CN107738612B - Automatic parking space detection and identification system based on panoramic vision auxiliary system - Google Patents
Automatic parking space detection and identification system based on panoramic vision auxiliary system Download PDFInfo
- Publication number
- CN107738612B CN107738612B CN201710864999.8A CN201710864999A CN107738612B CN 107738612 B CN107738612 B CN 107738612B CN 201710864999 A CN201710864999 A CN 201710864999A CN 107738612 B CN107738612 B CN 107738612B
- Authority
- CN
- China
- Prior art keywords
- parking space
- detection
- parking
- image
- vehicle
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/10—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used
- B60R2300/105—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used using multiple cameras
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/20—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of display used
- B60R2300/207—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of display used using multi-purpose displays, e.g. camera image and navigation or video on same display
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/30—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of image processing
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/80—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement
- B60R2300/806—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for aiding parking
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Mechanical Engineering (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an automatic parking space detection and identification system based on a panoramic vision auxiliary system, which mainly solves the problem of inaccurate parking space detection and identification caused by incomplete parking space marking lines and internal shadows or obstacles in the prior art. The system comprises a camera detection module and an identification module, wherein cameras are arranged around a vehicle and spliced into a seamless panoramic image capable of reflecting information around the vehicle; the detection module completes detection of the parking space marking line and completes detection of the parking space under the condition that the parking space marking line is incomplete through the perimeter of the marking line; the recognition module completes recognition of parking spaces with shadows or obstacles in the parking spaces by calculating the gray level change difference value inside the parking spaces and the heights of the obstacles, and the detection and recognition results are displayed on a vehicle-mounted central control large screen. The invention realizes efficient and accurate parking space detection and identification, provides effective basis for path planning and path tracking control in subsequent automatic parking, and can be used for a driver to find a parking position.
Description
Technical Field
The invention belongs to the technical field of computer vision processing, and particularly relates to an automatic parking space detection and identification system which can be used for a driver to find a parking position.
Background
With the rapid rise of automobile holding capacity, the problem of 'difficult parking' in urban scenes is more and more prominent. When a driver parks the vehicle, the vehicle is limited by objective conditions such as narrow visual field and parking space, and the technical and psychological influences, so that the vehicle is very easy to rub and touch, and unnecessary loss is brought. An effective parking auxiliary system can help a driver to complete parking operation quickly and safely, and an automatic parking system can complete safe and accurate parking without the help of the control of the driver.
At present, the detection and identification method of the automatic parking space commonly used in the market is based on an ultrasonic radar method. However, the method based on the ultrasonic radar requires that vehicles are parked at the front and the rear of the target parking space to realize parking space detection, and the ultrasonic radar detection method has the defects of small detection range, blind areas and the like. In response to this problem, vision-based parking assistance systems that combine ultrasound with machine vision are undoubtedly the direction of development of future parking assistance systems. However, the current visual-based parking space detection and identification method only aims at the detection of the ground parking space marking line in the common scene, and ignores the parking space detection problem under the complex conditions that the target parking space has obstacles, shadows, incomplete marking lines and the like, so how to more accurately and reliably detect the parking space in the complex scene is an urgent need problem for solving the current traffic management.
Disclosure of Invention
The invention aims to provide an automatic parking space detection and identification system based on a panoramic vision auxiliary system aiming at the defects of the prior art, so as to improve the accuracy and reliability of detecting a parking position by a driver in a complex scene.
The technical idea for realizing the purpose of the invention is as follows: the method comprises the steps of generating a panoramic image of the surrounding environment of the vehicle through four wide-angle cameras installed around the vehicle body, and detecting and identifying parking spaces around the vehicle body by combining a computer vision algorithm so as to realize efficient and accurate parking space detection and identification under the special conditions of obstacle, shadow and incomplete marking line.
According to the above thought, the automatic parking space detection and identification system based on the panoramic vision auxiliary system of the invention comprises:
the panoramic shooting unit is used for acquiring images around the vehicle body, generating a seamless spliced 360-degree top view through camera calibration, distortion correction, top view transformation and image splicing and transmitting the seamless spliced 360-degree top view to the embedded unit;
the embedded unit is used for processing the top view acquired by the panoramic shooting module, detecting the parking space, judging whether the parking space is occupied or not and sending a detection result to the vehicle-mounted electronic control unit ECU and the vehicle-mounted central control display screen;
the vehicle-mounted central control display screen is used for displaying the parking space detection result transmitted by the embedded unit;
the method is characterized in that: the embedded unit includes:
the interface module is used for sending the detection result of the embedded unit to the vehicle-mounted electronic control unit ECU;
an image processing module including a detection sub-module and an identification sub-module,
the detection submodule performs image preprocessing on a 360-degree top view of seamless splicing, extracts a parking space marking line in the top view by using a line segment detection algorithm, calculates the perimeter of the parking space marking line, and judges whether the parking space marking line is complete or not according to the perimeter: if the parking space is incomplete, the parking space marking line is completed by using an image segmentation algorithm, and whether the parking space is an optional parking space is judged;
the identification submodule judges whether shadows or obstacles exist in the optional parking spaces or not by calculating the gray level change difference value in the parking spaces for the target parking spaces detected by the detection submodule, and calculates the heights of the obstacles if the shadows or the obstacles exist, so as to judge whether the optional parking spaces are occupied or not;
and the image display sub-module is used for displaying the detection result of the optional parking space of the embedded unit in the vehicle-mounted central control display screen.
The invention has the following advantages or beneficial effects:
according to the invention, the detection process does not depend on the parking posture of an adjacent automobile but only depends on the parking space and parking line, in the panoramic vision auxiliary system, the parking space marking line in the top view is extracted by using the LSD line segment detection algorithm, and then the detection accuracy of the parking space under the condition that the parking space marking line is incomplete is improved by calculating the perimeter enclosed by each line segment of the parking space marking line; in addition, the method firstly judges whether the shadow or the obstacle exists or not by calculating the image gray level difference value information, and then judges the height of the obstacle if the obstacle exists, so that whether the optional parking space is occupied or not is determined, the parking space detection problem under the condition that the obstacle and the shadow exist in the parking space is effectively solved, the efficient and accurate parking space detection and identification functions are realized, and the precision and stability guarantee is provided for path planning and path tracking control in the subsequent automatic parking.
Embodiments of the present invention will now be described more fully hereinafter with reference to the accompanying drawings. The drawings are, however, to be regarded as illustrative and explanatory only and are not restrictive of the scope of the invention.
Drawings
Fig. 1 is a schematic structural diagram of an automatic parking space detection and identification system according to the present invention;
FIG. 2 is a diagram illustrating a process of performing parking space detection by the detection submodule according to the present invention;
fig. 3 is a process diagram of the recognition submodule performing parking space recognition according to the present invention.
Detailed Description
First, technical principle
The invention comprises detection of automatic parking spaces and identification of automatic parking spaces, wherein:
detection of parking spaces for automatic parking
The detection of the automatic parking space comprises three parts of image preprocessing, parking mark line detection and parking mark line perimeter calculation.
The image preprocessing comprises image graying and image edge detection, wherein the image graying is to convert a color image acquired by a camera into a grayscale image, the edge detection is to detect and identify a set formed by pixels with severe brightness change in the image, and the image preprocessing process is mainly used for reducing noise in the image and external interference so as to simplify the subsequent processing process.
The parking mark line detection is characterized in that on the basis of the edge detection in the early period, an LSD line segment detection algorithm is used for extracting parking mark lines in parking spaces, the algorithm obtains a linear pixel point set through local image analysis, then verification and solution are carried out through assumed parameters, the pixel point set and an error control set are combined, the number of error detection is adaptively controlled, the detection accuracy is further improved, the algorithm is capable of extracting linear features of sub-pixel level images in linear time, and compared with a traditional line detection method through Hough transformation, the LSD algorithm is well balanced in detection accuracy and calculation efficiency in the aspect of detecting linear segments.
According to the national standard GB50067-2014, in a real scene, the width of a parking space is about 2.5 meters, and the width of a parking space marking line is about 10 centimeters. Setting the physical distance between parallel lines to w1In the range of 0.1 m to 0.15 cm, the physical distance between two pairs of parallel line segments is set to be w2In the range of 2.3 to 2.8 meters. Detecting in the edge image that the physical distance between the parallel lines is w1And the physical distance between two parallel line segment pairs is w2The two parallel line segment pairs complete the parking marking line detection.
The calculation of the perimeter of the parking mark line aims at the accurate detection of the parking space under the condition that the target parking space has incomplete mark lines, the camera in the panoramic shooting unit is used for calibrating the obtained internal and external parameters of the camera and the mapping relation between the image coordinate system and the world coordinate system, the perimeter of the parking mark line is calculated, and the calculated perimeter of the parking mark line is compared with the set threshold value by setting the high threshold value and the average threshold value of the perimeter of the parking mark line so as to judge whether the parking space mark is complete or not: and if the parking marking line is judged to be incomplete, the image segmentation technology is utilized to complement the missing parking line to form a closed rectangle, and the parking space detection is completed.
(II) automatic parking space identification
The identification of the automatic parking space comprises two parts of calculation of the gray difference value of the inner area of the parking mark line and calculation of the height of an obstacle in the parking mark line.
The gray scale difference value calculation of the parking mark line internal area is that the gray scale change difference of the parking mark line internal area is obviously different when the parking space is occupied and when the parking space is not occupied, the gray scale change difference value of the parking space mark line internal area needs to be calculated firstly, then the gray scale change difference average threshold value when the parking space is not occupied is set, and the gray scale change difference value of the parking space internal area is compared with the gray scale change difference average threshold value when the parking space is not occupied so as to preliminarily judge whether the parking space is occupied or not.
The height calculation of the obstacles in the parking marking line is to further judge the height of the obstacles to finally judge whether the parking space is occupied under the condition of preliminarily judging that the obstacles exist in the internal area of the parking space:
firstly, extracting obstacles in a parking space area by using an image segmentation algorithm, and displaying the obstacles in a two-dimensional image by using a minimum circumscribed rectangle, wherein the top point of the obstacle is the tangent point between the minimum circumscribed rectangle and the obstacles in the two-dimensional image;
and then, calculating the three-dimensional coordinates of the top point of the obstacle by using a monocular stereoscopic vision algorithm so as to calculate the height of the obstacle, and comparing the calculated height of the obstacle with the average minimum ground clearance threshold of the vehicle by setting the average minimum ground clearance threshold of the vehicle so as to finally judge whether the parking space is occupied.
Second, system structure
An example of the present invention is described below with reference to fig. 1, but the scope of the present invention is not limited thereto.
Referring to fig. 1, the automatic parking space detection and identification system based on the panoramic vision auxiliary system of the invention comprises a panoramic shooting unit, a vehicle-mounted central control large screen, an embedded processing unit and a power supply unit. The embedded processing unit is connected with the panoramic shooting unit and is in bidirectional link with the vehicle-mounted central control large screen, the power supply unit is connected with the embedded processing unit and the panoramic shooting unit, and the panoramic shooting unit is connected with the embedded processing unit. Wherein:
the panoramic shooting unit comprises 4 170-degree wide-angle cameras, the front camera is installed below a vehicle air inlet grille vehicle logo, the cameras on the two sides are installed above a vehicle B column, the rear camera is installed above the license plate frame, four pairs of wide-angle images shot in front, at the back, at the left and at the right of the vehicle are processed to generate a 360-degree seamlessly spliced top view for displaying scenes around the vehicle, and the top view is sent to the embedded processing unit;
the embedded unit is mainly responsible for completing the detection and identification of the parking spaces of the seamlessly spliced top view, sending the detection result to the vehicle-mounted electronic control unit ECU, providing basis for path planning and path tracking control in subsequent automatic parking, and meanwhile sending the detection result to a vehicle-mounted central control display screen through the image display module, wherein the vehicle-mounted central control display screen comprises an interface module, an image display module and an image processing module;
the interface module is used for being respectively connected with the panoramic shooting unit, the vehicle-mounted electronic control unit ECU, the vehicle-mounted central control large screen and the power supply unit;
the image processing module is used for completing the detection and identification functions of the parking space and comprises a detection submodule and an identification submodule.
And the image display module is used for sending the result detected by the image processing module to the vehicle-mounted central control display screen, displaying the detection result for the driver and selecting the target parking space.
Referring to fig. 2, the detection sub-module in the image processing module includes three parts, namely image preprocessing, parking mark line detection and parking mark line perimeter calculation. Wherein:
image preprocessing, including image graying and image edge detection, namely converting a color image into a gray image to graye the image, and then adopting a Canny operator to finish edge detection, wherein the Canny operator can meet three optimal edge detection evaluation standards of low error rate, high positioning property and minimum response;
the parking mark line segment extraction is to extract a line segment in an edge image by applying an LSD line segment detection algorithm on the basis of image preprocessing, and detect that the physical distance between parallel lines is w in the extracted line segment according to national standard GB50067-20141And the physical distance between two parallel line segment pairs is w2The two parallel line segment pairs complete the parking marking line detection.
The perimeter of the mark line of the parking space is calculated, the parking space is accurately detected under the condition that the mark line is incomplete in the target parking space, and the internal and external parameters of a camera in the panoramic shooting unit and the image coordinate system of the mark line of the parking space are utilizedThe mapping relation with the world coordinate system is calculated, and the perimeter P surrounded by all line segments of the mark line of the parking space is calculated1Then two thresholds of the perimeter of the stop line are set, and the high threshold PhAnd an average threshold value PmThe perimeter P enclosed by the line segments of the mark line of the parking space is calculated1Comparing with two set thresholds of the perimeter of the stop line:
if the perimeter P of the stop line1＞PhAnd judging that the parking space marking line is complete.
If the perimeter P of the stop lineh＞P1＞PmJudging that the parking space marking line is not complete;
and when the parking space marking line is judged to be incomplete, the image segmentation technology is utilized to complement the missing parking line, a closed rectangle is formed, and the parking space detection is completed.
Referring to fig. 3, the identification submodule in the image processing module includes two parts of calculating the gray level difference value and the obstacle height of the parking mark line. Wherein:
the gray level difference value of the area inside the parking mark line is calculated according to the gray level histogram inside the parking mark line, namely, the average threshold value T of the gray level difference when the parking space is not occupied is firstly set, and then the calculated gray level difference value T is calculated1Comparing with the average threshold value T of the gray scale change difference when the gray scale is not occupied:
if the gray level changes, the difference value T1If the parking is more than T, judging that no obstacle exists in the expected parking;
if the gray level changes, the difference value T1If the number is less than T, judging that an obstacle exists in the expected parking;
the method comprises the steps of firstly, when an obstacle is judged to be in the expected parking space, marking the outline of the obstacle in the parking space by using an image segmentation algorithm, and calculating the height H of the obstacle by using a stereoscopic vision algorithm by using the visual difference generated by vehicle displacement1The calculated height H of the obstacle is calculated by setting the minimum ground clearance of the vehicle1Comparing with the vehicle ground clearance minimum average threshold value H:
if the height of the obstacle is H1If the parking space is less than H, the parking space is judged to be unoccupied,
if the height of the obstacle is H1And if the parking space is larger than H, the parking space is judged to be occupied.
When the system identifies that the parking space is not occupied, the identification result is sent to the vehicle-mounted electronic control unit ECU through the embedded unit interface module so as to complete subsequent path planning and path tracking control in automatic parking, and meanwhile, the identification result is sent to the vehicle-mounted central control large screen through the embedded unit image display module so as to display a detection result for a driver to select a target parking space.
When the system identifies that the parking space is occupied, the identification result is sent to the embedded unit image processing module detection submodule, and a new round of parking space detection is carried out again.
While the invention has been particularly shown and described with reference to exemplary embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.
Claims (6)
1. An automatic parking space detection and identification system based on a panoramic vision auxiliary system comprises:
the panoramic shooting unit is used for acquiring images around the vehicle body, generating a seamless spliced 360-degree top view through camera calibration, distortion correction, top view transformation and image splicing and transmitting the seamless spliced 360-degree top view to the embedded unit;
the embedded unit is used for processing the panoramic image acquired by the panoramic shooting module, detecting the parking space, judging whether the parking space is occupied or not and sending the detection result to the vehicle-mounted electronic control unit ECU and the vehicle-mounted central control display screen;
the vehicle-mounted central control display screen is used for displaying the parking space detection result transmitted by the embedded module;
the method is characterized in that: the embedded unit includes:
the interface module is used for sending the detection result of the embedded module to the vehicle-mounted electronic control unit ECU;
an image processing module including a detection sub-module and an identification sub-module,
the detection submodule performs image preprocessing on a seamless spliced 360-degree top view, and extracts a parking space mark line in the top view by using a line segment detection algorithm, and the detection submodule is realized as follows:
1) calculating the gradient value and gradient direction of each pixel point in the image, and generating a linear support area;
2) performing rectangle approximation on the linear support area, calculating the center point, the angle of the direction, the length and the width of the rectangle, and representing a line segment by using the rectangle;
3) based on the Helmholtz principle, calculating the number NFA of false alarms according to the number n of total pixel points in the region and the number k of pixel points in the direction consistent with that of the rectangular region, and when the NFA is smaller than the average value epsilon of the perfect noise image, judging whether the straight line support region rectangle is meaningful or not, namely, the straight line is detected;
4) in all the straight lines detected in the step 3), searching a parallel line segment pair with a physical distance of about 0.2 m according to national standard GB 50067-2014;
5) in all the parallel line segment pairs with fixed distances detected in the step 4), searching two parallel line segment pairs with a physical distance of about 2.5 meters or 5.5 meters between the two parallel line segment pairs according to the national standard GB50067-2014, and obtaining a mark line of the parking space;
and calculating the perimeter of the parking space marking line, and judging whether the parking space marking line is complete according to the perimeter: if the parking space is incomplete, the parking space marking line is completed by using an image segmentation algorithm, and whether the parking space is an optional parking space is judged;
the identification submodule judges whether shadows or obstacles exist in the optional parking spaces or not by calculating the gray level change difference value in the parking spaces for the target parking spaces detected by the detection submodule, and calculates the heights of the obstacles if the shadows or the obstacles exist, so as to judge whether the optional parking spaces are occupied or not;
and the image display sub-module is used for displaying the detection result of the optional parking space of the embedded unit in the vehicle-mounted central control display screen.
2. The system as recited in claim 1, wherein: the panorama shooting unit includes 4 cameras, and these cameras are installed respectively around the vehicle, and leading camera is installed in vehicle air inlet grille car logo below promptly, and both sides camera installation vehicle B post top, back camera are installed in license plate frame top, gather the real-time image on ground all around the vehicle respectively.
3. The system as recited in claim 1, wherein: the embedded unit detection submodule firstly performs image preprocessing on a seamlessly spliced 360-degree top view, namely converts a color image acquired by a panoramic shooting unit into a gray image, and then generates an edge image by using a Canny edge detection algorithm so as to improve the image processing efficiency.
4. The system as recited in claim 1, wherein: aiming at the parking line mark, the embedded unit detection submodule calculates the perimeter P enclosed by each line segment of the parking space mark line by utilizing the internal and external parameters of a camera in the panoramic shooting unit and the mapping relation of the parking mark line in an image coordinate system and a world coordinate system1。
5. The system as recited in claim 1, wherein: the embedded unit detection submodule is used for accurately detecting the parking space under the condition that the marking lines of the parking space are incomplete, and two thresholds of the perimeter of the parking line, namely a high threshold P, are set firstlyhAnd an average threshold value PmThen the perimeter P enclosed by the line segments of the parking space marking line1And a high threshold value PhAnd an average threshold value PmAnd (3) comparison:
if the perimeter P of the stop line1＞PhJudging that the parking space marking line is complete;
if the perimeter P of the stop lineh＞P1＞PmIf the parking space marking line is not complete, it is goodAnd (5) completing the missing stop lines by using an image segmentation technology to form a closed rectangle and finish the parking space detection.
6. The system as recited in claim 1, wherein: the embedded unit identification submodule identifies whether the parking space is occupied or not under the scene that shadows or obstacles exist in the parking space, and the embedded unit identification submodule is realized as follows:
firstly, calculating a gray level change difference value T by utilizing a gray level histogram in a parking space area for the parking space detected by the detection submodule1；
Then, setting an average threshold value T of gray level change difference when the parking space is not occupied, and changing the gray level change difference value T in the parking space area1And comparing the average threshold value T of the gray level change difference when the parking space is not occupied:
if the gray level changes, the difference value T1If the parking space is less than T, no shadow or barrier exists in the parking space area, and the parking space is judged to be an optional parking space;
if the gray level changes, the difference value T1When the height is greater than T, a shadow or an obstacle exists in the parking space area, and the height of the obstacle needs to be detected;
finally, extracting the obstacles in the parking space area by using an image segmentation algorithm, and calculating the height H of the obstacles by using a stereoscopic vision algorithm1And calculating the height H of the obstacle1Comparing with the average minimum ground clearance of the vehicle as H:
if the height of the obstacle is H1If the parking space is less than H, the parking space is judged to be unoccupied;
if the height of the obstacle is H1And if the parking space is larger than H, the parking space is judged to be occupied.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710864999.8A CN107738612B (en) | 2017-09-22 | 2017-09-22 | Automatic parking space detection and identification system based on panoramic vision auxiliary system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710864999.8A CN107738612B (en) | 2017-09-22 | 2017-09-22 | Automatic parking space detection and identification system based on panoramic vision auxiliary system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107738612A CN107738612A (en) | 2018-02-27 |
| CN107738612B true CN107738612B (en) | 2020-04-14 |
Family
ID=61235234
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710864999.8A Active CN107738612B (en) | 2017-09-22 | 2017-09-22 | Automatic parking space detection and identification system based on panoramic vision auxiliary system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107738612B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4016496A4 (en) * | 2020-10-20 | 2022-07-20 | Guangzhou Xiaopeng Autopilot Technology Co., Ltd. | Parking space detection method and apparatus, vehicle and readable medium |
Families Citing this family (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110654375A (en) | 2018-06-29 | 2020-01-07 | 比亚迪股份有限公司 | Automatic parking method, device and system and vehicle |
| CN109278861B (en) * | 2018-07-05 | 2021-06-11 | 惠州市德赛西威汽车电子股份有限公司 | Steering wheel return-to-normal reminding method and system based on automobile look-around |
| CN109631896B (en) * | 2018-07-23 | 2020-07-28 | 同济大学 | Parking lot autonomous parking positioning method based on vehicle vision and motion information |
| CN110889974B (en) * | 2018-09-11 | 2021-02-19 | 广州汽车集团股份有限公司 | Intelligent parking space identification method and device and automobile |
| CN109508682A (en) * | 2018-11-20 | 2019-03-22 | 成都通甲优博科技有限责任公司 | A kind of detection method on panorama parking stall |
| CN109685000A (en) * | 2018-12-21 | 2019-04-26 | 广州小鹏汽车科技有限公司 | A kind of method for detecting parking stalls and device of view-based access control model |
| CN109740521B (en) * | 2018-12-29 | 2021-02-19 | 百度在线网络技术（北京）有限公司 | Parking space position determining method and device for automatic parking, electronic device and computer readable medium |
| CN109727481A (en) * | 2019-01-08 | 2019-05-07 | 北京优位智停科技有限公司 | A kind of more mesh parking position monitorings and detection device |
| CN109649384B (en) * | 2019-02-15 | 2020-08-14 | 华域汽车系统股份有限公司 | Parking assisting method |
| CN109754639B (en) * | 2019-02-28 | 2020-12-25 | 北京智行者科技有限公司 | Parking garage entry method and device |
| CN109934140B (en) * | 2019-03-01 | 2022-12-02 | 武汉光庭科技有限公司 | Automatic reversing auxiliary parking method and system based on detection of ground transverse marking |
| CN111746503B (en) * | 2019-03-27 | 2022-09-06 | 上海欧菲智能车联科技有限公司 | Parking method, system, device, vehicle and computer readable storage medium |
| CN111429469B (en) * | 2019-04-17 | 2023-11-03 | 杭州海康威视数字技术股份有限公司 | Berth position determining method and device, electronic equipment and storage medium |
| CN112009461A (en) * | 2019-05-13 | 2020-12-01 | 上海博泰悦臻网络技术服务有限公司 | Parking assist method and parking assist system |
| US10867192B1 (en) * | 2019-08-06 | 2020-12-15 | Black Sesame International Holding Limited | Real-time robust surround view parking space detection and tracking |
| CN112389419B (en) * | 2019-08-12 | 2022-04-08 | 欧特明电子股份有限公司 | Method for identifying parking space and parking assistance system |
| CN110751850B (en) * | 2019-08-30 | 2023-03-07 | 的卢技术有限公司 | Parking space identification method and system based on deep neural network |
| CN110415555B (en) * | 2019-08-30 | 2020-09-29 | 的卢技术有限公司 | Effective lineation parking space identification method and system based on deep learning |
| CN110544386A (en) * | 2019-09-18 | 2019-12-06 | 奇瑞汽车股份有限公司 | parking space identification method and device and storage medium |
| CN111071248B (en) * | 2019-12-24 | 2021-11-05 | 浙江合众新能源汽车有限公司 | Intelligent parking method based on electronic power-assisted brake |
| CN111968132A (en) * | 2020-07-28 | 2020-11-20 | 哈尔滨工业大学 | Panoramic vision-based relative pose calculation method for wireless charging alignment |
| CN113060125B (en) * | 2020-08-31 | 2022-08-30 | 惠州华阳通用电子有限公司 | Parking assisting method and device |
| CN112183413B (en) * | 2020-09-30 | 2024-05-14 | 东风柳州汽车有限公司 | Parking space detection method and device, storage medium and vehicle |
| CN112767425A (en) * | 2020-12-30 | 2021-05-07 | 智车优行科技（北京）有限公司 | Parking space detection method and device based on vision |
| CN113320474A (en) * | 2021-07-08 | 2021-08-31 | 长沙立中汽车设计开发股份有限公司 | Automatic parking method and device based on panoramic image and human-computer interaction |
| CN113554882A (en) * | 2021-07-20 | 2021-10-26 | 阿波罗智联(北京)科技有限公司 | Method, apparatus, device and storage medium for outputting information |
| CN115909795B (en) * | 2023-03-09 | 2023-06-23 | 斯润天朗（北京）科技有限公司 | Autonomous parking system and method based on parking lot cooperation |
| CN117261877B (en) * | 2023-08-18 | 2024-05-14 | 广州优保爱驾科技有限公司 | Self-correction image acquisition system and method based on vehicle appearance change |
| CN118015599B (en) * | 2024-04-09 | 2024-06-25 | 深圳市前海铼停科技有限公司 | Binocular parking identification method, system and processor based on image stitching |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000134608A (en) * | 1998-10-22 | 2000-05-12 | Fujitsu Ten Ltd | Rear monitoring device for vehicle |
| KR101327736B1 (en) * | 2011-12-23 | 2013-11-11 | 현대자동차주식회사 | AVM Top View Based Parking Support System |
| CN102774324B (en) * | 2012-07-06 | 2014-12-10 | 广东好帮手电子科技股份有限公司 | Panoramic parking assist system and implementation method thereof |
| GB2515800B (en) * | 2013-07-04 | 2017-06-07 | Jaguar Land Rover Ltd | Vehicle control system |
| CN105539430B (en) * | 2015-12-29 | 2018-04-03 | 北京理工大学 | A kind of people's car mutual intelligent parking method based on handheld terminal |
-
2017
- 2017-09-22 CN CN201710864999.8A patent/CN107738612B/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4016496A4 (en) * | 2020-10-20 | 2022-07-20 | Guangzhou Xiaopeng Autopilot Technology Co., Ltd. | Parking space detection method and apparatus, vehicle and readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107738612A (en) | 2018-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107738612B (en) | Automatic parking space detection and identification system based on panoramic vision auxiliary system | |
| US11854272B2 (en) | Hazard detection from a camera in a scene with moving shadows | |
| US9846812B2 (en) | Image recognition system for a vehicle and corresponding method | |
| Goldbeck et al. | Lane detection and tracking by video sensors | |
| WO2020097840A1 (en) | Systems and methods for correcting a high-definition map based on detection of obstructing objects | |
| JP4919036B2 (en) | Moving object recognition device | |
| JP4930046B2 (en) | Road surface discrimination method and road surface discrimination device | |
| CN110738121A (en) | front vehicle detection method and detection system | |
| US20130286205A1 (en) | Approaching object detection device and method for detecting approaching objects | |
| CN104881645B (en) | The vehicle front mesh object detection method of feature based point mutual information and optical flow method | |
| CN105225482A (en) | Based on vehicle detecting system and the method for binocular stereo vision | |
| CN110334678A (en) | A kind of pedestrian detection method of view-based access control model fusion | |
| WO2015024407A1 (en) | Power robot based binocular vision navigation system and method based on | |
| Lin et al. | Lane departure and front collision warning using a single camera | |
| CN104636724B (en) | A kind of quick Pedestrians and vehicles detection method of in-vehicle camera based on goal congruence | |
| CN104751119A (en) | Rapid detecting and tracking method for pedestrians based on information fusion | |
| CN109063632B (en) | Parking space characteristic screening method based on binocular vision | |
| CN104063882A (en) | Vehicle video speed measuring method based on binocular camera | |
| Ponsa et al. | On-board image-based vehicle detection and tracking | |
| JP4344860B2 (en) | Road plan area and obstacle detection method using stereo image | |
| KR100508763B1 (en) | System for detecting and recognizing a car plate area by using stereo vision and method thereof | |
| CN111860270B (en) | Obstacle detection method and device based on fisheye camera | |
| Yang | Estimation of vehicle's lateral position via the Lucas-Kanade optical flow method | |
| JP4055785B2 (en) | Moving object height detection method and apparatus, and object shape determination method and apparatus | |
| JP4333683B2 (en) | Windshield range detection device, method and program |
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 |