor vehicle in the environment image information of the current frame based on the wheel speed information;
s1043: and according to the position information and the attitude information of the motor vehicle in the environment image information of the current frame, converting the initial coordinate information of the library site corner points of the second class of library sites under a global coordinate system into the self-vehicle coordinate system, and converting the initial coordinate information of the library site corner points of the second class of library sites under the global coordinate system into the image coordinate system so as to update the second class of library sites.
Optionally, referring to fig. 6, the obtaining, based on the initial position of the second-class library bit, initial coordinate information of the library bit corner point of the second-class library bit in the global coordinate system includes:
s10411: acquiring coordinates of corner points of the second-class library positions in an image coordinate system based on the initial positions of the second-class library positions;
s10412: and converting the coordinates of the corner points of the second-class library positions under the image coordinate system to the self-vehicle coordinate system, and converting the coordinates of the corner points of the second-class library positions under the self-vehicle coordinate system to the global coordinate system to obtain the initial coordinate information of the library position corner points of the second-class library positions under the global coordinate system.
In an optional embodiment of the present application, the updating the first class library bits based on the environment image information, and the updating the second class library bits based on the wheel speed information and the initial position of the second class library bits further include:
and in the wheel speed tracking process of the second type of library positions, deleting the library position information of the second type of library positions, of which the distance between the second type of library positions and the motor vehicle exceeds the maximum threshold value, after the distance between the second type of library positions and the motor vehicle exceeds the maximum threshold value.
In this embodiment, deleting the bin information (bin corner coordinates and bin ID) of the second type of bin having an excessively large distance from the motor vehicle is advantageous for releasing the storage space in the bin container, and reducing the amount of calculation of the algorithm.
In another alternative embodiment of the present application, step S104 may be performed in two parts:
part one: there are three states for the bin state: foreground tracking, background tracking and fusion tracking are respectively carried out. Compared with foreground tracking, background tracking is weak tracking and low in tracking precision. The first module calculates the coordinates of the vehicle and the image. And then the positions with overlarge speed, overlarge change of the yaw angle of the position, the position exceeding the display range, and overlarge change of the distance between the tracking position and the detection position are set as the background, and the position exceeding the mileage range is deleted. Part one also applies kalman filtering to the global coordinates.
And part two: the newly detected bin is first calculated from the vehicle coordinates and the global coordinates. And determining whether to directly update the library bit in the library bit container or add a new library bit in the library bit container according to whether the IDs are the same and the overlapping degree.
The following experiment verifies that the library position tracking method provided by the embodiment of the present application, referring to fig. 7 and 8, in fig. 7, the library position can still be perceived under the condition that the library position (ID: 5) is blocked by a vehicle. Whereas in fig. 8, the bin bits 27, 19 and 43 are still perceptible even if they are not in the ambient image information.
The library location tracking system provided in the embodiments of the present application is described below, and the library location tracking system described below may be referred to in correspondence with the library location tracking method described above.
Correspondingly, an embodiment of the present application provides a parking space tracking system, configured to track a parking space of an environment where a motor vehicle is located in an automatic parking process, where the motor vehicle includes a visual information obtaining device, where the visual information obtaining device is configured to obtain environment image information, and the parking space tracking system includes:
the system comprises a storage space container establishing module, a storage space storage module and a storage space storage module, wherein the storage space container establishing module is used for initializing a storage space container when an automatic parking system of the motor vehicle is started, and the storage space container stores the storage space information of at least one storage space;
a wheel speed information acquisition module for acquiring wheel speed information of the motor vehicle;
a library position classification module, configured to analyze the environment image information based on the current frame, and classify library positions in the library position container into a first class library position and a second class library position, where the first class library position includes a library position visible in the environment image information, and the second class library position includes a library position invisible in the environment image information;
and the bin tracking module is used for updating the first type of bin based on the environment image information and updating the second type of bin based on the wheel speed information and the initial position of the second type of bin to obtain an updated bin container.
Optionally, the method further includes:
and the initial position updating module is used for updating the initial position of a third class of library positions based on the environment image information of the current frame, wherein the third class of library positions comprises the library positions which are the first class of library positions in the environment image information of the current frame and are the second class of library positions in the environment image information of the historical frame.
Optionally, the initial position of the second-class library bit includes position information of the second-class library bit in the environment image information of a historical latest frame;
the initial position of the third class of bin bits includes position information of the third class of bin bits in the environmental image information of a historical last frame.
Optionally, the process of updating the second class library position by the library position tracking module based on the wheel speed information and the initial position of the second class library position specifically includes:
acquiring initial coordinate information of the library position corner points of the second class library positions in a global coordinate system based on the initial positions of the second class library positions;
determining position information and attitude information of the motor vehicle in the environment image information of the current frame based on the wheel speed information;
and according to the position information and the attitude information of the motor vehicle in the environment image information of the current frame, converting the initial coordinate information of the library site corner points of the second class of library sites under a global coordinate system into the self-vehicle coordinate system, and converting the initial coordinate information of the library site corner points of the second class of library sites under the global coordinate system into the image coordinate system so as to update the second class of library sites.
Optionally, the process of the library position tracking module acquiring, based on the initial position of the second-class library position, initial coordinate information of the library position corner point of the second-class library position in the global coordinate system specifically includes:
acquiring coordinates of corner points of the second-class library positions in an image coordinate system based on the initial positions of the second-class library positions;
and converting the coordinates of the corner points of the second-class library positions under the image coordinate system to the self-vehicle coordinate system, and converting the coordinates of the corner points of the second-class library positions under the self-vehicle coordinate system to the global coordinate system to obtain the initial coordinate information of the library position corner points of the second-class library positions under the global coordinate system.
To sum up, the embodiment of the present application provides a library position tracking method and a library position tracking system, wherein, in the library position tracking process, the library position in the library position container is divided into a first class library position and a second class library position based on the environment image information of the current frame, the first class library position is updated depending on the environment image information, the second class library position is updated depending on the acquired wheel speed information, so as to achieve the purpose of continuous tracking when the library position to be tracked is not in the environment image information.
Features described in the embodiments in the present specification may be replaced with or combined with each other, each embodiment is described with a focus on differences from other embodiments, and the same and similar portions among the embodiments may be referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (4)
1. A depot tracking method for tracking a depot of an environment in which a motor vehicle is located during automatic parking, the motor vehicle including visual information acquisition means for acquiring environmental image information, the depot tracking method comprising:
when the automatic parking system of the motor vehicle is started, a storage space container is initialized, and storage space information of at least one storage space is stored in the storage space container;
acquiring wheel speed information of the motor vehicle;
analyzing the environment image information based on the current frame, and dividing the library positions in the library position container into a first class library position and a second class library position, wherein the first class library position comprises the library positions visible in the environment image information, and the second class library position comprises the library positions invisible in the environment image information;
updating the first class of library positions based on the environment image information, and updating the second class of library positions based on the wheel speed information and the initial positions of the second class of library positions to obtain an updated library position container;
further comprising:
updating the initial position of a third class of library positions based on the environment image information of the current frame, wherein the third class of library positions comprises library positions which are the first class of library positions in the environment image information of the current frame and are the second class of library positions in the environment image information of the historical frame;
the updating the second class bin bit based on the wheel speed information and the initial position of the second class bin bit comprises:
acquiring initial coordinate information of the library position corner points of the second class library positions in a global coordinate system based on the initial positions of the second class library positions;
determining position information and attitude information of the motor vehicle in the environment image information of the current frame based on the wheel speed information;
according to the position information and the attitude information of the motor vehicle in the environment image information of the current frame, converting the initial coordinate information of the bin corner points of the second class of bin positions in a global coordinate system into a self-vehicle coordinate system, and converting the initial coordinate information of the bin corner points of the second class of bin positions in the global coordinate system into an image coordinate system so as to update the second class of bin positions;
the obtaining of the initial coordinate information of the bin corner point of the second-class bin in the global coordinate system based on the initial position of the second-class bin includes:
acquiring coordinates of corner points of the second-class library positions in an image coordinate system based on the initial positions of the second-class library positions;
and converting the coordinates of the corner points of the second-class library positions under the image coordinate system to the self-vehicle coordinate system, and converting the coordinates of the corner points of the second-class library positions under the self-vehicle coordinate system to the global coordinate system to obtain the initial coordinate information of the library position corner points of the second-class library positions under the global coordinate system.
2. The method according to claim 1, wherein the initial position of the second class of bin bits comprises position information of the second class of bin bits in the environment image information of a historical last frame;
the initial position of the third class of bin bits includes position information of the third class of bin bits in the environmental image information of a historical last frame.
3. A depot tracking system for tracking a depot of an environment in which a motor vehicle is located during automatic parking, the motor vehicle including visual information acquisition means for acquiring environmental image information, the depot tracking system comprising:
the system comprises a storage space container establishing module, a storage space storage module and a storage space storage module, wherein the storage space container establishing module is used for initializing a storage space container when an automatic parking system of the motor vehicle is started, and the storage space container stores the storage space information of at least one storage space;
a wheel speed information acquisition module for acquiring wheel speed information of the motor vehicle;
a library position classification module, configured to analyze the environment image information based on the current frame, and classify library positions in the library position container into a first class library position and a second class library position, where the first class library position includes a library position visible in the environment image information, and the second class library position includes a library position invisible in the environment image information;
the bin tracking module is used for updating the first type of bin based on the environment image information and updating the second type of bin based on the wheel speed information and the initial position of the second type of bin to obtain an updated bin container;
further comprising:
the initial position updating module is used for updating the initial position of a third class of library positions based on the environment image information of the current frame, wherein the third class of library positions comprises the library positions which are the first class of library positions in the environment image information of the current frame and the library positions which are the second class of library positions in the environment image information of the historical frame;
the process of updating the second class library position by the library position tracking module based on the wheel speed information and the initial position of the second class library position specifically comprises the following steps:
acquiring initial coordinate information of the library position corner points of the second class library positions in a global coordinate system based on the initial positions of the second class library positions;
determining position information and attitude information of the motor vehicle in the environment image information of the current frame based on the wheel speed information;
according to the position information and the attitude information of the motor vehicle in the environment image information of the current frame, converting the initial coordinate information of the bin corner points of the second class of bin positions in a global coordinate system into a self-vehicle coordinate system, and converting the initial coordinate information of the bin corner points of the second class of bin positions in the global coordinate system into an image coordinate system so as to update the second class of bin positions;
the process that the library position tracking module acquires the initial coordinate information of the library position corner point of the second class library position under the global coordinate system based on the initial position of the second class library position specifically comprises the following steps:
acquiring coordinates of corner points of the second-class library positions in an image coordinate system based on the initial positions of the second-class library positions;
and converting the coordinates of the corner points of the second-class library positions under the image coordinate system to the self-vehicle coordinate system, and converting the coordinates of the corner points of the second-class library positions under the self-vehicle coordinate system to the global coordinate system to obtain the initial coordinate information of the library position corner points of the second-class library positions under the global coordinate system.
4. The system according to claim 3, wherein the initial position of the second class of library bits comprises position information of the second class of library bits in the environment image information of a historical last frame;
the initial position of the third class of bin bits includes position information of the third class of bin bits in the environmental image information of a historical last frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110035749.XA CN112356831B (en) | 2021-01-12 | 2021-01-12 | Warehouse location tracking method and warehouse location tracking system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110035749.XA CN112356831B (en) | 2021-01-12 | 2021-01-12 | Warehouse location tracking method and warehouse location tracking system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112356831A CN112356831A (en) | 2021-02-12 |
| CN112356831B true CN112356831B (en) | 2021-04-20 |
Family
ID=74534814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110035749.XA Active CN112356831B (en) | 2021-01-12 | 2021-01-12 | Warehouse location tracking method and warehouse location tracking system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112356831B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106767813A (en) * | 2016-11-29 | 2017-05-31 | 西华大学 | Parking navigation method and system based on mobile terminal |
| CN109299686A (en) * | 2018-09-14 | 2019-02-01 | 深圳市灵动飞扬科技有限公司 | A kind of parking stall recognition methods, device, equipment and medium |
| CN109443348A (en) * | 2018-09-25 | 2019-03-08 | 同济大学 | It is a kind of based on the underground garage warehouse compartment tracking for looking around vision and inertial navigation fusion |
| CN110070724A (en) * | 2018-01-24 | 2019-07-30 | 北京英泰智科技股份有限公司 | A kind of video monitoring method, device, video camera and image information supervisory systems |
| WO2019204296A1 (en) * | 2018-04-16 | 2019-10-24 | Ohio University | Obstacle avoidance guidance for ground vehicles |
| CN112037265A (en) * | 2020-11-04 | 2020-12-04 | 天津天瞳威势电子科技有限公司 | Library bit tracking method and device |
-
2021
- 2021-01-12 CN CN202110035749.XA patent/CN112356831B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106767813A (en) * | 2016-11-29 | 2017-05-31 | 西华大学 | Parking navigation method and system based on mobile terminal |
| CN110070724A (en) * | 2018-01-24 | 2019-07-30 | 北京英泰智科技股份有限公司 | A kind of video monitoring method, device, video camera and image information supervisory systems |
| WO2019204296A1 (en) * | 2018-04-16 | 2019-10-24 | Ohio University | Obstacle avoidance guidance for ground vehicles |
| CN109299686A (en) * | 2018-09-14 | 2019-02-01 | 深圳市灵动飞扬科技有限公司 | A kind of parking stall recognition methods, device, equipment and medium |
| CN109443348A (en) * | 2018-09-25 | 2019-03-08 | 同济大学 | It is a kind of based on the underground garage warehouse compartment tracking for looking around vision and inertial navigation fusion |
| CN112037265A (en) * | 2020-11-04 | 2020-12-04 | 天津天瞳威势电子科技有限公司 | Library bit tracking method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112356831A (en) | 2021-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11556744B1 (en) | Auto labeler | |
| JP4052650B2 (en) | Obstacle detection device, method and program | |
| CN103679119B (en) | Self adaptation slope road detection method and device | |
| US20200160561A1 (en) | Vehicle-mounted camera pose estimation method, apparatus, and system, and electronic device | |
| JP7036400B2 (en) | Vehicle position estimation device, vehicle position estimation method, and vehicle position estimation program | |
| CN110678872A (en) | Direct vehicle detection as 3D bounding box by using neural network image processing | |
| JP4957807B2 (en) | Moving object detection apparatus and moving object detection program | |
| US20130222589A1 (en) | Single-camera distance estimation | |
| CN109871732B (en) | Parking grid identification system and method thereof | |
| CN108367710B (en) | Bird's-eye view image generation device, bird's-eye view image generation system, and storage medium | |
| CN105405319A (en) | Approaching object detection apparatus for a vehicle and approaching object detection method for the same | |
| CN108197590B (en) | Pavement detection method, device, terminal and storage medium | |
| JP2021117048A (en) | Change point detector and map information delivery system | |
| CN114550042A (en) | Road vanishing point extraction method, vehicle-mounted sensor calibration method and device | |
| CN112193241A (en) | Automatic parking method | |
| CN108376384B (en) | Method and device for correcting disparity map and storage medium | |
| JP5086824B2 (en) | TRACKING DEVICE AND TRACKING METHOD | |
| CN112356831B (en) | Warehouse location tracking method and warehouse location tracking system | |
| JP3890928B2 (en) | Partition line recognition device | |
| CN111144415B (en) | Detection method for tiny pedestrian target | |
| JPH11345392A (en) | Device and method for detecting obstacle | |
| JP4106163B2 (en) | Obstacle detection apparatus and method | |
| CN111192290A (en) | Blocking processing method for pedestrian image detection | |
| JP2022123153A (en) | Stereo image processing device and stereo image processing method | |
| JP2004251886A (en) | Device for detecting surrounding object |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Storage Location Tracking Method and System Effective date of registration: 20231017 Granted publication date: 20210420 Pledgee: Bank of Beijing Limited by Share Ltd. Tianjin branch Pledgor: TIANJIN TIANTONG WEISHI ELECTRONIC TECHNOLOGY Co.,Ltd. Registration number: Y2023120000086 |