Operational assistance procedure, control unit, operational assistance system and work device

Abstract

Operational assistance procedure (S) for a work device (1), in which (S1) Object boxes (54) for an object (52) in a field of view of the work device (1) at successive time points or such object boxes (54) characterizing data are obtained, in which, at or for the step (S1) of obtaining the object boxes (54) and / or the object boxes (54) characterizing data are obtained, (S1a) a field of view (50) of the underlying working device (1) is optically captured two-dimensionally and monocularly by recording temporally successive images and (S1b) in successive recorded images at least one object (52) and an object box (54) associated with the object (52) are identified, (S2) from object boxes (54) of a given object (52) to successively or directly successively recorded images, an instantaneous scaling change or derived sizes of an object box (54) to the respective object (52) and an instantaneous lateral position change of the object box in the image (54) to the respective object (52) can be determined, (S3) from the current scaling change or quantities derived therefrom and the current lateral position change in the image to an object box (54) to a respective object (52) a future predicted object box (55) is determined and (S4) the position of the predicted object box (55) and / or the ratio of a lateral extent of the predicted object box (55) to a lateral extent of a captured field of view (50) and / or the captured images or a portion thereof are determined and evaluated and (S5) depending on the result of the evaluation (i) determines whether an object (52) underlying the predicted object box (55) is critical with respect to a possible collision or not, and / or (ii) controls or regulates an operating state of the working device (1), wherein an object (52) underlying a predicted object box (55) is determined to be non-critical with respect to a possible collision, in particular with a criticality value of 0%, if the predicted object box (55) is completely outside of an underlying image or a predefined section thereof.

Description

State of the art

[0001] The present invention relates to an operating assistance system for a work device or for a vehicle, a control unit for an operating assistance system of a work device, an operating assistance system as such, and a work device and in particular a vehicle.

[0002] In the case of work equipment, and particularly in the automotive sector, operational assistance systems and procedures are increasingly being used. These systems and procedures analyze the environment of the respective device for potential collisions with objects and issue corresponding warnings and / or intervene in the operation of the device. With known systems and procedures, comparatively complex systems and data structures are used, for example, with the evaluation of three-dimensional data, and / or the predictive power of the corresponding assessments of the environment is insufficient for intervening in the operation of the device, for example, for a braking decision.

[0003] Patent application US 2005 / 0131 646 A1 discloses a method for collision detection, comprising: detection of an object within a first operational area of ​​an object tracker; determination of a classification of the detected object with the object tracker; tracking of said object with the object tracker; detection of the detected object within a second operational area of ​​a collision detector; and activation of a safety measure by means of the collision detector based on the classification.

[0004] Document WO 2016 / 014 548 A1 discloses a method for operating a pedestrian collision avoidance system in a vehicle, comprising: sensing the vehicle's surroundings with a radar sensor and a video camera; transmitting radar information from the radar sensor and video information from the video camera to an electronic control unit; detecting an object in the video information with the electronic control unit; classifying the object as a pedestrian based on a comparison of the video information with a database; determining, with the electronic control unit, a distance between an object classified as a pedestrian and the vehicle based on the radar information; determining, with the electronic control unit, a feature of the object classified as a pedestrian based on the video information, the distance, and the database.Storing the feature of the object classified as a pedestrian in memory; and, when the object classified as a pedestrian is no longer detected by the radar sensor: Determining, with the electronic control unit, an updated distance to the object classified as a pedestrian, based on the video information and the feature of the object classified as a pedestrian; Determining, with the electronic control unit, whether there is a collision potential between the vehicle and the object classified as a pedestrian, based in part on the distance to the object classified as a pedestrian; and if the collision potential exists, activating an automatic vehicle response. Disclosure of the invention

[0005] In contrast, the operational assistance method according to the invention with the features of claim 1 has the advantage that a particularly reliable collision prediction can be generated for the operation of a work device using comparatively simple means. According to the invention, this is achieved with the features of claim 1 by creating an operational assistance method for a work device, and in particular for a vehicle, in which (S1) Object boxes for an object in a field of view of the work device at successive time points in time or data characterizing such object boxes are obtained, (S2) from object boxes of a given object to consecutively or directly consecutively recorded images, a momentary scaling change or scale change of an object box to the respective object and a momentary lateral position change of the object box to the respective object can be determined, (S3) from the current scaling change, scale change or derived quantities and the current lateral position change to an object box, a future predicted object box is determined for a given object and (S4) the position of the predicted object box and / or the ratio of a lateral extent of the predicted object box to a lateral extent of a captured field of view and / or the captured images are determined and evaluated and (S5) depending on the result of the assessment, (i) it is determined whether an object underlying the predicted object box is critical with respect to a possible collision or not, and / or (ii) an operating state of the work device is controlled or regulated.

[0006] According to the invention, the evaluation of the environment of the work device is based on so-called object boxes and correspondingly predicted object boxes and their size development in relation to a captured field of view. This data can be acquired essentially in two dimensions and determined with high accuracy.

[0007] In principle, the data associated with the object boxes can be provided externally, for example by optical detection units of conventional driver assistance systems.

[0008] According to the invention, it is provided that in step (S1) or for step (S1) of obtaining the object boxes and / or the data characterizing the object boxes, (S1a) a field of view of the underlying work device is optically captured in two dimensions and / or monocularly by recording successive images and (S1b) in successive recorded images or excerpts thereof, at least one object and an object box associated with the object must be identified.

[0009] As mentioned above, a key aspect of the present invention is the prediction of a detected object box's position relative to an object in the field of view in the future. Such a prediction can be performed in various ways.

[0010] The dependent claims describe preferred embodiments of the invention.

[0011] In one embodiment of the operational assistance method according to the invention, an object box predicted into the future is determined to at least a currently last captured image or a section thereof.

[0012] This is done in particular by iteratively determining and updating values ​​for the scaling or derived quantities of a respective object box, for the coordinates of a respective object box, for the translation of a respective object box and / or for the lateral width of a respective object box over a plurality of time increments up to a forecast period.

[0013] The forecast period and / or the time increments can be predetermined and fixed. However, it is also advantageous to make the forecast period and / or the time increments dependent on further operating parameters, for example, on the device's own speed and / or position, and in particular the vehicle itself, or on a previously predicted speed and / or position of one or more objects in the vicinity of the device, especially the vehicle. This allows for more frequent monitoring if required due to the number of objects in the vicinity and / or a comparatively high speed of the device and / or the objects. Conversely, the monitoring effort can be reduced in relatively light traffic or similar situations.

[0014] In this context, according to another embodiment of the operational assistance method according to the invention, the following steps can be carried out for each time increment - in particular in the specified order: (I1) Resetting or pre-populating the values ​​to be calculated in accordance with the allocation rules Scaling alt := Scaling neu BoxTranslationX alt := BoxTranslationX neu BoxBreite alt := BoxBreite neu BoxPositionLinks alt := BoxPositionLinks neu Box position right alt := Box position right neu , (I2) Update the scaling according to the following assignment rule New scaling:=1 / (2−old scaling) (I3) Update the horizontal or lateral object box translation according to the following mapping rule. BoxTranslationXnew:=BoxTranslationXold×Scalingold (I4) Update the horizontal or lateral object box width according to the following assignment rule. BoxBreiteneu:=BoxPositionRechttsalt−BoxPositionLinkssalt (I5) Predicting the horizontal or lateral box positions according to the following assignment rules BoxPositionLinksneu:=BoxPositionLinksalt+BoxTranslationXneu− 0.5×BoxBreiteneu×(Skalierungneu−1) / Skalierungneu BoxPositionRightNew:=BoxPositionRightNew+BoxTranslationXNew+ 0.5×BoxWidthNew×(ScalingNew−1) / ScalingNew where scaling alt , scaling neu the old or the new scaling of an object box, BoxTranslationX alt , BoxTranslationX neu the old or new displacement of an object box, box width alt , Box width neu the old or new width of an object box, BoxPositionLeft alt , BoxPositionLinks neu the old or the new position of the lower left corner of an object box (52) as the first x-coordinate of the respective object box as well as BoxPositionRight alt , BoxPositionRight neu to denote the old or the new position of the lower right corner of an object box as the second x-coordinate of the respective object box or its values.

[0015] Alternatively or additionally, the equations mentioned above can be replaced or supplemented by the following calculation rules. BoxPositionLinksneu:=(BoxPositionLinksaktuell+ BoxGeschwindigkeitLinksaktuell*TPra¨diction) / (1+ NormGeschwindigkeitaktuell*TPra¨diction), and BoxPositionRightNew:=(BoxPositionRightCurrent+ BoxSpeedRightCurrent*TPradiction) / (1+ NormSpeedCurrent*TPradiction), where BoxPositionLinks neu and BoxPositionLinks aktuell or BoxPositionRight neu and BoxPositionRight aktuell the new or current position of the left or the right box edge is and box speed left aktuell and Box Speed ​​Right aktuell the currently measured angular velocity the left or right box edge is and standard speed aktuell the currently measured so-called normalized or standardized value Box speed is and T Prädiktion The prediction time is that associated with the prediction time step. The standard speed aktuell is or is derived in particular from the calculated scaling change of the object box.

[0016] In a specific embodiment of the operational assistance method according to the invention, it is provided that an object underlying a predicted object box is determined as critical with regard to a possible collision, in particular with a criticality value of 100%, if the proportion of the width of the predicted object box to the object in relation to the width of an underlying image or a predetermined section thereof exceeds a predetermined first threshold value. The threshold must be applied to each vehicle model and / or for each new one.

[0017] In this context, it is particularly advantageous if the value of a criticality assigned to an object is reduced by the proportion by which the object box predicted for the object is positioned outside the underlying image or the specified section thereof in its width.

[0018] According to the invention, it is provided that an object underlying a predicted object box is determined as non-critical with regard to a possible collision, in particular with a criticality value of 0%, if the predicted object box lies completely outside the underlying image or the specified section.

[0019] In order to take into account the most realistic scenario possible when predicting the object boxes in the future, according to another advantageous further development of the operational assistance method according to the invention, it is provided to identify a pedestrian as the object, to examine and evaluate the position and movement of the pedestrian as the object based on a pedestrian model, to determine an acceleration capability of the pedestrian as the object based on a speed determined for the pedestrian, and to determine the criticality for the pedestrian as the object based on the speed and the acceleration capability.

[0020] It is particularly advantageous if, based on the acceleration capability, an extended predicted object box is generated that encloses the predicted object box or at least encompasses it laterally or horizontally, and this is used as the basis for assessing criticality.

[0021] According to a further aspect of the present invention, a control unit for an operating assistance system of a work device and in particular of a vehicle is also created.

[0022] The control unit according to the invention is designed to control, execute and / or operate an underlying operational assistance system according to an operational assistance method according to the invention.

[0023] Furthermore, the present invention also relates to an operating assistance system for a work device and, in particular, for a vehicle as such. The operating assistance system is configured to execute an operating assistance method according to the invention. For this purpose, the operating assistance system includes, in particular, a control unit designed according to the invention.

[0024] Furthermore, the present invention also provides a working device which has an operational assistance system according to the invention.

[0025] The work device is designed in particular as a vehicle, motor vehicle or passenger car.

[0026] According to a further aspect of the present invention, the use of the inventive operating assistance method, the inventive control unit, the inventive operating assistance system and / or the inventive working devices for pedestrian protection, for cyclist protection, for ACC and / or for avoidance systems or methods is also proposed. Brief description of the characters

[0027] With reference to the attached figures, embodiments of the invention are described in detail. Fig. Figure 1 shows a schematic top view of a working device according to the invention in the form of a vehicle, in which an embodiment of the operational assistance method according to the invention can be used. Fig. Figures 2 to 4 show schematic side views of various scenes in a field of view, which can be evaluated using the operational assistance method according to the invention. Fig. 5 and Fig. Figure 6 shows flowcharts of an embodiment of the operational assistance method according to the invention or of the iterative determination of a predicted object box. Preferred embodiments of the invention

[0028] The following are, with reference to the Fig. Sections 1 to 6 describe exemplary embodiments of the invention and the technical background in detail. Identical and equivalent elements and components, as well as those acting in the same or equivalent way, are designated by the same reference numerals. Detailed descriptions of the designated elements and components are not provided in every instance where they occur.

[0029] The features and other properties shown can be isolated from one another and combined in any way without leaving the core of the invention.

[0030] Fig. Figure 1 shows a schematic top view of a working device 1 according to the invention in the form of a vehicle 1', in which an embodiment of the operating assistance method S according to the invention can be used.

[0031] The vehicle 1' according to the invention is formed in its core by a body 2 on which wheels 4 are mounted, which can be driven via a drive unit 20 by means of a drive train 12, and can be braked and / or steered via a steering and brake unit 30 and via a corresponding brake and / or steering train 13.

[0032] Furthermore, one embodiment of the operational assistance system 100 according to the invention is a component of the vehicle 1' according to the invention as a work device 1 within the meaning of the present invention. The operational assistance system 100 consists of a camera unit 40 for monocular imaging of a field of view 50 from the surroundings of the vehicle 1'. The field of view 50 contains a scene 53 with a pedestrian 52' as object 52.

[0033] The control unit 10 is connected via a control and detection line 11 on the one hand to the camera unit 40 and on the other hand to the drive unit 20 and the brake and / or steering unit 30 for control purposes.

[0034] At the in Fig. In the embodiment shown in Figure 1, images 51 of the scene 53 captured by the camera unit 40 from the field of view 50 are transmitted to the control unit 10 via the control and acquisition line 11 and evaluated there in connection with the operating assistance method S according to the invention.

[0035] According to the invention, in connection with the pedestrian 52' as object 52 in each image or frame 51, an object box 54 and parameters relating to position changes and scaling changes, angular velocities of the box edges and / or derived sizes of the object boxes 54 are determined from object boxes for temporally directly successive images 51 and are used as the basis for a prediction to specify a predicted box 55 for the object 52 on the basis of an interactive method I.

[0036] Fig. Figures 2 to 4 show schematic side views of various scenes 53 in a field of view 50, which can be evaluated using the operational assistance method S according to the invention.

[0037] In the Fig. In the situation depicted in scene 53, a pedestrian 52' is located as object 52 in the field of vision 50, which is connected to the in Fig. The camera unit 40 shown in Figure 1 is depicted in an image or frame 51. If necessary, the image or frame 51 is limited by a corresponding section or part 51'.

[0038] First, an object box 54 is derived for the pedestrian 52'. Compared to an object box 54 from a temporally preceding image or frame 51, a scaling change and the degree of displacement or translation of the object box 54, angular positions, angular velocities of the box edges, and / or derived quantities are then determined. From these quantities, a prediction regarding an expected predicted object box 55 for an elapsed prediction period can then be made in the iterative procedure I described above, with steps I1 to I5, over a number of time increments. In this way, the given object box 54 can be extrapolated with respect to its position with the lower right and left corners and width 55b to a predicted object box 55 for a prediction period into the future.

[0039] For the evaluation, the width 55b of object box 55, predicted to be present for the forecast period in the future, is compared with the width 51b of section 51' of image 51. If their ratio exceeds a predefined first threshold, object 52 is considered critical with a criticality of 100%.

[0040] While this criticality value can already be used, according to the invention, to send a warning to the user of the work device 1 and, in particular, to the driver of the vehicle 1', or to intervene directly in the operating procedure of the work device 1, it is also conceivable, if the object 52 is a pedestrian 52', to incorporate further aspects of the object 52 in a realistic manner, for example, a predicted acceleration behavior or the like.

[0041] For this purpose, the current speed of pedestrian 52' (object 52) ​​and its size can be derived and used as input parameters for a pedestrian model. The pedestrian model then outputs corresponding values ​​for expected acceleration or acceleration behavior. These values ​​can be used to calculate the following: Fig. 3 and Fig. 4 to construct a comprehensive or enclosing object box 56 whose right and left sections 56r and 56l, which extend beyond the originally predicted object box 55, represent uncertainty areas with respect to a positive or negative acceleration behavior of the pedestrian 52' as object 52.

[0042] Fig. 5 and Fig.Figure 6 shows flowcharts of an embodiment of the operational assistance method S according to the invention or of the iterative determination I of a predicted object box 55, as already discussed above in connection with the general description of the present invention.

[0043] In this context, it should also be mentioned that the iterative method I essentially forms step S3 of the embodiment of the operational assistance method S according to the invention, wherein in step I6 it is checked whether the forecast period has already been reached by the expiry of the time increments and / or whether another termination condition for the iteration exists.

[0044] An alternative or further termination condition can be seen, for example, in connection with exceeding a second threshold value by the width of the predicted object box 55 compared to the width of the image 51 or the section 51', where the second threshold value is greater than the first threshold value.

[0045] These and other features and properties of the present invention are further explained in the following sections: The present invention describes measures by which criticality measures for a collision warning system - for example as part of an operating assistance system of a work device and in particular of a vehicle - can be determined solely on the basis of measurement data from a monocular video system.

[0046] Commonly used collision indicators for this purpose are "Time-To-Collision" (TTC) and "Time-To-Brake" (TBB). These indicate when a collision will occur or when braking must be initiated to prevent a collision. The parameters TBB and TTC can be reliably calculated based on data from a mono video camera and primarily from the scaling changes of object boxes, without the need to determine distances, relative velocities, and relative accelerations.

[0047] Another collision indicator is the "Constant Bearing" (CB) value, which originally comes from shipping and indicates whether, with constant self-movement and constant object movement, one is on a collision course with another object. CB can also be calculated purely on the basis of mono video data, i.e., on a two-dimensional data basis.

[0048] The state of the art for criticality calculations is the use of a 3D-based world coordinate system.

[0049] The basis for such a procedure is the use of three-dimensional data or 3D data, for example in the sense of distances, relative velocities and relative accelerations - which can only be determined with a mono camera or monocular camera in a limited quality and by estimation.

[0050] The CB concept is difficult to understand, difficult to parameterize, does not allow prediction into the future, and does not allow the use of pedestrian movement models.

[0051] The concepts of TTC / TTB alone are insufficient for a braking decision, as they only consider the temporal aspect and not whether an object is on a collision course. For example, the concepts of TTC and TTB do not allow for any conclusions about whether an object will be passed.

[0052] The new and inventive two-dimensional or 2D-based approach for criticality calculation is based purely or essentially on measured two-dimensional or 2D data or signals and in particular on the determination of so-called box coordinates for object boxes as well as the parameters of the scaling change, the box translation, the angular positions and / or the angular velocities, which describe a change in scale or size or a movement or displacement of a respective object box in an image or frame or in the respective section of an image or frame and which, together with the box coordinates, are available or can be determined in high signal quality.

[0053] The approach according to the invention also includes a prediction, forecast or prediction into the future - namely with regard to the position of a respective object box 54 and its size / width or change in size / width - and thus allows the use of pedestrian movement models according to the invention.

[0054] Pedestrian movement models can therefore be used to predict the location area of ​​a pedestrian 52'. Models of a pedestrian's acceleration capability in various states of motion—for example, standing, walking, running, or sprinting—are used to make a statement about where the pedestrian 52' might be in the future. The criticality value is calculated from the overlap between the predicted or forecasted location area and the predicted or forecasted potential location area 56 of the pedestrian 52'.

[0055] The inventive approach is easier to understand and parameterize than the pure CB concept, and an experimental evaluation shows that the inventive approach delivers better results than is possible with CB implementations and conventional 3D-based methods based on 3D data estimated with a monocular camera.

[0056] A prediction can and generally is performed for each captured image or frame. For each captured image or frame, a target time interval, for example, 2 seconds, is set. The prediction is therefore made for this target time interval in the future. This target time interval is divided into multiple, for example, equal time increments. However, the target time interval and / or the time increments can also be variable and dependent on, selected from, and determined by other operating parameters.

[0057] The following processes are performed for each captured image or frame: - Capturing the lateral box coordinates of a respective object box 54 of a given object 52 in the field of view 50. - Capturing the scaling change of object box 54 of an object 52 in relation to one or more preceding images or frames. - Capturing the box movement, box displacement or box translation (unit pixel), angular positions and / or angular velocities of the box edges of an object box 54 of a given object 52 in the field of view 50 in the lateral direction with respect to the preceding image or frame or part or section thereof. - For the specific prediction or forecast, the procedure already described above with methods S and I is used as the basis for n time increments up to the target time period as the forecast period. - In each of the n cycles - i.e. for each time increment until the predetermined target time span is reached - the predicted box width is compared with the image width of the camera image 51 or with the width of a predetermined part or section 51' thereof. - The ratio of the box width in the image to the image width or the width of the cropped area can be used to determine a measure of criticality. As soon as the box width 55b occupies a certain width 51b of the image 51 or the cropped area 51' and thus exceeds a threshold value - e.g., 35% - a criticality of 100% is assumed and set. - On the other hand, if the predicted or forecasted box 55 lies, for example, partially or completely outside the image 51 or the section 51', the situation is non-critical, the criticality value is set to 0%. Depending on the position and / or speed of pedestrian 52', its acceleration capability can be determined using a pedestrian model. A second and wider object box 56 can be defined for pedestrian 52' as object 52, representing the possible lateral location of pedestrian 52' within image 51 or the section 51' of image 51, taking into account its acceleration capability. To determine the speed of pedestrian 52' as object 52 and to convert its acceleration capability into pixel or angular coordinates, assumptions can be made about the size of pedestrian 52' as object 52. For example, a common size of 1.75 m can be assumed. The previously calculated criticality value can be further reduced or minimized by the proportion of the last predicted or forecasted box 55 that lies outside the image 51 or frame and the respective section 51' or part thereof. For example, if 50% of the box width 55b—namely, if the object boxes 55 represent the possible area of ​​presence, taking the pedestrian model into account—lies outside the image 51 or frame, or the given part or section 51', the criticality is reduced accordingly. The criticality is reduced more significantly the further into the future the prediction lies, because potentially a larger area of ​​presence lies outside the image 51 or section 51'. This behavior may be desirable because, with increasing time horizons for the prediction, the uncertainty about the behavior of the pedestrian 52' grows. - If the predicted object box 55 of a pedestrian, as object 52, reaches a critical size - e.g., a threshold of 35% of the frame or image width - the prediction is aborted in this cycle of iteration I, since any collision would have already occurred at that time.

Claims

[1] Operational assistance procedure (S) for a work device (1), in which (S1) Object boxes (54) for an object (52) in a field of view of the work device (1) at successive time points or such object boxes (54) characterizing data are obtained, in which, at or for the step (S1) of obtaining the object boxes (54) and / or the object boxes (54) characterizing data are obtained, (S1a) a field of view (50) of the underlying working device (1) is optically captured two-dimensionally and monocularly by recording temporally successive images and (S1b) in successive recorded images at least one object (52) and an object box (54) associated with the object (52) are identified, (S2) from object boxes (54) of a given object (52) to successively or directly successively recorded images, an instantaneous scaling change or derived sizes of an object box (54) to the respective object (52) and an instantaneous lateral position change of the object box in the image (54) to the respective object (52) can be determined, (S3) from the current scaling change or quantities derived therefrom and the current lateral position change in the image to an object box (54) to a respective object (52) a future predicted object box (55) is determined and (S4) the position of the predicted object box (55) and / or the ratio of a lateral extent of the predicted object box (55) to a lateral extent of a captured field of view (50) and / or the captured images or a portion thereof are determined and evaluated and (S5) depending on the result of the evaluation (i) determines whether an object (52) underlying the predicted object box (55) is critical with respect to a possible collision or not, and / or (ii) controls or regulates an operating state of the working device (1), wherein an object (52) underlying a predicted object box (55) is determined to be non-critical with respect to a possible collision, in particular with a criticality value of 0%, if the predicted object box (55) is completely outside of an underlying image or a predefined section thereof. [2] Operational assistance method (S) according to one of the preceding claims, in which an object box (55) predicted into the future is determined at least to a currently most recently captured image by iteratively determining and updating values ​​for the scaling of a respective object box (54), for the coordinates of a respective object box (54), for the translation of a respective object box (54) and for the lateral width of a respective object box (54) over a plurality of time increments up to a forecast period. [3] Operational assistance method (S) according to claim 2, wherein for each time increment the following steps are performed - in particular in the specified order: (I1) Resetting or pre-populating the values ​​to be calculated in accordance with the allocation rules Scaling alt := Scaling neu BoxTranslationX alt := BoxTranslationX neu BoxBreite alt := BoxBreite neu BoxPositionLinks alt := BoxPositionLinks neu BoxPositionRight alt := BoxPositionRight neu , (I2) Update the scaling according to the following assignment rule New scaling:=1 / (2−old scaling) (I3) Update the horizontal object box translation according to the following mapping rule BoxTranslationXnew:=BoxTranslationXold×Scalingold (I4) Update horizontal object box width according to the following assignment rule BoxBreiteneu:=BoxPositionRechttsalt−BoxPositionLinkssalt (I5) Predicting the horizontal box positions according to the following allocation rules BoxPositionLinksneu:=BoxPositionLinksalt+BoxTranslationXneu− 0.5×BoxBreiteneu×(Skalierungneu−1) / Scalierungneu BoxPositionRightNew:=BoxPositionRightNew+BoxTranslationXNew+ 0.5×BoxWidthNew×(ScaleNew−1) / ScaleNew, where scaling alt , scaling neu the old or the new scaling of an object box (54), BoxTranslationX alt , BoxTranslationX neu the old or the new displacement of an object box (54), BoxWidth alt , Box width neuthe old or new width of an object box (54), BoxPositionLeft alt , BoxPositionLinks neu the old or the new position of the lower left corner of an object box (54) as the first x-coordinate of the respective object box (54) as well as BoxPositionRight alt , BoxPositionRight neu to denote the old or the new position of the lower right corner of an object box (54) as the second x-coordinate of the respective object box (54) or its values. [4] Operational assistance method (S) according to claim 2 or 3, in which the following calculation procedure is carried out to determine a new box position: BoxPositionLinksneu:=(BoxPositionLinksaktuell+ BoxGeschwindigkeitLinksaktuell*TPra¨diction) / (1 +NormGeschwindigkeitaktuell*TPra¨diction) BoxPositionRightNew:=(BoxPositionRightCurrent+ BoxSpeedRightCurrent*TPradiction) / (1+NormSpeedCurrent*TPradiction) where BoxPositionLinks neuand BoxPositionLinks aktuell or BoxPositionRight neu and BoxPositionRight aktuell the new or current position of the left or right box edge is and BoxSpeedLeft aktuell and Box Speed ​​Right aktuell The currently measured angular velocity of the left or right box edge is and standard speed. aktuell the currently measured so-called normalized box speed is and T Prädiktion the prediction time associated with the prediction time step, where the normal velocity aktuell is derived from the calculated scaling change of the object box. [5] Operational assistance method (S) according to one of the preceding claims, in which an object (52) underlying a predicted object box (55) is determined to be critical with respect to a possible collision, in particular with a criticality value of 100%, if the proportion of the width of the predicted object box (55) to the width of an underlying image or a predetermined section thereof exceeds a predetermined first threshold value. [6] Operational assistance method (S) according to claim 5, wherein the value of a criticality determined for an object (52) is reduced by the proportion by which the object box (55) predicted for the object (52) is positioned in its width outside the underlying image or the specified section. [7] Operational assistance method (S) according to one of the preceding claims, in which a pedestrian (52') is identified as object (52), the position and movement of the pedestrian (52') as object (52) are examined and evaluated on the basis of a pedestrian model, an acceleration capability of the pedestrian (52') as object (52) is determined on the basis of a velocity determined for the pedestrian (52'), and the criticality for the pedestrian (52') as object (52) is determined on the basis of the velocity and the acceleration capability, wherein, in particular, on the basis of the acceleration capability, an object box (56) enclosing or at least laterally or horizontally encompassing the predicted object box (55) is generated and is used as the basis for the evaluation of the criticality. [8] Control unit (10) for an operating assistance system (100) of a work device (1) and in particular of a vehicle, which is configured to control, run an operating assistance procedure (S) according to one of the preceding claims and / or to operate an underlying operating assistance system (100) according to an operating assistance procedure (S) according to one of the preceding claims. [9] Operational assistance system (100) for a work device (1) and in particular for a vehicle, which is equipped to perform an operational assistance method (S) according to one of claims 1 to 7 and which in particular has a control unit (10) according to claim 8. [10] Working device (1) which has an operating assistance system (100) according to claim 9 and which is designed in particular as a vehicle, motor vehicle or passenger car. [11] Use of the operational assistance method (S) according to any one of claims 1 to 7, the control unit (10) according to claim 8, the operational assistance system (100) according to claim 9 and / or the working device (1) according to claim 10 for pedestrian protection, for cyclist protection, for ACC and / or for avoidance systems or methods.

Images