CN111845713A - Parking route planning method based on vehicle-mounted 3D panoramic looking around - Google Patents
Parking route planning method based on vehicle-mounted 3D panoramic looking around Download PDFInfo
- Publication number
- CN111845713A CN111845713A CN201910346054.6A CN201910346054A CN111845713A CN 111845713 A CN111845713 A CN 111845713A CN 201910346054 A CN201910346054 A CN 201910346054A CN 111845713 A CN111845713 A CN 111845713A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- panoramic
- parking
- camera
- around
- 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 28
- 238000012937 correction Methods 0.000 claims abstract description 11
- 230000001133 acceleration Effects 0.000 claims abstract description 6
- 102100034112 Alkyldihydroxyacetonephosphate synthase, peroxisomal Human genes 0.000 claims abstract description 5
- 101000799143 Homo sapiens Alkyldihydroxyacetonephosphate synthase, peroxisomal Proteins 0.000 claims abstract description 5
- 238000000848 angular dependent Auger electron spectroscopy Methods 0.000 claims abstract description 5
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 4
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 4
- 238000007500 overflow downdraw method Methods 0.000 claims description 3
- 238000011426 transformation method Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 10
- 238000012545 processing Methods 0.000 abstract description 2
- 230000000007 visual effect Effects 0.000 abstract description 2
- 230000004888 barrier function Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/06—Automatic manoeuvring for parking
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a parking route planning method based on vehicle-mounted 3D panoramic looking around, which comprises the following steps: route planning, image acquisition and image splicing and synthesis; the invention has the advantages that the cameras are arranged at eight different directions of the vehicle, the image picture without blind areas is provided, the imx6+ NVP6324 processor is matched, the processing capabilities of image splicing, correction and the like are improved, meanwhile, the image quality is ensured to be clear, and high-definition vehicle panoramic images can be obtained even at night with weak light; according to the invention, the spliced panoramic image is subjected to combined calibration and distortion correction through the vehicle corner information acquired by the corner sensor and the vehicle speed and acceleration information acquired by ADAS, so as to obtain a more real vehicle panoramic image around the vehicle; the 3D panoramic all-round viewing technology is adopted to guide the parking route of the vehicle to give visual influence to the driver around the vehicle, and meanwhile, the cooperation of the ultrasonic sensor ensures that the situations of collision and the like cannot occur in the parking process of the vehicle.
Description
Technical Field
The invention relates to the technical field of automatic parking, in particular to a parking route planning method based on vehicle-mounted 3D panoramic looking around.
Background
With the rapid development of the vehicle manufacturing industry, vehicle electronics technology is continuously increasing. As two typical examples of the application of artificial intelligence in the field of vehicles, the automatic parking technology and the 3D panoramic looking around technology are considered as two important signs for realizing automatic driving. The automatic parking path selection is that the vehicle acquires the parking space condition of the parking lot and the position of the vehicle through a wireless communication technology, and the path of the vehicle reaching the parking space is automatically planned through a computer. The 3D panoramic all-round looking technology completes three-dimensional live-action modeling through technologies such as artificial intelligence and image recognition, can help a driver to accurately judge the self condition of the automobile and the state around the automobile, accurately eliminates blind spots of the automobile, and avoids safety problems. However, the existing automatic parking path selection method can only realize the function of planning a parking driving path, and cannot judge whether barriers exist on the driving path and a parking space, although a vehicle-mounted ultrasonic or infrared sensor can identify the barriers around the vehicle, the identification range is limited, so that the barriers can not be identified in an all-around and dead-angle-free manner, and meanwhile, the conditions around the vehicle can not be visually displayed, and a driver parking error may occur.
Disclosure of Invention
The invention aims to provide a parking route planning method based on vehicle-mounted 3D panoramic looking around, which applies a 3D panoramic looking around technology to vehicle parking planning, realizes identification barriers without dead angles of 360 degrees around a vehicle, and guides the vehicle to safely enter a parking space.
In order to achieve the purpose, the technical scheme of the invention is as follows: a parking route planning method based on vehicle-mounted 3D panoramic looking around comprises the following steps:
step 1, a vehicle is connected with a parking lot cloud through a WIFI network, space position information of each parking space and the use state of each parking space are obtained, and a vehicle parking driving route is automatically planned;
step 2, in the running process of the vehicle, the camera device collects spherical images of the right front, the left front, the right left, the right rear, the left rear and the right rear of the vehicle;
step 3, splicing repeated parts of the spherical images in the eight directions obtained in the step 2 to obtain a spliced image, and simultaneously carrying out distortion correction on the spliced image according to vehicle speed, acceleration and rotation angle parameters acquired by a vehicle ADAS system to obtain a real panoramic image;
step 4, carrying out binarization on the panoramic image obtained in the step 3, identifying parking spaces right in front of, right to left of and right of the vehicle, and starting parking if the parking spaces are detected;
And 5, in the process of parking the vehicle, the panoramic image displays the position relation between the parking space and the vehicle in real time, so that a driver can conveniently park the vehicle.
Preferably, the imx6+ NVP6324 processor is adopted in step 3 to perform image stitching, distortion correction and panoramic video synthesis.
Preferably, in step 3, a polynomial transformation method or an inverse division model is used to correct distortion of the stitched image.
Preferably, in the step 3, the stitching seam of the stitched image is eliminated by a weighted fusion method.
Preferably, the camera device comprises a fisheye camera and a binocular camera, and is connected with the imx6+ NVP6324 processor through a Can bus.
Preferably, the number of the cameras in step 2 is eight, wherein a front camera is installed in the center of a front windshield of the vehicle, a left front camera and a right front camera are respectively installed on the left side and the right side of a front cover of the vehicle, a front left camera and a front right camera are respectively installed at the bottoms of a left rearview mirror and a right rearview mirror, and a front rear camera, a left rear camera and a right rear camera are respectively installed in the center, the left side and the right side of a rear cover of the vehicle.
Preferably, the front camera and the rear camera are binocular cameras, and the rest cameras are fisheye cameras.
Preferably, the vehicle further comprises four ultrasonic sensors, and the four ultrasonic sensors are respectively arranged in four directions of the front, the back, the left and the right of the vehicle.
Preferably, the step 4 comprises the following steps:
step 4.1, in the driving process of the vehicle, obtaining a panoramic image around the vehicle by the binarized panoramic image so as to confirm whether the vehicle is in the parking space;
and 4.2, detecting the relative distances of the obstacles in the front direction, the rear direction, the left direction and the right direction of the vehicle by the ultrasonic sensor, and judging whether the relative distances meet the requirement that the vehicle is warehoused and parked in a linear-curve-linear mode or a curve-linear mode according to the prestored vehicle size.
In conclusion, the beneficial effects of the invention are as follows:
(1) the invention arranges the cameras in eight different directions of the vehicle, provides image pictures without blind areas, and can ensure clear image quality while improving the processing capabilities of image splicing, correction and the like by matching with an imx6+ NVP6324 processor, and can obtain high-definition vehicle panoramic images even at night with weak light;
(1) according to the invention, the spliced panoramic image is subjected to combined calibration and distortion correction through the vehicle corner information acquired by the corner sensor and the vehicle speed and acceleration information acquired by ADAS, so as to obtain a more real vehicle panoramic image around the vehicle;
(2) Compared with the traditional GPS guidance, the 3D panoramic looking-around technology is adopted to guide the vehicle parking route planning to give visual influences to the driver around the vehicle more visually, and meanwhile, the 3D panoramic looking-around technology is matched with the ultrasonic sensor to ensure that the situations of collision and the like cannot occur in the vehicle parking process.
Drawings
Fig. 1 is a work flow chart of a parking route planning method based on a vehicle-mounted 3D panoramic looking around.
Detailed Description
The embodiments of the present invention are further described below with reference to the drawings.
Referring to fig. 1, a parking route planning method based on a vehicle-mounted 3D panoramic looking around includes the following steps:
step 1, a vehicle is connected with a parking lot cloud through a WIFI network, space position information of each parking space and the use state of each parking space are obtained, and a vehicle parking driving route is automatically planned;
step 2, in the running process of the vehicle, the camera device collects spherical images of the right front, the left front, the right left, the right rear, the left rear and the right rear of the vehicle;
step 3, splicing repeated parts of the spherical images in the eight directions obtained in the step 2 to obtain a spliced image, and simultaneously carrying out distortion correction on the spliced image according to vehicle speed, acceleration and rotation angle parameters acquired by a vehicle ADAS system to obtain a real panoramic image;
Step 4, carrying out binarization on the panoramic image obtained in the step 3, identifying parking spaces right in front of, right to left of and right of the vehicle, and starting parking if the parking spaces are detected;
and 5, in the process of parking the vehicle, the panoramic image displays the position relation between the parking space and the vehicle in real time, so that a driver can conveniently park the vehicle.
Preferably, the imx6+ NVP6324 processor is adopted in step 3 to perform image stitching, distortion correction and panoramic video synthesis.
Preferably, in step 3, distortion correction of the stitched image is performed by using a polynomial transformation method or an inverse division model, so that the problem that influence of factors such as speed, acceleration and turning angle of the vehicle is real can be compensated.
Preferably, in the step 3, the splicing seam of the spliced images is eliminated by adopting a weighted fusion method, so that the problem that the joint of different camera devices has black lines and the like to influence the merging quality is avoided.
Preferably, the camera device comprises a fisheye camera and a binocular camera, and is connected with the imx6+ NVP6324 processor through a Can bus.
Preferably, the number of the cameras in step 2 is eight, wherein a front camera is installed in the center of a front windshield of the vehicle, a left front camera and a right front camera are respectively installed on the left side and the right side of a front cover of the vehicle, a front left camera and a front right camera are respectively installed at the bottoms of a left rearview mirror and a right rearview mirror, and a front rear camera, a left rear camera and a right rear camera are respectively installed in the center, the left side and the right side of a rear cover of the vehicle.
Preferably, the front camera and the rear camera are binocular cameras, and the rest cameras are fisheye cameras.
Preferably, the vehicle further comprises ultrasonic sensors, the four ultrasonic sensors are respectively installed in four directions of the front, the rear, the left and the right of the vehicle, the ultrasonic sensors and the eight image pick-up devices are simultaneously used for identifying whether obstacles exist around the vehicle, and the obstacles are directly judged visually through the image pick-up devices.
Preferably, the step 4 comprises the following steps:
step 4.1, in the driving process of the vehicle, obtaining a panoramic image around the vehicle by the binarized panoramic image so as to confirm whether the vehicle is in the parking space;
and 4.2, detecting the relative distances of the obstacles in the front direction, the rear direction, the left direction and the right direction of the vehicle by the ultrasonic sensor, and judging whether the relative distances meet the requirement that the vehicle is warehoused and parked in a linear-curve-linear mode or a curve-linear mode according to the prestored vehicle size.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all equivalent structural changes made by using the contents of the present specification, or any direct or indirect application attached to other related technical fields, are included in the scope of the present invention.
Claims (9)
1. A parking route planning method based on vehicle-mounted 3D panoramic looking around is characterized by comprising the following steps:
step 1, a vehicle is connected with a parking lot cloud through a WIFI network, space position information of each parking space and the use state of each parking space are obtained, and a vehicle parking driving route is automatically planned;
step 2, in the running process of the vehicle, the camera device collects spherical images of the right front, the left front, the right left, the right rear, the left rear and the right rear of the vehicle;
step 3, splicing repeated parts of the spherical images in the eight directions obtained in the step 2 to obtain a spliced image, and simultaneously carrying out distortion correction on the spliced image according to vehicle speed, acceleration and rotation angle parameters acquired by a vehicle ADAS system to obtain a real panoramic image;
step 4, carrying out binarization on the panoramic image obtained in the step 3, identifying parking spaces right in front of, right to left of and right of the vehicle, and starting parking if the parking spaces are detected;
and 5, in the process of parking the vehicle, the panoramic image displays the position relation between the parking space and the vehicle in real time, so that a driver can conveniently park the vehicle.
2. The vehicle-mounted 3D panoramic looking-around-based parking route planning method according to claim 1, characterized in that: and 3, performing image splicing, distortion correction and panoramic video synthesis by adopting an imx6+ NVP6324 processor.
3. The vehicle-mounted 3D panoramic looking-around-based parking route planning method according to claim 1, characterized in that: and 3, correcting the distortion of the spliced image by adopting a polynomial transformation method or an inverse division model.
4. The vehicle-mounted 3D panoramic looking-around-based parking route planning method according to claim 1, characterized in that: and 3, eliminating the splicing seams of the spliced images by adopting a weighted fusion method.
5. The vehicle-mounted 3D panoramic looking-around-based parking route planning method according to claim 1, characterized in that: the camera device comprises a fisheye camera and a binocular camera, and is connected with the imx6+ NVP6324 processor through a Can bus.
6. The vehicle-mounted 3D panoramic looking-around-based parking route planning method according to claim 5, characterized in that: the number of the cameras in the step 2 is eight, wherein a front camera is arranged in the center of a front windshield of the vehicle, a left front camera and a right front camera are respectively arranged on the left side and the right side of a front cover of the vehicle, a front left camera and a front right camera are respectively arranged at the bottoms of a left rearview mirror and a right rearview mirror, and a front rear camera, a left rear camera and a right rear camera are respectively arranged in the center, the left side and the right side of a rear cover of the vehicle.
7. The vehicle-mounted 3D panoramic looking-around-based parking route planning method according to claim 6, characterized in that: the front camera and the rear camera are binocular cameras, and the remaining cameras are fisheye cameras.
8. The vehicle-mounted 3D panoramic looking-around-based parking route planning method according to claim 1, characterized in that: the vehicle ultrasonic detection system is characterized by further comprising four ultrasonic sensors which are respectively arranged in four directions of front, back, left and right of the vehicle.
9. The vehicle-mounted 3D panoramic looking-around-based parking route planning method according to claim 8, wherein the step 4 comprises the following steps:
step 4.1, in the driving process of the vehicle, obtaining a panoramic image around the vehicle by the binarized panoramic image so as to confirm whether the vehicle is in the parking space;
and 4.2, detecting the relative distances of the obstacles in the front direction, the rear direction, the left direction and the right direction of the vehicle by the ultrasonic sensor, and judging whether the relative distances meet the requirement that the vehicle is warehoused and parked in a linear-curve-linear mode or a curve-linear mode according to the prestored vehicle size.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910346054.6A CN111845713A (en) | 2019-04-26 | 2019-04-26 | Parking route planning method based on vehicle-mounted 3D panoramic looking around |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910346054.6A CN111845713A (en) | 2019-04-26 | 2019-04-26 | Parking route planning method based on vehicle-mounted 3D panoramic looking around |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111845713A true CN111845713A (en) | 2020-10-30 |
Family
ID=72951829
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910346054.6A Pending CN111845713A (en) | 2019-04-26 | 2019-04-26 | Parking route planning method based on vehicle-mounted 3D panoramic looking around |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111845713A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114274948A (en) * | 2021-12-15 | 2022-04-05 | 武汉光庭信息技术股份有限公司 | Automatic parking method and device based on 360-degree panorama |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7415335B2 (en) * | 2003-11-21 | 2008-08-19 | Harris Corporation | Mobile data collection and processing system and methods |
| KR101188588B1 (en) * | 2008-03-27 | 2012-10-08 | 주식회사 만도 | Monocular Motion Stereo-Based Free Parking Space Detection Apparatus and Method |
| CN104182933A (en) * | 2013-05-28 | 2014-12-03 | 东北大学 | Wide-angle lens image distortion correcting method based on reverse division model |
| CN104865578A (en) * | 2015-05-12 | 2015-08-26 | 上海交通大学 | Indoor parking lot high-precision map generation device and method |
| CN105946853A (en) * | 2016-04-28 | 2016-09-21 | 中山大学 | Long-distance automatic parking system and method based on multi-sensor fusion |
| CN106994936A (en) * | 2016-01-22 | 2017-08-01 | 广州求远电子科技有限公司 | A kind of 3D panoramic parking assist systems |
| CN108909625A (en) * | 2018-06-22 | 2018-11-30 | 河海大学常州校区 | Vehicle bottom based on panoramic looking-around system ground plane display method |
-
2019
- 2019-04-26 CN CN201910346054.6A patent/CN111845713A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7415335B2 (en) * | 2003-11-21 | 2008-08-19 | Harris Corporation | Mobile data collection and processing system and methods |
| KR101188588B1 (en) * | 2008-03-27 | 2012-10-08 | 주식회사 만도 | Monocular Motion Stereo-Based Free Parking Space Detection Apparatus and Method |
| CN104182933A (en) * | 2013-05-28 | 2014-12-03 | 东北大学 | Wide-angle lens image distortion correcting method based on reverse division model |
| CN104865578A (en) * | 2015-05-12 | 2015-08-26 | 上海交通大学 | Indoor parking lot high-precision map generation device and method |
| CN106994936A (en) * | 2016-01-22 | 2017-08-01 | 广州求远电子科技有限公司 | A kind of 3D panoramic parking assist systems |
| CN105946853A (en) * | 2016-04-28 | 2016-09-21 | 中山大学 | Long-distance automatic parking system and method based on multi-sensor fusion |
| CN108909625A (en) * | 2018-06-22 | 2018-11-30 | 河海大学常州校区 | Vehicle bottom based on panoramic looking-around system ground plane display method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114274948A (en) * | 2021-12-15 | 2022-04-05 | 武汉光庭信息技术股份有限公司 | Automatic parking method and device based on 360-degree panorama |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7245295B2 (en) | METHOD AND DEVICE FOR DISPLAYING SURROUNDING SCENE OF VEHICLE-TOUCHED VEHICLE COMBINATION | |
| CN109435852B (en) | Panoramic auxiliary driving system and method for large truck | |
| CN112180373B (en) | Multi-sensor fusion intelligent parking system and method | |
| CN111046743B (en) | Barrier information labeling method and device, electronic equipment and storage medium | |
| CN106573577B (en) | Display system and method | |
| JP4695167B2 (en) | Method and apparatus for correcting distortion and enhancing an image in a vehicle rear view system | |
| CN103763517B (en) | Vehicle-mounted around view display method and system | |
| US8199975B2 (en) | System and method for side vision detection of obstacles for vehicles | |
| CN105141945B (en) | Panorama camera chain (VPM) on-line calibration | |
| JP5132249B2 (en) | In-vehicle imaging device | |
| US20140114534A1 (en) | Dynamic rearview mirror display features | |
| US20150042799A1 (en) | Object highlighting and sensing in vehicle image display systems | |
| US20050163343A1 (en) | Movable body circumstance monitoring apparatus | |
| US20110169957A1 (en) | Vehicle Image Processing Method | |
| CN102163331A (en) | Image-assisting system using calibration method | |
| CN104859538A (en) | Vision-based object sensing and highlighting in vehicle image display systems | |
| CN107507131A (en) | 360 degree of panorama reverse image generation methods based on single camera | |
| CN102158684A (en) | Self-adapting scene image auxiliary system with image enhancement function | |
| CN102196242A (en) | Self-adaptive scene image auxiliary system with image enhancing function | |
| JP2004240480A (en) | Operation support device | |
| JP2008222153A (en) | Merging support device | |
| CN113320474A (en) | Automatic parking method and device based on panoramic image and human-computer interaction | |
| JP2012071833A (en) | Display device for vehicle and image display control method for vehicle | |
| JP2006027556A (en) | Periphery monitor for vehicle | |
| JP2012071832A (en) | Display device for vehicle and image display control method for vehicle |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201030 |
|
| RJ01 | Rejection of invention patent application after publication |