CA2132346A1 - Vision apparatus - Google Patents
Vision apparatusInfo
- Publication number
- CA2132346A1 CA2132346A1 CA002132346A CA2132346A CA2132346A1 CA 2132346 A1 CA2132346 A1 CA 2132346A1 CA 002132346 A CA002132346 A CA 002132346A CA 2132346 A CA2132346 A CA 2132346A CA 2132346 A1 CA2132346 A1 CA 2132346A1
- Authority
- CA
- Canada
- Prior art keywords
- image
- vision apparatus
- cameras
- signals
- line scan
- 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.)
- Abandoned
Links
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 10
- 230000008569 process Effects 0.000 claims abstract description 5
- 230000001133 acceleration Effects 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 8
- 150000002500 ions Chemical class 0.000 description 16
- 238000001514 detection method Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000001513 hot isostatic pressing Methods 0.000 description 3
- 241000582342 Carria Species 0.000 description 2
- 241001508687 Mustela erminea Species 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 241000950314 Figura Species 0.000 description 1
- 241000282339 Mustela Species 0.000 description 1
- 240000004543 Vicia ervilia Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005670 electromagnetic radiation Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000007775 late Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- KRTSDMXIXPKRQR-AATRIKPKSA-N monocrotophos Chemical compound CNC(=O)\C=C(/C)OP(=O)(OC)OC KRTSDMXIXPKRQR-AATRIKPKSA-N 0.000 description 1
- 239000002674 ointment Substances 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 229920000136 polysorbate Polymers 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P3/00—Measuring linear or angular speed; Measuring differences of linear or angular speeds
- G01P3/64—Devices characterised by the determination of the time taken to traverse a fixed distance
- G01P3/68—Devices characterised by the determination of the time taken to traverse a fixed distance using optical means, i.e. using infrared, visible, or ultraviolet light
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/015—Detecting movement of traffic to be counted or controlled with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
Vision apparatus is disclosed which comprises at least one single-line scan type line scan camera (30, 40) mounted for viewing a passing object (60, 150). The cameras (30, 40) are connected with electronic means (50) which includes store means (53) which stores signals indicative of the image of the object throughout line scans. The electronic means (50) includes processing means (52) whhich processes the signals indicative of the image of the object together with a signal representative of at least one of the speed or length of the object to determine a length of the object between line scans. That determined length between line scans is provided to image recognition means (100) and utilized with signals in the store means (53) and compared against expected image signature or image attribute signals for recognition. If there is recognition an output is provided representative of a recognised image signature or image attribute. Preferably two cameras (30, 40) are utilized so that one views the object (60, 150) at a different position along its path of travel and where a signal representative of the speed of the object is obtained by comparing particular time instants when a part of the object is detected by each camera.
Description
W093/19429 PCT/A~193/00111 VISION APPARATUS
Field of the Invention __ _ SThis inv~ntion relate~ ~o a vi~ion apparatus for recognising a passing obj~ct an~ it relat~s particularly, but not exclusively, to such appar~tus for use in detecting passing objects such as passin~ vehi~ on roadways, passing packa~in~ ~ntainer~ su~h a~ shi~ping container~.
Ve~ i ~
Hlthertv, it has be~n desired ~o electronically capture an image of a passing o~ject ~or subsequent processing. This ma~ be required to con~rol processes where the passing of an object initiate~ some ac~ion in the process.
It i5 particularly desired to ob~ain image recognition of the object ~uch as characters or ~he like which may appear on a surface of t~e o~ect~ In rela~ion : to apparatu~ which is u~ed to view a roadway ~o o~erve passing vehicles, it can be nece~sary to recognise some :
: feature of the object such as a charac~e~istic ~isnature andtor an image attribute. This ima~e ~i~nature may comprise ~he shape of ~he vehicle, and the image attribute may comprise the registration n~mber or ~ome other characteristic. In the case of shipping containers it may be code information applied to a face of the ~hipping container.
Hitherto, viewing of passing objects in such envixonments has reguired the use of expensi~e cameras which ha~e the required high image resolution capabilitie~.
Such cameras ar typically frame cameras whereby ~ignals frame-by-fr~me of the passing object can be stored and subse~uently analysed to extract the required image ~ignature or image attribute. By using whole frame cameras W093/19429 ~ PCT/A~'93/00111 L1 3 1~l r;~ ~Yo of this ~ype not only is there the expense of the initial purchase cost of the cameras themselves but the signal processing and nece~sary storage medium~ are relatively expensive to purchase and maintain.
On open roads and highways ~here is a tendency for trucks and mo~or Yehicl~s to exceed the allowable ~paed : limit. Speedin~ will of~en cau~ accident~ and po~sibly result in 105~ of li~e, ~ well a~ cau~ing damage to ~roperty and th~ roadway~ them~lv~s. Sp~Qding can al80 cause gradual dam~ to roadways~ especially if trucks are overladen si~ce road suxfac~s are not normally de3isned to bear heavy loads txavelling at exce~s s~eed~.
~any m~asures h~ve been taken in an attempt to : control speeding vehicles~ including obs~rving elapsed era~e~ t~me oYer a ~ixed distance t~ de~ermine the ~eed of a vehi~le. Thi~ type of measuring de~ice is commonly referred to as an 'amphometer'. In more recent times speed cameras, radar detector~ an~ the like have be~n used by law enforcement agencies. Fines or the like ~aYe been ap~lied 0 to the vehicle or to the driver îf ~peeding i8 detected.
An extension to ~he use o~ ~peed detection :: : de~:ices has been to incorporate t~e facility of allowing :: :
iden~ification of a Yehicle's regi~r~tion number. Thi~ i8 achiev~d by taking ~ither a photographic image or a video recording;of a speeding vehicle, the~ proces~in~ tha~ data to decipher the actual registration number from the registration number plate. ~xamples of ~uch techniqu~. ran : be found in ;~.S. Patent No. 4,~17,166 assigned to Perceptics Corporation, and U.S. Patent No. 4,878,248 assigned to Industrial T~chnolo~y Research Institute.
All these systems rely on the technique of capturing an image of a vehicle and storing the image ~ either on photographic film or magnetic media for ; ~ subsequent processing. There are numerous technical ~ :
WO93~19429 PCTIA~'93/OOIlI
c~ .
Field of the Invention __ _ SThis inv~ntion relate~ ~o a vi~ion apparatus for recognising a passing obj~ct an~ it relat~s particularly, but not exclusively, to such appar~tus for use in detecting passing objects such as passin~ vehi~ on roadways, passing packa~in~ ~ntainer~ su~h a~ shi~ping container~.
Ve~ i ~
Hlthertv, it has be~n desired ~o electronically capture an image of a passing o~ject ~or subsequent processing. This ma~ be required to con~rol processes where the passing of an object initiate~ some ac~ion in the process.
It i5 particularly desired to ob~ain image recognition of the object ~uch as characters or ~he like which may appear on a surface of t~e o~ect~ In rela~ion : to apparatu~ which is u~ed to view a roadway ~o o~erve passing vehicles, it can be nece~sary to recognise some :
: feature of the object such as a charac~e~istic ~isnature andtor an image attribute. This ima~e ~i~nature may comprise ~he shape of ~he vehicle, and the image attribute may comprise the registration n~mber or ~ome other characteristic. In the case of shipping containers it may be code information applied to a face of the ~hipping container.
Hitherto, viewing of passing objects in such envixonments has reguired the use of expensi~e cameras which ha~e the required high image resolution capabilitie~.
Such cameras ar typically frame cameras whereby ~ignals frame-by-fr~me of the passing object can be stored and subse~uently analysed to extract the required image ~ignature or image attribute. By using whole frame cameras W093/19429 ~ PCT/A~'93/00111 L1 3 1~l r;~ ~Yo of this ~ype not only is there the expense of the initial purchase cost of the cameras themselves but the signal processing and nece~sary storage medium~ are relatively expensive to purchase and maintain.
On open roads and highways ~here is a tendency for trucks and mo~or Yehicl~s to exceed the allowable ~paed : limit. Speedin~ will of~en cau~ accident~ and po~sibly result in 105~ of li~e, ~ well a~ cau~ing damage to ~roperty and th~ roadway~ them~lv~s. Sp~Qding can al80 cause gradual dam~ to roadways~ especially if trucks are overladen si~ce road suxfac~s are not normally de3isned to bear heavy loads txavelling at exce~s s~eed~.
~any m~asures h~ve been taken in an attempt to : control speeding vehicles~ including obs~rving elapsed era~e~ t~me oYer a ~ixed distance t~ de~ermine the ~eed of a vehi~le. Thi~ type of measuring de~ice is commonly referred to as an 'amphometer'. In more recent times speed cameras, radar detector~ an~ the like have be~n used by law enforcement agencies. Fines or the like ~aYe been ap~lied 0 to the vehicle or to the driver îf ~peeding i8 detected.
An extension to ~he use o~ ~peed detection :: : de~:ices has been to incorporate t~e facility of allowing :: :
iden~ification of a Yehicle's regi~r~tion number. Thi~ i8 achiev~d by taking ~ither a photographic image or a video recording;of a speeding vehicle, the~ proces~in~ tha~ data to decipher the actual registration number from the registration number plate. ~xamples of ~uch techniqu~. ran : be found in ;~.S. Patent No. 4,~17,166 assigned to Perceptics Corporation, and U.S. Patent No. 4,878,248 assigned to Industrial T~chnolo~y Research Institute.
All these systems rely on the technique of capturing an image of a vehicle and storing the image ~ either on photographic film or magnetic media for ; ~ subsequent processing. There are numerous technical ~ :
WO93~19429 PCTIA~'93/OOIlI
c~ .
2~3 problems associated with converting the stored image data on a frame-by-frame basis to decipher the registration number, and these problems are only solved by com~lex ~oftware and lar~e co~puter power to identify the field of S the registratiQn nu~ber plate. Cl~arly such ~oftware and ~: hardware incurs substan~ial expense.
Another mea~ure which has been adopted ir an :~ ~ aStempt to reduce the incid~nce o~ sp~ding i8 to insSall :~ speed limiting devi~es on v~hicl~s, and particularly on trucks and buses. Even with spe~d limiting devices in ~; place there haYe been instanc~ where vehicles have been recorded travelling at speeds in ~xc~ o~ the limited speed, which suggest~ tha the speed limiters either do not ~work cQrrectly else may have been ~ypa~sed.
Law snforcemen~ agencies and ~tatutory bodie~
responslble for the upkeep and regulation of use of roadways have also recen~ly noticed a dsvelopment among~t :operators of trucks which seeks to a~oid payment of correct user fees and chaxges. ~he practice in~olves a truck operator registering a new truck wi~h the responsible : : authority then ~wltching the registration number ~lates to a~truck of the same make but of a lar~er ~ize. This allows ; ; the truck operator to carry a great~r load yet only pay fees and charge~s~ as if it wexe for a ~maller truck. Thi~
25~ ~e~asion scheme~has~led to the concept of obtaining unique ' gnatures;' of :trucks. A 'signature' i~ obtained by ~, measuring certain characteristics of a truck at the time of registration and storing this information ln a central registry. A detection system is then required to operate on the roadway~, so that as a ~ru~k passes a detection station, a measurement of the truck~s charact~ristics are made. A comparison is performed to determine whether the :~ truck is indeed the same truck that was presented at the :~ time of initial registration.
WO 93/ 1 9429 PCl /A ~193/OOl 11 One example of such systems in the prior ar~ are th~ TAG type of systems in which a transponder is fitted to : a truck and interroyated by a~ antenna array mounted at ~he roadside, t~pically to rea~ a unique number ~tored within the transpon.~er. ~ difficulty with the transponders i8 that it is not easy to ~now whe~hex they are, in fact, : operatio.ali hence truck~ w~th ~aulty tran~ponders may ~:~ unwittingly avoid det*ction. Tha ~y~tem i~ al80 expen3ive`~ ~ an~ difficult to implement ~ince each truck mu~t be fitted~;: 10 with a transponder~
: It:is an ob~ect o~ the presen~ invention to provide a reliable and less expensive vision ~ystem than in the past.
~ This i~achieved by use of single-line ~can type line scan c~meras. By collec~ing a series of line scan signal~ as the~object passes, a picture image of the passing o~ject can~be obtained. If the passing object i8 to be reco~nised then it is necessary to obtain some ::information eoncerning the length of ~he ob~ect between :: : line scans - normalization - so that the si~nal~ can be ~ , `appropriately length scaled znd the image eize normalized.
ccording to ~he present in~ention there i8 proYided vision apparatus for recognising an image 25~:~ attribute of a passinq object where either on~ or other of the speed or the: length of the object are unXnown, said apparatu~ comprising at least one single-: line scan type line scan camera mounted so the passingobject will be viewed, ~ 30 electronic means comprising:
:~ store means for storing signals indica~ive of the : image of the~object throughout line scans, processing means for determining a length of the ~: object between line scans, said processing means ha~ing WO93/19429 PCT/AU93/0011l J ?, .~
s input means where signals repre~enta~ive of at least one of the speed or length of the o~ject can be inputted to enable ~aid signal representa~ive of ~he length of the object between line scans to be processed, image reco~nition m~n~ ~o which the signals ~tored in 9aid ~tor~ mean~ ~nd to whi~h said sîgnal represen ative o~ the le~g~h of thQ obj~ct between line ~cans and ~o which expe ~ed ima~ nature or image : attribute signals are supplied for reco~nition ~roces~ing, to obtain an output r~pre~entatiYe o~ a recognised image ~ignature or i~age attribute.
: Such apparatus is indep~nd~nt of the direction of approach of the object.
In one embodiment, t.here may be a ~econd ~ingle-line scan type line scan camera which is directed ~o that the camera views the o~ject, spac~d alon~ the direction of travel of the object, S8 that two ~ets of ~ignals indica~ive of the image of the ob~ect can be obtained and processed. ~y directing the field~ of view of each of t~e 0 line scan cameras in this way, i~ is possib}e to obtain tim~ difference signals from each camera and to calculate the speed of the object without knowing it~ len~th. By using two su~h cameras and by no ing the time of entry and exit~from ~he~ line scan image~ of one camera and the ent~y and exit from the line scans of the other camera it i~ al~o possi~le to c~lculate accelera~ivn. ~h~ distance of s~aci~g of the fields of view of each line scan camera can be relatively close as, for example, one third m~ter~
By using a third such camera spaced it i8 possible to obtain a better indication o~ the acceleration of the object by determining the difference in speed over the time taken for the object to pass between the camera fields of view.
The apparatus may be duplicated at other ~ .y~ 6 locations along the path of the object to provide for interval ro~te timing. In that instance the processor~ at the two locations may be in communication with each other or with yet ano~her processor at a central location, The distances between each of t~1e loca~ion~ i5 known ~o that when the object pa~se~ one locatior ~t~ feature ~uch as : image signature or i~ag~ ~t~ributa or bo~h will be ~; obtained, and wh~n he same ob~ct p~e~ another location its same image sign~ture or image attribute or both will again be obtained, and from ~he respective times of pas~ing the two locations and th~ knswn di~tance therebetween the : a~erage speed can ~e~determined, ~; . Tha appara~us may be directed to the detection of the position of a vehicle on a roadway, A marking ~attern may be laid on the roadway of a known length and position with respect to ~n ed~e of ~he roadway and being coincident with the line scan image field of a camera; the markin~
pattern~comprising a regular pattern which, in the absence : : of a vehicle, produc~s a regu~arly repeating digiti~ed ;20 ;imàge as determined by the processor, and upo~ a vehicle ~ntering the~image:field the digitised îmage will change to form a resulting digitised image, and by comparison with :the ~aid regular;digltised image, the width of the vehicle can be~determined. In one:e~bodimen~ the determination can 25~ be~ made from the-points in the re~ulti~g ima~e where the aid:regularity c ases and reco~mences. Further, the :~ : position of the vehicle on the roadway can be determined wlth rsference;to the sides of the roadway f~om that point along the line image field where the regularity in the ; 30 resulting digitised i~age ceases and recommences. The determined width will indlcate what cateyory of vehicle ha~
: been detected through a comparison with a store of characteristic widths.
The apparatus may also identify an object in WO93/19429 PCT/AU93/OOlll !~ ?~ 3 ;~ ~
terms of the object~s lensth and height. By recording an image of the whole of the obiect as it passes through the field of view of a cam~ra a unique ~signa~ure' of the object can be obtained. T~e heig~t and length of the object can b~ det~rmined from proce~sing the image data obtained from the surface o~ the o~j~ct as it passes through the field of a camera. An e~imate of a object'~
: length might be obtain~d ~rom th~ sum of the len~th~ of image segments haYing str~ight ~iides af ter normalization~
The object~s height will ~e approximately the sum of the length~ of ima~e s~gments ~aving curved sides after ha~ing ~: ~ normalis~d those curved sides to repres~nt true length.
Brief Descri~ti n of ~he Drawinqs In order that the inven~ion may ~e more clearly unders~ood, examples of preferred embodiments will now be described with reference to the accompanying drawin~, in whic~:
Figure 1 shows schema~ic detail of Swo CCD
Change Co~pled Device) cameras located above a roadway in a eystem onstructed in accordance with the invention for ~:: : viewing passing vehicles;
~:: Figure ~ shows a top view of the configuration in : Figure 1;
:Figure 3:shows in schema~ic block circuit dia~ram 25: form the components of the system;
Figure 4 shows in side slevation a truck just entering the first line scan image fieldi Figure 5 shows a top Yiew of the arrangement. in Figure 4;
Figure 6 shows the truck of Fi~ure 4 having moved along the roadway to enter the second line ~can image field;
Figure 7 shows the truck yet further progre~ed along the roadway;
WO 93/19429 , PC~/A~193~00111 Figure 8 shows a rear view of the truck and the f irst 1 ine scan image f ield;
Fi~ure 9 shows example~ of images obtained over the surf ace of the truc~ f or ~ryin~ condit ions;
Figure 10 shows an ~xam~le of a marking pattern applied to ~he roadway.
FiçJure 11 show~ an ~m~oc3is~ent having coverage of two lanes of a roa~w~y; and Figure 12 s~:~ow~ a f lc:~w diagram of ty~>ical steps performed by softwar~ in op~a~ion of a preferred ~ystem constructed in accordance with the abov~ ~mbodiments of the invent ion;
Fi~urR 13 shows schema~ic detail of a single CCD
:~ ~ camera located to one side of path Q~ tra~el of an object such as a shipping container in a sy~em cons~ructed in ~: accordan~e with the inYention for viewing pas~ing ~hipl?ing containers and for r~cognizing code infonnation on a face of the shipping containers;
Fisrure 14 is a f low diagram of ty~ical ~tep~
pexformed by software in operation of a preferred system in accordance w1th~Figurs 13.
De~iled Description of Preferred Embodiment~
. ~ ~
he embodiments to be de8cribed in Fi~ure5 1 and ; 2 relate to a system installed on a public highway for 2~5~ : viewing passing:vehicles. Referring then to Figure3 1, 2 :: and 3, the syste~ ~0 has components located a~ove and beside the roadway 2Q. Particularly, two CCD camera~ 30 40 are arr~nged ~o be above the roadway 20 respectlvely at heights h~ and h2, and located approximately above the mid-;30 point of the left hand carriageway of roadway 20 (for right ~- hand drive vehicles). The cameras 30,40 are in spaced arrangement. The cameras are charge coupled devices of the single-line scan type line scan cameras. One sui~able type of CCD line-scan camera is manufactured by ~he French WO93/19429 PCT/A~193/OOlll ~ 2 l ~ 2 r~? !i~ ~
: company i2R, and sold under type number iVClO0. These cameras are less expensive than ~rame cameras which have a required re~olution to detect image attri~u~es such as vehicle registration number plate characters.
In the example of Fi~ures l and 2 the cameras are sited a~1jacent one anoth~r in t~e horizontal ~lane, howe~er the camera~ could be mount~d in ~eh~r ways but it i8 desired tha~ th~ angle~ of ths imag~ field between the respective cameras and the perpendicular from the roadway, : lO being and ~ respecti~ely, are substantially the same.
These angles are not orthogonal to the direction of travel of the vehicles the image fie~d of eacb ~amera is therefore represented as lines al and a~ and must be regularly ~paced at distance x along the whole of their path length. Thi~
arrangement facilitatQs easy proc~s~iny of image ~i~nal~
such that inexpensive computers, such as P.C. type computer processing or:similar costing dedicated computer~ can be utilized. If the fields of view are n~t parallel - i.e.
an~les a and ~ - thsn involved mathematical computation~
;20~ ~must be made to ~ths image signal~ to equate ~he image ignals of the two cameras to a fixed datum for determining para~eters of the image signals which can be appropriately related to one another.
The line-scan cameras 30,40 of ~he type s~ecified 25: ha~e a resolution of 2048 pixels in each line, which translates to typically 2 mm lateral resolution on the road urf~ce, gi~-en that lane width is typically 3.3 m. Best ; results are obtai.1ed for angles a,~ in the range 30-S0.
For an angle of 4S. since there is one-one correspondence ~:~ : 30 of horizontal speed with vertical speed, any image ~: attribute obtained by the camera of numerals or letters will be 1 to 1 scaled, thereby aiding recognition. There i~
often a judgement required to be made, in that at an angle near 30 there will be a large ~shadow' behind a vehicle W0~3/19429 t ~ ~ PCT/AU93/0011!
and therefore tail gating v~hicles may escape detection.
On the other hand, i~ an angle of 60 is selected ta~l gating vehicles will be detected, but ther~ is a loss of resolution in capturing a ~ s ignature ~ image of a vehic~e -: 5 the shape of the vehicl~ - and a similar los~ of resolution in ca~turing an ~mage ~tr~bu~e - re~istration number~ A~
the cameras operate at a line scan f~uency of 10,000 : lines per secQnd, ~e. ~0 ~Hx, for a vehicle ~eed of 70 km/h th~-resolu~ion o~taina~le 15 2 mm at a 45 angle, ; 10 which is su~ficient to allow r~coc3nition of vehicle signatures and image attrl~ute~ such as registration n~mbers. I~ a vehicle~s speed i5, say, 140 km/h, res,olution : reduces to 4 mm,:but it is still pos~ible to recognize the : registration~ number as only the height of the character ha~
15~ been affected, and not the width.
: The two camer~s 30,40 do no~ necessarily neQd to have the same: reBolution~ nor do they~ need to have a~ hi~h a resolution a8;~frame cameras, as t~e application and ~peed ; of ~ehicles bein~de~ected will dictate a~ ap~ropriate 20~ c;onfiguràtion, partLcularly if the expected top ~eed of :vehicles~ is ~ess:than 140 kmfh.
The~cameras 30,40 are mounted off the road by a~y sui~table means~such:as on a gantry, or on ~ome other structure whi~h may~also hold road ~i~ns, or even from a 25~ :bridge. The::cameras 30,40 are connected to a remote statioD SO~which~comprises an e~closure hou~ing electronic : means utilised ir,:implementing the localised control and ~ "
processi~g of`the system 10. The remote station 50 may include a power supply 51 which can be used to power the 30 : electronic~means~as well as the cameras 30,40.
Referring~in detail to Figure 3, the local : processor 52 controls the operation of the locali~ed control/processing at the remote station 50. The processor : 52 is in two-way communication with the camaras 30,40.
:
: :
W093/19429 PCT/A~'~3/00111 1i Information received by the local processor 52 from the cameras 30,40 typically relates to signals re~resentative of image data collec~ed, wheraas ~ con~rol line~ from the local processor 5~ to the camer~5 30,40 r~l~te to issuing of control inst~lction~ and ~rovidir1g power to the camera~.
The local processor 52 c~n r~a~ and wri~e in~ormation from a store means in the form sf a ma~ storage device 53. As shown in Figura 3 it is possible to connect further ~airs ; of cameras 30', 40' to the local processor 52, ~he other pairs being sited ahove another carriagewa~.
The local processor 52 will p~riodically be ~: required to transmit information ~o a c~ntralised location at a central station lOO for reasons ~hat will become apparent. For this purpose a modemJTx/Rx device 54 i~
connected to th~ local processor 52. The communications from the local processor S2 to the central station lOO can ~: be via land line or radio tran~mission or the like.
Signals of the image data to be tran mi~ted is likely to be compressed to reduce transmission tim~s. For , .
this purpose the JPEG ~JQint Photographers ~xper~ Group) compression technique could be adopted~ althou~h many other technigues would be equally suitable. There i8 alss provided a local control station 55 which allows an : : operator to interrogate or control the operation of the local processor 52. It is likely thi~ control station 55 ~::: would only be used for maintenance purpo~es, ~nd otherwise :~, the remote station 50 would operate au~omatically.
The central station lO0 can support a number of remote stations 50, with a suitable number of modem/Tx/Rx devices 102 being provided. The host computer lOl ha~
~: access to a mass storage device 103 and a central control ~tation 104. The central control station 104 would enable an operator to monitor the performance of any one of a number of remote stations S0 as well as performing other , W093/19429 ~ 3 i`~ PCT/A~1~3/~Ol1 1 operational functions.
Turning then to consider the operation of a remote ~ta~ion 50. Figur~ ~ ghQws a truck travelling on the roadway 20 having reached a position wh~se its front bumper enters the ima~e fi ld al. The cameras 30,40 are typically chosen to op~rate u~ng infra-red light in the range 600-800 nm, henc~ thQ li~ht would not normally be visible to a driver of a truck ~r oth~r motor vehicls.
ven so, it i~ p~ssibl~ to use th~ cam~ras a~ bei~g ~: 10 ~;ensitive to ~he ~isible light s~ectrum~
or~ally the camera~ 30, 40 are isl constant operation, hence the sy~tem does not require remote ; triggering from an~ other sensor to start ~he image recording. There are particular advantages in not ; requiring a trip~me~hanism. First, there is ~o stray electromagnetic radiation such as a~ microwaY~ or RF
fre ~ encies.:: There is great concer~ in the co~munity generally ag eo excessive man-made elec~romagnetic radiation and what are perceived as being a~æociated health ; 20 : issues. Second, the system îs non-invasive to the roadway as the road~:need no~:be disturbed to install ~rip ~en~ors :or the~like~.~ This, in turn, avoids ~ub~eguent road repair Co8ts.~The reason:both cameras are operational i~ because the~ sy8tem i~s:designed to operate for a vehicle travelling 2;5:~ in either direction on the roadway, in which case either image;field al;~or a2 may be~entered fir~t. The camera will : : therefore usually be taking an image ~f the road ~urface to se as a reference. Once the image change~ by virtue of the front-most part of the truck passing through the line ~can field a~, the local proces~or 52 will commence storage ~ ,:
~ of signals of digitised image data. As can be s2en from :::
Figure 5, only the mlddle portion of the line ~can image will show a change as each side portion is still incident ~ on the roadway 20. As soon as the truck 60 enters the line : ~ :
~: :
WQ93/19429 j~.J.~ PCT/AU93/00111 ~can of the first image field al it is pos~ible to switch the local processor 52 into a hi~h intensity/high capture mode to enhance the data image.
In another embodi~ent, the detection of a vehicle may ~ake place by meanS of proCe~ir~g the image data obtained fr~m th~ roadway or a rvadway marking pattern as will presently b~ described with ref~rence to Figure l~
: utilising a fast fouri~r tr~n~form ~FFT~ ~rogram ~o :~ translate the lnforma~io~ into Ch~ fr~quency domain. When a vehi le enters the image field a change in the recorded :~ frequency characteri8tic occur~, tri~gering the s~eed determination and other proceSse~.
~ eferring then t~ ~igure 6, as ~he truck 60 progresses alony t~,e roa~way 20 th~ frorlt-most portion of 15 the truck then enters the l ine scan of field a2. Thi8 :
event is signalled by the c~mera 40 to the local ~rocessor 52 in which case the elapsed time, t, between field al :
ha~ring been entered and ~ield a2 now been entered will be : known, and by knowi~g the horizontal ~e~aration of the 20 f ields, x ( gi~ven that the sa~ne point of the tnlck will : break both line scan beams in the first instance~, the speed of the truck can be determined as x/t. This can then be scaled to~give an indic~tio~ of the speed of the ~ruck in~ units such as km/h.
2S~ ~ In other wods a signal representati~e of the : epeed of the truck is determined by comparing a time instant when a part of the trucX is at a particular line ~san of on~ of the cameras, and a line instant when ~he . ~
:: same part of the truck is at the same line scan of the ~:~ 30 :other of the cameras, to obtain a line difference signal.
If it is determined that the speed of the truck ~: ~is in excess of the permissibl~ speed limi~, then the recording of the image of the truck as performed by camera 30 or 40 should contain image information as to an image ~: :
W093/l9429 j,~ PCT/AU93/001ll attri~ute - in this case - the reyistration number plate from which the registra~ion number can be deciphered and appropriat~ action taken. It may be e~ually ap~licable to determine the registration number o a vehicle that is not speeding, for example in ~o~c~ interval timing as will ~e ~escribed presently. If t~ se~aration x between the fields al and a2 is ~uite small, say 100 mm, then a ~ufficient amount o~ imag~ in~ormation may not have been recorded by camera 30 in ord~r to include the regi~tration number pl~te. ~n this ins~ance, it ~ay be possible to co~tinue the recordi~ for some per~od of time based on a generalised understanding of the a~erage height of the boDnet of a truck when considered against ~he speed of the truck. In the alternative, it is pos~ible to continue the recording of the truck over the who}e length of the truck : until such time as the field a~ pas~es across the back of the truck and an image of the only roadway 20 i5 again : obtained.
, If it is desired to obtai~ a m~asure of the 20: acceleration of a vehicle this can be achieved utilising the two camera ystem. If the time at which the front of the truck enters field al is ascribed So be to~ and the time the front of the truck enters field a~ having travelled distance x is t~, then a first velocity Vl iB
25: known from x/t. In the same way another ~elocity can be determined using the rear of the truck as a reference. The ime~ the rear of the truck pass fields al and a2 are t2 and t3 respect.ively~ This then determines V2. The acceleration can be determined from tv2 ~ Vl) t ( (tl ~ to) ~
30 (t3 ~ t2)). In other words the acceleration i~ determined by comparing the time difference in the signals indicative ~.
of the image of the truck, of the entry an~ exit instants ~;~ of the truck within the fields of each camera~
A further embodiment to that shown in Figure 2 i~
WO93/l9429 PCT/A~193/00111 ~ ,?~.~6 to include a third single-line scan type line-scan CCD
camera. This third camera will be spaced from the other two cameras either in ~ron~ o~ camera 30 or behind camera 40 or between the two cameras, and such that the line field of images a3 is sub~tantially p~rallel to f~elds a~ and a~.
The separa~ion betwe~n fi~ld a~ and ei~her a~ or a2 need not be x as between tho~ ~wo. The f~nction of the third camera is to provide anothar mea~ur~ o~ a vehicle'~ speed :: ~ome time a~ter, ~efose or during ~hat ob~ained by the time interval between al and a~. In this way a measure of the vehicle~ 5 acce1eration can also be obtained, through knowin~ the change in sp~ed and the time between t~e respective speeds being recorded. It may be impor~ant to k~ow the acceleration of a vehicle. ~ne exam~le of the ~alue of knowing this quan~ity would he where ~he cameras were mo~nted~near a set of ~raffic ligh~s, and if a v~hicle was determined to be spe~ding and accelerating it may be possible to cause t~e state of ~he traffic lights to ~e ~: : changed and avoid a collision. Alternative~y, it can be determined a driver is engaging in unsafe driving practice ; : by~speeding or accelerating through traffic ~ignals.
::: Thus, in this arrangement, ~he third c~mera views the:truck at a position along its path of travel differe~t : to the two c~meras, and where the acceleration of the object is obtained by comparing ~he time diff~rence in said ignals~indicatiYe of a part of the truck at a particular line scan image of the truck in each of the cameras.
~: : As has been noted above, the central station 100 can support a number of remote stations 50. Given the instance that the registration number of a vehicle has been ~: : obtained at one remote station 50, it is then possible to check the xoute interval time of the vehicle once it pas~es ~:; another remote station 50 simply by matching registrativn ~: numbers and 'times of day'. This will give an indication WO 93/19429 PCr/A~193/OOl 11 r~
of the average sp~ed of that v~hicle.
There may be only one route or a number of routes between remote station~ 50. ~f there i~ more than one routa a minimum time for t~ ourney b~ the fastest rou~e would serve to de~ermin~ wh~th~r speeding might have occurred. It is unlik~ly that trucks would take a longer rout~ between tw~ poi~t~, unl~ss it wer~ the case that route proved shorter in ~m~. In th~t ev~nt the longer rou~e distance-wise i~ ~evertheless the æhortest route : ~ 10 time-wise henc~ cho~en a~ the baselin~. It is also ~:~ possible that the remo~e station~ 50 can be networked across differ~nt ~ajor routes, and in ~his way ~till track ~ehicles travelling between dest~na~iQns which span different highways. The necessary processing would be ~erformed y the host computer 101. ~n ~djunct to route ~ .:
: i~terval timing is t~ allow fl~et per~ormance monitoring.
: The ~ystem described is a ~mper proo~ method of conirming : the trip details of individual vehicles in a fleet.
moaif ication of the sy~tem permit~ determi~ing the vehicle parameters of position in a carriageway and it8 width. ~his is shown in Figure }0. This modifica~ion comprises use of a roadway marking pattern 120 which i8 :laid across the width of the carria~eway at a position coincident with fields a1 and a2. The patern 120 25: comprises regularly spaced white squares or rectangles which are periodically interposed by alternately oriented : ~ triangles. As the cameras 30,4Q record the marking pattern ,, :
120 they will generate a re~ularly re~eating digitised îmage based on 256 grey scale levels. The width of the : 30 white segments is at least 2 pixels. A white objec~ will :
be recorded as a series of pixels ~corresponding to the width of each segment according to the resolution) havi~g a grey scale value of, say, 0-10. The roadway segments are black and therefore detected as a series of plxels having a ~ ~. 2 ~ i ~
grey scale value of, say, 246-256. When there is no vehicle present a known pattern o~ ~rey scsled pixels i~
continually recorded. ~her~ is di~ect known correlation : between each widthwi~e po~ition in th~ carriagewaY and each pixel in the sequence. ~hen ~ v~hicle enter~ the image field it will causQ a chang~ ~n the ima~. By deter~ining where the known pattern c~ases and reco~m~nce~, the side~
of the vehicle can ~e locat~d, and ther~fore the position o the ve~icle in t:he carriag~way. ~ first estimate of it~
~; 10 width can also be determine~. Alternatively, it is ~: ~ po~sible to apply ~he digitis~ ima~es to a fast fourier trans f orm (FFT) to conYert the information to ~h~ frequency domain. A change in the frequency spectrum will indicate an object e~tering the image field.
: 15 : The triangular shapes in the pat~ern 12Q serve a special purpose. The cameras 30,40 are ~ubject to the environment including wind and structural vibrational ~: :
effects. This may result in the ima~e field~ a~ and a2 being:n~t precisely normal to the carriagQway but 20 ~ :tra~slating forward and backward along the roadway, or possibly becoming slightly skewed. This translation or skewing Qffect will be determinate since the reflected ; image will va~ry~slightly as more or less cf the triangle i~
imaged~depending~upon the skew. This allows correcting : adjustment to be;made in the processing of image data of a , ~. ~ . :
: ~ehiclej hence~maintaining the desired accuracy.
~:j The task of obtaining a ~signatuxe' of a truck is ~:: :: made more difficult whare the truck i~ not travelling down : the centre of a carriageway, is straddling lane~ or iB
: 30 skewed by virtue of changing lanes. ~hese considerations impact on the system configuration and the software required to generate a total image of the truck. There are four angular measures as well as the speed and acceleration ~ : of the truck which come into play. These angular measure~
1;~' :
WO93/1g429 PCT/A~193/00111 ~ 3 are the image field inclination (a), the truck centre-line offset, the skew of motion and ~he camera angle field of ~iew (which is a ~unction of focal length). Th~se considerations are complicated by a trad~-off in camera S object lens sizet wher~ lar~r ocal len~Sh lenses can resolve imag~s in the distance ~tt~r, i.~., the extent of the image f.eld such ~ a~ bumper b~r level, compared to better resoluti~n over ~hor~r di~tances for smaller focal lenyth lenses, i.e.~ at windshield level. Th~ ~hoice of object lens will therefore ~e partly application dependant.
Where there are two adjac~nt carriageway~ ~t is advantageous to have ~he system raplicat~d for the other carriageway, as is shown in Figure ll. In this instance ; the degree o~ coverage of each camera must be such as to 15 partly o~erlap into the adja~ent carriageway, and at least by one half of~ the widt~ of a registra~ion number plate.
The~second carriageway could be for trafic travelling in the same or di~feren direction. Aside rom performing the same functions~as have been described, the duplîcated ~system can also be used in conjunction with the fir~t for the detection, discrimination, deciphering of reg~stration ; number and 'signature' image capture i~ a vehicle i~
straddling the lanes. The cameras ~0,40 and 7Q,80) of both carria~eways~will record respectivP part~ of the 25~ whole, including so~e of the sides of the vehicle. Often there will be information on the sides of a vehicle wh~ch , , will aid identification of the vehicle in addition to the regi~tration number plate. It is possible to confirm that it is the one vehicle straddling the carriageway ~ the , ~
image recorded by both sets of cameras will occur at the same instant in time, and there will be no xoadway component at the common edges of the carriageway.
As the truck passes through field al, the whole top surface of ~he truck is recorded and stored in the ma~
W0~3/19429 ~ ' PCT/A~193/~
storage device 53, and thereby forms a unique ~signature~
of the truc~. Because the resolution offered by the ~y~tem is so g~eat (say a ~ mm X 2 mm comb over the truck at 70 km/h a~d 45 for ang~es ~,~, the very small differences be~ween trucks of an iden~ic~l make and m~del may be detected. For exam~le, the l~ngth of the exh~ust stack may be 5 cm longer or shorter b~tween i~dividual tracks, and ~: this difference could be dete~ted. Feature~ ~uch as the numbe~ of driv~ng li~hts ~ould al~o be determ~ned.
:::
~ ; 10 Figure 9 shows a number of inst~nces of truck ~ , ~
passing throu~h: tXe image field al and a~. Particularly the~variables cons;idered are of~set from the carriageway centre line and two camera object len~ sizes. The registrati~on numb~er:pla~e is also ~hown to give an : lS: indicatio~ o~ how ehe resulting ima~e will appear, and therefore dictating the requiremen~ of the character recognition softwase. Figure 9A shows a per~pective front view o a truck~:60 centred in the lane a~d for a 50 mm obj~ect~lens.~Fi ~ re 9B is the resulting image. The 0:: ~configurations~o~:Figures 9C-9~ are ~ident fr~m the annotation~:on~the:;drawings themselves.
: Figu~rè 12 shows a flow dia~ram indicating typical s;teps in~performing~alI the functions of speed determination, ~Yehlcle detection and discrimination, Z5~ registration~number, capture and decryption and vehicle 'signature'~acquisition. It would be within the capability o~ a computer programmer to write sof~ware to implement the system:.ollowing the instructions of this specification a the flow d~iagram and without requiring inventive input.
30 ~ Two other physical properties of a truck which :can be estimated from the overaIl image of the truck are ~ : : its height and length. As the truck progresses through .~ field al, any part which has a vertical component ~ increasing the height of the truck will generally appear as ., ~3 ~ A'~
a curv~d sided i~nage since a narrawer part of the field a is being en~ered at ~hat greater height. Conversely, any horizontal part of the truck, such as the bonnet or trailer roof, will generally ~pp~ar ~s a regular~y sided image. sy appropriate so~tware proce~3sis~ it i~ ~os~ible to estimate ~:: the height of th~3 v~hicle from ~he 8Um of curved section~
in the i~a~e once ~ho~ curved section~ hav~ been normalised to r~resent true length, whereas ~he length of the vehicle ~an be e~timated from the sum of the ~ections ~: : 10 of the image which ha~e straight sides.
: Once the lmage of a s~eeding truck i~ comple~ed, the local procèssor~S~ will analyse that data to de~ermine the actual speed and may also identify and decipher the registration number plate. The re~istration number plate identification is~p2rfo ~ed by known so~tw~re written by the present a~plicant which iB incorporated into ~ system in use at the~raffic Camera Vffice ~n Victoria, Australia, and known under the trade ~ r~ ICONISCAN. Thi~ information : is then transmitted to the host computer 101 where it can 20~ ~ be:acted on ~by issuing such as a fine or interfacing with other:records over some external b~s or communi~ations ;de~ice represented:as lO5 such as those that mi~ht be held by traffic enforcement agencies ana which ide~tify the truck's owner~and~or~driver. The registration number 25~ deciphering~could~equally be performed by the host computer 101~. The:complete~truck image information is al~o : transmi~ted to the host computer 101 which can call up the releYant recor~; from th~ mass stora~e device 103 in relation to the identified registration number plate to determine whether the truck bearing that registration number plate is~the same as the one measured at the time of : original registration. It may also be possible to raise an alarm at the central control station 104 such that an ~ operator can alert law enforcement agencies whom may take ''~
`'^"'`! ~ ~_ ':; i~ t~ _ ~ P~/Al l93/001 1 1 2' whatever act ion deemed appropria~ e .
Referring now to Figure 13 and to Figure 14 thexe is shown a furth~r en~c~dimen~ which uses only a single-line type line scan camer~ ~0, This system is useful for : 5 reco~nising an image s:ic~naeu~ o~ image ~ttribute of a ~assing object. ~n this ~y5t~m one or other of the ~pePd or the length o ~h~ obj~c~ may b~ unXnow~. In one particular application th~ y5tem can be used for detecting passing shippin~ containars lS0 which may be lO li~d from transport vehi~les into a ship or other ~torage area. In this inst~nce, the line scan camera 30 i~
directed with its f ield of Yiew orthogonal to an intended . front face of the object - th~ ~hipping ~on~ainer 150. The ~; longitudinal exterlt of the line scan is directed generally : 15 horiz;ontally assuming that th~ shipping container 1~0 will be: lifted vertically. Thus, camera 30 views a side face 151 o~ the shipping container 150 so that a code 153 marked on the face 151 can be viewed line by line a~ the shipping co~ta~ner 150 passes through the lin~ scan ima~e. ~he :;20 ; ~ignals provided by the camera 30 o~ the image of the object are provided to a remote station S0 as in previous ; embodiment~. Tha remote station S0 may include all the omponentry referred to in previous ~mbodiment~ a~ well as : the componentry at th2 central station 100 in the ~reviou~
25~ :embodiments. :The exact arrangement of components i~
dictated by the~in-use envirvnment. For example, all the processing may be done in the remote unit 50 or there may : be transmission of :infor-~ation from the remote unit 50 to the central stat:ion 100 as in the previous embodiment~. As previously s~ated, the length of the object may or may not ~ be known. Similarly, the speed of the object may or may :~ not be known. With this embodiment it is possible by ~ubsequently ascertaining the length of the object or the speed of the object to input one or other of signals WO93/19429 PCT/A~'93/00111 ~ 22 repres~ntative of the speed Qr length of the object to enable a signal to be gene~ated which is representative of the length of the objec~ between ~ine scans. In thi~ way, each single line s~an ima~ of ~h~ object can be proces~ed relative to another lin~ ~can ima~ of the object to form a : nor~alized ima~e o~ the o~ject oYer all the line scan~.
When the imac1e ~i~nals have be~n normali~ed they can be : processed with image ~eco~ni~ion ~ans for recognition processing of either the si~nature of the object or an :~ l0 image attribute of the o~ect - ~ither the shape of the : object or the code numbers respeceiv~ly. These signal~
when recognised by the recognition mean~ can provide an output representative of a recognised ima~e signature or ~:~ image at~ribute.
:
Figure l4 shows a typical sof~ware flow diagram which can be u~ed to provid~ the necessary software for the ystem. The:image attribute such as the code characters : can be recognised by the softwar~ I~ONISCAN ~reviously referred to. :In the embodiment o~ Figure 13 ~or use 20~ ~pecifically with;~hipping containers, it can be assumed : that the length of ~he shipping container (in this ca~e the ; height of the shipping container) is pre-known. Thu~, ~uch :height need not be cal~ulated or obtained at another location for~ub~eguent inputting to obtain a normalized 2~: image of the shipping container. The known height (length) can be pre-stored as an appropriate ~ignal.
The~system descri~d provides an inexpensive, reliable and accurate method of Getermining the speed of oblects utilising readily available equipment and avoiding time consuming and difficult data analysis. The ~ystem also has the advantages of allowing other characteristic measurements of objects ~Q be performed, such as an object~s positioning, width and an estimate of height and length together with a 'signature~ image.
Another mea~ure which has been adopted ir an :~ ~ aStempt to reduce the incid~nce o~ sp~ding i8 to insSall :~ speed limiting devi~es on v~hicl~s, and particularly on trucks and buses. Even with spe~d limiting devices in ~; place there haYe been instanc~ where vehicles have been recorded travelling at speeds in ~xc~ o~ the limited speed, which suggest~ tha the speed limiters either do not ~work cQrrectly else may have been ~ypa~sed.
Law snforcemen~ agencies and ~tatutory bodie~
responslble for the upkeep and regulation of use of roadways have also recen~ly noticed a dsvelopment among~t :operators of trucks which seeks to a~oid payment of correct user fees and chaxges. ~he practice in~olves a truck operator registering a new truck wi~h the responsible : : authority then ~wltching the registration number ~lates to a~truck of the same make but of a lar~er ~ize. This allows ; ; the truck operator to carry a great~r load yet only pay fees and charge~s~ as if it wexe for a ~maller truck. Thi~
25~ ~e~asion scheme~has~led to the concept of obtaining unique ' gnatures;' of :trucks. A 'signature' i~ obtained by ~, measuring certain characteristics of a truck at the time of registration and storing this information ln a central registry. A detection system is then required to operate on the roadway~, so that as a ~ru~k passes a detection station, a measurement of the truck~s charact~ristics are made. A comparison is performed to determine whether the :~ truck is indeed the same truck that was presented at the :~ time of initial registration.
WO 93/ 1 9429 PCl /A ~193/OOl 11 One example of such systems in the prior ar~ are th~ TAG type of systems in which a transponder is fitted to : a truck and interroyated by a~ antenna array mounted at ~he roadside, t~pically to rea~ a unique number ~tored within the transpon.~er. ~ difficulty with the transponders i8 that it is not easy to ~now whe~hex they are, in fact, : operatio.ali hence truck~ w~th ~aulty tran~ponders may ~:~ unwittingly avoid det*ction. Tha ~y~tem i~ al80 expen3ive`~ ~ an~ difficult to implement ~ince each truck mu~t be fitted~;: 10 with a transponder~
: It:is an ob~ect o~ the presen~ invention to provide a reliable and less expensive vision ~ystem than in the past.
~ This i~achieved by use of single-line ~can type line scan c~meras. By collec~ing a series of line scan signal~ as the~object passes, a picture image of the passing o~ject can~be obtained. If the passing object i8 to be reco~nised then it is necessary to obtain some ::information eoncerning the length of ~he ob~ect between :: : line scans - normalization - so that the si~nal~ can be ~ , `appropriately length scaled znd the image eize normalized.
ccording to ~he present in~ention there i8 proYided vision apparatus for recognising an image 25~:~ attribute of a passinq object where either on~ or other of the speed or the: length of the object are unXnown, said apparatu~ comprising at least one single-: line scan type line scan camera mounted so the passingobject will be viewed, ~ 30 electronic means comprising:
:~ store means for storing signals indica~ive of the : image of the~object throughout line scans, processing means for determining a length of the ~: object between line scans, said processing means ha~ing WO93/19429 PCT/AU93/0011l J ?, .~
s input means where signals repre~enta~ive of at least one of the speed or length of the o~ject can be inputted to enable ~aid signal representa~ive of ~he length of the object between line scans to be processed, image reco~nition m~n~ ~o which the signals ~tored in 9aid ~tor~ mean~ ~nd to whi~h said sîgnal represen ative o~ the le~g~h of thQ obj~ct between line ~cans and ~o which expe ~ed ima~ nature or image : attribute signals are supplied for reco~nition ~roces~ing, to obtain an output r~pre~entatiYe o~ a recognised image ~ignature or i~age attribute.
: Such apparatus is indep~nd~nt of the direction of approach of the object.
In one embodiment, t.here may be a ~econd ~ingle-line scan type line scan camera which is directed ~o that the camera views the o~ject, spac~d alon~ the direction of travel of the object, S8 that two ~ets of ~ignals indica~ive of the image of the ob~ect can be obtained and processed. ~y directing the field~ of view of each of t~e 0 line scan cameras in this way, i~ is possib}e to obtain tim~ difference signals from each camera and to calculate the speed of the object without knowing it~ len~th. By using two su~h cameras and by no ing the time of entry and exit~from ~he~ line scan image~ of one camera and the ent~y and exit from the line scans of the other camera it i~ al~o possi~le to c~lculate accelera~ivn. ~h~ distance of s~aci~g of the fields of view of each line scan camera can be relatively close as, for example, one third m~ter~
By using a third such camera spaced it i8 possible to obtain a better indication o~ the acceleration of the object by determining the difference in speed over the time taken for the object to pass between the camera fields of view.
The apparatus may be duplicated at other ~ .y~ 6 locations along the path of the object to provide for interval ro~te timing. In that instance the processor~ at the two locations may be in communication with each other or with yet ano~her processor at a central location, The distances between each of t~1e loca~ion~ i5 known ~o that when the object pa~se~ one locatior ~t~ feature ~uch as : image signature or i~ag~ ~t~ributa or bo~h will be ~; obtained, and wh~n he same ob~ct p~e~ another location its same image sign~ture or image attribute or both will again be obtained, and from ~he respective times of pas~ing the two locations and th~ knswn di~tance therebetween the : a~erage speed can ~e~determined, ~; . Tha appara~us may be directed to the detection of the position of a vehicle on a roadway, A marking ~attern may be laid on the roadway of a known length and position with respect to ~n ed~e of ~he roadway and being coincident with the line scan image field of a camera; the markin~
pattern~comprising a regular pattern which, in the absence : : of a vehicle, produc~s a regu~arly repeating digiti~ed ;20 ;imàge as determined by the processor, and upo~ a vehicle ~ntering the~image:field the digitised îmage will change to form a resulting digitised image, and by comparison with :the ~aid regular;digltised image, the width of the vehicle can be~determined. In one:e~bodimen~ the determination can 25~ be~ made from the-points in the re~ulti~g ima~e where the aid:regularity c ases and reco~mences. Further, the :~ : position of the vehicle on the roadway can be determined wlth rsference;to the sides of the roadway f~om that point along the line image field where the regularity in the ; 30 resulting digitised i~age ceases and recommences. The determined width will indlcate what cateyory of vehicle ha~
: been detected through a comparison with a store of characteristic widths.
The apparatus may also identify an object in WO93/19429 PCT/AU93/OOlll !~ ?~ 3 ;~ ~
terms of the object~s lensth and height. By recording an image of the whole of the obiect as it passes through the field of view of a cam~ra a unique ~signa~ure' of the object can be obtained. T~e heig~t and length of the object can b~ det~rmined from proce~sing the image data obtained from the surface o~ the o~j~ct as it passes through the field of a camera. An e~imate of a object'~
: length might be obtain~d ~rom th~ sum of the len~th~ of image segments haYing str~ight ~iides af ter normalization~
The object~s height will ~e approximately the sum of the length~ of ima~e s~gments ~aving curved sides after ha~ing ~: ~ normalis~d those curved sides to repres~nt true length.
Brief Descri~ti n of ~he Drawinqs In order that the inven~ion may ~e more clearly unders~ood, examples of preferred embodiments will now be described with reference to the accompanying drawin~, in whic~:
Figure 1 shows schema~ic detail of Swo CCD
Change Co~pled Device) cameras located above a roadway in a eystem onstructed in accordance with the invention for ~:: : viewing passing vehicles;
~:: Figure ~ shows a top view of the configuration in : Figure 1;
:Figure 3:shows in schema~ic block circuit dia~ram 25: form the components of the system;
Figure 4 shows in side slevation a truck just entering the first line scan image fieldi Figure 5 shows a top Yiew of the arrangement. in Figure 4;
Figure 6 shows the truck of Fi~ure 4 having moved along the roadway to enter the second line ~can image field;
Figure 7 shows the truck yet further progre~ed along the roadway;
WO 93/19429 , PC~/A~193~00111 Figure 8 shows a rear view of the truck and the f irst 1 ine scan image f ield;
Fi~ure 9 shows example~ of images obtained over the surf ace of the truc~ f or ~ryin~ condit ions;
Figure 10 shows an ~xam~le of a marking pattern applied to ~he roadway.
FiçJure 11 show~ an ~m~oc3is~ent having coverage of two lanes of a roa~w~y; and Figure 12 s~:~ow~ a f lc:~w diagram of ty~>ical steps performed by softwar~ in op~a~ion of a preferred ~ystem constructed in accordance with the abov~ ~mbodiments of the invent ion;
Fi~urR 13 shows schema~ic detail of a single CCD
:~ ~ camera located to one side of path Q~ tra~el of an object such as a shipping container in a sy~em cons~ructed in ~: accordan~e with the inYention for viewing pas~ing ~hipl?ing containers and for r~cognizing code infonnation on a face of the shipping containers;
Fisrure 14 is a f low diagram of ty~ical ~tep~
pexformed by software in operation of a preferred system in accordance w1th~Figurs 13.
De~iled Description of Preferred Embodiment~
. ~ ~
he embodiments to be de8cribed in Fi~ure5 1 and ; 2 relate to a system installed on a public highway for 2~5~ : viewing passing:vehicles. Referring then to Figure3 1, 2 :: and 3, the syste~ ~0 has components located a~ove and beside the roadway 2Q. Particularly, two CCD camera~ 30 40 are arr~nged ~o be above the roadway 20 respectlvely at heights h~ and h2, and located approximately above the mid-;30 point of the left hand carriageway of roadway 20 (for right ~- hand drive vehicles). The cameras 30,40 are in spaced arrangement. The cameras are charge coupled devices of the single-line scan type line scan cameras. One sui~able type of CCD line-scan camera is manufactured by ~he French WO93/19429 PCT/A~193/OOlll ~ 2 l ~ 2 r~? !i~ ~
: company i2R, and sold under type number iVClO0. These cameras are less expensive than ~rame cameras which have a required re~olution to detect image attri~u~es such as vehicle registration number plate characters.
In the example of Fi~ures l and 2 the cameras are sited a~1jacent one anoth~r in t~e horizontal ~lane, howe~er the camera~ could be mount~d in ~eh~r ways but it i8 desired tha~ th~ angle~ of ths imag~ field between the respective cameras and the perpendicular from the roadway, : lO being and ~ respecti~ely, are substantially the same.
These angles are not orthogonal to the direction of travel of the vehicles the image fie~d of eacb ~amera is therefore represented as lines al and a~ and must be regularly ~paced at distance x along the whole of their path length. Thi~
arrangement facilitatQs easy proc~s~iny of image ~i~nal~
such that inexpensive computers, such as P.C. type computer processing or:similar costing dedicated computer~ can be utilized. If the fields of view are n~t parallel - i.e.
an~les a and ~ - thsn involved mathematical computation~
;20~ ~must be made to ~ths image signal~ to equate ~he image ignals of the two cameras to a fixed datum for determining para~eters of the image signals which can be appropriately related to one another.
The line-scan cameras 30,40 of ~he type s~ecified 25: ha~e a resolution of 2048 pixels in each line, which translates to typically 2 mm lateral resolution on the road urf~ce, gi~-en that lane width is typically 3.3 m. Best ; results are obtai.1ed for angles a,~ in the range 30-S0.
For an angle of 4S. since there is one-one correspondence ~:~ : 30 of horizontal speed with vertical speed, any image ~: attribute obtained by the camera of numerals or letters will be 1 to 1 scaled, thereby aiding recognition. There i~
often a judgement required to be made, in that at an angle near 30 there will be a large ~shadow' behind a vehicle W0~3/19429 t ~ ~ PCT/AU93/0011!
and therefore tail gating v~hicles may escape detection.
On the other hand, i~ an angle of 60 is selected ta~l gating vehicles will be detected, but ther~ is a loss of resolution in capturing a ~ s ignature ~ image of a vehic~e -: 5 the shape of the vehicl~ - and a similar los~ of resolution in ca~turing an ~mage ~tr~bu~e - re~istration number~ A~
the cameras operate at a line scan f~uency of 10,000 : lines per secQnd, ~e. ~0 ~Hx, for a vehicle ~eed of 70 km/h th~-resolu~ion o~taina~le 15 2 mm at a 45 angle, ; 10 which is su~ficient to allow r~coc3nition of vehicle signatures and image attrl~ute~ such as registration n~mbers. I~ a vehicle~s speed i5, say, 140 km/h, res,olution : reduces to 4 mm,:but it is still pos~ible to recognize the : registration~ number as only the height of the character ha~
15~ been affected, and not the width.
: The two camer~s 30,40 do no~ necessarily neQd to have the same: reBolution~ nor do they~ need to have a~ hi~h a resolution a8;~frame cameras, as t~e application and ~peed ; of ~ehicles bein~de~ected will dictate a~ ap~ropriate 20~ c;onfiguràtion, partLcularly if the expected top ~eed of :vehicles~ is ~ess:than 140 kmfh.
The~cameras 30,40 are mounted off the road by a~y sui~table means~such:as on a gantry, or on ~ome other structure whi~h may~also hold road ~i~ns, or even from a 25~ :bridge. The::cameras 30,40 are connected to a remote statioD SO~which~comprises an e~closure hou~ing electronic : means utilised ir,:implementing the localised control and ~ "
processi~g of`the system 10. The remote station 50 may include a power supply 51 which can be used to power the 30 : electronic~means~as well as the cameras 30,40.
Referring~in detail to Figure 3, the local : processor 52 controls the operation of the locali~ed control/processing at the remote station 50. The processor : 52 is in two-way communication with the camaras 30,40.
:
: :
W093/19429 PCT/A~'~3/00111 1i Information received by the local processor 52 from the cameras 30,40 typically relates to signals re~resentative of image data collec~ed, wheraas ~ con~rol line~ from the local processor 5~ to the camer~5 30,40 r~l~te to issuing of control inst~lction~ and ~rovidir1g power to the camera~.
The local processor 52 c~n r~a~ and wri~e in~ormation from a store means in the form sf a ma~ storage device 53. As shown in Figura 3 it is possible to connect further ~airs ; of cameras 30', 40' to the local processor 52, ~he other pairs being sited ahove another carriagewa~.
The local processor 52 will p~riodically be ~: required to transmit information ~o a c~ntralised location at a central station lOO for reasons ~hat will become apparent. For this purpose a modemJTx/Rx device 54 i~
connected to th~ local processor 52. The communications from the local processor S2 to the central station lOO can ~: be via land line or radio tran~mission or the like.
Signals of the image data to be tran mi~ted is likely to be compressed to reduce transmission tim~s. For , .
this purpose the JPEG ~JQint Photographers ~xper~ Group) compression technique could be adopted~ althou~h many other technigues would be equally suitable. There i8 alss provided a local control station 55 which allows an : : operator to interrogate or control the operation of the local processor 52. It is likely thi~ control station 55 ~::: would only be used for maintenance purpo~es, ~nd otherwise :~, the remote station 50 would operate au~omatically.
The central station lO0 can support a number of remote stations 50, with a suitable number of modem/Tx/Rx devices 102 being provided. The host computer lOl ha~
~: access to a mass storage device 103 and a central control ~tation 104. The central control station 104 would enable an operator to monitor the performance of any one of a number of remote stations S0 as well as performing other , W093/19429 ~ 3 i`~ PCT/A~1~3/~Ol1 1 operational functions.
Turning then to consider the operation of a remote ~ta~ion 50. Figur~ ~ ghQws a truck travelling on the roadway 20 having reached a position wh~se its front bumper enters the ima~e fi ld al. The cameras 30,40 are typically chosen to op~rate u~ng infra-red light in the range 600-800 nm, henc~ thQ li~ht would not normally be visible to a driver of a truck ~r oth~r motor vehicls.
ven so, it i~ p~ssibl~ to use th~ cam~ras a~ bei~g ~: 10 ~;ensitive to ~he ~isible light s~ectrum~
or~ally the camera~ 30, 40 are isl constant operation, hence the sy~tem does not require remote ; triggering from an~ other sensor to start ~he image recording. There are particular advantages in not ; requiring a trip~me~hanism. First, there is ~o stray electromagnetic radiation such as a~ microwaY~ or RF
fre ~ encies.:: There is great concer~ in the co~munity generally ag eo excessive man-made elec~romagnetic radiation and what are perceived as being a~æociated health ; 20 : issues. Second, the system îs non-invasive to the roadway as the road~:need no~:be disturbed to install ~rip ~en~ors :or the~like~.~ This, in turn, avoids ~ub~eguent road repair Co8ts.~The reason:both cameras are operational i~ because the~ sy8tem i~s:designed to operate for a vehicle travelling 2;5:~ in either direction on the roadway, in which case either image;field al;~or a2 may be~entered fir~t. The camera will : : therefore usually be taking an image ~f the road ~urface to se as a reference. Once the image change~ by virtue of the front-most part of the truck passing through the line ~can field a~, the local proces~or 52 will commence storage ~ ,:
~ of signals of digitised image data. As can be s2en from :::
Figure 5, only the mlddle portion of the line ~can image will show a change as each side portion is still incident ~ on the roadway 20. As soon as the truck 60 enters the line : ~ :
~: :
WQ93/19429 j~.J.~ PCT/AU93/00111 ~can of the first image field al it is pos~ible to switch the local processor 52 into a hi~h intensity/high capture mode to enhance the data image.
In another embodi~ent, the detection of a vehicle may ~ake place by meanS of proCe~ir~g the image data obtained fr~m th~ roadway or a rvadway marking pattern as will presently b~ described with ref~rence to Figure l~
: utilising a fast fouri~r tr~n~form ~FFT~ ~rogram ~o :~ translate the lnforma~io~ into Ch~ fr~quency domain. When a vehi le enters the image field a change in the recorded :~ frequency characteri8tic occur~, tri~gering the s~eed determination and other proceSse~.
~ eferring then t~ ~igure 6, as ~he truck 60 progresses alony t~,e roa~way 20 th~ frorlt-most portion of 15 the truck then enters the l ine scan of field a2. Thi8 :
event is signalled by the c~mera 40 to the local ~rocessor 52 in which case the elapsed time, t, between field al :
ha~ring been entered and ~ield a2 now been entered will be : known, and by knowi~g the horizontal ~e~aration of the 20 f ields, x ( gi~ven that the sa~ne point of the tnlck will : break both line scan beams in the first instance~, the speed of the truck can be determined as x/t. This can then be scaled to~give an indic~tio~ of the speed of the ~ruck in~ units such as km/h.
2S~ ~ In other wods a signal representati~e of the : epeed of the truck is determined by comparing a time instant when a part of the trucX is at a particular line ~san of on~ of the cameras, and a line instant when ~he . ~
:: same part of the truck is at the same line scan of the ~:~ 30 :other of the cameras, to obtain a line difference signal.
If it is determined that the speed of the truck ~: ~is in excess of the permissibl~ speed limi~, then the recording of the image of the truck as performed by camera 30 or 40 should contain image information as to an image ~: :
W093/l9429 j,~ PCT/AU93/001ll attri~ute - in this case - the reyistration number plate from which the registra~ion number can be deciphered and appropriat~ action taken. It may be e~ually ap~licable to determine the registration number o a vehicle that is not speeding, for example in ~o~c~ interval timing as will ~e ~escribed presently. If t~ se~aration x between the fields al and a2 is ~uite small, say 100 mm, then a ~ufficient amount o~ imag~ in~ormation may not have been recorded by camera 30 in ord~r to include the regi~tration number pl~te. ~n this ins~ance, it ~ay be possible to co~tinue the recordi~ for some per~od of time based on a generalised understanding of the a~erage height of the boDnet of a truck when considered against ~he speed of the truck. In the alternative, it is pos~ible to continue the recording of the truck over the who}e length of the truck : until such time as the field a~ pas~es across the back of the truck and an image of the only roadway 20 i5 again : obtained.
, If it is desired to obtai~ a m~asure of the 20: acceleration of a vehicle this can be achieved utilising the two camera ystem. If the time at which the front of the truck enters field al is ascribed So be to~ and the time the front of the truck enters field a~ having travelled distance x is t~, then a first velocity Vl iB
25: known from x/t. In the same way another ~elocity can be determined using the rear of the truck as a reference. The ime~ the rear of the truck pass fields al and a2 are t2 and t3 respect.ively~ This then determines V2. The acceleration can be determined from tv2 ~ Vl) t ( (tl ~ to) ~
30 (t3 ~ t2)). In other words the acceleration i~ determined by comparing the time difference in the signals indicative ~.
of the image of the truck, of the entry an~ exit instants ~;~ of the truck within the fields of each camera~
A further embodiment to that shown in Figure 2 i~
WO93/l9429 PCT/A~193/00111 ~ ,?~.~6 to include a third single-line scan type line-scan CCD
camera. This third camera will be spaced from the other two cameras either in ~ron~ o~ camera 30 or behind camera 40 or between the two cameras, and such that the line field of images a3 is sub~tantially p~rallel to f~elds a~ and a~.
The separa~ion betwe~n fi~ld a~ and ei~her a~ or a2 need not be x as between tho~ ~wo. The f~nction of the third camera is to provide anothar mea~ur~ o~ a vehicle'~ speed :: ~ome time a~ter, ~efose or during ~hat ob~ained by the time interval between al and a~. In this way a measure of the vehicle~ 5 acce1eration can also be obtained, through knowin~ the change in sp~ed and the time between t~e respective speeds being recorded. It may be impor~ant to k~ow the acceleration of a vehicle. ~ne exam~le of the ~alue of knowing this quan~ity would he where ~he cameras were mo~nted~near a set of ~raffic ligh~s, and if a v~hicle was determined to be spe~ding and accelerating it may be possible to cause t~e state of ~he traffic lights to ~e ~: : changed and avoid a collision. Alternative~y, it can be determined a driver is engaging in unsafe driving practice ; : by~speeding or accelerating through traffic ~ignals.
::: Thus, in this arrangement, ~he third c~mera views the:truck at a position along its path of travel differe~t : to the two c~meras, and where the acceleration of the object is obtained by comparing ~he time diff~rence in said ignals~indicatiYe of a part of the truck at a particular line scan image of the truck in each of the cameras.
~: : As has been noted above, the central station 100 can support a number of remote stations 50. Given the instance that the registration number of a vehicle has been ~: : obtained at one remote station 50, it is then possible to check the xoute interval time of the vehicle once it pas~es ~:; another remote station 50 simply by matching registrativn ~: numbers and 'times of day'. This will give an indication WO 93/19429 PCr/A~193/OOl 11 r~
of the average sp~ed of that v~hicle.
There may be only one route or a number of routes between remote station~ 50. ~f there i~ more than one routa a minimum time for t~ ourney b~ the fastest rou~e would serve to de~ermin~ wh~th~r speeding might have occurred. It is unlik~ly that trucks would take a longer rout~ between tw~ poi~t~, unl~ss it wer~ the case that route proved shorter in ~m~. In th~t ev~nt the longer rou~e distance-wise i~ ~evertheless the æhortest route : ~ 10 time-wise henc~ cho~en a~ the baselin~. It is also ~:~ possible that the remo~e station~ 50 can be networked across differ~nt ~ajor routes, and in ~his way ~till track ~ehicles travelling between dest~na~iQns which span different highways. The necessary processing would be ~erformed y the host computer 101. ~n ~djunct to route ~ .:
: i~terval timing is t~ allow fl~et per~ormance monitoring.
: The ~ystem described is a ~mper proo~ method of conirming : the trip details of individual vehicles in a fleet.
moaif ication of the sy~tem permit~ determi~ing the vehicle parameters of position in a carriageway and it8 width. ~his is shown in Figure }0. This modifica~ion comprises use of a roadway marking pattern 120 which i8 :laid across the width of the carria~eway at a position coincident with fields a1 and a2. The patern 120 25: comprises regularly spaced white squares or rectangles which are periodically interposed by alternately oriented : ~ triangles. As the cameras 30,4Q record the marking pattern ,, :
120 they will generate a re~ularly re~eating digitised îmage based on 256 grey scale levels. The width of the : 30 white segments is at least 2 pixels. A white objec~ will :
be recorded as a series of pixels ~corresponding to the width of each segment according to the resolution) havi~g a grey scale value of, say, 0-10. The roadway segments are black and therefore detected as a series of plxels having a ~ ~. 2 ~ i ~
grey scale value of, say, 246-256. When there is no vehicle present a known pattern o~ ~rey scsled pixels i~
continually recorded. ~her~ is di~ect known correlation : between each widthwi~e po~ition in th~ carriagewaY and each pixel in the sequence. ~hen ~ v~hicle enter~ the image field it will causQ a chang~ ~n the ima~. By deter~ining where the known pattern c~ases and reco~m~nce~, the side~
of the vehicle can ~e locat~d, and ther~fore the position o the ve~icle in t:he carriag~way. ~ first estimate of it~
~; 10 width can also be determine~. Alternatively, it is ~: ~ po~sible to apply ~he digitis~ ima~es to a fast fourier trans f orm (FFT) to conYert the information to ~h~ frequency domain. A change in the frequency spectrum will indicate an object e~tering the image field.
: 15 : The triangular shapes in the pat~ern 12Q serve a special purpose. The cameras 30,40 are ~ubject to the environment including wind and structural vibrational ~: :
effects. This may result in the ima~e field~ a~ and a2 being:n~t precisely normal to the carriagQway but 20 ~ :tra~slating forward and backward along the roadway, or possibly becoming slightly skewed. This translation or skewing Qffect will be determinate since the reflected ; image will va~ry~slightly as more or less cf the triangle i~
imaged~depending~upon the skew. This allows correcting : adjustment to be;made in the processing of image data of a , ~. ~ . :
: ~ehiclej hence~maintaining the desired accuracy.
~:j The task of obtaining a ~signatuxe' of a truck is ~:: :: made more difficult whare the truck i~ not travelling down : the centre of a carriageway, is straddling lane~ or iB
: 30 skewed by virtue of changing lanes. ~hese considerations impact on the system configuration and the software required to generate a total image of the truck. There are four angular measures as well as the speed and acceleration ~ : of the truck which come into play. These angular measure~
1;~' :
WO93/1g429 PCT/A~193/00111 ~ 3 are the image field inclination (a), the truck centre-line offset, the skew of motion and ~he camera angle field of ~iew (which is a ~unction of focal length). Th~se considerations are complicated by a trad~-off in camera S object lens sizet wher~ lar~r ocal len~Sh lenses can resolve imag~s in the distance ~tt~r, i.~., the extent of the image f.eld such ~ a~ bumper b~r level, compared to better resoluti~n over ~hor~r di~tances for smaller focal lenyth lenses, i.e.~ at windshield level. Th~ ~hoice of object lens will therefore ~e partly application dependant.
Where there are two adjac~nt carriageway~ ~t is advantageous to have ~he system raplicat~d for the other carriageway, as is shown in Figure ll. In this instance ; the degree o~ coverage of each camera must be such as to 15 partly o~erlap into the adja~ent carriageway, and at least by one half of~ the widt~ of a registra~ion number plate.
The~second carriageway could be for trafic travelling in the same or di~feren direction. Aside rom performing the same functions~as have been described, the duplîcated ~system can also be used in conjunction with the fir~t for the detection, discrimination, deciphering of reg~stration ; number and 'signature' image capture i~ a vehicle i~
straddling the lanes. The cameras ~0,40 and 7Q,80) of both carria~eways~will record respectivP part~ of the 25~ whole, including so~e of the sides of the vehicle. Often there will be information on the sides of a vehicle wh~ch , , will aid identification of the vehicle in addition to the regi~tration number plate. It is possible to confirm that it is the one vehicle straddling the carriageway ~ the , ~
image recorded by both sets of cameras will occur at the same instant in time, and there will be no xoadway component at the common edges of the carriageway.
As the truck passes through field al, the whole top surface of ~he truck is recorded and stored in the ma~
W0~3/19429 ~ ' PCT/A~193/~
storage device 53, and thereby forms a unique ~signature~
of the truc~. Because the resolution offered by the ~y~tem is so g~eat (say a ~ mm X 2 mm comb over the truck at 70 km/h a~d 45 for ang~es ~,~, the very small differences be~ween trucks of an iden~ic~l make and m~del may be detected. For exam~le, the l~ngth of the exh~ust stack may be 5 cm longer or shorter b~tween i~dividual tracks, and ~: this difference could be dete~ted. Feature~ ~uch as the numbe~ of driv~ng li~hts ~ould al~o be determ~ned.
:::
~ ; 10 Figure 9 shows a number of inst~nces of truck ~ , ~
passing throu~h: tXe image field al and a~. Particularly the~variables cons;idered are of~set from the carriageway centre line and two camera object len~ sizes. The registrati~on numb~er:pla~e is also ~hown to give an : lS: indicatio~ o~ how ehe resulting ima~e will appear, and therefore dictating the requiremen~ of the character recognition softwase. Figure 9A shows a per~pective front view o a truck~:60 centred in the lane a~d for a 50 mm obj~ect~lens.~Fi ~ re 9B is the resulting image. The 0:: ~configurations~o~:Figures 9C-9~ are ~ident fr~m the annotation~:on~the:;drawings themselves.
: Figu~rè 12 shows a flow dia~ram indicating typical s;teps in~performing~alI the functions of speed determination, ~Yehlcle detection and discrimination, Z5~ registration~number, capture and decryption and vehicle 'signature'~acquisition. It would be within the capability o~ a computer programmer to write sof~ware to implement the system:.ollowing the instructions of this specification a the flow d~iagram and without requiring inventive input.
30 ~ Two other physical properties of a truck which :can be estimated from the overaIl image of the truck are ~ : : its height and length. As the truck progresses through .~ field al, any part which has a vertical component ~ increasing the height of the truck will generally appear as ., ~3 ~ A'~
a curv~d sided i~nage since a narrawer part of the field a is being en~ered at ~hat greater height. Conversely, any horizontal part of the truck, such as the bonnet or trailer roof, will generally ~pp~ar ~s a regular~y sided image. sy appropriate so~tware proce~3sis~ it i~ ~os~ible to estimate ~:: the height of th~3 v~hicle from ~he 8Um of curved section~
in the i~a~e once ~ho~ curved section~ hav~ been normalised to r~resent true length, whereas ~he length of the vehicle ~an be e~timated from the sum of the ~ections ~: : 10 of the image which ha~e straight sides.
: Once the lmage of a s~eeding truck i~ comple~ed, the local procèssor~S~ will analyse that data to de~ermine the actual speed and may also identify and decipher the registration number plate. The re~istration number plate identification is~p2rfo ~ed by known so~tw~re written by the present a~plicant which iB incorporated into ~ system in use at the~raffic Camera Vffice ~n Victoria, Australia, and known under the trade ~ r~ ICONISCAN. Thi~ information : is then transmitted to the host computer 101 where it can 20~ ~ be:acted on ~by issuing such as a fine or interfacing with other:records over some external b~s or communi~ations ;de~ice represented:as lO5 such as those that mi~ht be held by traffic enforcement agencies ana which ide~tify the truck's owner~and~or~driver. The registration number 25~ deciphering~could~equally be performed by the host computer 101~. The:complete~truck image information is al~o : transmi~ted to the host computer 101 which can call up the releYant recor~; from th~ mass stora~e device 103 in relation to the identified registration number plate to determine whether the truck bearing that registration number plate is~the same as the one measured at the time of : original registration. It may also be possible to raise an alarm at the central control station 104 such that an ~ operator can alert law enforcement agencies whom may take ''~
`'^"'`! ~ ~_ ':; i~ t~ _ ~ P~/Al l93/001 1 1 2' whatever act ion deemed appropria~ e .
Referring now to Figure 13 and to Figure 14 thexe is shown a furth~r en~c~dimen~ which uses only a single-line type line scan camer~ ~0, This system is useful for : 5 reco~nising an image s:ic~naeu~ o~ image ~ttribute of a ~assing object. ~n this ~y5t~m one or other of the ~pePd or the length o ~h~ obj~c~ may b~ unXnow~. In one particular application th~ y5tem can be used for detecting passing shippin~ containars lS0 which may be lO li~d from transport vehi~les into a ship or other ~torage area. In this inst~nce, the line scan camera 30 i~
directed with its f ield of Yiew orthogonal to an intended . front face of the object - th~ ~hipping ~on~ainer 150. The ~; longitudinal exterlt of the line scan is directed generally : 15 horiz;ontally assuming that th~ shipping container 1~0 will be: lifted vertically. Thus, camera 30 views a side face 151 o~ the shipping container 150 so that a code 153 marked on the face 151 can be viewed line by line a~ the shipping co~ta~ner 150 passes through the lin~ scan ima~e. ~he :;20 ; ~ignals provided by the camera 30 o~ the image of the object are provided to a remote station S0 as in previous ; embodiment~. Tha remote station S0 may include all the omponentry referred to in previous ~mbodiment~ a~ well as : the componentry at th2 central station 100 in the ~reviou~
25~ :embodiments. :The exact arrangement of components i~
dictated by the~in-use envirvnment. For example, all the processing may be done in the remote unit 50 or there may : be transmission of :infor-~ation from the remote unit 50 to the central stat:ion 100 as in the previous embodiment~. As previously s~ated, the length of the object may or may not ~ be known. Similarly, the speed of the object may or may :~ not be known. With this embodiment it is possible by ~ubsequently ascertaining the length of the object or the speed of the object to input one or other of signals WO93/19429 PCT/A~'93/00111 ~ 22 repres~ntative of the speed Qr length of the object to enable a signal to be gene~ated which is representative of the length of the objec~ between ~ine scans. In thi~ way, each single line s~an ima~ of ~h~ object can be proces~ed relative to another lin~ ~can ima~ of the object to form a : nor~alized ima~e o~ the o~ject oYer all the line scan~.
When the imac1e ~i~nals have be~n normali~ed they can be : processed with image ~eco~ni~ion ~ans for recognition processing of either the si~nature of the object or an :~ l0 image attribute of the o~ect - ~ither the shape of the : object or the code numbers respeceiv~ly. These signal~
when recognised by the recognition mean~ can provide an output representative of a recognised ima~e signature or ~:~ image at~ribute.
:
Figure l4 shows a typical sof~ware flow diagram which can be u~ed to provid~ the necessary software for the ystem. The:image attribute such as the code characters : can be recognised by the softwar~ I~ONISCAN ~reviously referred to. :In the embodiment o~ Figure 13 ~or use 20~ ~pecifically with;~hipping containers, it can be assumed : that the length of ~he shipping container (in this ca~e the ; height of the shipping container) is pre-known. Thu~, ~uch :height need not be cal~ulated or obtained at another location for~ub~eguent inputting to obtain a normalized 2~: image of the shipping container. The known height (length) can be pre-stored as an appropriate ~ignal.
The~system descri~d provides an inexpensive, reliable and accurate method of Getermining the speed of oblects utilising readily available equipment and avoiding time consuming and difficult data analysis. The ~ystem also has the advantages of allowing other characteristic measurements of objects ~Q be performed, such as an object~s positioning, width and an estimate of height and length together with a 'signature~ image.
Claims (14)
1. Vision apparatus for recognising an image signature or image attribute of a passing object where either one or other of the speed or the length of the object are unknown, said apparatus comprising at least one single-line scan type line scan camera mounted so the passing object will be viewed, electronic means comprising:
store means for storing signals indicative of the image of the object throughout line scans, processing means for determining a length of the object between line scans, said processing means having input means where signals representative of at least one of the speed or length of the object can be inputted to enable said signal representative of the length of the object between line scans to be processed, image recognition means to which the signals stored in said store means and to which said signal representative of the length of the object between line scans and to which expected image signature or image attribute signals are supplied for recognition processing, to obtain an output representative of a recognised image signature or image attribute.
store means for storing signals indicative of the image of the object throughout line scans, processing means for determining a length of the object between line scans, said processing means having input means where signals representative of at least one of the speed or length of the object can be inputted to enable said signal representative of the length of the object between line scans to be processed, image recognition means to which the signals stored in said store means and to which said signal representative of the length of the object between line scans and to which expected image signature or image attribute signals are supplied for recognition processing, to obtain an output representative of a recognised image signature or image attribute.
2. Vision apparatus as claimed in claim 1, wherein said processing means also processes the signals indicative of the image of the object to obtain a signal representative of the time taken for the object to pass to that by inputting signals representative of the length of the object, a speed signal representative of the speed of the object can also be obtained.
3. Vision apparatus as claimed in claim 1 wherein the field of view of the camera is directed to view the object orthogonally to the direction of travel of the object.
4. Vision apparatus as claimed in claim 1 including at least two such cameras one being mounted relative to the other so that one views the object at a different position along its path of travel to the other, and where said signal representative of the speed of the object is determined by comparing a time instant when a part of the object is at a particular line scan of one of the cameras and a time instant when the same part of the object is at similar line scan of the other of the cameras, to obtain a time difference signal which will result in said signal representative of the speed of the object.
5. Vision apparatus as claimed in claim 4 where a signal representative of an acceleration change of the object is obtained by comparing the time difference in said signals indicative of the image of the object, of the entry and exit instants of the object within the fields of view of each camera.
6. Vision apparatus as claimed in claim 4 or claim 5 including a third such camera mounted to view the object along its path of travel at a position different than the positions of the two cameras, and where an acceleration of the object is obtained by comparing the time difference in said signals indicative of the image of the object at a particular line scan image of the object in each of said cameras.
7. Vision apparatus as claimed in claims 4, 5 or 6 wherein said expected image attributes are characters, to permit recognition of characters carried by said object.
8. Vision apparatus as claimed in claims 4, 5 or 6 wherein the fields of view of each camera are directed substantially parallel to one another.
9. Vision apparatus as claimed in claim 8 wherein the fields of view of each camera are inclined other than being orthogonal relative to the direction of travel of the object, whereby to provide viewing of a leading or trailing face of the object plus viewing of at least one other face of the object.
10. Vision apparatus as claimed in claim 8 or claim 9 wherein signals representative of an image shape of the object are stored and processed whereby to provide signals representative of a signature of the object.
11. Vision apparatus as claimed in claim 10 wherein the signals representative of the signature are processed with said output signals representative of a recognised image attribute, are compared by comparing means with matched signals representative of known signatures and signals representative of known image attributes, to verify the detected signature and image attribute corresponds to the known matched signature and image attribute.
12. Vision apparatus as claimed in claim 9, 10 or 11 and being for specific use in road traffic supervision, said apparatus comprising means for detecting position of the vehicle on a roadway or width of the vehicle, said means comprising a marking pattern applied to the surface of the roadway, coincident with a line scan field of view of at least one of the cameras and extending across the width of the roadway, said marking pattern generating a repeating unchanging image signal each line scan in the absence of a passing vehicle, and in the presence of a passing vehicle generating a different line scan image signal, said processing means processing the resulting image signals to determine either or both the position of the vehicle on the roadway or the width of the vehicle.
13. Vision apparatus as claimed in claimed 12 wherein the marking pattern comprises a series of spaced but different images at least one of the spaced images being an upright triangular image and another being an inverted triangular image whereby comparisons of the lengths of line scan across both can be made by said processing means to determine if there is skew of the line scan relative to the width of the roadway.
14. Vision apparatus as claimed in claim 12 being interconnected with similar vision apparatus at a remote position along the expected path of travel of the vehicle, each such vision apparatus being electronically connected with processing means to compare either or both the image signature or image attribute recognised by the two vision apparatus is for the same vehicle and to then calculate the time taken for travel between the two vision apparatus.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AUPL140392 | 1992-03-18 | ||
| AUPL1403 | 1992-03-18 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CA2132346A1 true CA2132346A1 (en) | 1993-09-30 |
Family
ID=3776043
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CA002132346A Abandoned CA2132346A1 (en) | 1992-03-18 | 1993-03-18 | Vision apparatus |
Country Status (2)
| Country | Link |
|---|---|
| CA (1) | CA2132346A1 (en) |
| WO (1) | WO1993019429A1 (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0631683B1 (en) * | 1992-03-20 | 2001-08-01 | Commonwealth Scientific And Industrial Research Organisation | An object monitoring system |
| DE4409996A1 (en) * | 1994-03-23 | 1995-09-28 | Daimler Benz Aerospace Ag | Device for the detection and classification of aircraft or vehicles moving preferably on runways or taxiways |
| AU2475895A (en) * | 1995-04-28 | 1996-11-18 | Schwartz Electro-Optics, Inc. | Intelligent vehicle highway system sensor and method |
| AU1066699A (en) * | 1997-10-08 | 1999-04-27 | Tracon Systems Ltd. | A road-embedded video camera system |
| EP0978811A3 (en) * | 1998-08-07 | 2000-08-16 | Siemens Aktiengesellschaft | Method and device to obtain travel times of vehicles |
| DE19919925C2 (en) * | 1999-04-30 | 2001-06-13 | Siemens Ag | Arrangement and method for the simultaneous measurement of the speed and the surface shape of moving objects |
| FR2975208B1 (en) * | 2011-05-11 | 2014-01-03 | Morpho | METHOD AND DEVICE FOR PRODUCING A CONTEXTUAL IMAGE OF A MOVING OBJECT |
| CN104730280A (en) * | 2015-04-10 | 2015-06-24 | 苏州大学 | Speed measuring method and system for balls |
| CN109085374B (en) * | 2018-07-27 | 2020-06-16 | 江苏科技大学 | Kinect-based multi-point speed measuring device for low-rotating-speed system and speed measuring method thereof |
| CN111650392A (en) * | 2020-07-03 | 2020-09-11 | 东北大学 | Metal sheet movement speed detection method based on linear array camera stereoscopic vision |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4063820A (en) * | 1975-11-10 | 1977-12-20 | Rca Corporation | Apparatus for measuring a dimension of an object |
| GB1573188A (en) * | 1977-09-23 | 1980-08-20 | British Railways Board | Measuring systems |
| FR2583882B1 (en) * | 1985-06-25 | 1989-02-03 | Renault | DEVICE FOR MEASURING THE SPEED AND THE POSITION OF A MOBILE IN RELATION TO THE GROUND |
| DE3829541A1 (en) * | 1987-09-03 | 1989-03-16 | Ricoh Kk | LEAF-SHAPED ELECTRODE, METHOD FOR PRODUCING THE SAME AND SECONDARY BATTERY CONTAINING THIS |
| GB2231952A (en) * | 1989-05-03 | 1990-11-28 | Serco Limited | Vehicle length measurement system |
-
1993
- 1993-03-18 WO PCT/AU1993/000111 patent/WO1993019429A1/en active Application Filing
- 1993-03-18 CA CA002132346A patent/CA2132346A1/en not_active Abandoned
Also Published As
| Publication number | Publication date |
|---|---|
| WO1993019429A1 (en) | 1993-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2820632B1 (en) | System and method for multipurpose traffic detection and characterization | |
| CN106462791B (en) | Vehicle identification and/or monitoring system | |
| USRE38626E1 (en) | Parking regulation enforcement system | |
| US8817101B2 (en) | Mobile device and method for monitoring of vehicles | |
| US9836967B2 (en) | Method and traffic monitoring device for detecting a wrong-way driving incident of a motor vehicle | |
| AU2017279793B2 (en) | Device for tolling or telematics systems | |
| EP1446678B1 (en) | Method and device for detecting and classifying moving vehicles | |
| CA2132346A1 (en) | Vision apparatus | |
| JP7153717B2 (en) | Vehicle controller and vehicle | |
| RU2493604C1 (en) | Method of detecting violations of road traffic rules | |
| KR20190014667A (en) | Apparatus for detecting velocity using laser | |
| JP3227247B2 (en) | Roadway detection device | |
| JPH0714037A (en) | Monitor system for checking state of fare payment of road user | |
| Fuerstenberg et al. | Object tracking and classification using laserscanners-pedestrian recognition in urban environment | |
| JPH1123250A (en) | Instrument for measuring length of object, object-monitoring device, instrument for measuring length of vehicle, and vehicle-monitoring device | |
| KR102390947B1 (en) | Vehicle detection system | |
| AU638929B1 (en) | ||
| RU2442218C1 (en) | Vehicle speed measurement method | |
| AU3739893A (en) | Vision apparatus | |
| WO1997050067A1 (en) | A multilane traffic registration system, comprising multiple and gantry-mounted detector means | |
| CN219303146U (en) | Vehicle type abnormality detection system for expressway exit toll station | |
| KR102567044B1 (en) | Vehicle profiling extraction using lidar sensor and tunnel collision notification system and method | |
| NL1020266C2 (en) | Device and method for registering journey data of a vehicle. | |
| Dontu et al. | Automatically collecting data traffic in intersections by using video analytics software for vehicle counting | |
| RU2567440C1 (en) | Measurement of vehicle overall length, measurement of spacing between vehicles and device to this end |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| EEER | Examination request | ||
| FZDE | Dead |