CN107738612A - The detection of automatic parking parking stall and identifying system based on panoramic vision accessory system - Google Patents

The detection of automatic parking parking stall and identifying system based on panoramic vision accessory system Download PDF

Info

Publication number
CN107738612A
CN107738612A CN201710864999.8A CN201710864999A CN107738612A CN 107738612 A CN107738612 A CN 107738612A CN 201710864999 A CN201710864999 A CN 201710864999A CN 107738612 A CN107738612 A CN 107738612A
Authority
CN
China
Prior art keywords
parking stall
detection
parking
image
module
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.)
Granted
Application number
CN201710864999.8A
Other languages
Chinese (zh)
Other versions
CN107738612B (en
Inventor
李长乐
李磊
蔡雪莲
张锲石
陈睿
朱丽娜
韩沁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xidian University
Original Assignee
Xidian University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xidian University filed Critical Xidian University
Priority to CN201710864999.8A priority Critical patent/CN107738612B/en
Publication of CN107738612A publication Critical patent/CN107738612A/en
Application granted granted Critical
Publication of CN107738612B publication Critical patent/CN107738612B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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

Abstract

The invention discloses a kind of automatic parking parking stall detection based on panoramic vision accessory system and identifying system, mainly solves prior art because parking stall mark line is incomplete, inside has shade or barrier and causes parking stall detection with identifying the problem of inaccurate.It includes camera detection module and identification module, and camera is arranged on vehicle periphery, is spliced into the seamless panoramic image that can reflect vehicle periphery information；Detection module completes the detection of parking stall mark line and the parking stall detection in the case where parking stall mark line is imperfect is completed by mark line girth；Identification module identifies that the detection and recognition result are shown by vehicle-mounted middle control large-size screen monitors by calculating the parking stall that parking stall interior intensity variation value and obstacle height are completed to exist in parking stall under shade or barrier.The present invention realizes efficient, accurate parking stall detection and identification, provides effective foundation for path planning in follow-up automatic parking and path following control, parking spot is found available for driver.

Description

The detection of automatic parking parking stall and identifying system based on panoramic vision accessory system
Technical field
The invention belongs to computer vision processing technology field, and in particular to a kind of detection of automatic parking parking stall and identification System, parking place is found available for driver.
Background technology
With the rapid increase of car ownership, what is showed in City scenarios the problem of " parking difficulty " is more and more prominent. Driver is when parking, because by the visual field and parking stall be narrow and small etc., objective condition is limited, and technology and psychic influence, Wiping easily occurs and touches accident, brings unnecessary loss.One effective parking assistance system, can help that driver is quick, peace Full completion parking manoeuvres, automated parking system can not be automatically performed by the manipulation of driver it is safe and accurate park into Position.
At present, the conventional automatic parking parking stall detection of in the market and recognition methods are the methods based on ultrasonic radar. However, vehicle, which is parked, before and after the method requirement target parking position based on ultrasonic radar can realize parking stall measure, and ultrasound Ripple radar detecting method has that detection range is small, the shortcomings that blind area etc. be present.For this problem, by ultrasonic wave and machine vision The parking assisting system for the view-based access control model being combined is undoubtedly the developing direction of following parking assisting system.But it is currently based on and regards Detection of the parking stall detection of feel with recognition methods just for ground parking position mark line under common scenarios, and have ignored target and stop There are the parking stall test problems under the not congruent complex situations of barrier, shade, mark line in parking stall, so how complex Scene under more accurately and reliably to detect parking stall be the urgent need for solving the problems, such as Current traffic management.
The content of the invention
It is an object of the invention to for above-mentioned the deficiencies in the prior art, propose based on the automatic of panoramic vision accessory system Park parking stall detection and identifying system, the accuracy of parking place and reliable is detected to improve driver under the scene of complexity Property.
Realizing the technical thought of the object of the invention is：By four wide-angle cameras around vehicle body, car is generated Surrounding environment panoramic picture, is detected and is identified to parking stall around vehicle body in conjunction with computer vision algorithms make, with identification Barrier, shade, mark line being present, these in particular cases, realize efficient, accurate parking stall detection and identification entirely.
According to above-mentioned thinking, automatic parking parking stall detection of the present invention based on panoramic vision accessory system is with identification System, including：
Pan-shot unit, become for gathering image around vehicle body, and by camera calibration, distortion correction, top view Change and generate 360 ° of seamless spliced top views with image mosaic, be sent to embedded unit；
Embedded unit, the top view for being gathered to pan-shot module are handled, and complete the detection on parking stall simultaneously Judge whether parking stall is occupied, and testing result is sent to vehicle-mounted electronic control unit ECU and vehicle-mounted middle control display screen；
Vehicle-mounted middle control display screen, the parking stall testing result transmitted for showing embedded unit；
It is characterized in that：The embedded unit includes：
Interface module, for embedded unit testing result to be sent to vehicle-mounted electronic control unit ECU；
Image processing module, it includes detection sub-module and identification submodule,
The detection sub-module, image preprocessing is first carried out to 360 ° of seamless spliced top views, then calculated with Line segment detection Method extracts the parking stall mark line in top view, and calculates the girth of parking stall mark line, judges parking stall mark according to girth Remember whether line is complete：With image segmentation algorithm by parking stall mark line completion if imperfect, then determine whether optional stop Parking stall；
The identification submodule, the target parking position detected to detection sub-module, become by calculating parking stall interior intensity Change difference value, judge to whether there is shade or barrier inside optional parking stall, barrier such as be present and calculate obstacle height again, So as to judge whether optional parking stall is occupied；
Image display sub-module, for the optional parking stall testing result of embedded unit to be shown in vehicle-mounted middle control display screen Show.
The invention has the advantages that or beneficial effect：
It is of the invention that parking stall stop line is only relied upon independent of adjacent the parking posture of automobile due to detection process, in panorama In vision-aided system, the parking stall mark line in top view is extracted first with LSD Line Segment Detection Algorithms, then stop by calculating The girth that each line segment of parking stall mark line is surrounded, the detection for improving the parking stall in the case where parking stall mark line is not complete are accurate Degree；Additionally due to the present invention first determines whether shade or barrier be present, such as existed by calculating gradation of image difference value information Barrier judges obstacle height again, so that it is determined that whether optional parking stall is occupied, efficiently solves parking stall and obstacle be present Parking stall test problems under thing, shadow condition, realize the detection of efficient, accurate parking stall and identification function, for it is follow-up from Dynamic park middle path planning and path following control provide the guarantee of precision and stability.
Below in conjunction with accompanying drawing, the present invention more fully describes embodiments of the invention.However, appended accompanying drawing is only used for Bright and elaboration, and be not meant to limit the scope of the invention.
Brief description of the drawings
Fig. 1 is the detection of automatic parking parking stall and the structural representation of identifying system in the present invention；
Fig. 2 is the procedure chart that detection sub-module carries out parking stall detection in the present invention；
Fig. 3 is to identify that submodule carries out the procedure chart of parking stall identification in the present invention.
Embodiment
First, technical principle
The present invention includes the detection on automatic parking parking stall and the identification on automatic parking parking stall, wherein：
(1) detection on automatic parking parking stall
The detection on automatic parking parking stall includes image preprocessing, the detection of stop sign line, stop sign line circumference calculating Three parts.
Described image pre-processes, including image gray processing and Image Edge-Detection, image gray processing refer to adopt camera The coloured image of collection is converted into gray level image, and rim detection refers to that detection identifies that brightness changes violent pixel structure in image Into set, image preprocessing process is mainly used in reducing noise and extraneous interference in image, to simplify subsequent treatment mistake Journey.
Stop sign line detection, it is on the basis of early stage rim detection, with LSD Line Segment Detection Algorithms to parking stall In stop sign line extracted, the algorithm draws the pixel point set of straight line by analyzing image local, then by assuming that Parameter carries out checking solution, and pixel point set is merged with control errors set, carries out the quantity of Self Adaptive Control flase drop, Jin Erti The accuracy of high detection, it is a kind of algorithm that sub-pix rank graph line feature can be extracted in linear session, with biography The method that the Hough transform of system carries out straight-line detection compares LSD algorithm in terms of detection of straight lines section, accuracy of detection and computational efficiency A balance is well obtained.
According to national standard GB50067-2014, in actual scene, the width on parking stall is about 2.5 meters, parking stall mark line Width be about 10 centimetres.Physical distance between parallel lines is arranged to w1, scope is 0.1 meter to 0.15 centimetre, and two flat Physical distance of the line section between is arranged to w2, scope is 2.3 to 2.8 meters.Detect to meet parallel lines in edge image Between physical distance be w1And the physical distance between two parallel segments pair is w2Two parallel segments pair, complete parking Mark line detects.
The stop sign line circumference calculating, be for target parking position exist mark line it is incomplete in the case of parking level Really detection, camera interior and exterior parameter and image coordinate system and the world in pan-shot unit obtained by camera calibration need to be utilized Mapping relations between coordinate system, stop sign line girth is calculated, by setting stop line girth high threshold and average threshold, The stop sign line girth calculated and the threshold value set are compared, to judge that parking stall marks whether completely：If it is determined that Stop sign line is incomplete, then is examined the stop line completion of missing, formation closed rectangular, completion parking stall using image Segmentation Technology Survey.
(2) identification on automatic parking parking stall
The identification on automatic parking parking stall, including stop sign line interior zone gray difference value calculates and stop sign line Internal reasons highly calculate two parts.
The stop sign line interior zone gray difference value calculates, and is due to when parking stall is occupied and unoccupied When, stop sign line interior zone gray-value variation difference has significantly different, need to first calculate ash inside parking stall mark line Variation value, then grey scale change difference average threshold during by setting parking stall unoccupied are spent, will ash inside the region of parking stall Variation value is spent when parking stall is unoccupied compared with grey scale change difference average threshold, inside preliminary judgement parking stall It is whether occupied.
The stop sign line internal reasons highly calculate, and are barrier be present in preliminary judgement parking stall interior zone In the case of, obstacle height need to be determined whether, finally judges whether parking stall is occupied：
First, barrier in the region of parking stall is extracted using image segmentation algorithm, will be hindered with minimum enclosed rectangle Thing is hindered to be shown in two dimensional image, the summit of barrier is exactly in two dimensional image between minimum enclosed rectangle and barrier Point of contact；
Then, the three-dimensional coordinate on the summit of barrier is calculated using single eye stereo vision algorithm, so as to calculate obstacle Thing height, by setting the average minimum ground clearance threshold value of vehicle, it is average minimum liftoff with vehicle that obstacle height will be calculated Gap threshold is compared, final to judge whether parking stall is occupied.
2nd, system architecture
Below in conjunction with accompanying drawing 1, the example of this invention is illustrated, but protection scope of the present invention is not limited in This.
Reference picture 1, automatic parking parking stall detection and identifying system of the present invention based on panoramic vision accessory system, including Pan-shot unit, vehicle-mounted middle control large-size screen monitors, embedded processing unit and power subsystem.The embedded processing unit connects panorama Shooting unit simultaneously connects embedded processing unit, pan-shot unit, panorama with vehicle-mounted middle control large-size screen monitors bi-directional chaining, power subsystem Shooting unit connects embedded processing unit.Wherein：
Pan-shot unit, including 4 170 ° of wide-angle cameras, preceding camera are arranged under vehicle intake grid logo Side, above both sides camera installation B pillar, rear camera is arranged on above licence-plate support, will photograph vehicle all around four Secondary wide angle picture processing generation shows 360 ° of seamless spliced top views of vehicle periphery scene, and sends to embedded processing list Member；
Embedded unit, it is main to be responsible for completing the parking stall detection and identification to seamless spliced top view, and will detection As a result send to vehicle-mounted electronic control unit ECU, foundation provided for path planning in follow-up automatic parking and path following control, Meanwhile send testing result to vehicle-mounted middle control display screen by image display, it includes interface module, image shows mould Block, image processing module；
Interface module, for respectively with pan-shot unit, vehicle-mounted electronic control unit ECU, it is vehicle-mounted it is middle control large-size screen monitors, power supply Unit is attached；
Image processing module, for completing detection and the identification function on parking stall, including detection sub-module and identification submodule Block.
Image display, the result for image processing module to be detected are sent to vehicle-mounted middle control display screen, to drive Member shows testing result, to select target parking position.
Reference picture 2, the detection sub-module in described image processing module, including the detection of image preprocessing, stop sign line, Three parts of stop sign line circumference calculating.Wherein：
Image preprocessing, including image gray processing and Image Edge-Detection, i.e., be first converted into gray level image by coloured image Make image gray processing, then rim detection is completed using Canny operators, the Canny operators disclosure satisfy that low error rate, high positioning Property, three optimal edges of minimum response detection evaluation criterions；
Stop sign line line segments extraction, it is on the basis of image preprocessing, with LSD Line Segment Detection Algorithms to edge graph Line segment as in is extracted, and in the line segment extracted, according to national standard GB50067-2014, is detected to meet between parallel lines Physical distance be w1And the physical distance between two parallel segments pair is w2Two parallel segments pair, complete stop sign Line detects.
Parking stall mark line circumference calculating, be for target parking position exist mark line it is incomplete in the case of parking stall accurately examine Survey, using camera inside and outside parameter in pan-shot unit and stop sign line image coordinate system and world coordinate system mapping Relation, first calculate the girth P that mark line each line segment in parking stall is surrounded1, then two threshold values of stop line girth, high threshold are set PhWith average threshold Pm, the girth P that each line segment of parking stall mark line will be calculated is surrounded1With the stop line girth two of setting Threshold value is compared：
If stop line girth P1＞ Ph, then it is determined as that parking stall mark line is complete.
If stop line girth Ph＞ P1＞ Pm, then it is determined as that parking stall mark line is incomplete；
When being determined as that parking stall mark line is incomplete, using image Segmentation Technology by the stop line completion of missing, formed Closed rectangular, complete parking stall measure.
Reference picture 3, submodule, including stop sign line interior zone gray difference value are identified in described image processing module Two parts are calculated with obstacle height.Wherein：
Stop sign line interior zone gray difference value calculates, and is according to the grey level histogram inside stop sign line, meter Calculate stop sign line interior zone gray difference value, i.e., grey scale change difference average threshold T when first setting parking stall unoccupied, The gray difference value T that will be calculated again1When unoccupied compared with grey scale change difference average threshold T：
If grey scale change difference value T1＞ T, then it is determined as clear in parking expection；
If grey scale change difference value T1＜ T, then it is determined as that parking has barrier in expected；
Parking stall mark line internal reasons highly calculate, and are first when being judged to having barrier in parking expection, to stopping Parking stall inner utilization image segmentation algorithm marks barrier profile, using visual difference caused by vehicle movement, utilizes stereopsis Feel that algorithm calculates obstacle height H1, pass through the obstacle height H for setting vehicle minimum ground clearance to calculate again1With car Liftoff minimum clearance average threshold H is compared：
If obstacle height H1＜ H, then it is determined as that parking stall is unoccupied,
If obstacle height H1＞ H, then it is determined as that parking stall is occupied.
When system identification is that parking stall is unoccupied, recognition result is sent to vehicle-mounted by embedded unit interface module Electronic control unit ECU, to complete path planning and path following control in follow-up automatic parking, meanwhile, by recognition result Sent by embedded unit image display to vehicle-mounted middle control large-size screen monitors, testing result is shown for driver, to select mesh Mark parking stall.
When system identification is that parking stall is occupied, recognition result is sent to embedded unit image processing module and detects son Module, re-start the parking stall detection of a new round.
Above description is only the specific example of the present invention, does not form any limitation of the invention, it is clear that for , all may be without departing substantially from the principle of the invention, structure after present invention and principle has been understood for one of skill in the art In the case of, the various modifications and changes in progress form and details, but these modifications and variations based on inventive concept Still within the claim protection domain of the present invention.

Claims (7)

1. a kind of detection of automatic parking parking stall and identifying system based on panoramic vision accessory system, including：
Pan-shot unit, for gathering image around vehicle body, and by camera calibration, distortion correction, top view conversion and Image mosaic generates 360 ° of seamless spliced top views, is sent to embedded unit；
Embedded unit, the panoramic picture for being gathered to pan-shot module are handled, and are completed the detection on parking stall and are sentenced Whether occupied determine parking stall, and testing result is sent to vehicle-mounted electronic control unit ECU and vehicle-mounted middle control display screen；
Vehicle-mounted middle control display screen, the parking stall testing result transmitted for showing flush bonding module；
It is characterized in that：The embedded unit includes：
Interface module, for flush bonding module testing result to be sent to vehicle-mounted electronic control unit ECU；
Image processing module, it includes detection sub-module and identification submodule,
The detection sub-module, image preprocessing is first carried out to 360 ° of seamless spliced top views, then carried with Line Segment Detection Algorithm The parking stall mark line in top view is taken out, and calculates the girth of parking stall mark line, parking stall mark line is judged according to girth It is whether complete：With image segmentation algorithm by parking stall mark line completion if imperfect, then determine whether optional parking stall；
The identification submodule, the target parking position detected to detection sub-module, by calculating parking stall interior intensity difference in change Different value, judge to whether there is shade or barrier inside optional parking stall, barrier such as be present and calculate obstacle height again, so as to Judge whether optional parking stall is occupied；
Image display sub-module, for the optional parking stall testing result of embedded unit to be shown in vehicle-mounted middle control display screen.
2. system as described in claim 1, it is characterised in that：Pan-shot unit includes 4 cameras, these cameras Vehicle's surroundings are separately mounted to, i.e. front camera is arranged on below vehicle intake grid logo, both sides camera installation vehicle B Above post, rear camera is arranged on above licence-plate support, respectively all around realtime graphic on ground around collection vehicle.
3. system as described in claim 1, it is characterised in that：Embedded unit detection sub-module is to seamless spliced 360 ° Top view carries out image preprocessing first, is that the coloured image that pan-shot unit gathers is converted into gray level image, recycles Canny edge detection algorithms generate edge image, to improve image processing efficiency.
4. system as described in claim 1, it is characterised in that：Detection sub-module is to the edge graph by image preprocessing Picture, the parking stall mark line in top view is extracted with LSD Line Segment Detection Algorithms, its realization is as follows：
1) Grad and gradient direction of each pixel in image are calculated, and generates straight support region；
2) rectangle approximation is carried out to straight support region, calculates the central point of rectangle, the angle in direction, length and width, and profit Line segment is represented with rectangle；
3) Helmholtz's principle is based on, passes through total pixel number n and the pixel consistent with rectangular area direction in region Number k calculates false alarm number NFA, when NFA is less than perfect noise image average value ε, judges that the straight support domain rectangle is It is no significant, it is detected straight line.
4) in all straight lines detected by step 3), according to national standard GB50067-2014, lookup has physical distance about 0.2 One parallel segment pair of rice；
5) in all parallel segment centerings with fixed range detected by step 4), according to national standard GB50067-2014, Two parallel segments pair that physical distance between two parallel segments pair of lookup is about 2.5 meters or 5.5 meters, as parking stall Mark line.
5. system as described in claim 1, it is characterised in that：Embedded unit detection sub-module is directed to parking wire tag, It is to utilize in pan-shot unit camera inside and outside parameter and stop sign line in the mapping of image coordinate system and world coordinate system Relation, calculate the girth P that mark line each line segment in parking stall is surrounded1。
6. system as described in claim 1, it is characterised in that：Embedded unit detection sub-module exists for parking stall to be marked Parking stall in the case of note line is not complete is accurately detected, and is two threshold values for first setting stop line girth, i.e. high threshold PhWith average threshold Value Pm, then the girth P that mark line each line segment in parking stall is surrounded1With high threshold PhWith average threshold PmIt is compared：
If stop line girth P1＞ Ph, then it is determined as that parking stall mark line is complete；
If stop line girth Ph＞ P1＞ Pm, then it is determined as that parking stall mark line is incomplete, and will lack using image Segmentation Technology Stop line completion, formed closed rectangular, complete parking stall measure.
7. system as described in claim 1, it is characterised in that：Embedded unit identification submodule exists cloudy for parking stall Under shadow or barrier scene, whether identification parking stall is occupied, and its realization is as follows：
First, the parking stall detected to detection sub-module utilizes parking stall region interior intensity histogram, calculates gray scale change Change difference value T1；
Then, grey scale change difference average threshold T when setting parking stall unoccupied, by parking stall region interior intensity variation Value T1When parking stall is unoccupied compared with grey scale change difference average threshold T：
If grey scale change difference value T1During ＜ T, then shadow-free or barrier in the region of parking stall, are determined as optional parking stall.
If grey scale change difference value T1During ＞ T, then there are shade or barrier in the region of parking stall, obstacle height detection need to be carried out.
Finally, barrier in the region of parking stall is extracted using image segmentation algorithm, and calculated using stereoscopic vision algorithm Go out obstacle height H1, and the obstacle height H that will be calculated1Compared with the average minimum ground clearance of vehicle is H：
If obstacle height H1During ＜ H, then it is determined as that parking stall is unoccupied；
If obstacle height H1During ＞ H, then it is determined as that parking stall is occupied.
CN201710864999.8A 2017-09-22 2017-09-22 Automatic parking space detection and identification system based on panoramic vision auxiliary system Active CN107738612B (en)

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 true CN107738612A (en) 2018-02-27
CN107738612B 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 (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109278861A (en) * 2018-07-05 2019-01-29 惠州市德赛西威汽车电子股份有限公司 A kind of positive based reminding method of steering wheel return looked around based on automobile and system
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
CN109631896A (en) * 2018-07-23 2019-04-16 同济大学 A kind of parking lot autonomous parking localization method based on vehicle vision and motion information
CN109649384A (en) * 2019-02-15 2019-04-19 华域汽车系统股份有限公司 A kind of parking assistance method
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
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
CN109740521A (en) * 2018-12-29 2019-05-10 百度在线网络技术（北京）有限公司 The parking stall location determining method and device of automatic parking, electronic equipment and computer-readable medium
CN109754639A (en) * 2019-02-28 2019-05-14 北京智行者科技有限公司 It parks storage method and device
CN109934140A (en) * 2019-03-01 2019-06-25 武汉光庭科技有限公司 Automatic backing method for assisting in parking and system based on detection ground horizontal marking
CN110415555A (en) * 2019-08-30 2019-11-05 的卢技术有限公司 A kind of recognition methods of effective scribing line parking stall 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
CN110751850A (en) * 2019-08-30 2020-02-04 的卢技术有限公司 Parking space identification method and system based on deep neural network
CN110889974A (en) * 2018-09-11 2020-03-17 广州汽车集团股份有限公司 Intelligent parking space identification method and device and automobile
CN111071248A (en) * 2019-12-24 2020-04-28 浙江合众新能源汽车有限公司 Intelligent parking method based on electronic power-assisted brake
CN111429469A (en) * 2019-04-17 2020-07-17 杭州海康威视数字技术股份有限公司 Parking position determining method and device, electronic equipment and storage medium
CN111746503A (en) * 2019-03-27 2020-10-09 上海欧菲智能车联科技有限公司 Parking method, system, device, vehicle and computer readable 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
CN112183413A (en) * 2020-09-30 2021-01-05 东风柳州汽车有限公司 Parking space detection method and device, storage medium and vehicle
CN112348845A (en) * 2019-08-06 2021-02-09 黑芝麻智能科技(重庆)有限公司 System and method for parking space detection and tracking
CN112389419A (en) * 2019-08-12 2021-02-23 欧特明电子股份有限公司 Method for identifying parking space and parking assistance system
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
CN113060125A (en) * 2020-08-31 2021-07-02 惠州华阳通用电子有限公司 Parking assisting method and device
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
US11541881B2 (en) 2018-06-29 2023-01-03 Byd Company Limited Automatic parking method, device, system, and vehicle
CN115909795A (en) * 2023-03-09 2023-04-04 斯润天朗（北京）科技有限公司 Autonomous parking system and method based on parking lot cooperation
CN117261877A (en) * 2023-08-18 2023-12-22 广州优保爱驾科技有限公司 Self-correction image acquisition system and method based on vehicle appearance change

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112289070B (en) * 2020-10-20 2021-12-07 广州小鹏自动驾驶科技有限公司 Parking space detection method and device, vehicle and readable medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000134608A (en) * 1998-10-22 2000-05-12 Fujitsu Ten Ltd Rear monitoring device for vehicle
CN102774324A (en) * 2012-07-06 2012-11-14 广东好帮手电子科技股份有限公司 Panoramic parking assist system and implementation method thereof
CN103171552A (en) * 2011-12-23 2013-06-26 现代自动车株式会社 AVM top view based parking support system
CN105539430A (en) * 2015-12-29 2016-05-04 北京理工大学 Intelligent man-car interaction parking method based on hand-held terminal
US20160129939A1 (en) * 2013-07-04 2016-05-12 Jaguar Land Rover Limited Vehicle control system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000134608A (en) * 1998-10-22 2000-05-12 Fujitsu Ten Ltd Rear monitoring device for vehicle
CN103171552A (en) * 2011-12-23 2013-06-26 现代自动车株式会社 AVM top view based parking support system
CN102774324A (en) * 2012-07-06 2012-11-14 广东好帮手电子科技股份有限公司 Panoramic parking assist system and implementation method thereof
US20160129939A1 (en) * 2013-07-04 2016-05-12 Jaguar Land Rover Limited Vehicle control system
CN105539430A (en) * 2015-12-29 2016-05-04 北京理工大学 Intelligent man-car interaction parking method based on hand-held terminal

Cited By (38)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11541881B2 (en) 2018-06-29 2023-01-03 Byd Company Limited Automatic parking method, device, system, and vehicle
CN109278861A (en) * 2018-07-05 2019-01-29 惠州市德赛西威汽车电子股份有限公司 A kind of positive based reminding method of steering wheel return looked around based on automobile and system
CN109631896A (en) * 2018-07-23 2019-04-16 同济大学 A kind of parking lot autonomous parking localization method based on vehicle vision and motion information
CN110889974A (en) * 2018-09-11 2020-03-17 广州汽车集团股份有限公司 Intelligent parking space identification method and device and automobile
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
WO2020124988A1 (en) * 2018-12-21 2020-06-25 广州小鹏汽车科技有限公司 Vision-based parking space detection method and device
CN109740521A (en) * 2018-12-29 2019-05-10 百度在线网络技术（北京）有限公司 The parking stall location determining method and device of automatic parking, electronic equipment 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
CN109649384A (en) * 2019-02-15 2019-04-19 华域汽车系统股份有限公司 A kind of parking assistance method
CN109754639A (en) * 2019-02-28 2019-05-14 北京智行者科技有限公司 It parks storage method and device
CN109934140A (en) * 2019-03-01 2019-06-25 武汉光庭科技有限公司 Automatic backing method for assisting in parking and system based on detection ground horizontal marking
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
CN111746503A (en) * 2019-03-27 2020-10-09 上海欧菲智能车联科技有限公司 Parking method, system, device, vehicle and computer readable storage medium
CN111429469A (en) * 2019-04-17 2020-07-17 杭州海康威视数字技术股份有限公司 Parking position determining method and device, electronic equipment and 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
CN112348845A (en) * 2019-08-06 2021-02-09 黑芝麻智能科技(重庆)有限公司 System and method for parking space detection and tracking
CN112348845B (en) * 2019-08-06 2024-02-23 黑芝麻智能科技(重庆)有限公司 System and method for parking space detection and tracking
CN112389419A (en) * 2019-08-12 2021-02-23 欧特明电子股份有限公司 Method for identifying parking space and parking assistance system
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
CN110415555A (en) * 2019-08-30 2019-11-05 的卢技术有限公司 A kind of recognition methods of effective scribing line parking stall and system based on deep learning
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
CN110751850A (en) * 2019-08-30 2020-02-04 的卢技术有限公司 Parking space identification method and system based on deep neural network
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
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
CN111071248A (en) * 2019-12-24 2020-04-28 浙江合众新能源汽车有限公司 Intelligent parking method based on electronic power-assisted brake
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
CN113060125A (en) * 2020-08-31 2021-07-02 惠州华阳通用电子有限公司 Parking assisting method and device
CN112183413A (en) * 2020-09-30 2021-01-05 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
CN115909795A (en) * 2023-03-09 2023-04-04 斯润天朗（北京）科技有限公司 Autonomous parking system and method based on parking lot cooperation
CN117261877A (en) * 2023-08-18 2023-12-22 广州优保爱驾科技有限公司 Self-correction image acquisition system and method based on vehicle appearance change

Also Published As

Publication number Publication date
CN107738612B (en) 2020-04-14

Similar Documents

Publication Publication Date Title
CN107738612A (en) The detection of automatic parking parking stall and identifying system based on panoramic vision accessory system
CN109435942B (en) Information fusion-based parking space line and parking space recognition method and device
CN109446909B (en) Monocular distance measurement auxiliary parking system and method
CN104933409B (en) A kind of parking stall recognition methods based on panoramic picture dotted line feature
US9013286B2 (en) Driver assistance system for displaying surroundings of a vehicle
CN106128115B (en) A kind of fusion method based on twin camera detection Traffic Information
CN109389578A (en) Railroad track abnormality detection
CN106485233A (en) Drivable region detection method, device and electronic equipment
CN110738121A (en) front vehicle detection method and detection system
CN105512720A (en) Public transport vehicle passenger flow statistical method and system
CN104723991A (en) Parking assistance apparatus and parking assistance method for vehicle
CN110386065A (en) Monitoring method, device, computer equipment and the storage medium of vehicle blind zone
CN108764108A (en) A kind of Foregut fermenters method based on Bayesian inference
CN107256636A (en) A kind of traffic flow acquisition methods for merging laser scanning and video technique
CN104574393A (en) Three-dimensional pavement crack image generation system and method
JP2007234019A (en) Vehicle image area specifying device and method for it
CN111178295A (en) Parking space detection and model training method and device, vehicle, equipment and storage medium
CN109522847A (en) A kind of track and road barricade object detecting method based on depth map
CN110334678A (en) A kind of pedestrian detection method of view-based access control model fusion
CN110246183A (en) Ground contact point detection method, device and storage medium
CN109785354A (en) A kind of method for detecting parking stalls based on background illumination removal and connection region
CN111967396A (en) Processing method, device and equipment for obstacle detection and storage medium
CN110147748A (en) A kind of mobile robot obstacle recognition method based on road-edge detection
CN111222441A (en) Point cloud target detection and blind area target detection method and system based on vehicle-road cooperation
JP2011209896A (en) Obstacle detecting apparatus, obstacle detecting method, and obstacle detecting 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