CN103065520B - Detection system for backing car into storage and detection method thereof - Google Patents
Detection system for backing car into storage and detection method thereof Download PDFInfo
- Publication number
- CN103065520B CN103065520B CN201210585168.4A CN201210585168A CN103065520B CN 103065520 B CN103065520 B CN 103065520B CN 201210585168 A CN201210585168 A CN 201210585168A CN 103065520 B CN103065520 B CN 103065520B
- Authority
- CN
- China
- Prior art keywords
- image
- warehouse
- camera
- coordinate
- sign board
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a detection system for backing a car into a store and a detection method thereof. According to the detection system and the detection method thereof, a main camera and an auxiliary camera are used for completely recording a whole dynamic process of backing the car into the store and obtaining the position and the distance of the car relative to a storage location marker line, quantitative analysis of the process of backing the car into the store can be realized through an image analysis meter, and analyzed results are reported to a server for storage, management, and comprehensive grading, and drivers and trainers inquire information or consult video videotapes through a client side of the rear end. Accordingly, the drivers are trained effectively, and study efficiency of driving personnel is improved.
Description
Technical field
The present invention relates to a kind of reversing warehouse-in detection system and detection method thereof.
Background technology
As automobile driver, reversing warehouse-in is one of driving efficiency that must skillfully grasp.But during traditional driver training, generally at warehouse compartment surrounding sign-posting bar, student is object of reference training with flag-rod, need after causing actual setting out on a journey again to cultivate position sense and warehouse-in skill.Although can by installing the sensor collection vehicle position of some on road surface, as Chinese utility model 201120277707.9 the permanent magnet that adopts, or engineering range finding upper conventional infrared ray, laser, ultrasound wave etc., but sensors with auxiliary electrode all can only perception on indivedual point of fixity position, construction, maintenance complexity, overall cost is also expensive, and still needs linkage camera could realize evidence obtaining.
No matter student learns or trainer's teaching, is all mainly that view-based access control model information judges again, and it is also the most received for therefore carrying out detection mode based on machine vision to the whole dynamic process of reversing warehouse-in.
Although China's utility model 201120489062.5 describes a kind of video detecting device of the straight line distance for examination of driver, but its core is: " image obtained is mapped to HSV and LAB color space by graphics processing unit respectively; and in each spatial threshold value; form straight line pixel; pixel comparing unit uses principle of probability; input pixel is added up, draw the straight line unit meeting right side bearing feature most, calculate the rightmargin of this straight line unit ".Total institute is known, this mode is difficult to possess operability under actual environment, because there are many straight line pixels in vehicle self, as vehicle window, ceiling etc., also often there is a large amount of straight line pixel in background environment simultaneously, as kerbstone, flowers, plants and trees etc., in this case, be difficult in pixel aspect, " car " be extracted from background environment, finally cause detection inaccurate.
The present invention discloses a kind of completely based on reversing warehouse-in detection system and the method for machine vision, not only simple for structure, can in real time, accurately detect simultaneously vehicle location, attitude and and the bee-line of warehouse compartment boundary line, can also provide while providing the comprehensive grading of whole process and capture the information such as picture, video record.
Summary of the invention
The object of the invention is to provide a kind of reversing warehouse-in detection system and detection method thereof, and it can realize the quantitative test carried out training cart in reversing warehouse-in process, is conducive to Real-Time Monitoring and the tracking of training result.
In order to solve these problems of the prior art, technical scheme provided by the invention is:
A kind of reversing warehouse-in detection system, it comprises the front end system be arranged near reversing warehouse-in warehouse compartment and the back-end system being deployed in administrative center, described front end system comprises main camera, image analyzer and the sign board be placed on training cart, back-end system comprises server and client, front end system connects back-end system by transmission network, monitored picture covers the main camera in warehouse compartment region for shooting with video-corder the travel conditions of warehouse compartment place training cart, the monitoring image that the image analyzer continuous reception main camera be connected with main camera is caught also is compressed into monitoring image, the operation attitude of image analyzer monitor vehicle simultaneously, monitoring result and monitoring image are sent to the server of back-end system by image analyzer, client can be called and check monitoring result in server and monitoring image.
For technique scheme, inventor also has further optimal enforcement scheme.
As optimization, the main camera of the described warehouse compartment overlooked panorama is arranged in the vertical rod above warehouse compartment.
As optimization, be also provided with auxiliary camera in the both sides of main camera, supplement for auxiliary the running orbit catching training cart in warehouse compartment.
As optimization, described notice plate is arranged on roof, engine top cover or case cover, and the marker graphic on described notice plate is some gauge points, and gauge point is arranged in the specific line segment with fixed angle and unique intersection point.
As optimization, the seat in the plane of main camera, auxiliary camera is other is equipped with light compensating lamp, and the synchronizing signal of described light compensating lamp is provided by main camera or auxiliary camera, for carrying out strobe type light filling when illumination is crossed dark.
Present invention also offers a kind of reversing warehouse-in detection method, described method relates to system and comprises the front end system be arranged near reversing warehouse-in warehouse compartment and the back-end system being deployed in administrative center, described front end system comprises main camera, auxiliary camera, image analyzer and the sign board be placed on training cart, back-end system comprises server and client, front end system connects back-end system by transmission network, monitored picture covers the main camera in warehouse compartment region for shooting with video-corder the travel conditions of warehouse compartment place training cart, image analyzer and main camera, auxiliary camera is connected, concrete detection method comprises the following steps:
Step S1: measure warehouse compartment length and width size by direct labor, runs camera calibration program, realizes the mutual conversion of image coordinate system and world coordinate system;
Step S2: the monitoring image that image analyzer continuous reception main camera is caught, is compressed into video record, simultaneously running mark board recognizer, obtains position and the direction of sign board;
Step S3: image analyzer is according to main camera calibration result and sign board recognition result, and operational vehicle position and attitude trace routine, obtains the position in vehicle world coordinate system and attitude; According to vehicle location, attitude and known vehicle dimension, determine vehicle ' s contour scope and the profile outer edge bee-line to warehouse compartment mark line;
Step S4: the vehicle location obtained in step S3, attitude, range measurement and data such as candid photograph picture, video record etc. are sent to server by transmission network by image analyzer 4, server service data supervisory routine is analyzed various information and is provided the application data such as comprehensive grading, project used time, in the mode of data record stored in database, by picture, video stored in specified file path, run application services support, administrative client access simultaneously;
Step S5: student's operated client, by transmission network logon server, browses the information such as data record, picture, video that training is relevant, and according to demand printing, Download Info; Trainer's operated client, by transmission network logon server, browse the information such as data record, picture, video of teaching person, and print according to demand, Download Info.
For above-mentioned detection method, inventor also has further optimal enforcement scheme equally.
As optimization, in step S3, trigger main camera 1 or auxiliary camera 2 when vehicle line ball or distance are less than setting threshold value in docking process and capture picture and be sent to image analyzer.
As optimization, in step S1, when carrying out camera calibration, (coordinate system of the real world at world coordinate system and vehicle place, by 3 coordinate axis: X-axis, Y-axis, Z axis form, the plane picture of image coordinate system and shot by camera, by 2 coordinate axis: U axle, V axle form), in step S1, when carrying out camera calibration, the step of described camera calibration program is:
With any summit of warehouse compartment for true origin, measure the world coordinates on four summits of rectangle warehouse compartment in actual place;
Video capture piece image, with any pixel for initial point, hand labeled goes out the image coordinate on rectangle warehouse compartment four summits;
The world coordinates on four warehouse compartment summits and pixel coordinate are substituted into image-world coordinates transform in system of linear equations, solve image-world coordinates transformed matrix;
Certain point coordinate value under any one world coordinate system is substituted into image-world coordinates transformed matrix known image-world coordinates and transform system of linear equations, the image coordinate of this some correspondence can be calculated; Under the prerequisite of the known world coordinate height, any one image coordinate is substituted into image-world coordinates transformed matrix known image-world coordinates and transform system of linear equations, the world coordinates of this some correspondence can be calculated; So far, camera calibration is completed.
As optimization, the flow process of carrying out sign board identification in step S2 is as follows:
Threshold segmentation is carried out to image, obtains the image after segmentation;
Connected domain extraction is carried out to the image after Threshold segmentation, judges whether connected domain length and width meets the length and width setting value of sign board gauge point figure, if met, then mark this connected domain;
Can the connected domain of judge mark connect into the shape consistent with real marking board one by one, comprises angle formed by gauge point quantity and gauge point line, if passable, be then reference points detection figure depending on connected region, otherwise give up this connected domain; Repeat this step, until travel through all connected domains;
With reference points detection figure for reference point, identify other additional letter and numeric area and identify, so far completing the identification of whole sign board.
The steps flow chart carrying out vehicle location attitude detection in this detection method in step S3 is:
Image-world coordinates that the image coordinate of the reference points detection figure obtained in sign board recognizer substitutes into camera calibration program is transformed in system of linear equations, the world coordinates of reference points detection figure can be obtained;
In world coordinate system, reference points detection figure is linked to be according to the queueing discipline of sign board mark original tally dot pattern the line segment that there is intersection point;
In world coordinate system, calculate the coordinate of intersection point and the angle of line segment, intersecting point coordinate is vehicle location, and line segment angle is vehicle attitude.
Relative to scheme of the prior art, advantage of the present invention is:
1. the invention describes a kind of reversing warehouse-in detection system and detection method thereof, the present invention puts whole dynamic process by main camera in storage with auxiliary camera complete documentation vehicle backing and obtains the position of the relative warehouse compartment markings of vehicle, distance, and the quantitative test to reversing warehouse-in process can be realized by image analyzer, analysis result reports to server preservation and manages and carry out comprehensive grading, driver and trainer to be inquired about information by the client of rear end or have access to video record, student's correctable error operation whereby, and coach assesses student's study schedule whereby or improves guidance, realization like this is to effective training of driver, improve the learning efficiency of driving training personnel,
2. the present invention is completely based on video technique, does not need ground on the scene to bury other sensor underground, does not also need to increase any electric apparatus mounted on vehicle, and structure is simple, with low cost;
3. the present invention is directly based on video technique, supports to capture the picture of the abnormal conditions such as line ball, and evidence obtaining is convenient.
Accompanying drawing explanation
Below in conjunction with drawings and Examples, the invention will be further described:
Below in conjunction with drawings and Examples, the invention will be further described:
Fig. 1 is the system architecture schematic diagram of the embodiment of the present invention;
Fig. 2 is the sign board schematic diagram of the embodiment of the present invention;
Fig. 3 is the overall system workflow diagram of the embodiment of the present invention;
Fig. 4 is the camera calibration program flow diagram of the embodiment of the present invention;
Fig. 5 is the sign board recognizer process flow diagram of the embodiment of the present invention;
Fig. 6 is the vehicle location attitude detection process flow diagram of the embodiment of the present invention;
Fig. 7 is the scoring procedures process flow diagram of the embodiment of the present invention.
Wherein: 1, main camera; 2, auxiliary camera; 3, light compensating lamp; 4, image analyzer; 5, sign board; 6, transmission network; 7, server; 8, client.
Embodiment
Embodiment:
Present embodiment describes one reversing warehouse-in detection system and detection method thereof, as shown in Figure 1, system is made up of with the back-end system being deployed in administrative center the front end system be arranged near reversing warehouse-in warehouse compartment system architecture.Front end system mainly contains: main camera 1, auxiliary camera 2, light compensating lamp 3, image analyzer 4 and the sign board 5 be placed on training cart; Back-end system mainly contains: server 7, client 8; Front and back ends system is interconnected by transmission network 6.
Take into account saving lower deployment cost to obtain good monitoring effect simultaneously, main camera 1 is installed on about 4-8 rice above warehouse compartment, be on the center line of warehouse compartment Width, horizontal direction distance warehouse compartment central point is 6 meters, adopt the wide temperature design of technical grade, sensor adopts 5,000,000 CCD, resolution is greater than 2592x1936, frame per second is not less than 8 frames/second, built-in gigabit ethernet interface, be equipped with 10mm ~ 35mm many moneys tight shot or zoom wide-angle lens simultaneously, under effectively ensureing above-mentioned mounting condition like this, monitored picture at least covers warehouse compartment region, and guarantee that sign board pixels across width is no less than 500 pixels.Auxiliary camera 2 can be installed on the same vertical rod transverse arm of main camera 1, particular location is the outer 0.2-1 rice of warehouse compartment left bounding lines, auxiliary camera adopts the wide temperature design of technical grade, sensor adopts 2,000,000 CCD, resolution is greater than 1920x1080, and frame per second is not less than 8 frames/second, built-in gigabit ethernet interface, be equipped with 10mm ~ 25mm many moneys tight shot or zoom lens simultaneously, can effective monitoring wheel line ball under effectively ensureing above-mentioned mounting condition like this.
Light compensating lamp 3 adopts strobe type LED light supplement lamp, and what synchronizing signal was provided by main camera 1 is main light compensating lamp, and what synchronizing signal was provided by auxiliary camera is auxiliary light compensating lamp.Light compensating lamp 3 power and visible angle are determined according to installation site.For avoiding vehicle body reflection to cause video camera overexposure, light compensating lamp 3 should keep at a certain distance away with its synchronous video camera of control and install, and is generally not less than 0.5 meter.When light compensating lamp 2 setting height(from bottom) is 6 meters, when distance parking stall central horizontal distance is 6 meters, visible angle is not less than 40 degree, and power is not less than 15W, and video camera interval 1 meter ampere fills and can satisfy the demands.
Image analyzer 4 adopts built-in industrial control computer, and the integrated heat-dissipating casing of its shell, does not need radiator fan, and effectively the inner laying dust of control, improves system stability; When the ccd video camera of connection 5,000,000 pixel, require that configuration dominant frequency is not less than the CPU of 2.4GHz, be no less than the internal memory of 4GB, be no less than the hard disk of 32GB as external memory and the hardware interface such as gigabit Ethernet, RS232, above-mentioned configuration guarantees that image analyzer 4 has enough calculating, storage and the communication resource to run all kinds of image processing algorithm and application program.
Server 7 can adopt tower server, and select dominant frequency to be greater than four core processors of 2.8GHz, 8MB buffer memory, internal memory is not less than 4GB, to ensure still can ensure system responses real-time when disposing multiple stage image analyzer 4.
Client 8 is common PC, can be equipped with the peripherals such as printer, IC-card card reader or fingerprint capturer.
Transmission network 6 adopts optical fiber or 3G cordless communication network when cross-over connection front and back ends system, and front and back ends system this locality adopts the gigabit Ethernet based on twisted-pair feeder more.
Main camera 1, auxiliary camera 2, image analyzer 4, server 7, client 8 realize exchanges data by transmission network 6.
As shown in Figure 2, sign board 5 schematic diagram of the present invention is made up of three parts: gauge point figure, driving school's code name character, training cart numbering character: the gauge point figure clear and definite indicating signboard position of necessary energy and direction, as adopted T-shaped mark, and its horizontal line segment is made up of 5 black circle diagram shapes of white background, vertical line segment is made up of 3 white with black circle diagram shapes, horizontal line segment and longitudinal line segment after extracting by figure binaryzation, connected domain can be distinguished easily and identify, horizontal line segment and longitudinal line segment exist vertical angle; Driving school's code name character adopts two English alphabets, and as available in " Hua Feng driving school " " HF " refers to; Training cart numbering character adopts three arabic numeral.
Overall system workflow diagram of the present invention as shown in Figure 3:
Step S1: measure warehouse compartment length and width size by direct labor, runs camera calibration program, realizes the mutual conversion of image coordinate system and world coordinate system;
Step S2: the monitoring image that image analyzer 4 continuous reception main camera 1 is caught, is compressed into video record, simultaneously running mark board recognizer, obtains position and the direction of sign board 5;
Step S3: image analyzer 4 is according to main camera 1 calibration result and sign board 5 recognition result, and operational vehicle position and attitude trace routine, obtains the position in vehicle world coordinate system and attitude; According to vehicle location, attitude and known vehicle dimension, determine vehicle ' s contour position and the profile outer edge bee-line to warehouse compartment mark line, and trigger main camera 1 when vehicle line ball or distance are less than setting threshold value or auxiliary camera 2 captures picture.
Step S4: the vehicle location obtained in step S3, attitude, range measurement and data such as candid photograph picture, video record etc. are sent to server 7 by transmission network 6 by image analyzer 4, server 7 service data supervisory routine is analyzed various information and is provided the application data such as comprehensive grading, project used time, in the mode of data record stored in database, by picture, video stored in specified file path, run application services support, administrative client access simultaneously.
Step S5: student's operated client 8, by transmission network 6 logon server 7, browses the information such as data record, picture, video that training is relevant, and according to demand printing, Download Info; Trainer's operated client 8, by transmission network 6 logon server 7, browse the information such as data record, picture, video of teaching person, and print according to demand, Download Info.
The object of camera calibration is the corresponding relation calculating world coordinate system and image coordinate system, the coordinate system of the real world at world coordinate system and vehicle place, by 3 coordinate axis: X-axis, Y-axis, Z axis form, the plane picture of image coordinate system and shot by camera, by 2 coordinate axis: U axle, V axle form.Suppose that the coordinate that certain is put in world coordinate system X, Y, Z tri-coordinate axis is (x
w, y
w, z
w), its corresponding point coordinate in image coordinate system is (u, v), then the corresponding relation of this two point coordinate can be expressed as system of linear equations:
This system of equations is called " image-world coordinates transforms system of linear equations ", and wherein α is the intermediate parameters of computation process, and (u, v) is image pixel coordinates, (x
w, y
w, z
w) be world coordinates, (f
x, f
y) be respectively the focal length of X-axis and Y direction in image coordinate system, (u
0, v
0) be the position of intersection point in image coordinate of camera optical axis and the plane of delineation.T=[t
x, t
y, t
z, 1] and be the mapping parameters of world coordinates initial point in image coordinate, R is orthogonal matrix, is defined as:
Metzler matrix is image-world coordinate system transformation matrix, and contain all camera calibration parameters to be determined, camera calibration is exactly the process solving Metzler matrix.We are by measuring world coordinates the value { (x on four summits obtaining training site
wi, y
wi, z
wi) | i=1 ..., 4}, obtains these 4 angle points coordinate figure { (u in the picture in image by manual markings
i, v
i) | i=1 ..., 4}, the method namely by separating above-mentioned system of linear equations obtains Metzler matrix.
After calculating Metzler matrix, appoint to certain point coordinate value under a world coordinate system, the image coordinate value of this some correspondence can be calculated; Appoint to the coordinate of certain point under an image coordinate system and the height z of these corresponding point in world coordinates known
w, can calculate the world coordinates of corresponding point, therefore the present invention adopts camera calibration program flow diagram as shown in Figure 4:
Step S101: with any summit of warehouse compartment for true origin, is obtained the world coordinates { (x on four summits of rectangle warehouse compartment by measurement data
wi, y
wi, z
wi) | i=1 ..., 4};
Step S102: video capture piece image, with any pixel for initial point, hand labeled goes out the image coordinate { (u on rectangle warehouse compartment four summits
i, v
i) | i=1 ..., 4};
Step S103: the world coordinates of warehouse compartment and image coordinate are substituted into image-world coordinates and transforms in system of linear equations, solve image-world coordinates transformed matrix M;
Step S104: certain point coordinate value under any one world coordinate system is substituted into M known image-world coordinates and transform system of linear equations, the image coordinate of this some correspondence can be calculated; Under the prerequisite of the known world coordinate height zw, any one image coordinate is substituted into image-world coordinates transformed matrix known image-world coordinates and transform system of linear equations, the world coordinates of this some correspondence can be calculated; So far, camera calibration is completed.
When adopting the T-shaped sign board shown in Fig. 2, black circle is the Main Basis of distinguishing mark with white circle, and the present invention can adopt sign board recognizer process flow diagram as shown in Figure 5:
Step S201: establish the pixel value at image coordinate (x, y) place to be designated as p
x,y, define two width Threshold segmentation image LB, LD and be respectively used to detect black circle and circle in vain, its pixel value is for being respectively:
Wherein T
b, T
dit is preset value.The all pixel values of LB, LD are calculated according to above formula.
Step S202: for the white circle of detection, find out in LB be 1 connected region, the length and width value in this region is converted to the length and width value under world coordinate system, judges whether length and width value meets the white round size in sign board 5, meets, be designated as the white circle detected.In like manner, same process is done for LD, black circle can be detected.
Step S203: utilize the white circle that detects and black circle, judge whether one by one to connect into the specific line segment consistent with sign board, if passable, then depending on this in vain circle, black circle be reference points detection figure, otherwise give up this circle or black circle in vain; Repeat this step, until travel through all white circles and black circle;
Step S204: if step S203 finds reference points detection figure, then with reference points detection figure for reference point, locate other additional letter and numeric area, as for the identification of letter and number, the method identifications such as template matches can be adopted, because character and numeral identify it has been the common technology of image procossing, in this patent and non-key technologies point, do not repeat them here simultaneously.So far the identification of whole sign board 5 is completed.
Because sign board 5 is the fixed position and the direction that are pasted on vehicle, so position and the attitude of vehicle can be extrapolated according to the position of sign board 5 and direction.Here suppose the dimensional parameters of vehicle, such as length, and the position of sign board on vehicle body and direction obtain by measuring.
When adopting the T-shaped sign board 5 shown in Fig. 2 and the sign board detection method shown in Fig. 3, the angle Theta of the line segment of multiple black circle composition and the line segment of multiple white circle composition is sign board 5 direction.Suppose that the image coordinate indicated is (u
i, v
i), angle is Theta, and sign board 5 is pasted on roof, then z
w=height of car is known, and therefore the position of positioned vehicle and attitude can adopt vehicle location attitude detection flow process as shown in Figure 6:
Step S301: by the image coordinate (u of reference points detection figure obtained in sign board recognizer
i, v
i) substitute in image-world coordinates conversion system of linear equations of camera calibration program, the world coordinates (x of reference points detection figure can be obtained
w, y
w, z
w);
Step S302: in world coordinate system, is linked to be according to the queueing discipline of the original note dot pattern of sign board mark the line segment that there is intersection point by reference points detection figure;
Step S303: in world coordinate system, calculates the coordinate of intersection point and the angle Theta of line segment
w, intersecting point coordinate is vehicle location, and line segment angle is vehicle attitude.
Scoring procedures process flow diagram of the present invention as shown in Figure 7.
Step S401: whether statistics exists vehicle line ball, the used time exceedes the not obviously misoperation such as in regulation region of maximum time limit, parking spot, if existed, then directly judge that this reversing warehouse-in is defective, scoring terminates;
Step S402: judge the used time whether in critical field, if the critical field of being no more than, then do not deduct points, if exceeded, then according to setting rule deduction corresponding scores, if time-out reaches the upper limit, then directly judge that this reversing warehouse-in is defective, such as every time-out detains 1 point in 5 seconds, until overtime 200 seconds, the used time be described in step S401 exceedes the maximum time limit;
Step S403: the air line distance calculating the parking spot criterion distance position at the end of reversing warehouse-in, vehicle location is obtained by step S3, and air line distance can obtain by calculating in calculating world coordinate system; Air line distance can be set as with deduction of points: if distance is less than 200mm, do not deduct points; Distance is greater than 200mm and is less than 1000mm, reduces according to 1 point/20mm; Distance is greater than 1000mm, is parking spot described in step S401 not in regulation region;
Step S404: add up final integrate score, if lower than setting value, then judges defective, otherwise is judged to be qualified and provides judgement mark.
Certain above-described embodiment, only for technical conceive of the present invention and feature are described, its object is to person skilled in the art can be understood content of the present invention and implement according to this, can not limit the scope of the invention with this.All modifications done according to the Spirit Essence of main technical schemes of the present invention, all should be encompassed within protection scope of the present invention.
Claims (8)
1. a reversing warehouse-in detection system, it is characterized in that, it comprises the front end system be arranged near reversing warehouse-in warehouse compartment and the back-end system being deployed in administrative center, described front end system comprises main camera, image analyzer and the sign board be placed on training cart, back-end system comprises server and client, front end system connects back-end system by transmission network, monitored picture covers the main camera in warehouse compartment region for shooting with video-corder the travel conditions of warehouse compartment place training cart, the monitoring image that the image analyzer continuous reception main camera be connected with main camera is caught also is compressed into monitoring image, the operation attitude of image analyzer monitor vehicle simultaneously, monitoring result and monitoring image are sent to the server of back-end system by image analyzer, client can be called and check monitoring result in server and monitoring image, described sign board is arranged on roof, engine top cover or case cover, and the marker graphic on described sign board is some gauge points, and gauge point is arranged in the specific line segment with fixed angle and unique intersection point.
2. reversing warehouse-in detection system according to claim 1, is characterized in that, be also provided with auxiliary camera in the both sides of main camera, supplement for auxiliary the running orbit catching training cart in warehouse compartment.
3. reversing warehouse-in detection system according to claim 1 and 2, it is characterized in that, the seat in the plane of main camera, auxiliary camera is other is equipped with light compensating lamp, and the synchronizing signal of described light compensating lamp is provided by main camera or auxiliary camera, for carrying out strobe type light filling when illumination is crossed dark.
4. a reversing warehouse-in detection method, it is characterized in that, described method relates to system and comprises the front end system be arranged near reversing warehouse-in warehouse compartment and the back-end system being deployed in administrative center, described front end system comprises main camera, auxiliary camera, image analyzer and the sign board be placed on training cart, back-end system comprises server and client, front end system connects back-end system by transmission network, monitored picture covers the main camera in warehouse compartment region for shooting with video-corder the travel conditions of warehouse compartment place training cart, image analyzer and main camera, auxiliary camera is connected, concrete detection method comprises the following steps:
Step S1: measure warehouse compartment length and width size by direct labor, runs camera calibration program, realizes the mutual conversion of image coordinate system and world coordinate system;
Step S2: the monitoring image that image analyzer continuous reception main camera is caught, is compressed into video record, simultaneously running mark board recognizer, obtains position and the direction of sign board;
Step S3: image analyzer is according to main camera calibration result and sign board recognition result, and operational vehicle position and attitude trace routine, obtains the position in vehicle world coordinate system and attitude; According to vehicle location, attitude and known vehicle dimension, determine vehicle ' s contour scope and the profile outer edge bee-line to warehouse compartment mark line;
Step S4: the data of the vehicle location obtained in step S3, attitude, range measurement and candid photograph picture, video record are sent to server by transmission network by image analyzer 4, server service data supervisory routine is analyzed various information and is provided comprehensive grading, the application data of project used time, in the mode of data record stored in database, by picture, video stored in specified file path, run application services support, administrative client access simultaneously;
Step S5: student's operated client, by transmission network logon server, browses the information of the relevant data record of training, picture, video, and according to demand printing, Download Info; Trainer's operated client, by transmission network logon server, browse the data record of teaching person, picture, video information, and print according to demand, Download Info.
5. reversing according to claim 4 warehouse-in detection method, is characterized in that, in step S3, triggers main camera or auxiliary camera is captured picture and is sent to image analyzer when vehicle line ball or distance are less than setting threshold value in docking process.
6. reversing warehouse-in detection method according to claim 4, it is characterized in that, in step S1, when carrying out camera calibration, the step of described camera calibration program is:
With any summit of warehouse compartment for true origin, measure the world coordinates on four summits of rectangle warehouse compartment in actual place; Video capture piece image, with any pixel for initial point, hand labeled goes out the image coordinate on rectangle warehouse compartment four summits;
The world coordinates on four warehouse compartment summits and pixel coordinate are substituted into image-world coordinates transform in system of linear equations, solve image-world coordinates transformed matrix;
Certain point coordinate value under any one world coordinate system is substituted into image-world coordinates transformed matrix known image-world coordinates and transform system of linear equations, the image coordinate of this some correspondence can be calculated; Under the prerequisite of the known world coordinate height, any one image coordinate is substituted into image-world coordinates transformed matrix known image-world coordinates and transform system of linear equations, the world coordinates of this some correspondence can be calculated; So far, camera calibration is completed.
7. the reversing warehouse-in detection method according to claim 4 or 5 or 6, it is characterized in that, the flow process of carrying out sign board identification in step S2 is as follows:
Threshold segmentation is carried out to image, obtains the image after segmentation;
Connected domain extraction is carried out to the image after Threshold segmentation, judges whether connected domain length and width meets the length and width setting value of sign board gauge point figure, if met, then mark this connected domain;
Can the connected domain of judge mark connect into the shape consistent with actual tag board one by one, comprises angle formed by gauge point quantity and gauge point line, if passable, be then reference points detection figure depending on connected region, otherwise give up this connected domain; Repeat this step, until travel through all connected domains;
With reference points detection figure for reference point, identify other additional letter and numeric area and identify, so far completing the identification of whole sign board.
8. reversing warehouse-in detection method according to claim 7, it is characterized in that, the steps flow chart carrying out vehicle location attitude detection in this detection method in step S3 is:
Image-world coordinates that the image coordinate of the reference points detection figure obtained in sign board recognizer substitutes into camera calibration program is transformed in system of linear equations, the world coordinates of reference points detection figure can be obtained;
In world coordinate system, reference points detection figure is linked to be according to the queueing discipline of sign board mark original tally dot pattern the line segment that there is intersection point;
In world coordinate system, calculate the coordinate of intersection point and the angle of line segment, intersecting point coordinate is vehicle location, and line segment angle is vehicle attitude.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210585168.4A CN103065520B (en) | 2012-12-28 | 2012-12-28 | Detection system for backing car into storage and detection method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210585168.4A CN103065520B (en) | 2012-12-28 | 2012-12-28 | Detection system for backing car into storage and detection method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103065520A CN103065520A (en) | 2013-04-24 |
| CN103065520B true CN103065520B (en) | 2015-04-01 |
Family
ID=48108131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210585168.4A Active CN103065520B (en) | 2012-12-28 | 2012-12-28 | Detection system for backing car into storage and detection method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103065520B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103606321B (en) * | 2013-10-29 | 2016-01-20 | 南京多伦科技股份有限公司 | Based on video location and the road test judgment method of digital modeling combined technology |
| JP6594736B2 (en) * | 2015-10-27 | 2019-10-23 | クラリオン株式会社 | Parking assistance device |
| CN107103814B (en) * | 2017-02-28 | 2019-12-10 | 广州地理研究所 | Parking garage check system based on automobile electronic identification |
| CN106952308B (en) * | 2017-04-01 | 2020-02-28 | 上海蔚来汽车有限公司 | Method and system for determining position of moving object |
| CN109996706B (en) * | 2017-09-19 | 2021-08-20 | Jvc 建伍株式会社 | Display control apparatus, system, method, and computer-readable storage medium |
| CN108022404A (en) * | 2017-10-18 | 2018-05-11 | 广州市果豆科技有限责任公司 | A kind of parking alarm method and system based on multi-cam |
| CN108154472B (en) * | 2017-11-30 | 2021-10-08 | 惠州市德赛西威汽车电子股份有限公司 | Parking space visual detection method and system integrating navigation information |
| CN108717800B (en) * | 2018-04-08 | 2020-11-24 | 郑州轻工业学院 | Management system and method for intelligent parking lot |
| CN108550225A (en) * | 2018-04-09 | 2018-09-18 | 廖辉 | A kind of share examines vehicle system and the shared business model based on the system |
| CN108873097B (en) * | 2018-05-08 | 2020-07-07 | 上海极歌企业管理咨询中心（有限合伙） | Safety detection method and device for parking of vehicle carrying plate in unmanned parking garage |
| CN110533950A (en) | 2018-05-25 | 2019-12-03 | 杭州海康威视数字技术股份有限公司 | Detection method, device, electronic equipment and the storage medium of parking stall behaviour in service |
| CN109120899A (en) * | 2018-09-03 | 2019-01-01 | 天津工业大学 | A kind of Camera Tracking System and method based on ultrasonic signal |
| CN109272821A (en) * | 2018-10-22 | 2019-01-25 | 广州星唯信息科技有限公司 | A kind of place driving evaluation method based on high-precision vision positioning |
| CN109413329B (en) * | 2018-11-06 | 2020-05-22 | 优信拍（北京）信息科技有限公司 | Vehicle panorama display method, device and system |
| CN110491168B (en) * | 2019-08-09 | 2020-09-25 | 智慧互通科技有限公司 | Method and device for detecting vehicle parking state based on wheel landing position |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3445197B2 (en) * | 1998-10-08 | 2003-09-08 | 松下電器産業株式会社 | Driving operation assist device |
| CN2600787Y (en) * | 2002-08-21 | 2004-01-21 | 张拥军 | Device for measuring running trace of vehicle starting using digital image identification technology |
| CN2901734Y (en) * | 2006-01-17 | 2007-05-16 | 东南大学 | Caliberating board of camera caliberating data |
| CN201037962Y (en) * | 2006-06-29 | 2008-03-19 | 北京艾曼特科技有限公司 | Electronic pile examining system |
| JP5697369B2 (en) * | 2010-06-28 | 2015-04-08 | キヤノン株式会社 | Image processing apparatus, image processing system, and image processing method |
| CN202003539U (en) * | 2011-01-07 | 2011-10-05 | 北京精英智通交通***科技有限公司 | Subject 3 video tracking examination system of motor vehicle drivers |
| CN102768811B (en) * | 2012-06-18 | 2014-07-02 | 柳州桂通科技有限公司 | Car driver driving skill practice guiding and examination scoring device and realization method |
| CN202615664U (en) * | 2012-06-20 | 2012-12-19 | 深圳市泰慧自动化技术有限公司 | Unsafe operation detection system for special work actual operation test |
-
2012
- 2012-12-28 CN CN201210585168.4A patent/CN103065520B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN103065520A (en) | 2013-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103065520B (en) | Detection system for backing car into storage and detection method thereof | |
| CN103065519B (en) | Detecting system of ramp fixed point stopping and starting and detecting method of ramp fixed point stopping and starting | |
| CN103076007B (en) | Lateral parking detection system and detection method thereof | |
| CN103000067B (en) | Right angle turning detection system and detecting method thereof | |
| US20200041284A1 (en) | Map road marking and road quality collecting apparatus and method based on adas system | |
| CN112633535A (en) | Photovoltaic power station intelligent inspection method and system based on unmanned aerial vehicle image | |
| US20140022281A1 (en) | Projecting airplane location specific maintenance history using optical reference points | |
| CN103630496B (en) | Based on the traffic video visibility detecting method of road surface apparent brightness and least square method | |
| CN111339905B (en) | CIM well lid state visual detection system based on deep learning and multiple visual angles | |
| CN106251695A (en) | Destination's parking stall intelligent recommendation system and method based on parking space state monitoring | |
| KR102119033B1 (en) | Apparatus and method for providing road marking information using image data and vibration | |
| CN108364466A (en) | A kind of statistical method of traffic flow based on unmanned plane traffic video | |
| CN103985131B (en) | Camera fast-calibration method for highway lane departure warning system | |
| CN103077639B (en) | Curve driving detection system and detection method thereof | |
| CN102073846A (en) | Method for acquiring traffic information based on aerial images | |
| CN102446355B (en) | Method for detecting target protruding from plane based on double viewing fields without calibration | |
| CN105938554B (en) | The tongue telescopic displacement monitoring method and system read based on image automatic judging | |
| CN112735253B (en) | Traffic light automatic labeling method and computer equipment | |
| CN112505663B (en) | Calibration method for multi-line laser radar and camera combined calibration | |
| CN103279760A (en) | Real-time classifying method of plant quarantine larvae | |
| CN114113118A (en) | Rapid detection device and detection method for water leakage disease of subway tunnel lining cracks | |
| CN106600561A (en) | Aerial image perspective distortion automatic correction method based on projection mapping | |
| CN115588040A (en) | System and method for counting and positioning coordinates based on full-view imaging points | |
| US20230108779A1 (en) | Road deterioration diagnostic device, road deterioration diagnostic system, roaddeterioration diagnostic method, and recording medium | |
| CN105869413A (en) | Method for measuring traffic flow and speed based on camera video |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |