EP0847030A2 - A method and device for automatically detecting and counting bodies passing through a gap - Google Patents

Abstract

A method for automatically detecting and counting bodies passing through a gap (A) includes the steps of monitoring the gap (A) with means for generating image signals (3; 4, 9) to obtain a succession of images (4a, 4b; L0, L1, ..., LN) of each body (B) passing through the gap (A), of processing these images (4a, 4b; L0, L1, ..., LN) to obtain an altimetric map for each body (B) passing through the gap (A) for each moment considered, of comparing at least one altimetric map obtained with at least one model of altimetric map stored in a processing unit (5), and of activating a counting procedure depending on the result of the comparison. <IMAGE>

Description

The present invention concerns a method for automaticallydetecting and counting bodies passing through a gap. In thefollowing description and the accompanying claims, the termgap is to be understood as an imaginary surface, or a linearprojection thereof, separating two adjacent areas. It can bea physical gap such as a doorway or gateway, or a logical gapsuch as a virtual flat surface perpendicular to the floor andwalls of a passage which can be visualised, for example, bymeans of a line along an imaginary communication plane, whichmay be a floor or a step or ramp, or a rotary mat or conveyorbelt, and in general, anything which can support a flow ofbodies in one or more directions in both senses of movement.

The detection of bodies passing through a gap has varioususes. It is particularly applicable when the access of peopleor things to specific areas must be controlled. For example,in the case of people, it may be necessary to control theiraccess to public transport means, such as the underground, orto public buildings or areas such as stadia or meeting places,or into shops or various public places.

One practical application may be, for example, to count thenumber of passengers getting on or off an urban service bus ateach stop in order continuously to check the total number ofpassengers on the bus. In this way it is possible to avoidexceeding the maximum capacity of the bus, for example, bypreventing further passengers getting on a bus which isalready full. In addition, auxiliary procedures may be activated when the maximum capacity is reached, such asinforming a service centre which can put additional buses inservice to meet the public demand. Further subsidiaryactivities may result from the knowledge of the passengerdata, such as statistical analyses based on the flow ofpassengers, or the derivation of information on possibledeception by the passengers.

Currently, the automatic control of bodies passing throughgaps is achieved with the use of various techniques, such asoptical transmission and/or reflection barriers, for example,using light or infra-red radiation, or physical barriers suchas turnstiles, pressure-sensitive platforms, or movementdetectors based on microwaves, passive infrared radiation orultrasound.

It must, however, be borne in mind that there are manypractical applications in which the use of physical barriersis not acceptable for safety reasons and/or in terms ofpracticality of use.

Furthermore, all the known systems have a number oflimitations which make them unable to discriminate betweenobjects and people, between objects and people that are veryclose together, or between objects and people moving inopposite directions or not perpendicular to the imaginary lineof the gap. In addition, the known systems use sensors whichmay easily be tricked by objects or people moving at a steadyspeed.

An object of the invention is to provide a method forautomatically detecting and counting bodies passing through agap, which is simple and reliable and which enables thecontemporaneous discrimination between their direction andsense of movement in order to check the flow into or out of atleast one of the areas adjacent the gap.

This object is achieved by virtue of the fact that the methodcomprises the steps of:

• monitoring the gap with means for generating imagesignals in order to obtain a succession of images of each bodypassing through the gap, each image corresponding to aspecific moment in time;
• processing these images to obtain an altimetric map ofeach body passing through the gap for each moment considered;
• comparing at least one altimetric map obtained with atleast one model altimetric map stored in a processing unit;and
• depending on the result of the said comparison,activating a counting procedure.

By virtue of these characteristics, the method according tothe invention enables bodies of different shapes to bediscriminated between with a high degree of reliability, andthe selection of solely a particular type of body forcounting, for example, people only. In addition, the quantityof information that can be obtained by the method of theinvention, which is significantly more than that which can bederived by the known techniques, enables more reliable androbust counting to be effected, overcoming the limitationswhich usually affect known systems, and thus providing greater adaptability to different working conditions and, therefore,greater generality of application.

It is therefore possible, with the invention, to discriminatebetween objects and people even when they are very closetogether, between objects and people moving in differentdirections or generally not perpendicular to the imaginaryline of the gap, between objects and people moving at a steadyspeed or otherwise behaving in a way which could easilyconfuse the sensors used in known systems.

In particular, the term altimetric map is to be understood asany representation of the altimetric, or elevational,distortions caused by the presence of a body. One such map isobtained from the altimetric analysis of the body itselfutilising known automatic methods which enable characteristicsof the shape of the body to be described in a form which iseasily comparable with similar maps of other bodies. If thisanalysis is conducted in correspondence with a gap, it ispossible to distinguish between the bodies passing through itand, in the present case, to count just those which satisfypredetermined shape characteristics. Typically, in order todistinguish a person from other, differently-shaped bodies,one starts with the assumption that a person has a head on topof a generally cylindrical trunk, conferring a characteristicaltimetric profile thereon.

Naturally, a data processing system can be programmed in aknown way to conduct an altimetric analysis of bodies with theaim of recognising the characteristic shape of people or otherkinds of objects under consideration. Programming may be by means of conventional algorithmic approaches, the altimetriccharacteristics of the bodies to be recognised then beingprogrammed into the processing system, or by means ofstatistical learning techniques like, for example, neuralnetworks. In addition, a data processing system can bedeveloped that is capable of evaluating the space-timeevolution of the position of the bodies under consideration inorder to deduce the dynamics of their movements, inparticular, the direction and sense thereof.

A model of altimetric map of a body stored in the processingunit and utilisable for comparison with other altimetric mapsobtained for bodies passing through the gap may be of thestatic type and thus formed on the basis of a singlealtimetric map referring to one moment in the traversal of thegap by a body, or it may be of the dynamic type and thusformed on the basis of a plurality of altimetric maps relatingto a single body, each corresponding to a different moment ingap traversal.

A further subject of the invention is a device forautomatically detecting and counting bodies passing through agap, characterised in that it comprises:

• means for generating image signals relating to a gap;
• a processing unit connected to the image-signal-generatormeans for processing images arising therefrom inorder to obtain altimetric maps of each body passing throughthe gap for successive moments, the processing unit also beingcapable of comparing at least one altimetric map obtained withat least one model altimetric map stored therein in order to activate at least one counting process depending on the resultof the comparison.

Further characteristics and advantages of the presentinvention will become clearer from the following detaileddescription, given purely by way of non-limitative example andwith reference to the accompanying drawings, in which:

• Figure 1 is a schematic perspective view showing a firstembodiment of a device according to the invention;
• Figures 2a, 2b and 3 are, respectively, schematicillustrations of two views obtained by means of the device ofFigure 1, and a stereoscopic view derived therefrom;
• Figure 4 is a view similar to Figure 1 of a furtherembodiment of a device according to the invention; and
• Figures 5 to 9 are views illustrating schematically themodes of operation of the device of Figure 4.

With reference to Figures 1 to 3, the reference numeral 1generally indicates a device for automatically detecting andcounting bodies passing through a gap. In particular, thedevice 1 is intended for obtaining the altimetric map of abody B which passes close to it, in this particular case belowit, following to the composition of its stereoscopic image.

More specifically, the device 1 includes a pair of televisioncameras 3, conveniently of the low-resolution type, spacedfrom each other and preferably on the vertical of the gap tobe checked. This gap is defined by an imaginary surface whichis, for example, flat and vertical, capable of being traversedby moving bodies B, and defined at the base by a threshold line A which constitutes the projection on the ground of theimaginary surface.

Each television camera 3 takes anelementary image 4a, 4b at aspecific moment, as shown in Figures 2a and 2b respectively.The twoelementary images 4a and 4b obtained simultaneously bythe two television cameras 3 are processed by aprocessingunit 5 which combines them to derive a singlestereoscopicimage 4, shown schematically in Figure 3 by a group of contourlines forming an altimetric map of the body B. The processingcarried out by theunit 5 is such as to obtain a real worldcorrespondence between the projections of the points of eachelementary image to enable information relating to thedisparity, namely, the distance between different positions ofa single point on the two correspondingelementary images 4aand 4b, to be deduced. With theelementary images 4a and 4btaken simultaneously by each television camera 3 and thearrangement of the television cameras 3 with respect to thegap all being known, the three-dimensional spatial positionsof all the points observed can be determined unequivocally.It is therefore possible to obtain a moment-by-momentaltimetric, or elevational, map of the gap and the bodies Bpassing through it. As a result of a comparison of thisaltimetric map and its evolution over time with models knownto theprocessing unit 5, it is easy to deduce whether a bodyB which passes through the gap satisfies predeterminedconditions, for example, the fact that it has a head on top ofa trunk in the case of a person, and is therefore to becounted. As discussed above, the models of altimetric mapsalready stored in the processing unit for the purpose ofcomparison may be based on a single moment in the traversal of the gap by the body B, thus being of the static type, and/orthey may each be constituted by a plurality of altimetric mapsof a single body corresponding to different moments in thetraversal of the gap and may therefore be of the dynamic type.

From the mutual comparison of altimetric maps corresponding toa single body obtained at successive moments, it is alsopossible to deduce the direction and sense of movement of eachbody B. In this way, it is possible to count a body B in adifferent way or to decide whether to count it or notdepending on its sense of movement with respect to thethreshold line A.

According to a further embodiment, and with reference toFigures 4 to 9, adevice 7 according to the invention uses theso-called "structured light" technique which utilisesparticular characteristics of light to obtain informationrelating to the geometry of a scene.

In this case, thedevice 7 includes asingle television camera4 and a monochromatic light source 9 constituted, for example,by a solid state laser with an associated optic, whichprojects a plane of light coincident with the imaginarysurface defining the gap. In this way, each body B passingthrough the gap breaks the plane of light and, as a result ofits intersection therewith, causes luminous contour lines L tobe generated on the edges of the body B, each of which, beingilluminated by the plane of light, corresponds to aninstantaneous, two-dimensional image of part of the contour ofa section through the body B (see Figures 4, 5 and 7).

Thetelevision camera 4 is preferably positioned with itsoptical axis incident on the plane of light emitted by thesource 9 and so that the entirety of the gap to be checked iscovered to enable the detection of all parts of the sceneilluminated by the intersection with the plane of light. Theinstantaneous two-dimensional image L of part of the contourof a body B (see Figure 8) transversing the surfaceconstituting the gap, and defined by the plane of light, iscomposed of a plurality of points, each of which identifies aline of view in the three-dimensional space, which lineextends from the respective point in the space to itsprojection on the image plane passing through the focus of thetelevision camera 4. The three-dimensional position of eachpoint on the luminous line L may then be obtained from acalculation of the position of the intersection of the line ofview with the plane of light, the position of the plane oflight being known as it is defined by the position of thesource 9, and eventually determinable by direct measurement,as is the spatial position of thetelevision camera 4 and itsfocal axis.

Only those surfaces of a body B that are substantiallyparallel to the plane of light are of uncertain detection bythis technique, but this disadvantage can be overcome by thechoice of an appropriate arrangement of thetelevision camera4 with respect to the light source 9.

Thetelevision camera 4 may, to advantage, be provided with anoptical filter set to the frequency of the monochromatic lightsource.

From an analysis of the group of luminous lines L_o, L_1, ..., L_N(see Figure 9) generated at successive moments t_0, t_1, ..., t_Nby the intersection of the plane of light projected by thesource 9 with the profile of a body B traversing it,sufficient information about the shape of the surface of thebody itself can be obtained to form the altimetric map of thebody B.

The altimetric map obtained for each body B passing throughthe gap, which corresponds to the shape of the body itself ata specific moment, may be coded as illustrated in Figure 6 bymeans of a band which represents the various zones of itsprofile at different heights given by various shades of grey.Each instantaneous altimetric map, and/or its evolution overtime during the traversal of the gap, can then be comparedwith static or dynamic models of altimetric maps of otherbodies, that is, based on a single altimetric map or on aplurality of altimetric maps relating to successive moments,similarly coded and already stored in theprocessing unit 5 inorder to recognise those of the bodies B passing through thegap that are to be counted. In this way it is possible, forexample, to discriminate between people and luggage passingthrough the doorway of a transport means. It is also possibleto recognise the contemporaneous presence of several people inthe same scene.

By considering the variation of the altimetric map of a bodyover time, the movement of the body through the gap can bereconstructed to enable the direction and sense of itsmovement to be deduced with the consequent evaluation ofwhether it is entering or exiting one of the areas adjacent the gap and the activation of a counting procedure provided bythe system.

Claims (14)

1. A method for automatically detecting and counting bodiespassing through a gap, characterised that in it comprises thesteps of:

   monitoring the gap (A) with means for generating imagesignals (3; 4, 9) to obtain a succession of images (4a, 4b;L₀, L₁, ...,L_N) of each body (B) passing through the gap (A),each image (4a, 4b; L₀, L₁, ..., L_N) corresponding to aspecific moment in time;

   processing these images (4a, 4b; L₀, L₁, ..., L_N) toobtain an altimetric map of each body (B) passing through thegap (A) for each moment considered;

   comparing at least one altimetric map obtained with atleast one models of altimetric map stored in the processingunit (5); and

   activating a counting procedure depending on the resultof the said comparison.
2. A method according to Claim 1, characterised in that themodels of altimetric maps include at least one altimetric mapof a reference body corresponding to one moment in thetraversal of the gap (A) by the respective body, and/or atleast a plurality of altimetric maps of a reference bodycorresponding to different moments in the traversal of the gap(A) by that body.
3. A method according to Claim 1 or Claim 2, characterised inthat the altimetric maps of a body (B) obtained at differentmoments are compared with each other to determine the dynamicsof the movement of the body (B) through the gap (A).
4. A method according to claim 3, characterised in that thecounting procedure is activated in different ways depending onthe dynamics of movement of each body (B) passing through thegap (A).
5. A method according to any of Claims 1 to 4, characterisedin that the images (4a, 4b) obtained by the means forgenerating the image signals (3) are processed to obtain astereoscopic image (4) of each body (B) passing through thegap (A).
6. A method according to any of Claims 1 to 4, characterisedin that the means for generating the image signals (4, 9) arecapable of obtaining two-dimensional images (L₀, L₁, ..., L_N)containing altimetric information by the application of thestructured light technique.
7. A device for automatically detecting and counting bodiespassing through a gap, characterised in that it comprises:

   means for generating image signals (3; 4, 9) associatedwith a gap (A); and
   a processing unit (5) connected to the image-signal-generatormeans (3; 4, 9) for processing images (4a, 4b; L₀, L₁, ..., L_N)arising therefrom in order to obtain altimetric maps of eachbody (B) passing through the gap (A) for successive moments,the processing unit (5) also being capable of comparing atleast one altimetric map obtained with at least one modelaltimetric map stored therein in order to activate at leastone counting procedure depending on the result of thecomparison.
8. A device according to Claim 7, characterised in that theprocessing unit (5) is capable of storing models of altimetricmaps including at least one altimetric map of a reference bodycorresponding to one moment in the traversal of the gap (A) bythat body, and/or at least a plurality of altimetric maps of areference body corresponding to different moments in thetraversal of the gap (A) by that body.
9. A device according to Claim 7 or Claim 8, characterised inthat the image-signal-generator means comprise two televisioncameras (3) disposed with their respective focal axes spacedfrom each other, and in that the processing unit (5) iscapable of handling a pair of images (4a, 4b) acquired by thesaid television cameras (3) at a single moment to formtherefrom a stereoscopic image (4) of each body (B) passingthrough the gap (A) at that moment, and to obtain anassociated altimetric map from this stereoscopic image (4).
10. A device according to Claim 9, characterised in that thefocal axes of the said television cameras (3) lie in animaginary surface defining the gap (A).
11. A device according to Claim 7 or Claim 8, characterised inthat the image-signal-generator means comprise a light source(9) capable of projecting a plane of light coincident with animaginary surface defining the gap (A), and a televisioncamera (4) disposed with its focal axis incident on thissurface, and in that the processing unit (5) is capable ofhandling a plurality of two-dimensional images (L₀, L₁, ...,L_N) acquired by the television camera (4), each corresponding to a different moment, in order to obtain an altimetric map ofeach body which passes through the gap (A).
12. A device according to Claim 11, characterised in that thelight source (9) is a monochromatic light source, preferably asolid state laser.
13. A device according to Claim 12, characterised in that thetelevision camera (4) has an optic provided with a filter setto the frequency of the light emitted by the light source (9).
14. A device according to Claim 10 or Claim 11, characterisedin that the processing unit (5) is capable of comparingaltimetric maps relating to successive moments for each body(B) passing through the gap (A), and of determining thedirection and sense of movement of each body (B) through thegap (A).

Images