DE102017129663A1 - Sensor system with a light field camera for determining the characteristic of a scene - Google Patents

Abstract

A sensor system (100) and a method for determining the characteristic of a scene (190) are described. The sensor system (100) has a sensor (120) based on the principle of a light field camera for the three-dimensional optical detection of the scene (190); and a data processing device (140) connected downstream of the optical sensor for evaluating the optically detected scene (190). The data processing device (140) is configured in such a way that motion profiles can be determined in real time by an object (195) contained in the scene (190). The invention also relates to a use of a sensor system with a sensor based on the principle of a light field camera for controlling a coverage characteristic of an opening (184) to be passed by an object (195) through at least one closing body (186) and / or for detecting and / or Controlling traffic flows of objects (195).

Description

Technical area

The present invention relates to a sensor system and a method for three-dimensional detection of a scene. Furthermore, the present invention relates to several uses of such a sensor system.

Background of the invention

For opening and / or closing of openings operated by actuators closing body are often used, which facilitate the handling of the respective closure body for operators or operated fully automatically without any operation, for example, when an object to be passed the opening passes into the region of the opening. Such an opening may, for example, be a passageway in a building. A closure body may be, for example, a door or a gate.

In order to achieve a high level of operational reliability of automatically closing and closing closing bodies, it is known to detect the area in front of or within an opening which can be covered by a closing body by means of an optical sensor system. This can on the one hand be ensured that when shooting the opening accidentally an object, such as a person, is clamped by the closing body.

In addition, in some applications such a sensor system may cause automatic opening of the closure body or opening. In this context, it is also known that such a sensor system or a data processing device connected downstream of such a sensor system performs object recognition by means of known methods of image processing and only releases the opening when an object authorized to pass through the openings is in the area of the (still closed Opening). Such an object recognition can be for example a face recognition.

A particularly high degree of operational reliability can be achieved by the use of sensor systems which carry out a three-dimensional (3D) monitoring of the (input) region of an opening which can be closed by means of a closing body. So for example describes US 7,984,590 a stereometry sensor, which opens a sliding door by independent control and motorization of horizontal door leaves so that it is adapted to the contours of the object to be passed.

Out EP 2 453 252 B1 For the field of application of the monitoring of automatically opening doors and / or gates a 3D sensor system is known, which is based on the principle of transit time measurement of light rays emitted by illumination sources and detected by at least partial reflection or 180 ° backscatter from a light receiver become. Such sensor systems are commonly referred to as "time-of-flight" (TOF) sensor systems. However, TOF sensor systems have the disadvantage that they are relatively complex in terms of the evaluation of the received data and have a relatively high energy consumption. This is especially true when extraneous light sources radiate into the monitored area (for example, sunlight), so that the intensity of the illumination light must be correspondingly high.

The present invention has for its object to enable an energetically efficient and yet reliable monitoring of passages, it being possible to distinguish between (a) objects which pass through the passage in question and (b) objects which are either not in the concept should enter the area of the passage area and / or not pass the passage.

Summary of the invention

This object is solved by the subject matters of the independent claims. Advantageous embodiments of the present invention are described in the dependent claims.

According to a first aspect of the invention, a sensor system for determining the characteristic of a scene is described. The described sensor system comprises (a) a sensor based on the principle of a light field camera for the three-dimensional optical detection of the scene; and (b) a data processing device connected downstream of the optical sensor for evaluating the optically detected scene. The data processing device is configured such that motion profiles can be determined in real time from an object contained in the scene.

The sensor system described is based on the recognition that by the use of a three-dimensional (3D) sensor system, which has a light field camera or at least one working on the principle of a light field camera sensor, detected in an energetically efficient manner moving objects and their motion profile in real time (by means of the optical sensor downstream data processing device) can be determined. From a knowledge of the motion profile of an object can then be reliably distinguished, for example, whether the object in the direction of an opening wearable by a closure body or otherwise moved in the scene monitored by the sensor. For example, in an automatic garage opening can be prevented that in a cross traffic, which passes through the entrance area of the garage opening, vehicles are erroneously recognized as objects that want to enter the garage in question.

In addition, it can be detected, for example, if I am an object, for example, a person or only limbs of a person, in the closure region of a closable by a closure but just opened opening. Then, namely, an automatic closing of the opening (by the closing body) can be prevented and thereby injury to the person or activation of an emergency stop can be prevented. A closing body can be used for a concrete closure of an opening and be realized for example by means of a door, a gate, a barrier, etc. However, a closing body can close off an opening or a passage in a non-representational manner by means of suitable signaling on "obedient" objects. Such a closing body can be, for example, a traffic light.

In this document, the term "light field camera" can be understood as meaning a plenoptic camera which, in addition to the usual two image dimensions, detects an additional dimension, namely the direction of incident light rays. Due to this additional dimension, plenoptic images contain information about the image depth. A particular advantage of plenoptic cameras lies in the theoretically infinite depth of field and the possibility of refocusing, ie the subsequent shift of the focal plane in the object space (focus variation). Due to the additional depth information, a plenoptic camera is used as a 3D camera in the described sensor system. The direction of the incident light beams can be selected, for example, by diaphragms or, energetically much more efficiently, given by suitable lens systems. If the light receiver of the sensor is a sensor array with a multiplicity of (semiconductor) light receivers, then the direction of the incident light beams can be closed by means of a suitably adapted array of microlenses in front of the sensor array and the depth information derived therefrom. In this document, the depth information is referred to as z-information or assigned to a z-direction. The two perpendicular directions (in the image plane of a two-dimensional image) are called x-direction and y-direction, respectively.

The use of a light field camera for the 3D sensor system according to the invention, in contrast to known stereometric or based on the principle of triangulation sensors, which must have a minimum spatial distance between different evaluated beam paths, the advantage that the sensor system can be implemented in a compact design. This results in a variety of applications for the sensor system according to the invention, which are not limited to a monitoring of input areas. A further advantage which results from the use of a light field camera is that the sensor system according to the invention is comparatively insensitive to extraneous light. This is because the directional selection of the light beams used for the three-dimensional detection of the scene is used by the light field camera.

In particular, compared to a 3D object detection based on a predefined structured illumination, which is spatially distorted by a 3D surface contour of an object to be detected, the sensor system according to the invention can get along without additional illumination, at least in good light conditions. Of course, however, the sensor system described may also have a suitable lighting device, so that a three-dimensional detection of the scene is possible even in low light conditions. In this case, however, can be dispensed with activation of the lighting in good lighting conditions, so that the lighting device only has to be supplied with (electrical) energy when the sensor system is operated in low light conditions.

The term "scene" may in particular be understood to mean that spatial area which is optically detected by the sensor system. Objects in the scene are recognized by a suitable image analysis. For this purpose, known methods for image analysis and / or image analysis can be used.

The term "characteristic of a scene" can be understood as the entirety of all spatial structures which are detected by the sensor. In this case, some structures can be recognized as being relevant and other structures as being less or even irrelevant by the data processing device by means of image processing and / or image recognition.

The term "motion profile" can be understood to mean all motion data which describe a variability of the object along at least one spatial coordinate. The transaction data can easily change the amount of Describe speed and / or the amount of acceleration of the object. Alternatively or in combination, the movement data can also describe the corresponding direction and in particular the vector of the variables speed and / or acceleration.

In other words, the movement data can describe all the location changes of the object. This can apply to all object movements with a nonzero speed and / or zero speed.

Since motion data is determined with the described sensor system, a scene is preferably detected at least twice with a specific time interval. From the change in the spatial position of a detected object, the velocity of the object can be determined by the relationship "speed = distance per time". Due to the "three-dimensionality" of the scene detection, the direction of motion or the motion vector in space can also be determined. It should be noted that a movement in the case of a long compared to the speed exposure time could also be determined based on the motion blur of the object.

The terms "optical" and / or "light" may refer to electromagnetic waves having a particular wavelength or frequency or a particular spectrum of wavelengths or frequencies. In particular, the electromagnetic waves used can be assigned to the spectral range visible to the human eye. Alternatively or in combination, electromagnetic waves associated with the ultraviolet (UV) or infrared (IR) spectral regions may also be used. The IR spectral range can extend into the long-wave IR range with wavelengths between 3.5 μm to 15 μm, which can be detected by means of a plenoptic thermal imaging camera.

According to one exemplary embodiment of the invention, the sensor system further has a holder which is mechanically coupled to the sensor, wherein the holder is designed such that the sensor system can be attached to a stationary holding structure with respect to the scene to be detected.

In terms of clarity, the holder ensures that the described sensor system can be a stationary system which has a certain spatially fixed detection range and thus always monitors the same scene. By comparing different temporally spaced detections of the dependent of the orientation of the sensor system scene spatially stationary objects that are present in the scene can be detected in an image analysis and hidden in a further image analysis with respect to movement profiles. As a result, computing power can be saved and the energy efficiency of the described sensor system can be improved.

The stationary support structure may be directly or indirectly mechanically coupled to a device for controlling a coverage characteristic of an opening to be passed through the object by at least one closure body. In addition to a suitable guidance or mounting of the closing body, this device preferably has an actuator for moving the closing body, in particular for moving the closing body between a closed position and an open position (and vice versa).

In the field of building security, the opening may be an entrance, for example for a person or a vehicle, the closure body may be a door, for example a front door or a garage door. The stationary support structure may be, for example, the stationary frame structure of an entrance, for example the frame of a door.

According to a further embodiment of the invention, the data processing device is further configured such that a coverage characteristic of an opening to be passed from the object is controllable by at least one closure body. Thereby, the opening, which is for example an entrance (or an exit) of a building, can be automatically monitored in an energetically favorable manner and by a suitable actuation of an actuator, the closing body can be moved in the desired manner between an open position and a closed position , For this purpose, the data processing device of the described sensor system can be coupled with the control of a known control system for a closing body.

According to a further exemplary embodiment of the invention, the sensor has a light detector with a plurality of pixels. Further, the sensor is configured to detect the scene based on at least one of the following characteristics of detected optical radiation: (a) intensity incident on at least one pixel, (b) intensity differences between different pixels, (c) wavelength, (d) spectral intensity distribution, (e) polarization direction, and (f) intensity distribution for different polarization directions. By an application-specific use of one of these features or by a suitable combination of at least two of these features, the objects to be recognized can be detected with particularly high accuracy and reliability.

The intensity of the optical radiation which is received or detected by a pixel is usually reflected in the form of gray values, which are forwarded to the data processing device and combined there to form a complete image of the detected scene. There can also take place a comparison of the gray values between different pixels, which are assigned to different spatial subregions of the scene. The wavelength, frequency or color of the detected optical radiation can be determined by means of suitable filters. In each case, a filter or a filter element can be assigned to a pixel of a sensor array or the light receiver of the sensor. Spectral intensity distributions can be determined by a suitable combination of such filters. In this case, continuously variable filters are possible. The polarization direction of the detected optical radiation can be determined in a known manner by the use of polarization filters or the corresponding polarization component of the optical radiation can be filtered out.

Differences in intensity and also different colors on different pixels represent a contrast, which in a known manner can be of great advantage for an evaluation of the detected scene and in particular for object recognition.

According to a further exemplary embodiment of the invention, the sensor has a spatial resolution that is different in different partial regions of a light-sensitive surface of the sensor.

A spatially inhomogeneous spatial resolution can lead to a further energetic optimization of the sensor system described, because both the operation of the sensor (including the reading of detected sensor data) and an image analysis performed by the data processing device requires less energy at a low resolution. Of course, the subareas with a higher resolution should preferably be assigned to those sections of the scene in which the object is located or in which the object is suspected with an increased probability. Expressed clearly, the sensor designed as a light field camera "looks" more precisely where the object is suspected. In the case of a closure control of a closable passage, the scene can be detected with a higher resolution within a so-called security zone than in other zones or sections of the scene.

A different spatial resolution of the sensor or its pixel-sensitive light-sensitive surface may be static or fixed. For this purpose, the sensor may consist of two different individual sensor chips with a mutually different resolution. A different resolution can for example be done by a so-called binning or summarizing mutually immediately adjacent pixels of the light-sensitive surface of the sensor.

According to a further embodiment of the invention, the spatial resolution of the sensor is dynamically adaptable to different characteristics of the scene. This has the advantage that a region captured with a high resolution does not always have to be the same section of the scene. In particular (with not too fast movement of the object) the high-resolution captured portion of the scene can "move through the scene" along with the movement of the object, so that the object which is typically most relevant to the scene's characteristic , always with the high resolution and thus very accurately recorded.

According to another embodiment of the invention, the resolution of the sensor is adaptable by combining adjacent pixels of the light-sensitive surface of the sensor. Such a pooling of pixels, which is also referred to as "binning", has the advantage that it can be carried out uncomplicated and also fast or dynamic. A local "binning" can be done at least in some known sensors without special electronic or apparatus elements simply by a corresponding control of the sensor, which control determines the "binning" and thus the operating mode of the sensor.

Another advantage of the described summarization of neighboring pixels can be seen in the fact that with two combined pixels compared to the amount of energy or the number of photons, which is assigned to a pixel at a full resolution, twice the amount of energy or double the number Photons for the two combined pixels is available. Thus, the light sensitivity of the described sensor system is significantly increased and unwanted, but never completely eliminate noise is reduced, so that there are many applications that do not require their own lighting, because the available extraneous light for optically detecting the scene by the in its resolution reduced sensor is sufficient.

According to a further embodiment of the invention, the sensor has a spatial resolution along different Coordinate directions is different. This embodiment has the advantage that different directions of movement of the object are detected with different accuracy. This means that the motion profile of the object along different directions is determined with a different accuracy. Again, a reduction in accuracy has the advantage that energy is saved for operating the sensor system both in the optical detection of the scene and in a subsequent evaluation.

If a direction of movement of the object is predetermined or the object moves with a higher probability along a certain direction coordinate, then the coordinate direction with the higher spatial resolution can at least approximately coincide with the (expected) direction of movement. In other cases, the coordinate direction with the higher spatial resolution can also be oriented perpendicular to the (expected) direction of movement, if less the speed of the object or the position of the object along the corresponding predetermined trajectory is to be determined exactly, and in particular any "path deviations" should be reliably detected by this trajectory.

A along different coordinate directions of the trained as a light field camera sensor can be used in a particularly advantageous manner to secure a control for a closing body. Because e.g. In the case of a sliding door which sheds a door opening, the greatest risk of being pinched is when a person or a part of a person moves perpendicularly to the sliding direction in the area of the sliding door, a higher resolution can be used along this direction for the object recognition. Thus, e.g. an outstretched finger (with respect to a symmetrical body) are preferably recognized, which is inserted into the range of movement of the closing edge of the sliding door. This takes into account the fact that particularly shaped (not symmetrical) objects can be better recognized by the sensor system by an asymmetrical resolution. For example, a high-resolution quasi one-dimensional detection area ("protection line") in the immediate vicinity of the movement range of the closure body to detect an unwanted penetration through an object. Before (and behind) this protection line can be worked with a lower resolution, without a loss of operational reliability would have to be accepted.

According to a further exemplary embodiment of the invention, the sensor has (a) a first sensor region for at least one first characteristic of detected optical radiation and (b) a second sensor region for at least one second characteristic of detected optical radiation, the second characteristic being different is the first characteristic feature.

In the case of two (spatially separated) sensor regions, the characteristic features may also include the above-mentioned features: (a) intensity on at least one pixel of the relevant region, (b) intensity differences between at least two different pixels, which are preferably assigned to different sensor regions, (c) Wavelength, (d) spectral intensity distribution, (e) polarization direction, (f) intensity distribution for different polarization directions, etc.

The embodiment described with different sensor regions may have the advantage that different characteristic features of the detected optical radiation, which features, as described above, can be used for an energetically favorable and / or particularly accurate and thus in particular for a reliable evaluation of the detected scene, can be recorded or measured simultaneously. In this case, each sensor region can be configured to detect its characteristic feature in a particularly accurate and reliable manner and also with a high degree of efficiency. A high efficiency in the detection in turn has the advantage that even comparatively dark scenes can be evaluated without a (particularly strong) illumination light.

It should be noted that a sensor with two sensor areas can also be replaced by or two separate sensors, which are functionally described in the sense of the embodiment described here as a (common) sensor.

It is further pointed out that the sensor can also have more than two, for example three or four or even more different sensor regions, each of which can be assigned to a characteristic feature of detected optical radiation. As a result, even more specific optical information about the detected scene or the object located therein can be determined and used for a subsequent evaluation by means of the data processing system.

According to a further exemplary embodiment of the invention, the first characteristic feature is a first spectral distribution and the second characteristic feature is a second spectral distribution, the second spectral distribution being different from the first spectral distribution Distribution. Since different spectral distributions represent different optical properties of the scene or the object located therein with different accuracy and / or different detail, the scene or the object located therein can be detected in a particularly comprehensive manner by the use of different spectral distributions and evaluated particularly accurately by means of the data processing device become.

The first spectral distribution may be a first wavelength or a first wavelength range, for example visible light, whereas the second spectral distribution may have a second different wavelength or a second different wavelength range, for example infrared ( IR ) Light can be. In this case, the first sensor area could by means of a conventional RGB Sensors be realized. The second sensor area can be IR Sensor, which IR Light is captured, or a IR and RGB Be sensor, which IR and visible light detected simultaneously.

In a further preferred embodiment, both sensitive zones for visible light and sensitive zones for IR radiation are integrated per pixel of the sensor. This can not only be advantageous in the case of special reflection properties of objects in the scene, even with extraneous energy radiations, for example due to a radiant heater, a floodlight, the sun, etc., corresponding external light can be particularly well discriminated against by "desired" radiation characterizing the scene.

According to a further embodiment of the invention, the sensor system further comprises a lighting device for illuminating the scene with an illumination light having a predetermined lighting characteristic. This has the advantage that the described sensor system can also be used in low light conditions and still good recognition results (of objects) of the scene can be achieved. The illumination device can be coupled to the data processing device and controlled by it in a suitable manner. For example, the illumination device can be operated only in comparatively short periods of time and with a certain repetition rate, thus saving energy. Of course, then the scene detection by the sensor with the "clocked lighting" should be synchronized.

It should be noted that, for example, in the case of passage areas of closable openings in buildings, which are monitored by light field cameras, a distinction can be made between so-called passive lighting and so-called passive lighting. Active illumination is realized by one or more illumination devices described above. Passive lighting is based on extraneous light sources, which may be natural light sources such as the sun and / or other external sources of light, such as a street lighting lamp, with respect to the described sensor system.

1. (1) Eine Objekterkennung innerhalb der Szene funktioniert aus einer durch die Lichtfeldkamera gewonnen „Punktwolke“ ausreichend zuverlässig. Dies kann von der Datenverarbeitungseinrichtung beispielsweise durch geeignete Plausibilitätsüberprüfungen festgestellt werden.
2. (2) Durch einen Anlernprozess kann eine „leere Szene“ (ohne Objekt aber optional mit vorhandenen Störfaktoren wie zum Beispiel Schnee und Regen) analysiert werden. Bei einer nachfolgenden Erfassung einer „nicht leeren Szene“ können dann Änderungen gegenüber der „leeren“ Szene zuverlässig erkannt und einem Objekt zugeordnet werden. Optional kann bei Berücksichtigung der Tatsache, dass keine freischwebenden Objekte erkannt werden dürfen, eine vereinfachte und diese Prämisse erfüllende Erkennung von in der Szene befindlichen Objekten vorgenommen werden. Dies kann auch den Vorteil einer Reduzierung der Rechenleistung (und damit der von dem Sensorsystem verbrauchten Energie) mit sich bringen. Eine solche Energieersparnis kann insbesondere bei einer ständigen Überwachung von Fluchtwegen und Fluchttüren große Vorteile bieten.

In bright ambient conditions generated by such extraneous light sources can be dispensed with an active lighting, if at least one of the following points can be fulfilled:

1. (1) An object recognition within the scene functions sufficiently reliably from a "point cloud" obtained by the light field camera. This can be determined by the data processing device, for example by suitable plausibility checks.
2. (2) Through a learning process, an "empty scene" (without object but optionally with existing disturbing factors such as snow and rain) can be analyzed. In a subsequent detection of a "non-empty scene" then changes against the "empty" scene can be reliably detected and assigned to an object. Optionally, taking into account the fact that no free-floating objects may be detected, a simplified and this premise fulfilling detection of objects located in the scene can be made. This can also bring with it the advantage of reducing the computing power (and thus the energy consumed by the sensor system). Such energy savings can offer great advantages, in particular with constant monitoring of escape routes and escape doors.

Even in consideration of the above-mentioned considerations for omitting active illumination, additional lighting for the light field camera can be provided in situations with difficult lighting conditions by means of the (additional) illumination device described above. Such difficult lighting conditions may be present, for example, in relatively dark (enclosed) spaces, outside buildings in the dark, fog, snow, rain, sleet, wind-swept vegetation, etc. However, it is understood that for this mode of operation Lighting energy should be optimized. This can be achieved in particular by varying the light intensity of the illumination. Thus, the reflected light quantity arriving at the light field camera can be optimized.

According to a further embodiment of the invention, the illumination device configured to emit the illumination light with a time-varying illumination characteristic, wherein in particular the temporal change of the illumination characteristic depends on the result of the evaluated by the data processing device scene. In this embodiment, in particular a dynamic, given by situational use or determined by learning adjustment of the lighting can be made. In this case, for example, a different light reflectivity of (movable) objects and / or backgrounds of a scene can be taken into account. Such a dynamic adjustment of the illumination can lead to significant energy savings (if active illumination is required by the sensor system described according to the exemplary embodiment described here).

According to a further exemplary embodiment of the invention, the illumination device is configured to emit the illumination light with a locally variable illumination characteristic, wherein in particular the local variation of the illumination characteristic depends on the result of the scene evaluated by the data processing device.

Illustratively, the illumination device ensures spatially inhomogeneous illumination of the scene, with characteristic features of the illumination, in particular the intensity of the illumination, being dependent on the solid angle of the beam path, via which the scene or in particular the object located therein is optically detected. In this case, it makes sense, of course, if those subregions of the scene in which the at least one object is located or in which the at least one object is suspected are illuminated with a higher illumination intensity compared to the other subregions of the scene. Furthermore, the (expected) distance of the at least one object can be taken into account when selecting or setting a suitable illumination intensity. Specifically, more distant objects are illuminated with a higher illumination intensity and thereby at least approximately compensates for the effect of the expansion of light beams of the illumination light.

Furthermore, by suitable focusing or optical imaging of the illumination light, care can be taken that at least partial areas of the scene are not illuminated completely but by means of discrete illumination light structures, for example light points or light lines, which are disputed from one another. This represents another possibility for an effective energy saving with respect to an active illumination. In this connection it is pointed out that the spacing of adjacent illumination light structures should be smaller than the minimum size of the objects or object parts to be detected. Optionally, it can also be taken into account that the illumination structures and their distances from each other increase or expand with increasing distance from the sensor. This means that, for detection of objects located farther away, the light beams of the illumination light or the illumination structures in the illumination light must not spread too much in order to ensure sufficient illumination and thus reliable detection of the object.

Preferably, the illumination device is (communicatively) coupled to the data processing device, so that the operation of the illumination device can be controlled by the data processing device. More preferably, this control is done depending on the current characteristics of the scene, so that the lighting dynamically adapted to changing scenes and always optimal lighting of the scene can be achieved. In this case, in particularly preferred embodiments, the illumination or the illumination intensity may depend on the brightness or the optical reflectivity of the surface of the object. Specifically, this means that in bright or highly reflective objects, the intensity of the illumination light can be smaller than in dark or weakly reflective objects.

According to a further embodiment of the invention, the illumination characteristic is determined by at least one of the following features: (a) intensity for at least a portion of the scene, (b) intensity differences between different portions of the scene, (c) wavelength, (d) spectral intensity distribution, ( e) polarization direction, and (f) intensity distribution for different polarization directions. By an application-specific use of one of these features or by a suitable combination of at least two of these features, the objects to be recognized can be illuminated particularly well and recognized as a result with particularly high accuracy and reliability.

With regard to the size of the subregions of the scene, there are no particular restrictions. In extreme cases, a partial area can be assigned to exactly one pixel of the sensor.

The wavelength, frequency or color of the illumination light can be varied by a suitable control of spectrally different light-emitting elements, in particular LEDs with different colors, or adapted to the expected characteristic of the scene. The polarization direction of the illumination light may be known For example, be set by the use of polarizing filters.

All mentioned characteristic features can optionally be adapted dynamically to changing scenes, so that the best possible illumination of the scene can always be achieved. In this case, an optimal lighting characteristic can also be determined according to the principle of "try-and-error" or by other statistical optimization procedures. This can be done dynamically during a real operation of the sensor system or as part of a calibration by means of a detection of suitable reference objects.

According to a further aspect of the invention, a method is described for determining the characteristic of a scene with a sensor system and in particular with a sensor system of the aforementioned type. The method comprises (a) three-dimensional optical detection of the scene and of an object contained in the scene by means of a sensor based on the principle of a light field camera; and (b) evaluating the optically detected scene by means of a data processing device connected downstream of the sensor, wherein motion profiles are determined in real time by an object contained in the scene.

The described method is also based on the knowledge that the use of a sensor designed as a light field camera can detect moving objects in an energy-efficient manner and determine their motion profile in real time (by means of the data processing device connected downstream of the optical sensor).

According to a further exemplary embodiment of the invention, the method further comprises illuminating the scene with an illumination light which is emitted by an illumination device and which has a predetermined illumination characteristic, wherein the illumination characteristic has a specific maximum illumination intensity for a predetermined subarea of the scene. As a result, it can be advantageously prevented that some areas of the scene are "overexposed". A determination of the level of this maximum illumination intensity can take place by means of a calibration automatically and / or cyclically in each case after a predetermined operating period of the described sensor system. The maximum illumination intensity level may also be dynamically adjusted during operation of the sensor system by appropriately using data processing device results for a corresponding intensity adjustment of the illumination light.

According to a further embodiment of the invention, the method further comprises comparing the detected object with at least one comparison object; and, if the object agrees with a comparison object within predetermined permissible deviations, identifying the object as an object authorized for a particular action.

The approved action may, for example, be an authorized passage through an opening in a building, which opening is closed by a closure body prior to identification as an approved object and is opened only after successful identification by a corresponding movement of the closure body. The objects to be identified may preferably be persons and / or vehicles. Successful identification may be to control or activate a closure mechanism for a closure body prior to opening a building.

By using the 3D (depth) information of the sensor designed as a light field camera, for example, a reliable face recognition can be realized in persons, which can be used to activate a shutter mechanism. Certain areas of the scene can be particularly illuminated and provided with an increased resolution, which in turn leads to an energy reduction compared to monitoring the entire scene in high definition or with full illumination.

Instead of persons embossed signs, in particular license plates of vehicles can be reliably detected and recognized in other embodiments. Namely, by the 3D information, the embossing of the mark can be recognized well, resulting in improved reading reliability. In particular, a possible counterfeiting of a license plate can be better recognized in this way.

According to a further aspect of the invention, a use of a sensor system with a sensor based on the principle of a light field camera, in particular of a sensor system described above, for controlling a coverage characteristic of an opening to be passed through an object by at least one closure body is described.

The described use of the sensor system having a light field camera is based on the finding that an energy-efficient detection and evaluation of an optical scene can be advantageously used in passages which are closed by a closing body can be. This applies in particular to passages which have a closure or a cover characteristic which is controlled or at least co-controlled by the described sensor system. Since such sensor systems are usually supplied with energy by the closure systems for the closure bodies, it is particularly important to manage with a comparatively small amount of energy and nevertheless to come to reliable scene evaluations. The inventive use of a trained as a light field camera sensor can be monitored in an energetically efficient manner and larger distances, which naturally leads to an earlier detection of an opening requirement of the closing body, which can be of great advantage especially for fast moving objects. Furthermore, the scene can be detected with a wider detection angle, which can lead, for example, to an early detection of transverse traffic moving transversely to the opening and thus to a more reliable detection of objects in the security area of the closure system.

According to one embodiment of the invention, the opening is an entrance or an exit, in particular an emergency exit in a building. By recognizing an existing, but possibly non-moving object in one pass, an input or output, in particular a blocked emergency exit can be detected and this information is transmitted to an affiliated system, for example to a monitoring system.

According to a further embodiment of the invention, the object is a person or a vehicle. In this case, the building may in particular be a house or a garage.

According to a further aspect of the invention is described a use of a sensor system with a sensor based on the principle of a light field camera, in particular a sensor system described above, for detecting and / or controlling traffic flows of objects which move through a scene of the sensor system, wherein the scene is determined by a spatial detection range of the sensor system.

This described use is also based on the finding that an energy-efficient sensor system is important in traffic detection and / or traffic flow control, since this sensor system is typically constantly in operation. The objects relevant to the traffic flow in question can be, for example, persons, vehicles, products such as e.g. Be packages, suitcases, etc. Since a plurality or even a multiplicity of 3D sensors are usually used for such applications, energy savings have a particularly positive effect here.

It should be noted that embodiments of the invention have been described with reference to different subject matters. In particular, some embodiments of the invention are described with apparatus claims and other embodiments of the invention with method claims. However, it will be readily apparent to those skilled in the art upon reading this application that, unless explicitly stated otherwise, in addition to a combination of features belonging to a type of subject matter, any combination of features that may result in different types of features is also possible Subject matters belong.

Before describing exemplary embodiments of the invention with reference to the drawing, some technical considerations in connection with the invention are presented below.

A light field camera allows a three-dimensional detection of a scene in a known manner. Particularly in the technical field of monitoring a closing area of an opening which can be closed by a closing body and / or controlling the movement of such a closing body, a sensor system which has high energy efficiency or low energy consumption is of great advantage. The same applies to (constantly in operation) sensor systems for monitoring and / or controlling traffic flows. In sensor systems with their own (active) lighting device, this contributes significantly to energy consumption. Therefore, high "light efficiency" not only of the illumination but also of the sensor device is of great importance.

In the knowledge of this fundamental importance of the highest possible optical energy efficiency can be saved by a low resolution significantly lighting energy and still ensure that a sufficient amount of light energy or light output is incident on the sensor. The decision criteria required for certain applications with regard to a reliable detection of an object of the scene can be determined by a suitable interpretation of additional optical features of the detected radiation energetically more favorable than could be achieved by a higher resolution. Such an interpretation can be made in particular by the data processing device of the described sensor system.

Particularly in the case of recognition and tracking of the object, it is of great importance to reliably interpret object parts with similar optical properties which belong together in the respectively detected scene as belonging to an object. Since connected object parts very often have similar properties, a sensor system that recognizes such properties can form a corresponding relationship and save computing power and therefore also energy.

Such similar properties may be patterns, colors, reflection properties over an arbitrarily wide optical spectrum, polarization direction of the detected light, optical contrasts, etc. Furthermore, with regard to the sensor system, internal factors such as the properties of a separate illumination by a lighting device and / or external illumination in the optical detection of the scene and thus also in the subsequent evaluation of the optically detected scene can be taken into account.

Thus, e.g. It should be appreciated that light rays reflected from extraneous light (e.g., sunlight) have a different polarization direction than the light intended to be used to detect the scene. Also spectral influences such as the fact that e.g. Red surfaces reflect little blue and green light, can be used as valuable additional information in the evaluation or interpretation of the optically captured scene (and thereby compared to a disregard of this additional information) energy can be saved. Furthermore, disturbing influences can be masked out by a targeted (dynamic) optimization of the lighting characteristic of a separate active lighting.

An embodiment of the invention achieves energy savings by means of dynamic lighting energy optimization using illumination energies of different wavelengths or frequencies. In this case, depending on the color of the object, the wavelengths which lead to the most intense reflections or light scattering can be emitted with a lower illumination energy, for example. In contrast, other wavelengths or other wavelength regions are illuminated with less reflection or scattering with a higher intensity. Thus, for example, a red object is illuminated primarily with a red light component and the green and the blue light component are reduced (for the relevant solid angle), preferably to at least approximately an intensity of zero. The same principle can also be applied in the relationship between visible light and infrared (IR) light.

The above-described additional information or additional optical features of the detected radiation (per pixel and with the associated distance and solid angle) can be of great advantage in determining the motion profile of objects according to the invention, since in this way simple objects can be detected and tracked. In addition, functional relationships of spatial points (to one and the same object) can additionally be grouped and interpreted in a grouping manner via the additional information mentioned.

If the sensor system described in this document is used for securing and / or activating a closing body on a passage, it is additionally possible to work with different resolutions and measuring safety. For example, in the context of securing a sliding door or a vertical door drive, the fact that the safeguarding of a closing function with the risk of entrapment associated therewith must take place only in the immediate vicinity of the closing body. Thus, in the sense of energy optimization, in particular, this zone can be monitored immediately before or during the closing process with a high resolution. Other areas of the scene, e.g. the areas where the closing body has already passed can be monitored at a lower resolution, which leads to energy savings.

Further advantages and features of the present invention will become apparent from the following exemplary description of presently preferred embodiments. The individual figures of the drawing of this document are merely schematic and not to scale.

list of figures

• 1 shows the use of a sensor system for controlling a coverage characteristic of an opening by means of closing bodies formed as sliding doors.
• 2 shows the use of a sensor system for detecting a traffic flow of transported on a conveyor belt objects.
• 3a to 3c show various embodiments of a sensor chip for in 1 illustrated light field camera.

Detailed description

It should be noted that in the following detailed description features or components of different embodiments, with the corresponding features or Components of another embodiment are the same or at least functionally identical, are provided with the same reference numerals or with reference numerals, which are identical in the last two digits with the reference numerals of corresponding same or at least functionally identical features or components. In order to avoid unnecessary repetitions, features or components already explained on the basis of a previously described embodiment will not be explained in detail later.

It should also be noted that the embodiments described below represent only a limited selection of possible embodiments of the invention. In particular, it is possible to suitably combine the features of individual embodiments with one another, so that a multiplicity of different embodiments are to be regarded as obviously disclosed to the person skilled in the art with the embodiment variants explicitly illustrated here.

1 shows the use of a sensor system 100 for controlling a coverage characteristic of an opening 184 depending on the characteristics of one of the sensor system 100 watched scene 190 , According to the embodiment shown here, the opening is an entrance opening for persons in a building or a garage entrance for motor vehicles in a garage. The corresponding input structure is denoted by the reference numeral 180 Provided.

The entrance structure 180 includes a stationary support structure 182 which a frame and a guide for two designed as a sliding closure body 186 represents. The sliding doors 186 can each by means of a motor 187 along the displacement directions represented by two thick double arrows. The control of the motors 187 takes place, as set out below, via the sensor system described in this document 100 ,

The sensor system 100 has a vision system 110 , a data processing device 140 as well as a database 150 on. In the vision system 110 are all optical components of the sensor system 100 accommodated. On a housing of the vision system 110 is a holder 111 intended. By means of this holder 111 is at least the vision system 110 at the stationary support structure 182 mounted in a mechanically stable and spatially fixed manner. The sensor system is preferred 100 (in contrast to the representation of 1 ) is constructed as a module, which is within a compact design next to the vision system 110 also the data processing device 140 as well as the database 150 having. A connection 160 can be an interface to an affiliated system, for example to a monitoring system, which system is signaled at least one detected object property. The corresponding signaling data may include, for example, the information that an escape route is blocked, that a license plate advertised for the search was recognized, that a parking lot was illegally occupied, that a suspicious object is in the monitored scene 190 is located, etc.

The vision system 110 includes one as a light field camera 120 trained sensor for spatially detecting a scene 190 in which there is an object 195 located. The corresponding sensor data are sent to the data processing device in real time 140 to hand over. According to the exemplary embodiment illustrated here, the detected optical scene is based on this sensor data 190 evaluated by suitable methods of image analysis and thereby a motion profile of the object 195 determined. For this purpose, within a certain time intervals, a picture of the scene is created 190 detected, so that the data processing device 140 is able, based on corresponding positional shifts of the object 195 not only to determine its velocity as an absolute value but as a motion vector (with a directional information). A knowledge of the motion profile of the object 195 can then be used to advantage, the two motors 187 suitably from the data processing device 140 to drive, with a closed opening 184 the sliding doors 186 only be opened when the object 195 actually in the direction of the opening 184 emotional. If it is the object 195 is a vehicle of a so-called cross traffic, which is essentially at the opening 184 is moved past, then the corresponding motion vector from the data processing device 140 recognized and there is no opening of the sliding doors 186 ,

After passing the object 195 through the opening 184 This can be quickly closed again to prevent passing of other objects. In this context, it is obvious that not only the time at which the opening must be released, but also the period for which the opening 184 must be kept open of the speed of the object 195 Depends on this in the direction of the opening 184 and through the opening 184 moved through. Through a recognition of the object 195 can optimize the operation of the input structure 180 by a suitable control of the motors 187 For a person, a passage should be opened sooner in comparison to inanimate objects, and should be closed later People are afraid of colliding with the sliding doors 186 to take.

According to the embodiment shown here, the sensor system 100 Furthermore, able to make an object detection. This is done by the data processing device 140 to one in the database 150 filed record of reference objects that correspond to those objects that are authorized, the opening 184 to happen. This means that at a suitable approach of the object 195 to the entrance 184 the sliding doors 186 only be opened when the detected object 195 at least approximately coincident with one of the stored reference objects. This clearly indicates that in the use of the sensor system described here 100 the coverage characteristic of the opening 184 not just the movement profile of the object 195 depends, but that also an access control takes place.

To the scene 190 with the object contained therein 195 detect with the highest possible accuracy (even with relatively poor lighting conditions), the sensor system has 100 and more specifically the vision system 110 a lighting device 130 on which a lighting light 130a can send out to the scene 190 to brighten up. According to the exemplary embodiment illustrated here, the illumination device has two illumination units. It should be noted that the lighting device 130 next to the in 1 Lighting units shown may also have other lighting units that the scene 190 illuminate from another angle. Also, the two lighting units can also be outside the housing of the vision system 110 arranged and thus by the light field camera 120 be further spaced.

For reasons of energy efficiency, the lighting device should 130 be operated such that with minimal energy consumption by the lighting units as accurate as possible scene detection or object detection is possible. Depending on the application, various measures can be taken.

(A) The scene 190 does not become continuous with the illumination light 130a but illuminates the illumination light 130a is emitted in the form of short light pulses, so that during these short light pulses, the illumination intensity is very high. Of course, in this case, the operation of the light field camera 120 with the pulses of the illumination light 130a be synchronized in time. The time periods between two such "pulses of exposure and image acquisition" may depend on the speed of the object 195 depend on which has been previously determined. In order to determine the movement profile as accurately as possible, it makes sense to move fast moving objects 195 to perform the "exposed images" with a high repetition rate. Through such a situation-adaptive repetitive evaluation of the scene 190 can be a good compromise between energy consumption especially the lighting device 130 and the accuracy of determining the motion profile (in real time).

(B) The spectral distribution of the illumination light can be adaptive to the visual appearance of the object 195 be adjusted. For this purpose, a spectral distribution is preferably selected, which provides for an illumination in which the object 195 can be recognized as well as possible.

(C) Further, the illumination light 131 have a temporally and / or locally variable lighting characteristic. This lighting characteristic can also be adaptively dependent on the previous image evaluations of the object 195 by the data processing device 140 respectively. With a locally inhomogeneous lighting characteristic, it makes sense, of course, if those parts of the scene 190 in which the object is 195 or in which the object is suspected, with one compared to the other portions of the scene 190 be illuminated higher illumination intensity.

(D) Further energy saving possibilities result from the utilization of different polarization directions of the illumination light 130a which can be adjusted in particular by the use of polarizing filters or filtered out of the originally emitted light.

It should be noted that also the capture of the scene 190 Captured light can be performed in various ways, which lead to a more or less strong energy savings. This will be explained below with reference to 3a . 3b , and 3c explained in more detail.

2 shows a further use or a further use of the sensor system 100 , For clarity, is in 2 only the vision system 110 of the sensor system 100 shown.

According to the embodiment illustrated here, the vision system captures 110 a traffic flow of (different) objects 295a . 295b . 295c . 295d and 295E , which are on a conveyor belt 298 and along the direction of movement represented by an arrow a scene 290 move through. Reliable knowledge of the number and / or type of objects 295a - 295E can be used in the field of logistics for traffic flow control. Only one example of such a control of a traffic flow is the control of the luggage transport in an airport. It can also labels on the objects 295a - 295E determine the type of the respective object. It should be noted, however, that use in an airport is just one example of a variety of other traffic control applications.

3a to 3c show various embodiments of a sensor chip for in 1 shown light field camera, with each of which a more or less strong energy savings in the detection of a scene can be realized.

3a shows a sensor chip 321a or its light-sensitive surface 321a which has a different spatial resolution in different partial regions or sensor regions. According to the embodiment shown here, the sensor chip 321a three different sensor areas 322a and 326a on. In the first sensor area 322a is the spatial density of the light-sensitive pixels 324 as high as the semiconductor architecture of the sensor chip 321a allowed. In the two sensor areas 326a each are four of the light-sensitive pixels (for a full resolution) to a parent pixel 328 (for a reduced resolution), making it one compared to a single pixel 324 a fourfold amount of light collected. This will change the light sensitivity of the sensor chip 321a (at the expense of spatial resolution) increased. By such a summarizing (English "Binning") the energy needed to evaluate the corresponding image area of the scene is reduced. Another probably even greater possibility of saving energy results from the fact that in the case of illumination by the lighting device described above, the corresponding image areas of the scene less or possibly even not need to be illuminated.

It should be noted that such an unequal spatial resolution does not lead to a reduced recognition reliability of an object when the subregions of the scene in which the object is located are captured with the full resolution, and other subregions of the scene, in particular backgrounds, be detected with the low resolution. It is further pointed out that the described summarization of pixels in some sensor chips can also be carried out dynamically or adaptively in exactly the subregions in which the object is currently located. In the case of a non-adaptive combination of pixels, the different sensor areas can also be realized by means of different sensor chips. This has the advantage that the costs for the different sensor chips can be lower than such a sensor chip with an adaptively adjustable spatial resolution.

3b shows a sensor chip 321b which has a different spatial resolution along different coordinate directions. Such asymmetric resolution can be achieved by combining pixels, with a smaller number of pixels merged along one direction than along the other direction. In this case, the smaller number can also be one, ie there is no aggregation of pixels. Again, the number of pixels that are combined can be adjusted adaptively by the data processing device independent of the previous or expected object positions.

According to the illustrated embodiment, the resolution along a y-direction is the full resolution that the sensor chip 321b allows. This resolution corresponds to the spacing of two pixels along the y-direction and is in 3b With " d " designated. In contrast, the resolution along the x-direction is only half as high, because each two individual pixels have been combined into one parent pixel. The resolution along the x direction thus corresponds to twice the distance between two adjacent individual pixels and is in 3b With " 2d " designated.

3c shows a sensor chip 321c which has a different spectral sensitivity in different sensor areas. 322 , In a first sensor area 322c is the sensor chip 321c optimized for detection of light in the visible spectral range. This is in 3c by the name " RGB "Illustrated. In the second sensor area 326c is the sensor chip 321c optimized for detection of light in the infrared spectral range. This is in 3c by the name " IR "Illustrated.

It should be noted that the spatial fixed and non-variable division into the two sensor areas 322c and 326c an embodiment in which suitable optical beamforming systems should be used to allow one and the same scene from both sensor areas 322c and 326c can be detected. In particular, a beam splitter can be used.

In another, for clarity, not shown in this document Embodiments are the two sensor areas 322c and 326c nested together. This means that in the plane of the sensor chip 321c the RGB Pixels and the IR Pixels are each arranged alternately and preferably can be activated dynamically or adaptively. Also conceivable are embodiments in which initially an image acquisition only in the visible range ( RGB ) and immediately or shortly thereafter a second image capture in the infrared range ( IR ) is performed (for example, by inserting a filter) and later the corresponding image information from the two spectral range are evaluated jointly by the data processing device. Of course, other combinations of image information acquired in different spectral range are possible.

Finally, it should be noted that the term "comprising" does not exclude other elements and that the "on" does not exclude a plurality. Also, elements described in connection with different embodiments may be combined. It should also be noted that reference signs in the claims should not be construed as limiting the scope of the claims.

LIST OF REFERENCE NUMBERS

100

sensor system

110

Vision system

111

holder

120

Sensor / light field camera

130

lighting device

130a

illumination light

140

Data processing device

150

Database

160

connection

180

input structure

182

stationary holding structure

184

Opening / entrance

186

Closing body / sliding door

187

engine

190

scene

195

object

290

scene

295a-e

objects

298

conveyor belt

321a-c

light-sensitive surface / sensor chip

322a / c

first sensor area

324

pixel

326a / c

second sensor area

328

parent pixels

QUOTES INCLUDE IN THE DESCRIPTION

This list of the documents listed by the applicant has been generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Cited patent literature

• US 7984590 [0005]
• EP 2453252 B1 [0006]

Claims (21)

A sensor system (100) for determining the characteristic of a scene (190), the sensor system (100) comprising a sensor based on the principle of a light field camera (120) for three-dimensional optical detection of the scene (190); and a data processing device (140) connected downstream of the optical sensor for evaluating the optically detected scene (190), wherein the data processing device (140) is configured such that motion profiles can be determined in real time from an object (195) contained in the scene (190). Sensor system (100) according to the preceding claim, further comprising a holder (111), which is mechanically coupled to the sensor (120), wherein the holder (111) is formed such that the sensor system (100) at one with respect scene to be detected (190) stationary support structure (182) is attachable. Sensor system (100) according to one of the preceding claims, wherein the data processing device (140) is further configured such that a coverage characteristic of an opening (184) to be passed by the object (195) is controllable by at least one closure body (186). The sensor system (100) of any of the preceding claims, wherein the sensor (120) includes a light detector (321a) having a plurality of pixels (324), and wherein the sensor (120) is configured to image the scene (190) based on at least one of To detect the following characteristics of detected optical radiation: Intensity on at least one pixel (324), Intensity differences between different pixels (324), - wavelength, - spectral intensity distribution, - Polarization direction, and - Intensity distribution for different polarization directions. Sensor system (100) according to one of the preceding claims, wherein the sensor (120) has a spatial resolution which is different in different sub-areas (322a, 326a) of a light-sensitive surface (321a) of the sensor (120). A sensor system (100) according to the preceding claim, wherein the spatial resolution of the sensor is dynamically adaptable to different characteristics of the scene (190). A sensor system (100) according to one of the two preceding claims, wherein the resolution of the sensor (120) is adaptable by combining adjacent pixels (324) of the light-sensitive surface (321a) of the sensor (120). Sensor system (100) according to one of the preceding claims, wherein the sensor (120) has a spatial resolution that is different along different coordinate directions (x, y). A sensor system (100) according to any one of the preceding claims, wherein the sensor (321c) comprises a first sensor region (322c) for at least a first characteristic of detected optical radiation and a second sensor region (326c) for at least a second characteristic of detected optical radiation, the second characteristic being different than the first characteristic feature. A sensor system (100) according to the preceding claim, wherein the first characteristic feature is a first spectral distribution and the second characteristic feature is a second spectral distribution, the second spectral distribution being different from the first spectral distribution. A sensor system (100) according to any one of the preceding claims, further comprising illuminating means (130) for illuminating the scene (190) with an illumination light (130a) having a predetermined illumination characteristic. Sensor system (100) according to the preceding claim, wherein the illumination device (130) is configured to emit the illumination light (130a) with a time-varying illumination characteristic, wherein in particular the temporal change of the illumination characteristic is dependent on the result of the scene evaluated by the data processing device (140). 190). Sensor system (100) according to one of the two preceding claims, wherein the illumination device (130) is configured to emit the illumination light (130a) with a locally variable illumination characteristic, wherein in particular the local variation of the illumination characteristic is dependent on the result obtained by the data processing device (140). evaluated scene (190) depends. Sensor system (100) according to one of the three preceding claims, wherein the Lighting characteristic is determined by at least one of the following features: intensity for at least a portion of the scene, intensity differences between different subregions of the scene, wavelength, spectral intensity distribution, polarization direction, intensity distribution for different polarization directions. Method for determining the characteristic of a scene (190) with a sensor system (100), in particular with a sensor system (100) according to one of the preceding claims, comprising the method three-dimensional optical detection of the scene (190) and of an object (195) contained in the scene by means of a sensor (120) based on the principle of a light field camera; and Evaluating the optically recorded scene (190) by means of a data processing device (140) connected downstream of the sensor (120), motion profiles being determined in real time by an object (195) contained in the scene (190). A method according to the preceding claim, further comprising illuminating the scene (190) with an illuminating light (130a) emitted by a illuminator (130) and having a predetermined illumination characteristic, the illuminance characteristic for a predetermined portion of the scene (190) has certain maximum illumination intensity. The method according to one of the two preceding claims, further comprising Comparing the detected object (195) with at least one comparison object; and, if the object (195) agrees with a comparison object within predetermined permissible deviations, identifying the object (195) as an object permitted for a particular action. Use of a sensor system (100) with a sensor (120) based on the principle of a light field camera, in particular a sensor system (100) according to one of the preceding Claims 1 to 14 for controlling a coverage characteristic of an opening (184) to be passed from an object (195) through at least one closure body (186). Use according to the preceding claim, wherein the opening is an entrance (184) or an exit, in particular an emergency exit in a building. Use according to one of the two preceding claims, wherein the object (195) is a person or a vehicle. Use of a sensor system (100) with a sensor (120) based on the principle of a light field camera, in particular a sensor system (100) according to one of the preceding Claims 1 to 14 for detecting and / or controlling traffic flows of objects (195) moving through a scene (190) of the sensor system (100), the scene (190) being determined by a spatial detection range of the sensor system (100).

Images