CN101661682B - Intelligent road tester based on omni-directional vision - Google Patents

Abstract

An intelligent road tester based on omni-directional vision comprises two omni-directional vision sensors without dead angle, a GPS sensor, a test prompter and a micro-processor, wherein the omni-directional vision sensors are used for obtaining video information of road condition around a vehicle used for road test; the GPS sensor is used for obtaining information of space position of the vehicle used for road test; the test prompter is used for prompting a testee of the content of next subject needing to be tested; and the micro-processor is used for processing, transmitting and memorizing the video information of road condition around the vehicle used for road test; one of the two omni-directional vision sensors is arranged on a support of the front base of the vehicle used for road test so as to obtain the video images in front of and on the left of the vehicle; the other omni-directional vision sensor is arranged on a support of the back base of the vehicle used for road test so as to obtain the video images in back of and on the right of the vehicle; and the GPS sensor, the test prompter and the micro-processor are all arranged in the vehicle. The intelligent road tester based on omni-directional vision can accurately record and judge the real capability of a driver operating and driving a motor vehicle, can conduct on-vehicle test instead of a tester, and has strong practicability.

Description

Intelligent Examination instrument based on omni-directional visual

Technical field

The invention belongs to omnibearing vision sensor technology, image recognition technology, GPS location and the application of Radio Transmission Technology aspect road test.

Background technology

Requirement according to The Ministry of Public Security of the People's Republic of China, MOPS's the 91st command defined, examinee to the application to get motor vehicle driving license needs to carry out the purpose examination of place driving efficiency test subject, driving path examination of technical ability section, and place driving efficiency test subject comprises: stake is examined, the ramp stopping a train at a target point and stop in starting, side, by monolateral bridge, curve driving, right-angled bend, speed limit by the limit for width door, travel by continuous obstacle, hundred meters plus-minus retainings, rough roads; Driving path examination of technical ability subject comprises: the preparation of getting on the bus, starting, straight-line travelling, change lane, by the crossing, keep to the side to stop, by zebra crossing, by school zone, by bus stop, meeting, overtake other vehicles, turn around, night running.And these examinations at present need the examiner to judge with car range estimation examinee's driving situation whether subject technical ability is passed through, and this mode depends on examiner's subjective judgement, promptly takes police strength to be easy to generate erroneous judgement again; Some subject is to judge by the sensation that the examiner is sitting in the car fully, also needs the observation of getting off in the time of can't judging.

China utility model 200420115448.X discloses a kind of vibration sensing type motor vehicle curve driving road test device.It is by inboard bend pipe, and outside bend pipe, elastic supporting mechanism and vibrating sensing device etc. are partly formed; It is characterized in that: form the bend sideline with two groups of bend pipes, bend pipe is installed on the elastic supporting mechanism, and vibration transducer is housed in the bend pipe.The utility model accurately and reliably touches in the monitoring motor vehicle road test process and rolls bend sideline, curve driving examination hall.This road test device is only at curve driving road test subject, and use face is narrower, also needs to do on the ground a road test device simultaneously.China's utility model 200520079228.0 discloses a kind of road test device with Hall element, detect whether short of vehicle by being embedded in the tested magnetic patch in underground magnetic field, examination hall and being placed in the field signal detector of examination on the vehicle, this measuring method belongs to point measurement, therefore sensing range is little, and use face is narrower.China utility model 200620012962.X discloses the vehicle-mounted identification road test of a kind of surface mark diffuse reflection device, include and examine car, truck-mounted computer, central control computer and be located at examination equipment on the road test track, it is characterized in that this examine be equiped with under the chassis left front, right front, left back, five electric transducers that diffuse in right back and preceding, the road test track is provided with the designation strip code set that many groups are made up of five rectangle designation strips, comprise the obstacle cake that is provided with vibration transducer and pressure switch in those examination equipments, be provided with the monolateral bridge of the last bridge check-out console of pressure switch, be provided with the hollow box of vibration transducer, be provided with the suspension rod of vibration transducer etc., and the distinctive mark that is provided with according to the requirement of examination equipment and examination project, these signs are discerned by vehicle-mounted recognition system, declare and know total marks of the examination, can reduce the kind of sensor; This road test device need be settled a lot of marks on the road test track, not too be suitable for the purpose examination of driving path examination of technical ability section, also exists the problem of the visual difference of examination process in addition.

The solution that the video road test is also arranged at present, but because the camera head that adopts can only obtain the video information on the some directions of road test vehicle, sensing range is very restricted.

GPS (GPS) is after stepchild's noon satellite navigation system, the second generation global position system that U.S. government releases.Utilization GPS carries out the Dynamic High-accuracy measurement and has become an important research direction both domestic and external.In order to improve the precision that GPS measures, the dynamic difference location more and more causes people's attention.Dynamic difference is tight and better effects if than coordinate difference.The high precision potential of GPS difference also is the application of carrier phase, and the difference method that phase place combines with pseudorange can reach the precision of 0.5-1m.Such bearing accuracy has satisfied the positioning requirements of vehicle basically, and GPS adopts the location come card S530.

Replacing with the car examiner with omnidirectional computer vision and mode identification technology is the direction of a road test development, utilize will the take an examination panoramic video data of vehicle periphery of wireless communication technique to send Test Centre to, utilize video data recording equipment and GPS sensor that all associated video data and spatial positional information in the road test are recorded truly, utilize computer vision technique and mode identification technology to analyze automatically and the every real vehicle total marks of the examination of judgement examinee, intelligent Examination instrument based on omni-directional visual helps the fair and just of road test, effectively reduces police strength.

Summary of the invention

Need a large amount of police strength in order to overcome present road test, owing to various artificial reasons produce the deficiency of the unfair injustice problem of road test, the invention provides and a kind ofly can write down accurately and judge that the driver handles the real ability of driving motor vehicle, can replace the examiner with car examination, the practical intelligent Examination instrument based on omni-directional visual.

The present invention for the technical scheme that solves the problems of the technologies described above proposition is:

A kind of intelligent Examination instrument based on omni-directional visual, comprise: be used to obtain road test with the omnibearing vision sensor at two no dead angles of the road conditions video information of vehicle periphery, be used to obtain road test with the GPS sensor of the locus of vehicle, be used to point out the examination prompting device that needs the subject content of taking an examination below the examinee, and be used to handle, transmit and store the microprocessor of road test with the road conditions video information of vehicle periphery; In the omnibearing vision sensor at two no dead angles, wherein on the preceding base support that is placed in the road test vehicle, in order to obtain the video image in vehicle front and left side; Another is placed on the rear base support of road test vehicle, in order to obtain the video image on rear view of vehicle and right side; Described GPS sensor, examination prompting device and microprocessor are installed in the vehicle, the omnibearing vision sensor at described two no dead angles is connected with described microprocessor by video interface, described GPS sensor is connected with described microprocessor by data-interface, and described examination prompting device is connected with described microprocessor;

Described no dead angle omnibearing vision sensor comprises the catadioptric minute surface one time, secondary catadioptric minute surface, transparent housing and shooting part, a described catadioptric minute surface and secondary catadioptric minute surface are installed on the transparent housing, described shooting part is positioned on the viewpoint of a catadioptric minute surface back, described secondary catadioptric minute surface is positioned at the front of a catadioptric minute surface, all have an aperture on a described catadioptric minute surface and the secondary catadioptric minute surface, described secondary catadioptric minute surface is embedded in wide-angle lens, described shooting part camera lens, wide-angle lens, the central shaft arrangement of catadioptric mirror and secondary catadioptric mirror is on same axial line

Described microprocessor comprises:

The video image reading unit is used to read the video image of two no dead angle omnibearing vision sensors, and the video image that obtains is sent to test subject data operation record unit;

The vehicle location acquiring unit is used for obtaining the residing positional information of road test vehicle, the position that obtains scene surveying instrument by the GPS sensor in the driving path examination of technical ability;

Examinee's relevant information input-output unit is used to import examinee's relevant information and is used for the examinee confirms the he or she on display relevant information;

The test subject unit of setting a question, the place driving efficiency test subject and the driving path examination of technical ability section purpose content that are used for sending over according to described examinee's relevant information input-output unit are set a question, set a question and at first determine driving efficiency examination still driving path examination of technical ability subject in place in the unit, do not examine the subject from this examinee then and set a question, the result that then will set a question sends to test subject data operation record unit and export the subject that the examinee will take an examination from the examination prompting device;

Test subject data operation record unit is used for writing down the examinee in the video data of road test process, the position data of vehicle, the time of examination, the subject of examination and ID number of examinee;

The test subject analytic unit is used for analyzing the examinee at the various sections purpose video image that road test is write down, and the standard-required by analysis video data and test subject compares analysis;

The test subject identifying unit, be used to judge examinee's road test situation, analysis result according to each test subject analytic unit, if being the subject of examining, passes through analysis result, then the achievement of this test subject is added in the pairing subject eligible list, do not pass through if analysis result is the subject of examining, then this test subject is unqualified; In subject eligible list table, stay blank for the result of determination that can't confirm, leave examiner's manual observation video for and back up and judge.

Further, in described examinee's relevant information input-output unit, when the examinee claimed road test, Examination instrument required the examinee to import examinee ID number from keyboard, and examinee's ID number identical with examinee's identification card number; Examination instrument checks that at first whether the number imported is the requirement whether the range of age of 18 bit digital and examinee meets the Ministry of Public Security's the 91st command defined, and then whether ID number of checking the examinee that the examinee imported exists in storage unit, if present, check whether this examinee has all finished the driving efficiency examination, if all do not finish on display the relevant information that shows the examinee and below need the content of taking an examination; It is the place driving efficiency test subject table and the driving path examination of technical ability Operating Chart of Accounts of major key by examinee ID number that words if there is no just produce one automatically, and shown in table 1, table 2, wherein, table 1 is a place driving efficiency total marks of the examination table; Table 2 is a driving path examination of technical ability list of results:

Examinee ID:

	Examine	Pass through	Test time
				Stake is examined
Ramp stopping a train at a target point and starting
				Stop in the side
By monolateral bridge
				Curve driving
Right-angled bend
				Speed limit is by the limit for width door
By continuous obstacle
				Hundred meters plus-minus retainings
Rough road travels

Table 1

	Examine	Pass through	Test time
				Straight-line travelling
Change lane
				Pass through the crossing
Keep to the side to stop
				Pass through zebra crossing
Pass through school zone
				Pass through bus stop
Meeting
				Overtake other vehicles
Night running

Table 2

After input examinee ID empirical tests was correct, the examinee entered road test; At last place driving efficiency test subject table and driving path examination of technical ability Operating Chart of Accounts are sent to the described test subject unit of setting a question.

Further again, in described test subject data operation record unit, the ambient image of the omnibearing vision sensor at two no dead angles of road test vehicle periphery is spliced, the image after splicing and the processing sends to test subject analytic unit and storage unit; Keep the real-time video backup of examination process in storage unit, the examinee has a question to examination result can access the video playback of examination process, avoids judging dispute; Real-time video backup file name is stored with examinee ID+ subject ID.

Further, in described test subject analytic unit, adopt edge detection algorithm to detect the examination vehicle and whether touch the sign edge; Described rim detection is to rely on image differentiated to try to achieve gradient and carry out rim detection, from marginal point often corresponding to the big point of single order differential amplitude, while also sets out corresponding to the zero cross point of second-order differential, design some single orders or second-order differential operator, try to achieve its gradient or second derivative zero crossing, select certain threshold value to extract the border again.

In described test subject analytic unit, adopt edge detection algorithm to detect the examination vehicle and whether touch the sign edge; Described rim detection is to rely on image differentiated to try to achieve gradient and carry out rim detection, from marginal point often corresponding to the big point of single order differential amplitude, while also sets out corresponding to the zero cross point of second-order differential, design some single orders or second-order differential operator, try to achieve its gradient or second derivative zero crossing, select certain threshold value to extract the border again.

Set the circular hole on the catadioptric mirror and between wide-angle lens and shooting part camera lens, be imaged as first imaging point, this imaging point passes through the shooting part camera lens in the imaging of viewpoint place, with the focal length of shooting part camera lens as f1, the focal length of wide-angle lens is as f2, the distance of the focus of shooting part camera lens and shooting part camera lens is as S1, focal length from the shooting part camera lens to first imaging point is as S2, distance from wide-angle lens to first imaging point is as S3, the distance of point obtains following relational expression as S4 according to the imaging formula of camera lens from the wide-angle lens to the material object:

$\frac{1}{\mathrm{<figure-callout\; id="1"\; label="f"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">f</figure-callout>}1}=\frac{1}{\mathrm{<figure-callout\; id="1"\; label="S"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">S</figure-callout>}1}+\frac{1}{S2}---\left(10\right)$

$\frac{1}{\mathrm{<figure-callout\; id="2"\; label="f"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">f</figure-callout>}2}=\frac{1}{\mathrm{<figure-callout\; id="3"\; label="S"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">S</figure-callout>}3}+\frac{1}{S4}---\left(11\right)$

d＝S2+S3 (12)

Focal length f2 by the design wide-angle lens satisfies the requirement of formula (12);

The focal distance f of combination shot unit is represented by following formula:

$\frac{1}{f}=\frac{(f1+f2-d)}{f1*f2}---\left(13\right)$

In addition, as D, its enlargement factor is represented by following formula with the diameter of process shot:

$n=\frac{D}{f}---\left(14\right)$

Satisfy following formula during process shot:

$n=\frac{D}{f}=2{\mathrm{\&theta;}}_{1\max }---\left(15\right)$

In the formula, θ _1maxIt is the maximum angle of secondary reflection light V3 and catadioptric main shaft Z.

Described no dead angle omnibearing vision sensor carries out the design of horizontal direction average resolution rate, specifically has:

The angle of incident ray V1 and catadioptric main shaft Z is Φ, and the angle of primary event light V2 and catadioptric main shaft Z is θ ₂, cross P ₁Point (t ₁, F ₁) tangent line and the angle of t axle be σ, the angle of normal and Z axle is ε; The angle of secondary reflection light V3 and catadioptric main shaft Z is θ ₁, cross P ₂Point (t ₂, F ₂) tangent line and the angle of t axle be σ, the angle of normal and Z axle is ε ₁, can obtain formula (1) based on above-mentioned relation:

Wherein, $\tan \mathrm{\&phi;}=\frac{t_1}{F_1(t_1-s)},$ $\tan {\mathrm{\&theta;}}_2=\frac{t_1-t_2}{F_2-{\mathrm{<figure-callout\; id="1"\; label="F"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">F</figure-callout>}}_1},$ $\tan {\mathrm{\&theta;}}_1=\frac{t_2}{{\mathrm{<figure-callout\; id="2"\; label="F"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">F</figure-callout>}}_2}$

In the formula, F ₁Be a catadioptric minute surface curve, F ₂It is secondary catadioptric minute surface curve;

Utilize triangle relation and simplify arrangement, obtain formula (2), (3):

${\mathrm{<figure-callout\; id="1"\; label="F"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">F</figure-callout>}}_1^{\&prime;2}-2\mathrm{\&alpha;}{\mathrm{<figure-callout\; id="1"\; label="F"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">F</figure-callout>}}_1^{\&prime;}-1=0---\left(2\right)$

${\mathrm{<figure-callout\; id="2"\; label="F"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">F</figure-callout>}}_2^{\&prime;2}-2\mathrm{\&beta;}{\mathrm{<figure-callout\; id="2"\; label="F"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">F</figure-callout>}}_2^{\&prime;}-1=0---\left(3\right)$

In the following formula,

$\mathrm{\&sigma;}=\frac{(F_1-s)(F_2-F_1)-t_1(t_1-t_2)}{t_1(F_2-F_1)-(t_1-t_2)(F_1-s)}$

$\mathrm{\&beta;}=\frac{t_2(t_1-t_2)+F_2(F_2-F_1)}{t_2(F_2-F_1)-F_2(t_1-t_2)}$

Solution formula (2), (3) can obtain formula (4), (5);

${{\mathrm{<figure-callout\; id="1"\; label="F"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">F</figure-callout>}}_1}^{\&prime;}=\mathrm{\&alpha;}\&PlusMinus;\sqrt{{\mathrm{\&alpha;}}^2+1}---\left(4\right)$

${{\mathrm{<figure-callout\; id="2"\; label="F"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">F</figure-callout>}}_2}^{\&prime;}=\mathrm{\&beta;}\&PlusMinus;\sqrt{{\mathrm{\&beta;}}^2+1}---\left(5\right)$

In the formula: F ' ₁Be F ₁The differential of curve, F ' ₂Be F ₂The differential of curve;

Set up a kind of pixel P to the Z wheelbase from and incident angle φ between linear relationship, represent with formula (6),

In the formula: a ₀, b ₀Be arbitrary parameter,

As f, P is the distance that pixel arrives the Z axle, the reflection spot (t on the secondary reflection minute surface with the focal length of image unit ₂, F ₂); Then according to image-forming principle, P is represented by formula (7):

$P=f*\frac{t_2}{F_2}---\left(7\right)$

With formula (7) substitution formula (6), can get formula (8),

$\mathrm{\&phi;}=a_0*(f*\frac{t_2}{F_2})+b_0---\left(8\right)$

Represent with formula (9) according to catadioptric principle formula (8):

${\tan }^{-1}\left(\frac{t_1}{F_1-s}\right)=a_0*(f*\frac{t_2}{F_2})+b_0---\left(9\right)$

Utilize formula (2), (3), (9), utilize 4 rank Runge-Kutta algorithms to ask F ₁And F ₂Digital solution, calculate the curve of catadioptric minute surface and secondary catadioptric minute surface.

Described transparent housing is bowl-shape.Described examination prompting device is a loudspeaker, and described loudspeaker is connected with described microprocessor by audio interface.

Technical conceive of the present invention is: the present invention proposes to adopt the omnibearing vision sensor at two no dead angles obtain the to take an examination video image of vehicle periphery road conditions, but present omnibearing vision sensor (hereinafter to be referred as ODVS) technology also can't realize the indeformable requirement of road surface top view video image; Therefore need carry out the design of horizontal direction average resolution rate, to satisfy the indeformable requirement of road surface top view video image; So can ascribe the design of catadioptric minute surface curve in the ODVS design, as shown in Figure 4, the incident light V1 of a light source point P on the space is at principal reflection minute surface (t1, F ₁) reflect on the point, reflected light V2 reflexes to secondary reflection minute surface (t2, F ₂) reflect again on the point, reflected light V3 goes up imaging with the camera lens that angle θ 1 enters camera head at image unit (CCD or CMOS).

According to image-forming principle, the angle of incident ray V1 and catadioptric main shaft Z is Φ, and the angle of primary event light V2 and catadioptric main shaft Z is θ ₂, cross P ₁Point (t ₁, F ₁) tangent line and the angle of t axle be σ, the angle of normal and Z axle is ε; The angle of secondary reflection light V3 and catadioptric main shaft Z is θ ₁, cross P ₂Point (t ₂, F ₂) tangent line and the angle of t axle be σ, the angle of normal and Z axle is ε ₁, can obtain formula (1) based on above-mentioned relation:

Wherein $\tan \mathrm{\&phi;}=\frac{t_1}{F_1(t_1-s)},$ $\tan {\mathrm{\&theta;}}_2=\frac{t_1-t_2}{F_2-{\mathrm{<figure-callout\; id="1"\; label="F"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">F</figure-callout>}}_1},$ $\tan {\mathrm{\&theta;}}_1=\frac{t_2}{{\mathrm{<figure-callout\; id="2"\; label="F"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">F</figure-callout>}}_2}$

In the formula, F ₁Be a catadioptric minute surface curve, F ₂It is secondary catadioptric minute surface curve;

Utilize triangle relation and simplify arrangement, obtain formula (2), (3):

${\mathrm{<figure-callout\; id="1"\; label="F"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">F</figure-callout>}}_1^{\&prime;2}-2\mathrm{\&alpha;}{\mathrm{<figure-callout\; id="1"\; label="F"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">F</figure-callout>}}_1^{\&prime;}-1=0---\left(2\right)$

${\mathrm{<figure-callout\; id="2"\; label="F"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">F</figure-callout>}}_2^{\&prime;2}-2\mathrm{\&beta;}{\mathrm{<figure-callout\; id="2"\; label="F"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">F</figure-callout>}}_2^{\&prime;}-1=0---\left(3\right)$

In the following formula,

$\mathrm{\&sigma;}=\frac{(F_1-s)(F_2-F_1)-t_1(t_1-t_2)}{t_1(F_2-F_1)-(t_1-t_2)(F_1-s)}$

$\mathrm{\&beta;}=\frac{t_2(t_1-t_2)+F_2(F_2-F_1)}{t_2(F_2-F_1)-F_2(t_1-t_2)}$

Solution formula (2), (3) can obtain formula (4), (5);

${{\mathrm{<figure-callout\; id="1"\; label="F"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">F</figure-callout>}}_1}^{\&prime;}=\mathrm{\&alpha;}\&PlusMinus;\sqrt{{\mathrm{\&alpha;}}^2+1}---\left(4\right)$

${{\mathrm{<figure-callout\; id="2"\; label="F"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">F</figure-callout>}}_2}^{\&prime;}=\mathrm{\&beta;}\&PlusMinus;\sqrt{{\mathrm{\&beta;}}^2+1}---\left(5\right)$

In the formula: F ' ₁Be F ₁The differential of curve, F ' ₂Be F ₂The differential of curve;

Point on the described imaging plane and the relation between the point on the surface level have certain linear relationship, with the distance of viewpoint S be C and with the perpendicular surface level L of Z axle on arbitrfary point P, the pixel p that a correspondence is arranged on imaging plane, as shown in Figure 4, with the coordinate polar coordinate representation on the surface level, at this moment (r z) can represent with following formula the arbitrfary point P on the surface level L

r＝C*tanφ，z＝s+C (6)

In order to have average resolution rate ODVS on the design level face, i.e. the indeformable ODVS of horizontal direction, the coordinate r of arbitrfary point P on surface level L and the perpendicular direction of Z axle and pixel p and Z axle apart from t ₂/ F ₂(t ₂) between to guarantee to have linear relationship.Make following formula to set up,

r＝a*f*t ₂/F ₂(t ₂)+b (7)

There is following relation to set up according to image-forming principle, incident angle formula (8) expression,

$\tan \mathrm{\&phi;}\frac{t_1}{F_1-s}---\left(8\right)$

With formula (6), (8) substitution formula (7) and arrangement, obtain indeformable in the horizontal direction condition, with formula (9) expression,

${\mathrm{<figure-callout\; id="2"\; label="t"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">t</figure-callout>}}_2=\frac{F_2\left(t_2\right)}{a*f}(\frac{t_1}{F_1\left(t_1\right)-s}-b)---\left(9\right)$

The minute surface curve design that satisfies formula (9) meets the requirement of horizontal direction average resolution rate;

Ask F by formula (2), (3), (9) being utilized 4 rank Runge-Kutta algorithms ₁And F ₂Digital solution, the catadioptric minute surface and the secondary catadioptric minute surface curve that calculate like this can be realized horizontal direction average resolution rate; Fig. 7 utilizes 4 rank Runge-Kutta algorithms to ask F ₁And F ₂The catadioptric minute surface curve map of digital solution;

Design transparent housing 2 is in order to make transparent housing 2 can not produce the reflection interference light of inwall, as shown in Figure 3.Specific practice is transparent housing to be designed to bowl-shape, promptly is designed to semi-round ball, can avoid like this at transparent housing 2 the reflection interference light taking place, and the structure of the ODVS at no dead angle as shown in Figure 3;

Reserve an aperture at the top of a catadioptric minute surface, video camera 3 can photograph the image information of a catadioptric minute surface back by this aperture, but can photograph catadioptric image on most of secondary catadioptric minute surface of image information of a catadioptric minute surface back by this aperture, still have some spatial image informations to be blocked by secondary catadioptric minute surface; Among the present invention wide-angle lens is configured on the secondary catadioptric minute surface, the position of design wide-angle lens and definite wide-angle lens is a task of the present invention.Fig. 8 is the location diagram of shooting part camera lens and wide-angle lens.In Fig. 8 wide-angle lens is configured on the place ahead and secondary catadioptric minute surface of a catadioptric mirror, the central shaft arrangement of shooting part camera lens, wide-angle lens, catadioptric mirror and secondary catadioptric mirror is on same axial line; Circular hole imaging between wide-angle lens and shooting part camera lens by on catadioptric mirror is called first imaging point, this imaging point by the shooting part camera lens in the imaging of viewpoint place.Here with the focal length of shooting part camera lens as the focal length of f1, wide-angle lens as the distance of the focus of f2, shooting part camera lens and shooting part camera lens as S1, focal length from the shooting part camera lens to first imaging point as S2, distance from wide-angle lens to first imaging point as S3, the distance of point can obtain following relational expression as S4 according to the imaging formula of camera lens from the wide-angle lens to the material object:

$\frac{1}{\mathrm{<figure-callout\; id="1"\; label="f"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">f</figure-callout>}1}=\frac{1}{\mathrm{<figure-callout\; id="1"\; label="S"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">S</figure-callout>}1}+\frac{1}{S2}---\left(10\right)$

$\frac{1}{\mathrm{<figure-callout\; id="2"\; label="f"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">f</figure-callout>}2}=\frac{1}{\mathrm{<figure-callout\; id="3"\; label="S"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">S</figure-callout>}3}+\frac{1}{S4}---\left(11\right)$

d＝S2+S3(12)

Formula (12) is set up, and is the place configuration wide-angle lens of d with the shooting part distance of camera lens behind the first catadioptric minute surface among Fig. 8 just, just can obtain the shown wide-angle image in image middle part among Fig. 2; But be that wide-angle lens is configured on the second catadioptric minute surface among the present invention, therefore with between shooting part camera lens and the wide-angle lens apart from d as a constraint condition, have only focal length f2 to satisfy the requirement of formula (12) by designing wide-angle lens;

For among Fig. 8 shooting part camera lens and wide-angle lens being considered that as a compound lens its focal distance f can be represented by following formula:

$\frac{1}{f}=\frac{(\mathrm{<figure-callout\; id="1"\; label="f"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">f</figure-callout>}1+f2-d)}{\mathrm{<figure-callout\; id="1"\; label="f"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">f</figure-callout>}1*f2}---\left(13\right)$

In addition, as D, its enlargement factor can be represented by following formula with the diameter of process shot:

$n=\frac{D}{f}---\left(14\right)$

For the visual field of process shot and the dead angle part of ODVS are matched, when the design process shot, need satisfy following formula:

$n=\frac{D}{f}=2{\mathrm{\&theta;}}_{1\max }---\left(15\right)$

In the formula, θ _1maxIt is the maximum angle of secondary reflection light V3 and catadioptric main shaft Z; The image effect figure that the ODVS of the above-mentioned design of process takes out as shown in Figure 2, from single ODVS, eliminated the dead angle part of original ODVS, and add the design of the first catadioptric minute surface and the second catadioptric minute surface by the array mode of shooting part camera lens and wide-angle lens, can cover the dead angle part of original ODVS effectively.

Aperture on the described first catadioptric minute surface, the first catadioptric minute surface, video camera, transparent housing, the second catadioptric minute surface, wide-angle lens are on same central axis; The camera lens of video camera is placed on the viewpoint position at the first catadioptric minute surface rear portion, as shown in Figure 3;

Described transparent housing, be mainly used in and support the first catadioptric minute surface, the second catadioptric minute surface, wide-angle lens and protect the first catadioptric minute surface and the second catadioptric minute surface is not subjected to the pollution of extraneous dust and influences catadioptric quality, but transparent housing itself also can be subjected to extraneous dust etc. and pollute and influence picture quality, thin film is coated in outside at transparent housing, and the principal ingredient of membraneous material is the nano material of titania;

The allocation plan of ODVS on the road test vehicle, an ODVS is placed on the preceding base support of road test vehicle, and as shown in Figure 9, the visual angle part of ODVS makes ODVS can capture the top view of the left front portion of vehicle just down; Another ODVS is placed on the rear base support of road test vehicle, and the visual angle part of ODVS makes ODVS can capture the top view of the right back portion of vehicle just down; Such ODVS allocation plan can obtain the full-view video image of the whole road conditions of road test vehicle periphery, shown in the part of the oblique line in accompanying drawing 1 and the accompanying drawing 5; Be placed in ODVS on the preceding base support of road test vehicle and obtain the video image in vehicle front and left side, be placed in the video image that ODVS on the rear base support of road test vehicle obtains rear view of vehicle and right side.

Beneficial effect of the present invention is: adopt technology such as omni-directional visual, computer vision, pattern-recognition, GPS location, make based on the intelligent Examination instrument of omni-directional visual can science, standard, the orderly overall process of finishing the automobile driver road examination automatically: (1) can write down accurately, judge that the driver handles the real ability of driving motor vehicle; (2) observation on the obstacle road surface of various road and complexity, judgement, prevention and adaptability to changes; (3), only need a small amount of the transformation just can become intelligent road test system to the place in existing road test training or examination place; (4) under tighter the situation, can build up mobile training field or mobile examination hall in the place; (5) need not to transform the road surface, be convenient to system's installation and maintenance, multiple mode such as picture control prevents to impersonate phenomenon, keeps the just, fair and open of examination; (6) alternative examiner takes an examination with car, can effectively reduce police strength.

Description of drawings

Fig. 1 is a right-angled bend section purpose video analysis synoptic diagram in a kind of road test;

Fig. 2 is the captured full-view video image synoptic diagram of no dead angle omnibearing vision sensor;

Fig. 3 is the imaging schematic diagram of no dead angle omnibearing vision sensor;

Fig. 4 is the imaging optical path analysis chart of no dead angle omnibearing vision sensor;

Fig. 5 is the fundamental diagram based on the intelligent Examination instrument of omni-directional visual;

Fig. 6 is the process flow block diagram based on the intelligent Examination instrument of omni-directional visual;

Fig. 7 is the minute surface curve map of secondary catadioptric minute surface design;

Fig. 8 is the optical schematic diagram that shooting part camera lens and wide-angle lens make up;

Fig. 9 is that no dead angle omnibearing vision sensor is placed in the synoptic diagram on the preceding base support of examination vehicle;

Figure 10 is the full-view video image synoptic diagram after splicing and the processing.

Embodiment

Invention will be further ex-plained with reference to the appended drawings.

With reference to Fig. 1～Figure 10, the invention provides a kind of intelligent Examination instrument based on omni-directional visual, comprise in the Examination instrument: be placed in the omnibearing vision sensor at two no dead angles on the vehicle frame of both sides, examination vehicle front and back, be used to obtain the road conditions video information of examination vehicle periphery; Be placed in the GPS sensor on the examination car, the locus that is used to obtain the examination car; Be placed in the microprocessor in the examination car, the road conditions video information that is used to handle, transmit and store the examination vehicle periphery; Be placed in the loudspeaker of examination in the car, being used to point out needs the subject content of taking an examination below the examinee; The omnibearing vision sensor at described two no dead angles is connected with described microprocessor by video interface, described GPS sensor is connected with described microprocessor by data-interface, and described loudspeaker is connected with described microprocessor by audio interface;

The present invention proposes to adopt the omnibearing vision sensor at two no dead angles obtain the to take an examination video image of vehicle periphery road conditions, but present omnibearing vision sensor (hereinafter to be referred as ODVS) technology also can't realize the indeformable requirement of road surface top view video image; Therefore need carry out the design of horizontal direction average resolution rate, to satisfy the indeformable requirement of road surface top view video image; So can ascribe the design of catadioptric minute surface curve in the ODVS design, as shown in Figure 4, the incident light V1 of a light source point P on the space is at principal reflection minute surface (t1, F ₁) reflect on the point, reflected light V2 reflexes to secondary reflection minute surface (t2, F ₂) reflect again on the point, reflected light V3 goes up imaging with the camera lens that angle θ 1 enters camera head at image unit (CCD or CMOS).

According to image-forming principle, the angle of incident ray V1 and catadioptric main shaft Z is Φ, and the angle of primary event light V2 and catadioptric main shaft Z is θ ₂, cross P ₁Point (t ₁, F ₁) tangent line and the angle of t axle be σ, the angle of normal and Z axle is ε; The angle of secondary reflection light V3 and catadioptric main shaft Z is θ ₁, cross P ₂Point (t ₂, F ₂) tangent line and the angle of t axle be σ, the angle of normal and Z axle is ε ₁, can obtain formula (1) based on above-mentioned relation:

Wherein $\tan \mathrm{\&phi;}=\frac{t_1}{F_1(t_1-s)},$ $\tan {\mathrm{\&theta;}}_2=\frac{t_1-t_2}{F_2-{\mathrm{<figure-callout\; id="1"\; label="F"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">F</figure-callout>}}_1},$ $\tan {\mathrm{\&theta;}}_1=\frac{t_2}{{\mathrm{<figure-callout\; id="2"\; label="F"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">F</figure-callout>}}_2}$

In the formula, F ₁Be a catadioptric minute surface curve, F ₂It is secondary catadioptric minute surface curve;

Utilize triangle relation and simplify arrangement, obtain formula (2), (3):

${\mathrm{<figure-callout\; id="1"\; label="F"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">F</figure-callout>}}_1^{\&prime;2}-2\mathrm{\&alpha;}{\mathrm{<figure-callout\; id="1"\; label="F"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">F</figure-callout>}}_1^{\&prime;}-1=0---\left(2\right)$

${\mathrm{<figure-callout\; id="2"\; label="F"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">F</figure-callout>}}_2^{\&prime;2}-2\mathrm{\&beta;}{\mathrm{<figure-callout\; id="2"\; label="F"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">F</figure-callout>}}_2^{\&prime;}-1=0---\left(3\right)$

In the following formula,

$\mathrm{\&sigma;}=\frac{(F_1-s)(F_2-F_1)-t_1(t_1-t_2)}{t_1(F_2-F_1)-(t_1-t_2)(F_1-s)}$

$\mathrm{\&beta;}=\frac{t_2(t_1-t_2)+F_2(F_2-F_1)}{t_2(F_2-F_1)-F_2(t_1-t_2)}$

Solution formula (2), (3) can obtain formula (4), (5);

${{\mathrm{<figure-callout\; id="1"\; label="F"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">F</figure-callout>}}_1}^{\&prime;}=\mathrm{\&alpha;}\&PlusMinus;\sqrt{{\mathrm{\&alpha;}}^2+1}---\left(4\right)$

${{\mathrm{<figure-callout\; id="2"\; label="F"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">F</figure-callout>}}_2}^{\&prime;}=\mathrm{\&beta;}\&PlusMinus;\sqrt{{\mathrm{\&beta;}}^2+1}---\left(5\right)$

In the formula: F ' ₁Be F ₁The differential of curve, F ' ₂Be F ₂The differential of curve;

Point on the described imaging plane and the relation between the point on the surface level have certain linear relationship, with the distance of viewpoint S be C and with the perpendicular surface level L of Z axle on arbitrfary point P, the pixel p that a correspondence is arranged on imaging plane, as shown in Figure 4, with the coordinate polar coordinate representation on the surface level, at this moment (r z) can represent with following formula the arbitrfary point P on the surface level L

r＝C*tanφ，z＝s+C (6)

In order to have average resolution rate ODVS on the design level face, i.e. the indeformable ODVS of horizontal direction, the coordinate r of arbitrfary point P on surface level L and the perpendicular direction of Z axle and pixel p and Z axle apart from t ₂/ F ₂(t ₂) between to guarantee to have linear relationship.Make following formula to set up,

r＝a*f*t ₂/F ₂(t ₂)+b (7)

There is following relation to set up according to image-forming principle, incident angle formula (8) expression,

$\tan \mathrm{\&phi;}=\frac{t_1}{F_1-s}---\left(8\right)$

With formula (6), (8) substitution formula (7) and arrangement, obtain indeformable in the horizontal direction condition, with formula (9) expression,

${\mathrm{<figure-callout\; id="2"\; label="t"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">t</figure-callout>}}_2=\frac{F_2\left(t_2\right)}{a*f}(\frac{t_1}{F_1\left(t_1\right)-s}-b)---\left(9\right)$

The minute surface curve design that satisfies formula (9) meets the requirement of horizontal direction average resolution rate;

Further, by formula (2), (3), (9) being utilized 4 rank Runge-Kutta algorithms ask F ₁And F ₂Digital solution, the catadioptric minute surface and the secondary catadioptric minute surface curve that calculate like this can be realized horizontal direction average resolution rate; Fig. 7 utilizes 4 rank Runge-Kutta algorithms to ask F ₁And F ₂The catadioptric minute surface curve map of digital solution;

Further, design transparent housing 2 is in order to make transparent housing 2 can not produce the reflection interference light of inwall, as shown in Figure 3.Specific practice is transparent housing to be designed to bowl-shape, promptly is designed to semi-round ball, can avoid like this at transparent housing 2 the reflection interference light taking place, and the structure of the ODVS at no dead angle as shown in Figure 3;

Further, reserve an aperture at the top of a catadioptric minute surface, video camera 3 can photograph the image information of a catadioptric minute surface back by this aperture, but can photograph catadioptric image on most of secondary catadioptric minute surface of image information of a catadioptric minute surface back by this aperture, still have some spatial image informations to be blocked by secondary catadioptric minute surface; Among the present invention wide-angle lens is configured on the secondary catadioptric minute surface, the position of design wide-angle lens and definite wide-angle lens is a task of the present invention.Fig. 8 is the location diagram of shooting part camera lens and wide-angle lens.In Fig. 8 wide-angle lens is configured on the place ahead and secondary catadioptric minute surface of a catadioptric mirror, the central shaft arrangement of shooting part camera lens, wide-angle lens, catadioptric mirror and secondary catadioptric mirror is on same axial line; Circular hole imaging between wide-angle lens and shooting part camera lens by on catadioptric mirror is called first imaging point, this imaging point by the shooting part camera lens in the imaging of viewpoint place.Here with the focal length of shooting part camera lens as the focal length of f1, wide-angle lens as the distance of the focus of f2, shooting part camera lens and shooting part camera lens as S1, focal length from the shooting part camera lens to first imaging point as S2, distance from wide-angle lens to first imaging point as S3, the distance of point can obtain following relational expression as S4 according to the imaging formula of camera lens from the wide-angle lens to the material object:

$\frac{1}{\mathrm{<figure-callout\; id="1"\; label="f"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">f</figure-callout>}1}=\frac{1}{\mathrm{<figure-callout\; id="1"\; label="S"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">S</figure-callout>}1}+\frac{1}{S2}---\left(10\right)$

$\frac{1}{\mathrm{<figure-callout\; id="2"\; label="f"\; filenames="H2009101524319E00021.png"\; state="\{\{state\}\}">f</figure-callout>}2}=\frac{1}{\mathrm{<figure-callout\; id="3"\; label="S"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">S</figure-callout>}3}+\frac{1}{S4}---\left(11\right)$

d＝S2+S3 (12)

Formula (12) is set up, and is the place configuration wide-angle lens of d with the shooting part distance of camera lens behind the first catadioptric minute surface among Fig. 8 just, just can obtain the shown wide-angle image in image middle part among Fig. 2; But be that wide-angle lens is configured on the second catadioptric minute surface among the present invention, therefore with between shooting part camera lens and the wide-angle lens apart from d as a constraint condition, have only focal length f2 to satisfy the requirement of formula (12) by designing wide-angle lens;

Further, among Fig. 8 shooting part camera lens and wide-angle lens being considered that as a compound lens its focal distance f can be represented by following formula:

$\frac{1}{f}=\frac{(\mathrm{<figure-callout\; id="1"\; label="f"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">f</figure-callout>}1+f2-d)}{\mathrm{<figure-callout\; id="1"\; label="f"\; filenames="H2009101524319E00031.png"\; state="\{\{state\}\}">f</figure-callout>}1*f2}---\left(13\right)$

In addition, as D, its enlargement factor can be represented by following formula with the diameter of process shot:

$n=\frac{D}{f}---\left(14\right)$

For the visual field of process shot and the dead angle part of ODVS are matched, when the design process shot, need satisfy following formula:

$n-\frac{D}{f}={2\mathrm{\&theta;}}_{1\max }---\left(15\right)$

In the formula, θ _1maxIt is the maximum angle of secondary reflection light V3 and catadioptric main shaft Z; The image effect figure that the ODVS of the above-mentioned design of process takes out as shown in Figure 2, from single ODVS, eliminated the dead angle part of original ODVS, and add the design of the first catadioptric minute surface and the second catadioptric minute surface by the array mode of shooting part camera lens and wide-angle lens, can cover the dead angle part of original ODVS effectively.

Further, the aperture on the described first catadioptric minute surface, the first catadioptric minute surface, video camera, transparent housing, the second catadioptric minute surface, wide-angle lens are on same central axis; The camera lens of video camera is placed on the viewpoint position at the first catadioptric minute surface rear portion, as shown in Figure 3;

Described transparent housing, be mainly used in and support the first catadioptric minute surface, the second catadioptric minute surface, wide-angle lens and protect the first catadioptric minute surface and the second catadioptric minute surface is not subjected to the pollution of extraneous dust and influences catadioptric quality, but transparent housing itself also can be subjected to extraneous dust etc. and pollute and influence picture quality, thin film is coated in outside at transparent housing, and the principal ingredient of membraneous material is the nano material of titania;

Further, be the allocation plan of ODVS on the road test vehicle, an ODVS is placed on the preceding base support of road test vehicle, and as shown in Figure 9, the visual angle part of ODVS makes ODVS can capture the top view of the left front portion of vehicle just down; Another ODVS is placed on the rear base support of road test vehicle, and the visual angle part of ODVS makes ODVS can capture the top view of the right back portion of vehicle just down; Such ODVS allocation plan can obtain the full-view video image of the whole road conditions of road test vehicle periphery, shown in the part of the oblique line in accompanying drawing 1 and the accompanying drawing 5; Be placed in ODVS on the preceding base support of road test vehicle and obtain the video image in vehicle front and left side, be placed in the video image that ODVS on the rear base support of road test vehicle obtains rear view of vehicle and right side;

Described microprocessor comprises video image reading unit, vehicle location acquiring unit, examinee's relevant information input-output unit, test subject set a question unit, test subject data operation record unit, storage unit, test subject analytic unit and test subject identifying unit;

Described video image reading unit, be used to read the ODVS on the preceding base support that is placed in the road test vehicle and be placed in the video image of the ODVS on the rear base support of road test vehicle, and this two width of cloth full-view video image is sent to test subject data operation record unit respectively;

Described vehicle location acquiring unit is used for obtaining the residing positional information of road test vehicle, the position that obtains scene surveying instrument by the GPS sensor in the driving path examination of technical ability; The GPS sensor is the sensor that is used for receiving world locational system (GPS) signal, and GPS refers to utilize 24 systems that artificial satellite is followed the tracks of GPS in the earth orbital operation of about 20183 kilometers height.That is, GPS is a kind of satellite navigation system, wherein be installed in GPS sensor on the road test vehicle and receive radiowave from satellite transmission, because the exact position of known satellite receives the required time of radiowave so can calculate, thus the position that obtains; The GPS sensor that is placed in the road test vehicle receives gps signal, and with the geometric coordinate x of road test vehicle, y, z and current time information t send to test subject data operation record unit respectively;

Described examinee's relevant information input-output unit is used to import examinee's relevant information and is used for the examinee confirms the he or she on display some relevant informations; When the examinee claimed road test, Examination instrument required the examinee to import examinee ID number from keyboard, and examinee's ID number identical with examinee's identification card number; Examination instrument checks that at first whether the number imported is the requirement whether the range of age of 18 bit digital and examinee meets the Ministry of Public Security's the 91st command defined, and then whether ID number of checking the examinee that the examinee imported exists in storage unit, the related content that on display, shows the examinee if present, it is the place driving efficiency test subject table and the driving path examination of technical ability Operating Chart of Accounts of major key by examinee ID number that words if there is no just produce one automatically, shown in table 1, table 2; After input examinee ID empirical tests was correct, the examinee just can enter road test; At last place driving efficiency test subject table and driving path examination of technical ability Operating Chart of Accounts are sent to the described test subject unit of setting a question;

Examinee ID:******************

Table 1 place driving efficiency total marks of the examination table

	Examine	Pass through	Test time
				Stake is examined
Ramp stopping a train at a target point and starting
				Stop in the side
By monolateral bridge
				Curve driving
Right-angled bend
				Speed limit is by the limit for width door
By continuous obstacle
				Hundred meters plus-minus retainings
Rough road travels

Table 2 driving path examination of technical ability list of results

	Examine	Pass through	Test time
				Straight-line travelling
Change lane
				Pass through the crossing
Keep to the side to stop
				Pass through zebra crossing
Pass through school zone
				Pass through bus stop
Meeting
				Overtake other vehicles
Night running

The described test subject unit of setting a question, the place driving efficiency test subject and the driving path examination of technical ability section purpose content that are used for sending over according to described examinee's relevant information input-output unit are set a question, set a question and at first determine driving efficiency examination still driving path examination of technical ability subject in place in the unit, do not examine the subject from this examinee then and set a question, the subject that the result that then will set a question sends to test subject data operation record unit and the output examinee will take an examination from loudspeaker;

Described test subject data operation record unit, be used for writing down the examinee in the video data of road test process, the position data of vehicle, the time of examination, the subject of examination and ID number of examinee, so that the examiner can the situation to the examinee evaluate from these data; In order to safeguard the seriousness of road test, among the present invention data such as the position data of vehicle, the time of examination, the subject of examination and ID number of examinee are embedded in the video data, as shown in Figure 10, recorded like this have a unalterable feature; Since the full-view video image that is placed in the ODVS (claiming ODVS1) on the preceding base support of road test vehicle and is placed in the ODVS (title ODVS2) on the rear base support of road test vehicle wherein have 90 ° of angular ranges be the road test vehicle just below, for the ambient image of road test vehicle periphery ODVS1 and ODVS2 is spliced, as shown in Figure 10, by such processing, examiner and follow-up test subject analytic unit can be judged the road test situation on same width of cloth video image, the image after splicing and the processing sends to test subject analytic unit and storage unit; Keep the real-time video backup of examination process in storage unit, the examinee has a question to examination result can access the video playback of examination process, avoids judging dispute; Real-time video backup file name is stored with examinee ID+ subject ID;

Described test subject analytic unit is used for analyzing the examinee at the various sections purpose video image that road test is write down, and mainly analyzes by the video shown in the accompanying drawing 10 and according to test subject; As test subject is " side parking ", and examination scene is exactly one and marks the parking stall come with white paint, as long as the student that takes an examination can pour car into parking stall, and then rolls away from smoothly and gets final product; Adopt edge detection algorithm to detect in the present invention and mark next parking stall as whether comprising white paint in the video image in the accompanying drawing 10, if in video image, exist obviously complete edge, parking stall and in docking process vehicle do not touch the edge and just be judged to be to stop and pass through, otherwise the video backup that will stop with artificial affirmation side;

Described edge detection method can be divided into following four steps haply:

1. filtering: edge detection algorithm mainly is based on the first order derivative and the second derivative of image intensity, but the calculating of derivative is very sensitive to noise, therefore must use wave filter to improve the performance of the edge detection method relevant with noise.It may be noted that most of wave filters have also caused the loss of edge strength when reducing noise.Therefore the edge strengthens and reduces between the picture noise needs to obtain a kind of balance.

2. strengthen: the basis that strengthens the edge is a changing value of determining each vertex neighborhood intensity in the image.Enhancement algorithms can be given prominence to the point that the neighborhood intensity level has significant change.The edge strengthens generally to be finished by the compute gradient amplitude.

3. detect: in image, have the gradient magnitude of many points bigger, and these might not all be the edges under specific situation, so should be with coming someway to determine that those points are marginal points.The simplest rim detection criterion is a gradient magnitude A value criterion.

4. locate: determine the pixel at place, edge, if more accurate definite marginal position also can come the estimated edge position on subpixel resolution, the direction at edge also can be estimated.

Adopt Suo Beier (Sobel) operator as edge detection algorithm in the present invention, the Sobel operator adopts the template of 3*3 size, has so just avoided compute gradient on the interpolated point between the pixel.The Sobel operator calculates partial derivative with following formula:

S _x＝(a ₂+ca ₃+a ₄)-(a ₀+ca ₇+a ₆) (16)

S _y＝(a ₀+ca ₁+a ₂)-(a ₆+ca ₅+a ₄)

Constant c is 2 in the formula.The Sobel operator can be realized with following convolution template:

$S_x=\left[\begin{array}{ccc}-1& 0& 1\\ -2& 0& 2\\ -1& 0& 1\end{array}\right]$ $S_y=\left[\begin{array}{ccc}1& 2& 1\\ 0& 0& 0\\ -1& -2& -1\end{array}\right]---\left(17\right)$

Such as subject to " by continuous obstacle ", all be fixed by bolts on the ground with " discus ", parse the edge of ground " discus " with analysis mode, if the edge that vehicle does not touch " discus " in by continuous obstacle examination process passes through with regard to the subject that is judged to be " by continuous obstacle ", otherwise will be with the video backup of artificial affirmation " by continuous obstacle ";

Such as detecting to rolling the sideline away from, as a same reason by analyzing the edge line in roadside,, passes through at the edge that vehicle does not touch road in the driving procedure if just being judged to be this subject, otherwise will be with this section's purpose video backup of artificial affirmation;

Detect for curve driving, right-angled bend and speed limit panoramic video, judge by analyzing the respective edges line equally by the limit for width door;

Described test subject identifying unit, be used for judging automatically examinee's road test situation, analysis result according to described test subject analytic unit, if analysis result be the subject of examining go by just the achievement of this test subject being added in table 1 or the pairing subject of table 2, in table, stay blank for the result of determination that can't confirm, leave examiner's manual observation video for and back up and judge.

Claims (8)

1. intelligent Examination instrument based on omni-directional visual, it is characterized in that: described intelligent Examination instrument comprises: be used to obtain road test with the omnibearing vision sensor at two no dead angles of the road conditions video information of vehicle periphery, be used to obtain road test with the GPS sensor of the locus of vehicle, be used to point out the examination prompting device that needs the subject content of taking an examination below the examinee, and be used to handle, transmit and store the microprocessor of road test with the road conditions video information of vehicle periphery; In the omnibearing vision sensor at two no dead angles, wherein on the preceding base support that is placed in the road test vehicle, in order to obtain the video image in vehicle front and left side; Another is placed on the rear base support of road test vehicle, in order to obtain the video image on rear view of vehicle and right side; Described GPS sensor, examination prompting device and microprocessor are installed in the vehicle, the omnibearing vision sensor at described two no dead angles is connected with described microprocessor by video interface, described GPS sensor is connected with described microprocessor by data-interface, and described examination prompting device is connected with described microprocessor;

Described no dead angle omnibearing vision sensor comprises the catadioptric minute surface one time, secondary catadioptric minute surface, transparent housing and shooting part, a described catadioptric minute surface and secondary catadioptric minute surface are installed on the transparent housing, the camera lens of described shooting part be positioned at after the viewpoint of a catadioptric minute surface back and with the position of viewpoint at a distance of s, described secondary catadioptric minute surface is positioned at the front of a catadioptric minute surface, all have an aperture on a described catadioptric minute surface and the secondary catadioptric minute surface, described secondary catadioptric minute surface is embedded in wide-angle lens, described shooting part camera lens, wide-angle lens, the central shaft arrangement of catadioptric minute surface and secondary catadioptric minute surface is on same axial line;

By the aperture imaging between wide-angle lens and shooting part camera lens on catadioptric minute surface, this imaging point in the imaging of viewpoint place, and satisfies formula (9) by the shooting part camera lens,

$t_2=\frac{F_2\left(t_2\right)}{a\&times;f}\&times;(\frac{t_1}{F_1\left(t_1\right)-s}-b)---\left(9\right)$

Wherein, a, b are linear coefficient, F ₁(t ₁) be a catadioptric minute surface curve, F ₂(t ₂) be secondary catadioptric minute surface curve, t ₁Be the horizontal coordinate of a reflection spot on the catadioptric minute surface, t ₂Be the horizontal coordinate of the reflection spot on the secondary catadioptric minute surface, s represents the camera lens of shooting part and the distance between the viewpoint;

Shooting part camera lens and wide-angle lens as a process shot, are satisfied formula (15) and make the visual field of process shot and the dead angle part of omnibearing vision sensor match;

$n=\frac{D}{f}=2{\mathrm{\&theta;}}_{1\max }---\left(15\right)$

Wherein, n is an enlargement factor, and D is the diameter of process shot, and f is the focal length of process shot, θ _1maxIt is the maximum angle of secondary reflection light V3 and catadioptric main shaft Z;

Described microprocessor comprises:

The video image reading unit is used to read the video image of two no dead angle omnibearing vision sensors, and the video image that obtains is sent to test subject data operation record unit;

The vehicle location acquiring unit is used for obtaining the residing positional information of road test vehicle, the position that obtains scene surveying instrument by the GPS sensor in the driving path examination of technical ability;

Examinee's relevant information input-output unit is used to import examinee's relevant information and is used for the examinee confirms the he or she on display relevant information;

The test subject unit of setting a question, the place driving efficiency test subject and the driving path examination of technical ability section purpose content that are used for sending over according to described examinee's relevant information input-output unit are set a question, set a question and at first determine driving efficiency examination still driving path examination of technical ability subject in place in the unit, do not examine the subject from this examinee then and set a question, the result that then will set a question sends to test subject data operation record unit and export the subject that the examinee will take an examination from the examination prompting device;

Test subject data operation record unit is used for writing down the examinee in the video data of road test process, the position data of vehicle, the time of examination, the subject of examination and ID number of examinee;

The test subject analytic unit is used for analyzing the examinee at the various sections purpose video image that road test is write down, and the standard-required by analysis video data and test subject compares analysis;

The test subject identifying unit, be used to judge examinee's road test situation, analysis result according to each test subject analytic unit, if being the subject of examining, passes through analysis result, then the achievement of this test subject is added in the pairing subject eligible list, do not pass through if analysis result is the subject of examining, then this test subject is unqualified; In subject eligible list table, stay blank for the result of determination that can't confirm, leave examiner's manual observation video for and back up and judge.

2. the intelligent Examination instrument based on omni-directional visual as claimed in claim 1, it is characterized in that: in described examinee's relevant information input-output unit, when the examinee claims road test, Examination instrument requires the examinee to import examinee ID number from keyboard, and examinee's ID number identical with examinee's identification card number; Examination instrument checks that at first whether the number imported is the requirement whether the range of age of 18 bit digital and examinee meets the Ministry of Public Security's the 91st command defined, and then whether ID number of checking the examinee that the examinee imported exists in storage unit, if present, check whether this examinee has all finished the driving efficiency examination, if all do not finish, then on display, show the examinee relevant information and below need the content of taking an examination; It is the place driving efficiency test subject table and the driving path examination of technical ability Operating Chart of Accounts of major key by examinee ID number that words if there is no just produce one automatically; After input examinee ID empirical tests was correct, the examinee entered road test; At last place driving efficiency test subject table and driving path examination of technical ability Operating Chart of Accounts are sent to the described test subject unit of setting a question.

3. the intelligent Examination instrument based on omni-directional visual as claimed in claim 2, it is characterized in that: in described test subject data operation record unit, the ambient image of the omnibearing vision sensor at two no dead angles of road test vehicle periphery is spliced, and the image after splicing and the processing sends to test subject analytic unit and storage unit; Keep the real-time video backup of examination process in storage unit, the examinee has a question to examination result can access the video playback of examination process, avoids judging dispute; Real-time video backup file name is stored with examinee ID+ subject ID.

4. the intelligent Examination instrument based on omni-directional visual as claimed in claim 2 is characterized in that: in described test subject analytic unit, adopt edge detection algorithm to detect the examination vehicle and whether touch the sign edge; Described edge detection algorithm is to rely on image differentiated to try to achieve gradient and carry out rim detection, from marginal point corresponding to the big point of single order differential amplitude, while also sets out corresponding to the zero cross point of second-order differential, design some single orders or second-order differential operator, try to achieve its gradient or second derivative zero crossing, select certain threshold value to extract the border again.

5. the intelligent Examination instrument based on omni-directional visual as claimed in claim 3 is characterized in that: in described test subject analytic unit, adopt edge detection algorithm to detect the examination vehicle and whether touch the sign edge; Described edge detection algorithm is to rely on image differentiated to try to achieve gradient and carry out rim detection, from marginal point corresponding to the big point of single order differential amplitude, while also sets out corresponding to the zero cross point of second-order differential, design some single orders or second-order differential operator, try to achieve its gradient or second derivative zero crossing, select certain threshold value to extract the border again.

6. the intelligent Examination instrument based on omni-directional visual as claimed in claim 5, it is characterized in that: set the aperture on the catadioptric minute surface and between wide-angle lens and shooting part camera lens, be imaged as first imaging point, this imaging point passes through the shooting part camera lens in the imaging of viewpoint place, with the focal length of shooting part camera lens as f1, the focal length of wide-angle lens is as f2, the distance of the focus of shooting part camera lens and shooting part camera lens is as S1, focal length from the shooting part camera lens to first imaging point is as S2, distance from wide-angle lens to first imaging point is as S3, the distance of point obtains following relational expression as S4 according to the imaging formula of camera lens from the wide-angle lens to the material object:

$\frac{1}{f1}=\frac{1}{S1}+\frac{1}{S2}---\left(10\right)$

$\frac{1}{f2}=\frac{1}{S3}+\frac{1}{S4}---\left(11\right)$

d＝S2+S3 (12)

Focal length f2 by the design wide-angle lens satisfies the requirement of formula (12);

As a process shot, its focal distance f is represented by following formula with shooting part camera lens and wide-angle lens:

$\frac{1}{f}=\frac{(f1+f2-d)}{f1*f2}---\left(13\right)$

In addition, the diameter of process shot is as D, and its enlargement factor is represented by following formula:

$n=\frac{D}{f}---\left(14\right)$

Satisfy following formula during process shot:

$n=\frac{D}{f}=2{\mathrm{\&theta;}}_{1\max }---\left(15\right)$

In the formula, θ _1maxIt is the maximum angle of secondary reflection light V3 and catadioptric main shaft Z.

7. the intelligent Examination instrument based on omni-directional visual as claimed in claim 5, it is characterized in that: described transparent housing is bowl-shape.

8. the intelligent Examination instrument based on omni-directional visual as claimed in claim 5 is characterized in that: described examination prompting device is a loudspeaker, and described loudspeaker is connected with described microprocessor by audio interface.

Images