CN114882727B - Parking space detection method based on domain controller, electronic equipment and storage medium - Google Patents
Parking space detection method based on domain controller, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114882727B CN114882727B CN202210253035.0A CN202210253035A CN114882727B CN 114882727 B CN114882727 B CN 114882727B CN 202210253035 A CN202210253035 A CN 202210253035A CN 114882727 B CN114882727 B CN 114882727B
- Authority
- CN
- China
- Prior art keywords
- parking space
- vehicle
- coordinate
- image data
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/141—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/586—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/168—Driving aids for parking, e.g. acoustic or visual feedback on parking space
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses a parking space detection method based on a domain controller, which comprises the following steps: the method comprises the steps that a quantization processing model detects a parking space on image data acquired by a panoramic image system of a vehicle to obtain parking space primary detection coordinates, the parking space primary detection coordinates are mapped to an absolute coordinate system, in the absolute coordinate system, a reference distance between the vehicle coordinates and the parking space primary detection coordinates at a target time is judged, when the reference distance is smaller than a preset value, the image data at the target time are input into a neural network model, the neural network model is used for detecting the parking space on the image data in a preset range taking the parking space primary detection coordinates as a center, so that parking space fine detection coordinates are obtained, and high-precision visual identification and high-frequency neural network model operation are achieved.
Description
Technical Field
The present invention relates to the field of automatic parking technologies, and in particular, to a parking space detection method based on a domain controller, an electronic device, and a storage medium.
Background
The automatic parking is a system for automatically parking without manual intervention, and reduces the driving burden of a driver. Because the real world environment is extremely complex, illumination, weather and ground stains in the real world all interfere with the recognition of parking spaces by machine vision. In the vehicle-mounted embedded platform, due to the limitation of cost, power and other reasons, a low-power chip is often adopted, and the low-power chip cannot provide high-frequency identification under the condition of ensuring the identification precision.
At present, hardware manufacturers of various vehicle-mounted embedded platforms are usually additionally provided with additional low-cost visual identification chips, but the low-cost visual identification chips do not have cores for processing floating point operations, if a deep learning model needs to be operated on the chips, the deep learning model needs to be processed, the deep learning model is quantized, and floating point operations in the model are converted into integer operations on the premise of ensuring the operation accuracy of the model as much as possible, so that the calculation force is saved. However, the error of the quantized deep learning model is difficult to control, reducing the parking rate of the automatic parking system.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a parking space detection method, electronic equipment and storage medium based on a domain controller, so as to solve the problem that the existing vision recognition parking system cannot achieve both high-precision vision recognition and high-frequency neural network model operation.
The invention adopts the following technical scheme:
a parking space detection method based on a domain controller, comprising the steps of:
the primary detection step comprises: the quantization processing model detects a parking space on image data acquired by a panoramic image system of a vehicle to obtain a parking space primary detection coordinate, and maps the parking space primary detection coordinate to an absolute coordinate system;
judging: in the absolute coordinate system, judging a reference distance between a vehicle coordinate at a target moment and the parking space initial detection coordinate, and inputting the image data of the target moment into a neural network model when the reference distance is smaller than a preset value;
fine inspection: and detecting the parking space by using the neural network model in a preset range taking the initial detection coordinate of the parking space as a center, so as to obtain the accurate detection coordinate of the parking space.
In certain alternative embodiments, prior to the preliminary inspection step, further comprising:
and (3) synchronizing: synchronizing a time stamp of the vehicle pose data and a time stamp of the image data;
a vehicle state acquisition step: obtaining a vehicle coordinate and a vehicle course angle of the vehicle in an absolute coordinate system according to the image data and the vehicle posture data at the same moment;
in the preliminary inspection step, further comprising: and the quantization processing model carries out parking space detection on image data acquired by a panoramic image system of the vehicle to obtain a reference position, and the initial detection coordinate of the parking space is obtained through calculation of the vehicle coordinate, the vehicle course angle and the reference position.
In some alternative embodiments, between the determining step and the fine inspection step, further comprising: an image processing step: mapping a virtual parking area in the image data in a preset range with the initial detection coordinate of the parking space as the center, and extracting an overlapped image of the observed parking frame in the image data and the virtual parking area;
the fine inspection step further comprises the following steps: and using the neural network model to detect the parking space of the overlapped image.
In some alternative embodiments, the image processing step further comprises: edge expansion is carried out on the overlapped images;
the fine inspection step further comprises the following steps: and detecting the parking space of the overlapped images after edge expansion by using the neural network model.
In some alternative embodiments, the image processing step further comprises: performing mask processing on the overlapped images after edge expansion to obtain mask images, and performing black setting processing on areas outside the mask images;
the fine inspection step further comprises the following steps: and detecting the parking space of the mask image by using the neural network model.
In certain alternative embodiments, the vehicle attitude data includes a wheel speed pulse signal and a steering wheel angle signal;
the vehicle state acquisition step further includes:
and fitting the steering wheel angle signal through a polynomial to obtain front wheel angle information, calculating the wheel speed information through the wheel speed pulse signal, and obtaining the course angle of the vehicle according to the front wheel angle information and the wheel speed information.
In certain alternative embodiments, the vehicle state acquisition step further comprises:
establishing a vehicle motion model, substituting the front wheel rotation angle information and the wheel speed information into the vehicle motion model to obtain the angular speed and the linear speed of the vehicle; and calculating the course angle of the vehicle through the angular speed and the linear speed.
In certain alternative embodiments, the vehicle state acquisition step further comprises:
and carrying out Kalman filtering on the angular velocity and the linear velocity, and calculating to obtain the heading angle of the vehicle.
In order to solve the same technical problems, the invention also provides electronic equipment, which comprises a memory and a processor;
the memory is used for storing executable computer instructions;
the processor is configured to implement the steps of the above method when executing the computer instructions.
To solve the same technical problem, the present invention also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the steps of the above method.
Compared with the prior art, the invention has the beneficial effects that:
and detecting by adopting a quantization processing model to obtain a parking space initial detection coordinate, and when the vehicle is close to a preset value from the parking space initial detection coordinate, carrying out parking space identification on the image data by using a neural network model to obtain a parking space accurate detection coordinate, so that both high-precision visual identification and high-frequency neural network model operation are considered.
Drawings
FIG. 1 is a flow chart illustrating steps of an inventive parking space detection method based on a domain controller;
Detailed Description
In order that the invention may be readily understood, a more complete description of the invention will be rendered by reference to the appended drawings. Preferred embodiments of the present invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "fixed to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Example 1
Referring to fig. 1, there is schematically shown a parking space detection method based on a domain controller according to the present invention, comprising the steps of:
step S10, a synchronization step: and synchronizing the time stamp of the vehicle posture data and the time stamp of the image data acquired by the panoramic image system of the vehicle. The vehicle attitude data includes a wheel speed pulse signal and a steering wheel angle signal. Specifically, wheel speed pulse data and time stamps thereof and steering wheel rotation angle data and time stamps thereof of a vehicle are collected, and vehicle gestures are calculated according to the wheel speed pulse data and time stamps thereof and the steering wheel rotation angle data and time stamps thereof.
The current vehicle posture can be calculated at the same time by collecting the wheel speed pulse data and the time stamp thereof and the steering wheel rotation angle data and the time stamp thereof. For example, when the vehicle posture at the time 04:37:26 needs to be calculated, the wheel speed pulse data and the steering wheel corner data at the time 04:37:26 are required to be called, the rotation speed of each wheel of the vehicle can be calculated according to the wheel speed pulse data, the steering condition of the vehicle can be calculated according to the steering wheel corner data, and the vehicle posture at the time 04:37:26 can be calculated according to the rotation speed and the steering condition of each wheel.
Step S20, a vehicle state acquisition step: and obtaining the vehicle coordinates and the vehicle course angle of the vehicle in the virtual map according to the image data and the vehicle posture data at the same moment. Based on the time stamp in step S10, the coordinates and heading angle of the vehicle are obtained from the image data and the vehicle posture data at the same time.
The method comprises the steps of fitting steering wheel angle signals through polynomials to obtain front wheel angle information, and calculating through wheel speed pulse signals to obtain wheel speed information; establishing a vehicle motion model, substituting front wheel rotation angle information and wheel speed information into the vehicle motion model to obtain the angular speed and linear speed of the vehicle; and (5) carrying out Kalman filtering on the angular velocity and the linear velocity, and then calculating to obtain the course angle of the vehicle.
Step S30, a primary inspection step: the quantization processing model detects the parking space on the image data acquired by the panoramic image system of the vehicle to obtain the primary detection coordinates of the parking space, and maps the primary detection coordinates of the parking space to an absolute coordinate system;
the method comprises the following steps: and the quantization processing model carries out parking space detection on image data acquired by a panoramic image system of the vehicle to obtain a reference position, and the initial detection coordinate of the parking space is obtained through calculation of the vehicle coordinate, the vehicle course angle and the reference position. When the coordinates and the heading angle of the vehicle are obtained, the position and the attitude of the vehicle in the virtual map can be obtained, and the initial detection coordinates of the parking space in the virtual map can be obtained by combining the reference position.
Step S40, judging step: in the absolute coordinate system, judging a reference distance between the vehicle coordinate and the parking space initial detection coordinate at the target moment, and inputting image data at the target moment into the neural network model when the reference distance is smaller than a preset value (for example, the preset value is 2 meters). That is, when the vehicle is close to the parking space, the operation of the image data using the neural network model is started.
Step S50, an image processing step: mapping a virtual parking area in image data in a preset range with a parking space initial detection coordinate as a center, extracting an overlapped image of an observed parking frame and the virtual parking area in the image data, expanding edges of the overlapped image, performing mask processing on the overlapped image after expanding the edges to obtain a mask image, and performing black placement processing on areas outside the mask image to enable the mask image to be suitable for visual identification of a neural network model.
Step S60, a fine inspection step: and detecting the parking space by using the neural network model in a preset range with the initial detection coordinate of the parking space as the center to obtain the accurate detection coordinate of the parking space, thereby combining high-precision visual identification and high-frequency neural network model operation. The mask is arranged so that the neural network model can focus on parking frame recognition on the mask image.
Example two
In order to solve the same technical problem, the invention also provides electronic equipment, which comprises a memory and a processor, wherein the memory is used for storing executable computer instructions, and the processor is used for realizing the steps of the method when executing the computer instructions.
Example III
To solve the same technical problem, the present invention also provides a computer readable storage medium storing computer instructions which, when executed by a processor, implement the steps of the above method.
Compared with the prior art, the invention has the beneficial effects that:
and detecting by adopting a quantization processing model to obtain a parking space initial detection coordinate, and when the vehicle is close to a preset value from the parking space initial detection coordinate, carrying out parking space identification on the image data by using a neural network model to obtain a parking space accurate detection coordinate, so that both high-precision visual identification and high-frequency neural network model operation are considered.
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (8)
1. The parking space detection method based on the domain controller is characterized by comprising the following steps of:
the primary detection step comprises: the quantization processing model detects a parking space on image data acquired by a panoramic image system of a vehicle to obtain a parking space primary detection coordinate, and maps the parking space primary detection coordinate to an absolute coordinate system;
judging: in the absolute coordinate system, judging a reference distance between a vehicle coordinate at a target moment and the parking space initial detection coordinate, and inputting the image data of the target moment into a neural network model when the reference distance is smaller than a preset value;
fine inspection: using the neural network model to detect the parking space in a preset range with the initial detection coordinate of the parking space as a center so as to obtain the accurate detection coordinate of the parking space;
before the preliminary inspection step, further comprising:
and (3) synchronizing: synchronizing a time stamp of the vehicle pose data and a time stamp of the image data;
a vehicle state acquisition step: obtaining a vehicle coordinate and a vehicle course angle of the vehicle in an absolute coordinate system according to the image data and the vehicle posture data at the same moment;
in the preliminary inspection step, further comprising: the quantization processing model carries out parking space detection on image data acquired by a panoramic image system of a vehicle to obtain a reference position, and the initial detection coordinate of the parking space is obtained through calculation of the vehicle coordinate, the vehicle course angle and the reference position;
between the judging step and the fine inspection step, further comprising: an image processing step: mapping a virtual parking area in the image data in a preset range with the initial detection coordinate of the parking space as the center, and extracting an overlapped image of the observed parking frame in the image data and the virtual parking area;
the fine inspection step further comprises the following steps: using the neural network model to detect parking spaces of the overlapped images;
the image processing step further includes: edge expansion is carried out on the overlapped images;
the image processing step further includes: and performing mask processing on the overlapped images after edge expansion to obtain mask images, and performing black setting processing on areas outside the mask images.
2. The parking space detection method based on a domain controller according to claim 1, wherein the fine detection step further comprises: and detecting the parking space of the overlapped images after edge expansion by using the neural network model.
3. The parking space detection method based on the domain controller according to claim 2, wherein the fine detection step further comprises: and detecting the parking space of the mask image by using the neural network model.
4. The domain controller-based parking space detection method according to claim 1, wherein the vehicle attitude data includes a wheel speed pulse signal and a steering wheel angle signal;
the vehicle state acquisition step further includes:
and fitting the steering wheel angle signal through a polynomial to obtain front wheel angle information, calculating the wheel speed information through the wheel speed pulse signal, and obtaining the course angle of the vehicle according to the front wheel angle information and the wheel speed information.
5. The domain controller-based parking space detection method according to claim 4, wherein the vehicle state acquisition step further comprises:
establishing a vehicle motion model, substituting the front wheel rotation angle information and the wheel speed information into the vehicle motion model to obtain the angular speed and the linear speed of the vehicle; and calculating the course angle of the vehicle through the angular speed and the linear speed.
6. The domain controller-based parking space detection method according to claim 5, wherein the vehicle state acquisition step further comprises:
and carrying out Kalman filtering on the angular velocity and the linear velocity, and calculating to obtain the heading angle of the vehicle.
7. An electronic device comprising a memory and a processor;
the memory is used for storing executable computer instructions;
the processor being adapted to carry out the steps of the method according to any one of claims 1 to 6 when said computer instructions are executed.
8. A computer readable storage medium storing computer instructions which, when executed by a processor, implement the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210253035.0A CN114882727B (en) | 2022-03-15 | 2022-03-15 | Parking space detection method based on domain controller, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210253035.0A CN114882727B (en) | 2022-03-15 | 2022-03-15 | Parking space detection method based on domain controller, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114882727A CN114882727A (en) | 2022-08-09 |
| CN114882727B true CN114882727B (en) | 2023-09-05 |
Family
ID=82667352
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210253035.0A Active CN114882727B (en) | 2022-03-15 | 2022-03-15 | Parking space detection method based on domain controller, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114882727B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009248765A (en) * | 2008-04-07 | 2009-10-29 | Nissan Motor Co Ltd | Parking support device and parking support method |
| WO2018028230A1 (en) * | 2016-08-10 | 2018-02-15 | 东方网力科技股份有限公司 | Deep learning-based method and device for segmenting vehicle license plate characters, and storage medium |
| CN108759667A (en) * | 2018-05-29 | 2018-11-06 | 福州大学 | Front truck distance measuring method based on monocular vision and image segmentation under vehicle-mounted camera |
| CN109712428A (en) * | 2019-02-27 | 2019-05-03 | 爱笔（北京）智能科技有限公司 | A kind of parking position localization method and device, system |
| DE102017130488A1 (en) * | 2017-12-19 | 2019-06-19 | Valeo Schalter Und Sensoren Gmbh | A method for classifying parking spaces in a surrounding area of a vehicle with a neural network |
| WO2019137915A1 (en) * | 2018-01-09 | 2019-07-18 | Connaught Electronics Ltd. | Generating input data for a convolutional neuronal network |
| CN110210350A (en) * | 2019-05-22 | 2019-09-06 | 北京理工大学 | A kind of quick parking space detection method based on deep learning |
| US10726723B1 (en) * | 2017-08-25 | 2020-07-28 | Objectvideo Labs, Llc | Parking lot use monitoring for small businesses |
| CN111476084A (en) * | 2020-02-25 | 2020-07-31 | 福建师范大学 | Deep learning-based parking lot dynamic parking space condition identification method |
| CN111508260A (en) * | 2019-01-30 | 2020-08-07 | 上海欧菲智能车联科技有限公司 | Vehicle parking space detection method, device and system |
| US10789846B1 (en) * | 2020-03-19 | 2020-09-29 | Cdw Llc | Available vehicle parking space dispatch |
| CN112507862A (en) * | 2020-12-04 | 2021-03-16 | 东风汽车集团有限公司 | Vehicle orientation detection method and system based on multitask convolutional neural network |
| CN112836633A (en) * | 2021-02-02 | 2021-05-25 | 蔚来汽车科技(安徽)有限公司 | Parking space detection method and parking space detection system |
| WO2021141833A1 (en) * | 2020-01-06 | 2021-07-15 | Continental Automotive Systems, Inc. | System and method for map generating and vehicle parking |
| CN113516852A (en) * | 2021-07-22 | 2021-10-19 | 珠海小可乐科技有限公司 | Multi-parking-space multi-target vehicle parking identification method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10304335B2 (en) * | 2016-04-12 | 2019-05-28 | Ford Global Technologies, Llc | Detecting available parking spaces |
-
2022
- 2022-03-15 CN CN202210253035.0A patent/CN114882727B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009248765A (en) * | 2008-04-07 | 2009-10-29 | Nissan Motor Co Ltd | Parking support device and parking support method |
| WO2018028230A1 (en) * | 2016-08-10 | 2018-02-15 | 东方网力科技股份有限公司 | Deep learning-based method and device for segmenting vehicle license plate characters, and storage medium |
| US10726723B1 (en) * | 2017-08-25 | 2020-07-28 | Objectvideo Labs, Llc | Parking lot use monitoring for small businesses |
| DE102017130488A1 (en) * | 2017-12-19 | 2019-06-19 | Valeo Schalter Und Sensoren Gmbh | A method for classifying parking spaces in a surrounding area of a vehicle with a neural network |
| WO2019137915A1 (en) * | 2018-01-09 | 2019-07-18 | Connaught Electronics Ltd. | Generating input data for a convolutional neuronal network |
| CN108759667A (en) * | 2018-05-29 | 2018-11-06 | 福州大学 | Front truck distance measuring method based on monocular vision and image segmentation under vehicle-mounted camera |
| CN111508260A (en) * | 2019-01-30 | 2020-08-07 | 上海欧菲智能车联科技有限公司 | Vehicle parking space detection method, device and system |
| CN109712428A (en) * | 2019-02-27 | 2019-05-03 | 爱笔（北京）智能科技有限公司 | A kind of parking position localization method and device, system |
| CN110210350A (en) * | 2019-05-22 | 2019-09-06 | 北京理工大学 | A kind of quick parking space detection method based on deep learning |
| WO2021141833A1 (en) * | 2020-01-06 | 2021-07-15 | Continental Automotive Systems, Inc. | System and method for map generating and vehicle parking |
| CN111476084A (en) * | 2020-02-25 | 2020-07-31 | 福建师范大学 | Deep learning-based parking lot dynamic parking space condition identification method |
| US10789846B1 (en) * | 2020-03-19 | 2020-09-29 | Cdw Llc | Available vehicle parking space dispatch |
| CN112507862A (en) * | 2020-12-04 | 2021-03-16 | 东风汽车集团有限公司 | Vehicle orientation detection method and system based on multitask convolutional neural network |
| CN112836633A (en) * | 2021-02-02 | 2021-05-25 | 蔚来汽车科技(安徽)有限公司 | Parking space detection method and parking space detection system |
| CN113516852A (en) * | 2021-07-22 | 2021-10-19 | 珠海小可乐科技有限公司 | Multi-parking-space multi-target vehicle parking identification method and system |
Non-Patent Citations (1)
| Title |
|---|
| 迁移学习场景下的实时停车位置检测;邢家源;张军;薛晨兴;雷雨婷;孙彦;;天津职业技术师范大学学报(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114882727A (en) | 2022-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3407294A1 (en) | Information processing method, device, and terminal | |
| CN110163912B (en) | Two-dimensional code pose calibration method, device and system | |
| CN109766757B (en) | Parking space high-precision positioning method and system integrating vehicle and visual information | |
| CN110766760B (en) | Method, device, equipment and storage medium for camera calibration | |
| CN105865461A (en) | Automobile positioning system and method based on multi-sensor fusion algorithm | |
| JP6776202B2 (en) | In-vehicle camera calibration device and method | |
| CN110728720B (en) | Method, apparatus, device and storage medium for camera calibration | |
| US11151729B2 (en) | Mobile entity position estimation device and position estimation method | |
| CN111967360A (en) | Target vehicle attitude detection method based on wheels | |
| CN110766761B (en) | Method, apparatus, device and storage medium for camera calibration | |
| CN112927303B (en) | Lane line-based automatic driving vehicle-mounted camera pose estimation method and system | |
| CN110751693B (en) | Method, apparatus, device and storage medium for camera calibration | |
| CN112257539A (en) | Method, system and storage medium for detecting position relation between vehicle and lane line | |
| CN112017236A (en) | Method and device for calculating position of target object based on monocular camera | |
| CN114755662A (en) | Calibration method and device for laser radar and GPS with road-vehicle fusion perception | |
| CN110675455A (en) | Self-calibration method and system for car body all-around camera based on natural scene | |
| CN113740871B (en) | Laser SLAM method, system equipment and storage medium under high dynamic environment | |
| CN112304322B (en) | Restarting method after visual positioning failure and vehicle-mounted terminal | |
| CN114882727B (en) | Parking space detection method based on domain controller, electronic equipment and storage medium | |
| CN112819711A (en) | Monocular vision-based vehicle reverse positioning method utilizing road lane line | |
| Yang | Estimation of vehicle's lateral position via the Lucas-Kanade optical flow method | |
| CN107248171B (en) | Triangulation-based monocular vision odometer scale recovery method | |
| CN106874837B (en) | Vehicle detection method based on video image processing | |
| CN116429098A (en) | Visual navigation positioning method and system for low-speed unmanned aerial vehicle | |
| CN114037977B (en) | Road vanishing point detection method, device, equipment and storage medium |
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 |