CN114454872A - Parking system and parking method - Google Patents
Parking system and parking method Download PDFInfo
- Publication number
- CN114454872A CN114454872A CN202011245514.5A CN202011245514A CN114454872A CN 114454872 A CN114454872 A CN 114454872A CN 202011245514 A CN202011245514 A CN 202011245514A CN 114454872 A CN114454872 A CN 114454872A
- Authority
- CN
- China
- Prior art keywords
- parking
- algorithm
- detection
- parking space
- obstacle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000001514 detection method Methods 0.000 claims abstract description 133
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 238000005259 measurement Methods 0.000 claims abstract description 10
- 230000000007 visual effect Effects 0.000 claims description 18
- 230000004927 fusion Effects 0.000 claims description 14
- 230000001133 acceleration Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 238000013135 deep learning Methods 0.000 claims description 9
- 230000003993 interaction Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000003708 edge detection Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 5
- 238000012216 screening Methods 0.000 description 5
- 230000004888 barrier function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001360 synchronised effect Effects 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
-
- 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
- B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
- B60W2420/54—Audio sensitive means, e.g. ultrasound
-
- 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
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/50—Barriers
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a parking system and a parking method. The parking system includes: a sensor unit including a camera, an ultrasonic radar, and an inertial measurement unit; a parking control unit configured to: receiving a signal from the sensor unit and pre-processing the received signal; performing obstacle detection and parking space detection based on the preprocessed signals to obtain obstacle information and parking space information; planning a parking path and a target vehicle speed based on the target parking space and the obtained obstacle information; generating a parking control instruction based on the parking path, the current steering angle, the target vehicle speed and the current vehicle speed; and an execution unit configured to execute a parking operation based on the parking control instruction from the parking control unit.
Description
Technical Field
The present invention relates to the field of object localization, and more particularly to a parking system and a parking method.
Background
With the rapid development of economy in China, the quantity of automobiles is increased, but the number of parking lots is small, so that the problem of difficulty and difficulty in parking is increasingly shown. At present, many vehicles start to be equipped with a parking auxiliary system for auxiliary parking, parking prompt, early warning and the like are mostly carried out through a backing image, the parking operation needs to be finished manually, and the problem of difficult parking cannot be changed substantially, so that the development of a full-automatic parking system to replace manual parking is an urgent need at present.
The automatic parking technology is mainly divided into two types. The first type is automatic parking based on an ultrasonic sensor, the technology is relatively mature, but the ultrasonic sensor can only detect obstacles and vehicles, and automatic parking cannot be realized if no vehicle exists on two sides of a parking space, so that the problems of detection blind areas, obstacle interference and the like exist, and the parking efficiency is low. The second is an automatic parking technology based on a camera sensor, which mostly adopts a traditional visual algorithm to detect the parking space, and because the parking space is greatly influenced by environmental factors such as illumination conditions, shadow shielding and the like, and the distance of an obstacle cannot be accurately identified, the requirement of accurate automatic parking cannot be realized.
Disclosure of Invention
Therefore, a high-precision parking system is needed to improve the parking space detection and obstacle detection precision, so as to realize the automatic parking function in a complex scene.
To achieve one or more of the above objects, the present invention provides the following technical solutions.
According to a first aspect of the present invention, there is provided a parking system comprising: a sensor unit including a camera, an ultrasonic radar, and an inertial measurement unit; a parking control unit configured to: receiving a signal from the sensor unit and pre-processing the received signal; performing obstacle detection and parking space detection based on the preprocessed signals to obtain obstacle information and parking space information; planning a parking path and a target vehicle speed based on the target parking space and the obtained obstacle information; generating a parking control instruction based on the parking path, the current steering angle, the target vehicle speed and the current vehicle speed; and an execution unit configured to execute a parking operation based on the parking control instruction from the parking control unit.
According to an embodiment of the present invention, the parking system further includes a human-machine interface interaction unit configured to interact with the parking control unit by displaying a parking image and alternative parking spaces.
The parking system according to an embodiment of the invention or any of the above embodiments, wherein the parking control unit further includes: a sensor data pre-processing module configured to receive signals from the sensor unit and pre-process the received signals; the parking space detection module is configured to perform parking space detection based on the preprocessed signals so as to obtain parking space information; an obstacle detection module configured to perform obstacle detection based on the preprocessed signals to obtain obstacle information; the algorithm fusion module is configured to fuse a parking space detection algorithm in the parking space detection module and an obstacle detection algorithm in the obstacle detection module so as to screen out effective parking spaces and eliminate occupied parking spaces, and therefore available parking spaces are obtained; a planning and decision module configured to plan a parking path and a target vehicle speed based on the target parking space and the obtained obstacle information; and a control algorithm module configured to include a lateral control algorithm and a longitudinal control algorithm, wherein the lateral control algorithm is configured to generate a steering angle control command based on the parking path and a current steering angle, and the longitudinal control algorithm is configured to generate a gear control command and an acceleration or braking command based on a current vehicle speed and the target vehicle speed.
The parking system according to an embodiment of the invention or any of the above embodiments, wherein the parking space detection module is configured to perform one or more of the following: the traditional vision algorithm is used for carrying out image graying, edge detection and parking space line detection on the original image from the camera; a deep learning algorithm for detection of vehicle location points in the image by a neural network trained via a plurality of vehicle location data sets; and an ultrasonic detection algorithm for identifying the vacant parking spaces by detecting vehicles or obstacles on the parking spaces.
The parking system according to an embodiment of the invention or any of the above embodiments, wherein the obstacle detection module is configured to perform one or more of: a visual obstacle detection algorithm for vehicle and pedestrian detection by designing their characterizers and classifiers; and an ultrasonic obstacle detection algorithm for detecting an obstacle using a signal from the ultrasonic radar.
The parking system of one or any of the above embodiments, wherein the planning and decision module is configured to perform one or more of the following: the map building and positioning algorithm is used for building a map by taking the vehicle center as a coordinate system based on the vehicle attitude, the position information and the current vehicle speed so as to position the vehicle in the map and the available parking space obtained by the algorithm fusion module; and the planning and decision algorithm is used for planning a parking path and a parking speed based on the target parking space and the obstacle information and sending the parking path and the parking speed to the control algorithm module.
According to a second aspect of the present invention, there is provided a vehicle comprising a parking system as described above.
According to a third aspect of the present invention, there is provided a parking method comprising: receiving a signal from the sensor unit and pre-processing the received signal; performing obstacle detection and parking space detection based on the preprocessed signals to obtain obstacle information and parking space information; planning a parking path and a target vehicle speed based on the target parking space and the obtained obstacle information; generating a parking control instruction based on the parking path, the current steering angle, the target vehicle speed and the current vehicle speed; and executing a parking operation based on the parking control instruction.
According to a fourth aspect of the present invention, there is provided a computer apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the parking method according to the third aspect of the present invention when executing the program.
According to a fifth aspect of the present invention, there is provided a computer storage medium having a computer program stored thereon, characterized in that the program is executable by a computer to implement the steps of the parking method according to the third aspect of the present invention.
Drawings
The above and/or other aspects and advantages of the present invention will become more apparent and more readily appreciated from the following description of the various aspects taken in conjunction with the accompanying drawings, in which like or similar elements are designated with like reference numerals. In the drawings:
fig. 1 is a simplified block diagram of a parking system according to a first embodiment of the first aspect of the present invention.
Fig. 2 is a system block diagram of a parking system according to a first embodiment of the first aspect of the present invention.
Fig. 3 is a flowchart of a parking method according to an embodiment of the third aspect of the present invention.
Fig. 4 is a block diagram of a computer device for carrying out the parking method according to the invention according to a fourth aspect of the invention.
Detailed Description
In this specification, the invention is described more fully with reference to the accompanying drawings, in which exemplary embodiments of the invention are shown. This invention may, however, be embodied in different forms and should not be construed as limited to the embodiments set forth herein. The embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Words such as "comprising" and "comprises" mean that, in addition to having elements or steps which are directly and explicitly stated in the description, the solution of the invention does not exclude other elements or steps which are not directly or explicitly stated. Terms such as "first" and "second" do not denote an order of the elements in time, space, size, etc., but rather are used to distinguish one element from another.
The present invention is described below with reference to block diagrams of apparatuses and devices according to embodiments of the invention.
Fig. 1 is a simplified block diagram of a parking system according to a first embodiment of the first aspect of the present invention. Parking system 10 includes a sensor unit 110, a parking control unit 120, an execution unit 130, and a human interface interaction unit 140.
The sensor unit 110 includes a camera, an ultrasonic radar, and an inertial measurement unit. As an example, the sensor unit 110 may include 4 look-around fisheye cameras, 12 ultrasonic radars, and inertial measurement unit(s). Optionally, a panoramic fisheye camera is additionally arranged on each of the left side, the right side, the front side and the rear side of the vehicle, and a video signal is input to form a panoramic image for a detection algorithm to perform parking space detection and obstacle detection. Optionally, the inertia measurement unit may output information such as a vehicle position and a vehicle posture, so as to be used for vehicle positioning and vehicle space mapping, and facilitate vehicle space tracking.
The parking control unit 120 is configured to receive signals from the sensor unit 110 and to preprocess the received signals; performing obstacle detection and parking space detection based on the preprocessed signals to obtain obstacle information and parking space information; planning a parking path and a target vehicle speed based on the target parking space and the obtained obstacle information; and generating a parking control instruction based on the parking path, the current steering angle, the target vehicle speed and the current vehicle speed. Optionally, the parking control unit 120 further includes: a sensor data pre-processing module configured to receive signals from the sensor unit and pre-process the received signals; the parking space detection module is configured to perform parking space detection based on the preprocessed signals so as to obtain parking space information; an obstacle detection module configured to perform obstacle detection based on the preprocessed signals to obtain obstacle information; the algorithm fusion module is configured to fuse a parking space detection algorithm in the parking space detection module and an obstacle detection algorithm in the obstacle detection module so as to screen out effective parking spaces and eliminate occupied parking spaces, and therefore available parking spaces are obtained; a planning and decision module configured to plan a parking path and a target vehicle speed based on the target parking space and the obtained obstacle information; and a control algorithm module configured to include a lateral control algorithm and a longitudinal control algorithm, wherein the lateral control algorithm is configured to generate a steering angle control command based on the parking path and a current steering angle, and the longitudinal control algorithm is configured to generate a gear control command and an acceleration or braking command based on a current vehicle speed and the target vehicle speed. The above-described modules are described in further detail in fig. 2.
The execution unit 130 is configured to execute a parking operation based on the parking control instruction from the parking control unit 120. Alternatively, the execution unit 130 may include an ECU/steering mechanism, a shift ECU/shift mechanism, an EBCM/brake mechanism, a throttle ECU/throttle acceleration mechanism, and the like.
The human interface interaction unit 140 is configured to interact with the parking control unit 120 by displaying parking images and alternative parking spaces. As an example, the driver selects a parking space desired to park, and the human interface interaction unit 140 may transmit target parking space information to the parking control unit 120 to perform a parking operation.
Fig. 2 is a system block diagram of a parking system according to a first embodiment of the first aspect of the present invention.
As shown in fig. 2, parking system 10' includes a sensor unit 110', a parking control unit 120', an execution unit 130', and a human interface interaction unit 140 '.
The sensor unit 110' includes a camera, an ultrasonic radar, and an inertial measurement unit.
The parking control unit 120' further includes: a sensor data pre-processing module configured to receive signals from the sensor unit and pre-process the received signals; the parking space detection module is configured to perform parking space detection based on the preprocessed signals so as to obtain parking space information; an obstacle detection module configured to perform obstacle detection based on the preprocessed signals to obtain obstacle information; the algorithm fusion module is configured to fuse a parking space detection algorithm in the parking space detection module and an obstacle detection algorithm in the obstacle detection module so as to screen out effective parking spaces and eliminate occupied parking spaces, and therefore available parking spaces are obtained; a planning and decision module configured to plan a parking path and a target vehicle speed based on the target parking space and the obtained obstacle information; and a control algorithm module configured to include a lateral control algorithm and a longitudinal control algorithm, wherein the lateral control algorithm is configured to generate a steering angle control command based on the parking path and a current steering angle, and the longitudinal control algorithm is configured to generate a gear control command and an acceleration or braking command based on a current vehicle speed and the target vehicle speed. The above six modules will be explained in detail below.
As an example, the sensor data preprocessing module receives data from the camera, the ultrasonic radar, and the inertial measurement unit and processes the data for use by the subsequent parking space detection module and obstacle detection module. Optionally, the sensor data preprocessing module receives 4 paths of fisheye camera signals, wherein the original fisheye image signals are not processed and are input into a traditional vision algorithm in the parking space detection module, and in addition, the 4 paths of fisheye images are subjected to correction, perspective transformation and image splicing to form a 360-degree panoramic image and are input into a depth learning algorithm in the parking space detection module. Optionally, the sensor data preprocessing module receives and analyzes a data signal from the ultrasonic radar to obtain information such as the position and distance of an obstacle, so that the information can be used by the subsequent parking space detection module and the obstacle detection module. Optionally, the sensor data preprocessing module analyzes a signal from the inertial measurement unit, which includes information of a vehicle position, a vehicle attitude, and the like, so as to establish map positioning, parking space memory, and the like.
As an example, the parking space detection module receives data from the camera and the ultrasonic radar after the data is processed by the sensor data preprocessing module to realize parking space detection. Optionally, in order to fully utilize the sensor data, the parking space detection module adopts three parking space detection algorithms, namely a traditional visual algorithm, a deep learning algorithm and an ultrasonic detection algorithm. The traditional visual algorithm realizes the detection of the parking space line by carrying out image graying, edge detection, parking space line detection and the like on an original image, and has the advantages of less occupied running resources and high detection speed, but effective parking spaces cannot be detected when the image definition is not high, so the precision is not high. The deep learning algorithm is used for detecting the parking spots in the images through the neural network trained by the plurality of parking spot data sets so as to complete the detection of the parking spots in the panoramic images, the accuracy of parking spot detection can be obviously improved under different scenes by adopting the deep learning algorithm, and the poor position of the traditional visual parking spot detection algorithm is effectively compensated under the scenes such as rainy days, dim light, parking spot reflection and the like. The ultrasonic detection algorithm identifies the vacant parking spaces by detecting vehicles (obstacles) on the parking spaces, and the parking spaces can be detected through the ultrasonic detection algorithm under the conditions that the parking space lines are blocked or damaged and the like so as to make up the defects of the camera image-based parking space detection algorithm. The results of the traditional visual algorithm, the deep learning algorithm and the ultrasonic detection algorithm are synchronously fused, so that the parking space detection precision is greatly improved.
As an example, the obstacle detection module is used to detect obstacle information to assist in the screening of available parking spaces and the subsequent operation of the planning and decision module. Alternatively, the obstacle detection module may include a visual obstacle detection algorithm and an ultrasonic obstacle detection algorithm. The visual obstacle detection algorithm completes the detection of the vehicles and the pedestrians by designing the characteristic devices, the classifiers and the like of the vehicles and the pedestrians, can realize the obstacle shielding when the detection of the vehicles and the pedestrians on the road is used for parking, and can realize the detection of the vehicles on the parking spaces so as to screen out effective parking spaces. The ultrasonic obstacle detection algorithm can detect various obstacles for obstacle shielding and effective parking space detection.
As an example, the algorithm fusion module includes a parking space detection fusion algorithm and an obstacle detection fusion algorithm. The parking space detection fusion algorithm is used for post-processing results of the three parking space detection algorithms. Specifically, the parking space points output by the deep learning algorithm form a plurality of parking space candidate frames, and effective parking spaces are screened out by judging the characteristics of the aspect ratio and the like of the parking space candidate frames; converting the parking space lines output by the traditional visual algorithm into a vehicle coordinate system, and then effectively combining the detected lines to screen out the parking spaces; the occupied parking spaces are removed by processing the vehicle barrier information on the parking spaces output by the ultrasonic detection algorithm, and the empty parking spaces are reserved. And finally, the algorithm fusion module simultaneously fuses the parking space information output by the three parking space detection algorithms through the confidence coefficient of each parking space detection so as to obtain the available parking space. The obstacle detection fusion algorithm is used for fusing a visual obstacle detection result based on an image and an obstacle detection result based on ultrasonic obstacle detection so as to detect vehicles in the parking space for screening parking spaces capable of being parked and detect obstacles such as vehicles, pedestrians and the like on the road for obstacle shielding operation.
As an example, the planning and decision module may include a mapping and positioning algorithm and a planning and decision algorithm, which, in combination with the target parking space and obstacle information given by the human-machine interface interaction unit, plan a parking path and a target vehicle speed. The map building and positioning algorithm is used for building a map in real time by taking the center of the vehicle as a coordinate system according to the information of the attitude, the position and the like of the vehicle from the inertia measurement unit and combining the current speed, positioning the vehicle and the parking space detected by the module in the map for parking space memory, and facilitating a driver to select a pre-parking target parking space from the man-machine interface interaction system. The planning and decision algorithm is used for planning a parking path and a parking speed according to a target parking space by combining a drivable area detected based on a vision and semantic segmentation technology, and then sending the feasible parking path and the parking speed to the control algorithm module for calculating a control command.
As an example, the control algorithm module includes a lateral control algorithm and a longitudinal control algorithm. The transverse control algorithm is used for calculating a steering angle control command based on a Proportional Integral Derivative (PID) algorithm according to a parking path and a current steering angle, and sending the steering angle control command to the steering ECU so as to control the EPS mechanism. The longitudinal control algorithm is used for calculating a gear control command, an acceleration command or a braking command based on a PID algorithm according to the current vehicle speed and the target vehicle speed, and respectively sending the gear control command, the acceleration command or the braking command to the gear shifting ECU, the electronic brake module (EBCM) or the accelerator ECU so as to control the gear shifting mechanism, the braking mechanism or the accelerator acceleration mechanism.
Through the cooperative operation of the six modules and the plurality of algorithms, the cost is reduced by optimizing the internal algorithm framework of the parking system on the premise of not increasing the hardware cost, and automatic parking can be completed when any one of the camera or the ultrasonic radar fails, so that the reliability and the safety of the automatic parking system are improved.
Fig. 3 is a flowchart of a parking method according to an embodiment of the third aspect of the present invention.
As shown in fig. 3, the parking method includes: in step 310, receiving a signal from the sensor unit and preprocessing the received signal; in step 320, performing obstacle detection and parking space detection based on the preprocessed signals to obtain obstacle information and parking space information; in step 330, planning a parking path and a target vehicle speed based on a target parking space and the obtained obstacle information; in step 340, a parking control instruction is generated based on the parking path, the current steering angle, the target vehicle speed, and the current vehicle speed, and a parking operation is performed based on the parking control instruction.
Based on the parking system according to the first aspect of the present invention, the parking method can be performed in 5 steps:
step 1: the parking space detection and the obstacle detection are completed based on the camera. Optionally, at first, 4 fisheye cameras output images to the parking control unit 120, one part of the images is directly subjected to conventional visual parking space detection, and the other part of the images is subjected to image processing to form a panoramic image, so that parking spaces in the panoramic image are detected by using a trained neural network algorithm, and obstacles such as vehicles and pedestrians are detected based on a visual obstacle detection algorithm, so that parking space screening with only cameras can be realized.
Step 2: and parking space detection and obstacle detection are finished based on the ultrasonic radar. Optionally, first, 12 ultrasonic radars output obstacle information to the parking control unit 120, and after data preprocessing, the obstacle information is sent to an ultrasonic obstacle detection algorithm, and a vacant parking space is identified according to a detected vehicle obstacle, so that parking space screening only by the ultrasonic radars can be realized.
And step 3: the parking space detection and obstacle detection results based on the vision and ultrasonic technology are fused, and the parking space detection precision under various parking scenes is further improved. Optionally, the parking space information detected based on the traditional visual algorithm, the deep learning algorithm and the ultrasonic detection algorithm is firstly subjected to post-processing, and is converted into a vehicle coordinate system for synchronous fusion, so that the parking space detection precision is obviously improved. And simultaneously fusing barrier information detected by the visual barrier detection algorithm and the ultrasonic barrier detection algorithm, and further screening the detected parking spaces to obtain parking space information. If the camera or the ultrasonic radar has a fault, the step cannot be carried out, and at this time, the step 1 or the step 2 can be directly skipped to the step 4, so that parking space detection based on a single sensor (the camera or the ultrasonic radar) is realized.
And 4, step 4: and finishing the path planning and decision of automatic parking. Firstly, a driver selects a parking space (target parking space) for pre-parking in a man-machine interface interaction unit, and after receiving target parking space information through a planning and decision algorithm, the planning of a target track and a target vehicle speed is completed by combining a drivable area obtained based on visual semantic segmentation and an ultrasonic technology, and the drivable area is sent to a control algorithm module.
And 5: in the control algorithm module, the transverse and longitudinal control algorithms respectively calculate control commands, and the control commands are sent to the execution unit 130 by the parking control unit 120 to complete the full-automatic parking operation. The transverse control algorithm receives target track information, calculates a control instruction by combining a current steering angle and a PID algorithm, and sends the control instruction to the steering ECU, and the ECU controls the steering mechanism to complete track tracking action; the longitudinal control algorithm receives the target vehicle speed information, and outputs a gear shifting command instruction, an acceleration instruction/a braking instruction to the gear shifting ECU and the acceleration ECU/EBCM based on the PID algorithm, so that gear shifting operation and acceleration/deceleration operation are controlled, and the target vehicle speed tracking action is completed until full-automatic parking is completed.
Fig. 4 is a block diagram of a computer device for carrying out the parking method according to the invention according to a fourth aspect of the invention. As shown in fig. 4, computer device 400 includes memory 410 and processor 420. Although not shown, the computer device 400 also includes computer programs that are stored on the memory 410 and can be run on the processor 420. The processor executes the program to implement the steps of the parking method according to the third aspect of the present invention, as shown in fig. 3, for example.
In addition, as described above, the present invention may also be embodied as a computer storage medium in which a program for causing a computer to execute the parking method according to the first embodiment of the third aspect of the present invention is stored.
Here, as the computer storage medium, various types of computer storage media such as a disk (e.g., a magnetic disk, an optical disk, etc.), a card (e.g., a memory card, an optical card, etc.), a semiconductor memory (e.g., a ROM, a nonvolatile memory, etc.), a tape (e.g., a magnetic tape, a cassette tape, etc.), and the like can be used.
By recording a computer program in these computer storage media that causes a computer to execute the parking method in the above-described embodiments. The parking method according to the above-described embodiment can be executed by loading the computer storage medium on a computer, reading a computer program recorded on the computer storage medium by the computer, storing the computer program in a memory, and reading and executing the computer program from the memory by a processor (CPU: Central Processing Unit (CPU)), or MPU: Micro Processing Unit (Micro Processing Unit)) provided in the computer.
According to the parking system and the parking method, based on fusion of multiple parking space detection algorithms, the cameras and the ultrasonic radar are utilized, the traditional visual parking space detection algorithm, the deep learning parking space detection algorithm and the ultrasonic parking space detection algorithm are fused, and the visual obstacle detection algorithm and the ultrasonic obstacle detection algorithm are fused at the same time, so that the parking space and obstacle detection precision is improved, and the full-automatic parking function under a complex scene is realized.
The embodiments and examples set forth herein are presented to best explain the embodiments in accordance with the present technology and its particular application and to thereby enable those skilled in the art to make and utilize the invention. However, those skilled in the art will recognize that the foregoing description and examples have been presented for the purpose of illustration and example only. The description as set forth is not intended to cover all aspects of the invention or to limit the invention to the precise form disclosed.
Claims (10)
1. A parking system, characterized in that the system comprises:
a sensor unit including a camera, an ultrasonic radar, and an inertial measurement unit;
a parking control unit configured to:
receiving a signal from the sensor unit and pre-processing the received signal;
performing obstacle detection and parking space detection based on the preprocessed signals to obtain obstacle information and parking space information;
planning a parking path and a target vehicle speed based on the target parking space and the obtained obstacle information; and
generating a parking control instruction based on the parking path, the current steering angle, the target vehicle speed and the current vehicle speed; and
an execution unit configured to execute a parking operation based on the parking control instruction from the parking control unit.
2. The parking system of claim 1, further comprising a human interface interaction unit configured to interact with the parking control unit by displaying parking images and alternative parking spaces.
3. The parking system according to claim 1, wherein the parking control unit further comprises:
a sensor data pre-processing module configured to receive signals from the sensor unit and pre-process the received signals;
the parking space detection module is configured to perform parking space detection based on the preprocessed signals so as to obtain parking space information;
an obstacle detection module configured to perform obstacle detection based on the preprocessed signals to obtain obstacle information;
the algorithm fusion module is configured to fuse a parking space detection algorithm in the parking space detection module and an obstacle detection algorithm in the obstacle detection module so as to screen out effective parking spaces and eliminate occupied parking spaces, and therefore available parking spaces are obtained;
a planning and decision module configured to plan a parking path and a target vehicle speed based on the target parking space and the obtained obstacle information; and
a control algorithm module configured to include a lateral control algorithm and a longitudinal control algorithm, wherein the lateral control algorithm is configured to generate a steering angle control command based on the parking path and a current steering angle, and the longitudinal control algorithm is configured to generate a gear control command and an acceleration or braking command based on a current vehicle speed and the target vehicle speed.
4. The parking system of claim 3, wherein the spot detection module is configured to perform one or more of:
the traditional vision algorithm is used for carrying out image graying, edge detection and parking space line detection on the original image from the camera;
a deep learning algorithm for detection of vehicle location points in the image by a neural network trained via a plurality of vehicle location data sets; and
and the ultrasonic detection algorithm is used for identifying the vacant parking spaces by detecting the vehicles or the obstacles on the parking spaces.
5. The parking system of claim 3, wherein the obstacle detection module is configured to perform one or more of:
a visual obstacle detection algorithm for vehicle and pedestrian detection by designing a vehicle and pedestrian feature and classifier; and
an ultrasonic obstacle detection algorithm for detecting obstacles using signals from the ultrasonic radar.
6. The parking system of claim 3 wherein the planning and decision module is configured to perform one or more of:
the map building and positioning algorithm is used for building a map by taking the vehicle center as a coordinate system based on the vehicle attitude, the position information and the current vehicle speed so as to position the vehicle in the map and the available parking space obtained by the algorithm fusion module; and
and the planning and decision algorithm is used for planning a parking path and a parking speed based on the target parking space and the obstacle information and sending the parking path and the parking speed to the control algorithm module.
7. A vehicle comprising a parking system according to any one of claims 1 to 6.
8. A method of parking a vehicle, comprising:
receiving a signal from the sensor unit and pre-processing the received signal;
performing obstacle detection and parking space detection based on the preprocessed signals to obtain obstacle information and parking space information;
planning a parking path and a target vehicle speed based on the target parking space and the obtained obstacle information;
generating a parking control instruction based on the parking path, the current steering angle, the target vehicle speed and the current vehicle speed; and
and executing a parking operation based on the parking control instruction.
9. A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the parking method according to claim 8 when executing the program.
10. A computer storage medium having a computer program stored thereon, wherein the program is executable by a computer to implement the parking method according to claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011245514.5A CN114454872A (en) | 2020-11-10 | 2020-11-10 | Parking system and parking method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011245514.5A CN114454872A (en) | 2020-11-10 | 2020-11-10 | Parking system and parking method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114454872A true CN114454872A (en) | 2022-05-10 |
Family
ID=81404051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011245514.5A Pending CN114454872A (en) | 2020-11-10 | 2020-11-10 | Parking system and parking method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114454872A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110696818A (en) * | 2019-10-12 | 2020-01-17 | 深圳市布谷鸟科技有限公司 | Automatic parking method and system based on optimal path |
| CN110775052A (en) * | 2019-08-29 | 2020-02-11 | 浙江零跑科技有限公司 | Automatic parking method based on fusion of vision and ultrasonic perception |
| WO2020056874A1 (en) * | 2018-09-17 | 2020-03-26 | 魔门塔(苏州)科技有限公司 | Automatic parking system and method based on visual recognition |
| CN111055838A (en) * | 2019-10-14 | 2020-04-24 | 江苏开沃汽车有限公司 | Full-automatic parking control system based on sensor fusion and control method thereof |
-
2020
- 2020-11-10 CN CN202011245514.5A patent/CN114454872A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020056874A1 (en) * | 2018-09-17 | 2020-03-26 | 魔门塔(苏州)科技有限公司 | Automatic parking system and method based on visual recognition |
| CN110775052A (en) * | 2019-08-29 | 2020-02-11 | 浙江零跑科技有限公司 | Automatic parking method based on fusion of vision and ultrasonic perception |
| CN110696818A (en) * | 2019-10-12 | 2020-01-17 | 深圳市布谷鸟科技有限公司 | Automatic parking method and system based on optimal path |
| CN111055838A (en) * | 2019-10-14 | 2020-04-24 | 江苏开沃汽车有限公司 | Full-automatic parking control system based on sensor fusion and control method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109949594B (en) | Real-time traffic light identification method | |
| CN112180373B (en) | Multi-sensor fusion intelligent parking system and method | |
| CN111081064B (en) | Automatic parking system and automatic passenger-replacing parking method of vehicle-mounted Ethernet | |
| US9076047B2 (en) | System and method for recognizing parking space line markings for vehicle | |
| CN113492851B (en) | Vehicle control device, vehicle control method, and computer program for vehicle control | |
| JP6866440B2 (en) | Object identification methods, devices, equipment, vehicles and media | |
| CN110689761A (en) | Automatic parking method | |
| CN111028534B (en) | Parking space detection method and device | |
| CN113561963B (en) | Parking method and device and vehicle | |
| US20210064913A1 (en) | Driving assistant system, electronic device, and operation method thereof | |
| CN103358993A (en) | A system and method for recognizing a parking space line marking for a vehicle | |
| JP7135665B2 (en) | VEHICLE CONTROL SYSTEM, VEHICLE CONTROL METHOD AND COMPUTER PROGRAM | |
| CN111178122A (en) | Detection and planar representation of three-dimensional lanes in a road scene | |
| JP7472832B2 (en) | Vehicle control device, vehicle control method, and vehicle control computer program | |
| CN114705121B (en) | Vehicle pose measurement method and device, electronic equipment and storage medium | |
| JP7226368B2 (en) | Object state identification device | |
| WO2022153896A1 (en) | Imaging device, image processing method, and image processing program | |
| CN113650607B (en) | Low-speed scene automatic driving method, system and automobile | |
| CN114495066A (en) | Method for assisting backing | |
| CN115366885A (en) | Method for assisting a driving maneuver of a motor vehicle, assistance device and motor vehicle | |
| JP7003972B2 (en) | Distance estimation device, distance estimation method and computer program for distance estimation | |
| US20230109473A1 (en) | Vehicle, electronic apparatus, and control method thereof | |
| CN113611008B (en) | Vehicle driving scene acquisition method, device, equipment and medium | |
| CN114454872A (en) | Parking system and parking method | |
| CN116434180A (en) | Lighting state recognition device, lighting state recognition method, and computer program for recognizing lighting state |
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 |