A method for operating a ramp detection device, a computer program product, a non-transitory computer-readable storage medium, as well as a ramp detection

Abstract

The invention relates to a method for operating a ramp detection device 10, comprising the following steps performed by a control unit 12 of the ramp detection device 10. A height map (18, figure 1 not shown) is received wherein the height map (18) assigns a respective elevation to a point within a predefined area (20). A gradient orientation map is evaluated based on the height map (18), wherein the gradient orientation map assigns a respective gradient orientation of the gradient of the elevation to the point within the predefined area (20). The evaluation of a gradient orientation gradient map is based on the gradient orientation map, wherein the gradient orientation gradient map assigns a respective gradient of the gradient orientation of the gradient of the elevation to the point within the predefined area (20). A continuous gradient orientation gradient area is segmented in the gradient orientation gradient map, wherein the respective gradient orientation gradients within the continuous gradient orientation gradient area have respective gradient orientation gradients within a predefined gradient orientation gradient magnitude range.

Description

[0001] The present invention relates to the field of automobiles. More specifically, the present invention relates to a method for operating a ramp detection device. Furthermore, the present invention relates to a corresponding computer program product, a corresponding non-transitory computer-readable storage medium, as well as to a corresponding ramp detection device. BACKGROUND INFORMATION

[0002] Driving strategies for guiding a vehicle depend on a surface of a ground around a vehicle. Therefore, vehicles comprise sensor devices based on Lidar, Radar or image based techniques for generating a height map of an area of the surface in an environment of the vehicle.

[0003] A height gradient in the height map describes a slope in the environment and can be related to an obstacle. Ramps share similar characteristics as obstacles, like a height gradient but are traversable for the vehicle, hence, classifying them is crucial to perform the correct driving strategy in Advanced Driver Assistance Systems, ADAS, and / or Autonomous Driving, AD. SUMMARY OF THE INVENTION

[0004] It is an object of the present invention to provide a method, a corresponding computer program product, a corresponding non-transitory computer-readable storage medium, as well as a corresponding ramp detection device, which an identification of pixels in a height map that represent ramps or elevated roads can be performed.

[0005] This object is solved by a method, a corresponding computer program product, a corresponding non-transitory computer-readable storage medium, as well as a corresponding ramp detection device according to the independent claims. Advantageous embodiments are presented in the dependent claims.

[0006] One aspect of the invention relates to a method for operating a ramp detection device. The method comprises steps performed by a control unit of the ramp detection device. The method comprises a receipt of an height map by the control unit. The height map assigns a respective elevation to a point within a predefined area. In other words, the height map gives the respective elevation of the point in the predefined area. The predefined area may be a surface in front of a vehicle, which may be detected by a sensor device of the vehicle. The method comprises an evaluation of a gradient orientation map based on the height map by the control unit. The gradient orientation map assigns a respective gradient orientation of a gradient of the elevation to the point within the predefined area. In other words, the control unit may generate a gradient map of the height map, wherein the gradient map assigns the gradient to the point. The gradient may describe a slope at the point. The gradient may have a gradient magnitude and a gradient orientation. The gradient orientation within the predefined area may be given in the gradient orientation map.

[0007] The method comprises an evaluation of a gradient orientation gradient map based on the gradient orientation map by the control unit. The gradient orientation gradient map assigns a respective gradient of the gradient orientation of the gradient of the elevation to the point within the predefined area.

[0008] The method comprises a segmentation of a continuous gradient orientation gradient area in the gradient orientation gradient map by the control unit. The respective gradient orientation gradients within the continuous gradient orientation gradient area have respective gradient orientation gradient magnitudes within a predefined gradient orientation gradient magnitude range.

[0009] According to an embodiment, the method comprises a step step performed by the control unit of the ramp detection device comprising a segmentation of the continuous gradient orientation gradient area in the gradient orientation gradient map by applying a morphological opening method with a predefined kernel to detect the continuous gradient orientation gradient area of a predefined minimal size.

[0010] According to an embodiment, the method comprises a step performed by the control unit of the ramp detection device comprising an evaluation of a gradient magnitude map based on the height map. The gradient magnitude map assigns a respective gradient magnitude to the point within the predefined area. The method comprises a segmentation of a continuous gradient magnitude area in the gradient magnitude map. The respective gradient magnitudes within the gradient magnitude area have a magnitude within a predefined magnitude range.

[0011] According to an embodiment, the method comprises a step performed by the control unit of the ramp detection device comprising a filtering of points within the continuous gradient magnitude area using a statistical filter. In other words, the control unit applies a statistical filter to keep pixel based of ratio of true pixels in large window.

[0012] According to an embodiment, the method comprises a step Performing an AND-operation of the gradient orientation gradient area and the continuous gradient magnitude area within the predefined area to detect ramp area in the predefined area. The method further comprises a generation of a ramp map describing the ramp area in the predefined area.

[0013] According to an embodiment, the method comprises a step of providing control data for guiding a vehicle depending on the ramp map. In other words, the control data may be configured to control a vehicle. The control unit may control the vehicle depending on the ramp map.

[0014] According to an embodiment of the present invention, the method comprises steps performed by a sensor device of the ramp detection device. The steps comprise a measuring a height of a surface within the predefined area and a generation of the height map. The steps comprise a provision of the height map to the control unit of the ramp detection device. The sensor device may be configured to measure the height within the predefined area by using Lidar, Radar or image based methods.

[0015] In particular, the method is a computer-implemented method. Therefore, another aspect to the invention relates to a computer program product comprising program code means for performing a method according to the preceding aspect.

[0016] Furthermore, the present invention relates to a non-transitory computer-readable storage medium comprising at least the computer program product according to the preceding aspect.

[0017] Furthermore, the present invention relates to a ramp detection device. The ramp detection device comprises a control unit, configured to receive a height map, wherein the height map assigns a respective elevation to a point within a predefined area. The control unit is configured to evaluate a gradient orientation map based on the height map, wherein the gradient orientation map assigns a respective gradient orientation of the gradient of the elevation to the point within the predefined area. The control unit is configured to evaluate a gradient orientation gradient map based on the gradient orientation map, wherein the gradient orientation gradient map assigns a respective gradient of the gradient orientation of the gradient of the elevation to the point within the predefined area. The control unit is configured to segment a continuous gradient orientation gradient area in the gradient orientation gradient map, wherein the respective gradient orientation gradients within the continuous gradient orientation gradient area have respective gradient orientation gradients within a predefined gradient orientation gradient magnitude range.

[0018] The control unit may comprise a computing unit / electronic computing device. The computing unit may in particular be understood as a data processing device, which comprises processing circuitry. The computing unit can therefore in particular process data to perform computing operations. This may also include operations to perform indexed accesses to a data structure, for example a look-up table, LUT.

[0019] In particular, the computing unit may include one or more computers, one or more microcontrollers, and / or one or more integrated circuits, for example, one or more application-specific integrated circuits, ASIC, one or more field-programmable gate arrays, FPGA, and / or one or more systems on a chip, SoC. The computing unit may also include one or more processors, for example one or more microprocessors, one or more central processing units, CPU, one or more graphics processing units, GPU, and / or one or more signal processors, in particular one or more digital signal processors, DSP. The computing unit may also include a physical or a virtual cluster of computers or other of said units.

[0020] In various embodiments, the computing unit includes one or more hardware and / or software interfaces and / or one or more memory units.

[0021] A memory unit may be implemented as a volatile data memory, for example a dynamic random access memory, DRAM, or a static random access memory, SRAM, or as a non-volatile data memory, for example a read-only memory, ROM, a programmable read-only memory, PROM, an erasable programmable read-only memory, EPROM, an electrically erasable programmable read-only memory, EEPROM, a flash memory or flash EEPROM, a ferroelectric random access memory, FRAM, a magnetoresistive random access memory, MRAM, or a phase-change random access memory, PCRAM.

[0022] Further advantages, features, and details of the invention derive from the following description of preferred embodiments as well as from the drawings. The features and feature combinations previously mentioned in the description as well as the features and feature combinations mentioned in the following description of the figures and / or shown in the figures alone can be employed not only in the respectively indicated combination but also in any other combination or taken alone without leaving the scope of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The novel features and characteristic of the disclosure are set forth in the appended claims. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and together with the description, serve to explain the disclosed principles. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the figures to reference like features and components. Some embodiments of system and / or methods in accordance with embodiments of the present subject matter are now described below, by way of example only, and with reference to the accompanying figures.

[0024] The drawings show in:

[0025] Fig. 1 a schematic illustration of a height map;

[0026] Fig. 2 a schematic illustration of a segmentation of a continuous gradient orientation gradient area;

[0027] Fig. 3 a schematic illustration of a segmentation of a continuous gradient magnitude area;

[0028] Fig. 4 a schematic illustration of segmentation of a continuous ramp area;

[0029] Fig. 5 a schematic illustration of a vehicle comprising a ramp detection device; and

[0030] Fig. 6 a schematic illustration of a method for operating a ramp detection device.

[0031] In the figures the same elements or elements having the same function are indicated by the same reference signs. DETAILED DESCRIPTION

[0032] In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration". Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

[0033] While the disclosure is susceptible to various modifications and alternative forms, specific embodiments thereof have been shown by way of example in the drawing and will be described in detail below. It should be understood, however, that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternatives falling within the scope of the disclosure.

[0034] The terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion so that a setup, device or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus preceded by “comprises” or “comprise” does not or do not, without more constraints, preclude the existence of other elements or additional elements in the system or method.

[0035] In the following detailed description of the embodiment of the disclosure, reference is made to the accompanying drawing that forms part hereof, and in which is shown by way of illustration a specific embodiment in which the disclosure may be practiced. This embodiment is described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.

[0036] Fig. 1 shows in a schematic illustration a height map 18. The height map 18 may describe a height of a predefined area 20. The predefined area 20 may be situated in an environment of the vehicle 14. Each point within the height map 18 may be assigned the respective height.

[0037] Fig. 2 shows in a schematic illustration a segmentation of a continuous gradient orientation gradient area 26.

[0038] The continuous gradient orientation gradient area 26 may be a segment area with a constant gradient orientation.

[0039] The map on the left may show a gradient orientation map 22 based on the height map 18 shown in Fig. 1. The gradient orientation map 22 may assign a respective gradient orientation of the gradient of the height to the point within the predefined area 20. The height map 18 may be converted into a gradient orientation represented in HSV with a circular color map.

[0040] The map in the center may show a gradient orientation gradient map 24 based on the gradient orientation map 22 on the left, wherein the gradient orientation gradient map 24 assigns a respective gradient of the gradient orientation of the gradient of the elevation to the point within the predefined area 20. Gradients may be identified in a RGB version of the HSV image and filtered by a threshold magnitude of gradients.

[0041] The map on the right may show a segmentation of a continuous gradient orientation gradient area 26 in the gradient orientation gradient map 24. The respective gradient orientation gradients within the continuous gradient orientation gradient area 26 have respective gradient orientation gradients within a predefined gradient orientation gradient magnitude range. The predefined gradient orientation gradient magnitude range may be related to an average orientation of the respective continuous gradient orientation gradient area 26 and may be limited by predefined values. The control unit 12 may apply an morphological opening with large kernel which only preserves large continuous gradient orientation gradient areas 26.

[0042] Fig. 3 shows in a schematic illustration a segmentation of a continuous gradient magnitude area 30.

[0043] The map on the left may show a gradient magnitude map 28 based on the height map 18 in Fig. 1. The gradient magnitude map 28 may assigns a respective gradient magnitude to the point within the predefined area 20. The control unit 12 may have converted the height map 18 into gradient magnitude.

[0044] The map in the center may show a gradient magnitude map 28 wherein the respective gradient magnitudes within a continuous gradient magnitude area 30 have a gradient magnitude within a predefined gradient magnitude range. The gradient magnitude map 28 may be created by thresholding the gradient magnitude map 28 on the left by a minimum threshold and a maximum threshold with respect to the gradient magnitude.

[0045] The map on the right may show a gradient magnitude map 28, generated by the control unit 12 by applying a statistical filter to keep pixel based of ratio of true pixels in large window.

[0046] Fig. 4 shows in a schematic illustration a segmentation of a continuous ramp area 32.

[0047] The control unit 12 may combine the continuous gradient orientation are 26 of the gradient orientation gradient map 24 and the continuous gradient magnitude area 30 of the gradient magnitude map 28 in an AND operation to determine a ramp area 32 in a ramp map 36. The control unit 12 may only select segments with sufficient area to remove false positives.

[0048] Fig. 5 shows a schematic illustration of a vehicle 14 comprising a ramp detection device 10.

[0049] The ramp detection device 10 may comprise a sensor device 16, configured to sense a surface 38 in front of the vehicle 14. The sensor device 16 may be configured to generate a height map 18 and to provide the height map 18 to a control unit 12. The control unit 12 may be configured to detect a ramp area 32 and to provide control data 34 to drive the vehicle 14 on the ramp 40.

[0050] Fig. 6 shows a schematic illustration of a method for operating a ramp detection device 10.

[0051] In step S10 the sensor device 16 may sense a surface 38 comprising a predefined area 20 and provide a height map 18 to the control unit 12.

[0052] In step S12 the control unit 12 may segment a gradient orientation gradient area.

[0053] In step S14 the control unit 12 may segment a continuous gradient magnitude area 30.

[0054] In step S16 the control unit 12 may perform an AND-operation of the gradient orientation gradient area and the continuous gradient magnitude area 30 within the predefined area 20 to detect ramp area 32 in the predefined area 20.

[0055] In step S18 the control unit 12 may generate control data 34 to drive the vehicle 14 onto the ramp 40.

[0056] The method provides an automated way to detect ramps 40 on height maps 18. It may generate annotation on pixel-level, allowing precise auto-labeling. The method may be used to automatically annotate height maps 18 generated from for example lidar point clouds. Reference signs 10 ramp detection device 12 control unit 14 vehicle 16 sensor device 18 height map 20 predefined area 22 gradient orientation map 24 gradient orientation gradient map 26 continuous gradient orientation gradient area 28 gradient magnitude map 30 continuous gradient magnitude area 32 ramp area 34 control data 36 ramp map 38 surface 40 ramp S10-S18 steps

Claims

1. A method for operating a ramp detection device (10);comprising the following steps performed by a control unit (12) of the ramp detection device (10);- receipt of an height map (18), wherein the height map (18) assigns a respective elevation to a point within a predefined area (20);- evaluation of a gradient orientation map (22) based on the height map (18), wherein the gradient orientation map (22) assigns a respective gradient orientation of the gradient of the elevation to the point within the predefined area (20);- evaluation of a gradient orientation gradient map (24) based on the gradient orientation map (22), wherein the gradient orientation gradient map (24) assigns a respective gradient of the gradient orientation of the gradient of the elevation to the point within the predefined area (20);- segmentation of a continuous gradient orientation gradient area (26) in the gradient orientation gradient map (24), wherein the respective gradient orientation gradients within the continuous gradient orientation gradient area (26) have respective gradient orientation gradients within a predefined gradient orientation gradient magnitude range.

2. The method according to claim 1,comprising the following step performed by the control unit (12) of the rampdetection device (10):segmentation of the continuous gradient orientation gradient area (26) in thegradient orientation gradient map (24) by applying a morphological opening methodwith a predefined kernel to detect the continuous gradient orientation gradient area (26) of a predefined minimal size.

3. The method according to claim 1 or 2, comprising the following steps performed by the control unit (12) of the ramp detection device (10);- evaluation of a gradient magnitude map (28) based on the height map (18), wherein the gradient magnitude map (28) assigns a respective gradient magnitude to the point within the predefined area (20); and- segmentation of a continuous gradient magnitude area (30) in the gradient magnitude map (28), wherein the respective gradient magnitudes within the gradient magnitude area have a magnitude within a predefined magnitude range;4. The method according to claim 3, comprising the following step performed by the control unit (12) of the ramp detection device (10):- filter points within the continuous gradient magnitude area (30) using a statistical filter.

5. The method according to claim 3 or 4, comprising the following steps performed by the control unit (12) of the ramp detection device (10):- performing an AND-operation of the continuous gradient orientation gradient area (26) and the continuous gradient magnitude area (30) within the predefined area (20) to detect a ramp area (32) in the predefined area (20); and- generation of ramp (40) map (36) describing the ramp area (32) in the predefined area (20);6. The method according to claim 5, comprising the following steps performed by the control unit (12) of the ramp detection device (10):- providing control data (34) for guiding a vehicle (14) depending on the ramp (40) map (36).

7. The method according to any one of claims 1 to 6,comprising the following steps performed by a sensor device (16) of the ramp detection device (10);- measuring a height of a surface (38) within the predefined area (20);- generation of the height map (18); and- provision of the height map (18) to the control unit (12) of the ramp detection device (10);8. A computer program product comprising program code means for performing a method according to any one of claims 1 to 7.

9. A non-transitory computer-readable storage medium comprising at least one computer program product according to claim 8.

10. A ramp detection device (10);characterized in thatthe ramp detection device (10) comprises a control unit (12), configured to- receive an height map (18), wherein the height map (18) assigns a respective elevation to a point within a predefined area (20);- evaluate a gradient orientation map (22) based on the height map (18), wherein the gradient orientation map (22) assigns a respective gradient orientation of the gradient of the elevation to the point within the predefined area (20);- evaluate a gradient orientation gradient map (24) based on the gradient orientation map (22), wherein the gradient orientation gradient map (24) assigns a respective gradient of the gradient orientation of the gradient of the elevation to the point within the predefined area (20);- segment a continuous gradient orientation gradient area (26) in the gradient orientation gradient map (24), wherein the respective gradient orientation gradients within the continuous gradient orientation gradient area (26) have respective gradient orientation gradients within a predefined gradient orientation gradient magnitude range.

Images