Detection of available parking spots

Abstract

To provide a computer-implemented method for detecting potentially available parking spots.SOLUTION: Receiving at least one image (I (E)) showing a vehicle driving environment from a camera system, determining at least one non-moving vehicle (Vnm) located in a parking spot in the vehicle driving environment, assigning a vehicle bounding box (BBV) to a non-moving vehicle (Vnm) in a parking spot, determining the presence of at least one characteristic feature (CF) within the vehicle bounding box (BBV) indicating a departure of the vehicle from the parking spot, assigning a departure probability (PL) to the identified non-moving vehicle (Vnm) based on the presence of the at least one determined characteristic feature (CF), and outputting information about the non-moving vehicle (Vnm) and the assigned departure probability (PL).SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a computer implementation method for detecting potentially available parking spots based on camera images acquired from a camera system comprising at least one camera, a computer program embodied to perform the method according to the present invention, and a computer-readable storage medium. The method can preferably be used, for example, in an advanced driver-assistance system to perform a parking function. [Background technology]

[0002] Advanced driver-assistance systems (ADAS) for vehicles are based on the processing of various data detected by various ADAS sensors, such as radar sensors, LiDAR sensors, ultrasonic sensors, and cameras. By using ADAS sensors, information about the vehicle's surrounding environment can be obtained, which is then used to perform various ADAS functions. ADAS functions can include, on the one hand, assisting the driver while vehicle control remains in the driver's hands, and on the other hand, enabling fully autonomous vehicles depending on the level of automation. Known ADAS functions include, for example, various methods for detecting and / or classifying objects and / or obstacles around the vehicle, lane detection and / or lane departure detection methods, rainfall detection methods, and various parking assistance functions.

[0003] In the case of parking assistance functions, methods are known for assisting in parking a vehicle, such as assisting in the search for a parking slot, assisting in the parking process, and even autonomously executing the parking process once an available parking slot is found.

[0004] A parking slot detection method based on neural networks has been proposed, for example, in Non-Patent Document 1.

[0005] However, current methods primarily focus on detecting parking slots that are available and vacant, but there is also a need to detect parking slots that may become vacant, i.e., those that may be vacated. [Prior art documents] [Non-patent literature]

[0006] [Non-Patent Document 1] Available in Q. Huy et al., “CNN-based Two-Stage Parking Slot Detection Using Region-Specific Multi-Scale Feature Extraction”, 2021, arXiv:210806185. [Non-Patent Document 2] Available at O. Ronneberger et al., “U-Net: Convolutional Networks for Biomedical Image Segmentation”, arXiv:1505.04597. [Non-Patent Document 3] J.Redmon et al., “You Only Look Once: Unified, Real-Time Object Detection”, available at arXiv:1506.02640. [Non-Patent Document 4] Available at F.Li et al., “DINO: Towards a Unified Transformer-based Framework for Object Detection and Segmentation”, arXiv:26206.02777. [Non-Patent Document 5] A Dosovitskiy et al., “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale”, available at arXiv arXiv:2010.11929. [Overview of the project]

Problems to be Solved by the Invention

[0007] Therefore, the objective technical problem underlying the present invention is to provide an option for determining a parking spot that is empty or will become available soon.

Means for Solving the Problems

[0008] This objective is achieved by the method according to claim 1, the computer program according to claim 15, and the computer-readable (storage) medium according to claim 16.

[0009] Regarding this method, the problem underlying the present invention is a computer-implemented method for detecting parking spots that may become available based on camera images obtained from a camera system equipped with at least one camera, - receiving at least one image indicating the vehicle's surrounding environment from the camera system, - identifying at least one non-moving vehicle located in a parking spot in the vehicle's surrounding environment and assigning a vehicle bounding box to the non-moving vehicle in the parking spot, - determining the presence of at least one characteristic feature indicating the departure of a vehicle from a parking spot within the vehicle bounding box, - assigning a departure probability to the identified non-moving vehicle based on the presence of at least one determined characteristic feature, and - outputting information regarding the non-moving vehicle and the assigned departure probability.

[0010] The camera system is preferably a vehicle camera system, and the vehicle may be any vehicle moving on a road, such as a car, a motorcycle, a bus, etc.

[0011] First, stationary vehicles located in parking slots are detected. That is, parking spots that may soon become available are detected not based on the boundaries of the parking lot, but rather through the vehicles already occupying them. Next, the characteristics of a vehicle leaving a parking spot are determined, and the probability of departure is determined based on these characteristics. Information regarding the identified stationary vehicles and departure probabilities can be output, for example, to the vehicle driver or as input to a parking function that is subsequently executed. For example, the output information could indicate parking spots as potentially available spots. In this case, a departure probability can be determined and assigned to the parking spot.

[0012] This procedure is particularly advantageous in urban environments and / or on congested roads, public outdoor parking lots, and indoor parking lots where finding available parking spots is often difficult. The present invention provides a method for automatically finding parking spots that will soon become available. This can assist the driver or be input into an advanced driver-assistance system that provides parking assistance.

[0013] In a preferred embodiment of the present invention, at least one non-moving vehicle is identified by performing an object detection process, in particular using an object detector. In this regard, any object detection process can be used. Where an object detector is applied, the object detector may be based on a machine learning model and may be any suitable known object detector.

[0014] Advantageously, identifying at least one non-moving vehicle involves performing a further depth estimation process based on the image sequence received from the camera system. This additional depth estimation makes it possible to reliably distinguish between moving and non-moving vehicles.

[0015] This method is generally implemented on streets or public parking areas where parking is dense. In such cases or similar situations, non-moving vehicles are typically parked vehicles, and other reasons for non-moving vehicles, such as being stopped at traffic lights or in congestion, can be disregarded.

[0016] In a preferred embodiment, the steps of identifying at least one non-moving vehicle located in a parking spot in the vehicle surrounding environment and / or determining the presence of at least one characteristic feature indicating the departure of a vehicle from the parking spot within the vehicle bounding box include using at least one neural network. The neural network is preferably a convolutional neural network (CNN) or a transformer neural network. Embodiments may involve a single multitask neural network, or multiple neural networks may be used for different purposes.

[0017] Preferred examples of suitable networks include the U-net described in Non-Patent Document 2 and the YOLO network proposed in Non-Patent Document 3, particularly YOLOv8 or VOLOv9. On the other hand, examples of suitable transformer networks include the Mask DINO network described in Non-Patent Document 4 and the Vision Transformer (ViT) network described in Non-Patent Document 5.

[0018] Advantageously, the characteristic feature indicating the departure of a vehicle from a parking spot is either a vehicle light or a person, particularly a human head. The vehicle light may be a front light, taillight, or indicator light. The person being detected is preferably a person detected inside the vehicle.

[0019] With respect to the method according to the present invention, it can be further verified that the detected features belong to the detected non-moving vehicle and can therefore be assigned as characteristic features.

[0020] In this regard, in a preferred embodiment, determining the presence of at least one characteristic feature includes detecting the feature, assigning a feature bounding box to the feature, and characterizing the feature as a characteristic feature if the ratio of the feature bounding box to the vehicle bounding box falls within a predetermined ratio range.

[0021] More advantageously, determining a characteristic feature having the morphology of a human head includes detecting a human head, and the detected head is characterized as a characteristic feature if it is detected in a predetermined upper part of the vehicle bounding box. In other words, a detected human head is considered only if the head bounding box is located in the upper part of the vehicle bounding box, for example, the upper half or the upper third.

[0022] Furthermore, advantageously, determining a characteristic feature having the form of a vehicle light includes detecting a vehicle light, and the detected vehicle light is characterized as a characteristic feature if it is detected at a predetermined lower part of the vehicle bounding box. In other words, the detected vehicle light is considered only if the vehicle light bounding box is located at the lower part of the vehicle bounding box.

[0023] Finally, advantageously, determining the existence of at least one characteristic feature involves calculating a first distance from the camera system to the feature and a second distance from the camera system to the non-moving vehicle, and characterizing the feature as a characteristic feature if the difference between the first and second distances is less than or equal to a predetermined threshold distance.

[0024] In another preferred embodiment, the step of assigning a departure probability to an identified non-moving vehicle includes pre-defining at least one probability value representing a specific characteristic feature or a combination of two different characteristic features. For example, a list of potential characteristic features can be generated, and the probability values ​​can be assigned to each characteristic feature of a combination of at least two characteristic features determined simultaneously.

[0025] Regarding the final method step of outputting relevant information about potentially available parking spots, several options are available. For example, instructions can be provided to the vehicle driver in the form of an audible or visual signal about potentially available parking spots. Alternatively, the information can be provided to an advanced driver-assistance system embodied to perform parking functions.

[0026] Furthermore, in this regard, advantageously, outputting information on non-moving vehicles and departure probabilities includes displaying a camera image, including the vehicle bounding box and departure probability, particularly to the vehicle driver. Also, departure probabilities can be assigned to multiple vehicle bounding boxes simultaneously. In the latter case, the driver or parking function can select one of the potentially available parking slots based on at least one criterion, such as the departure probability or the distance between the vehicle and a potentially vacant parking slot.

[0027] Preferably, the camera system further includes a thermal camera for measuring the temperature of features in the image received from the camera. Such a thermal camera can provide additional information regarding the temperature of a non-moving vehicle.

[0028] In this regard, advantageously, the detachment probability is further determined based on the measured temperature of the feature. For example, a relatively high temperature of a non-moving vehicle may indicate recent use of that vehicle and may reduce the detachment probability of that particular vehicle.

[0029] In any of the embodiments described herein, the method is preferably used in an advanced driver-assistance system that performs a parking function.

[0030] The fundamental problem of the present invention is further solved by a computer program, when executed by a computer, which includes instructions that cause the computer to perform the method according to the present invention, and which includes instructions that can be executed by at least one processor for performing the method according to the present invention, or by a computer-readable (storage) medium on which the computer program according to the present invention is stored.

[0031] The present invention and its preferred embodiments will be further described with reference to the following drawings. [Brief explanation of the drawing]

[0032] [Figure 1] Figure 1 shows a flowchart illustrating how to detect potentially available parking spaces. [Figure 2] Figure 2 shows the determination of characteristic features. [Figure 3] Figure 3 shows an image of the vehicle's surrounding environment with indications of potentially available parking spots. In the figure, identical elements are denoted by the same reference numeral. [Modes for carrying out the invention]

[0033] In particular, when there are few or no available parking spaces, such as on streets with dense on-street parking, crowded outdoor parking lots, or indoor parking lots, drivers will not necessarily look for an empty slot, but rather for a parking slot or space that may become available. This invention provides an option for automatically detecting parking slots that will soon become vacant. The proposed method is illustrated by the flowchart shown in Figure 1.

[0034] In the first step, at least one image I(E) showing the vehicle surrounding environment (E) is received from a camera system (not shown). In the received image I(E), in the second step, at least one non-moving vehicle V located at a parking spot in the vehicle surrounding environment E is shown. nm It is identified. Non-moving vehicle Vnm The identification can be performed, for example, particularly, by an object detection process using an object detector OD. Also, a vehicle bounding box BBV is assigned to the identified non-moving vehicle V nm to it.

[0035] Optionally, a depth estimation process d based on the image sequence I received from the camera system can be further executed. In this way, a moving vehicle or a dynamic vehicle can be easily distinguished from the non-moving vehicle V nm from. By analyzing the depth based on the image sequence I received from the camera system, the relative positions and speeds of the vehicle and other moving vehicles can be calculated. 1. For example, the distance between the (self) vehicle and the determined vehicle bounding box BB V can be determined in consecutive images I. If the distance determined based on the depth information does not match the displacement indicating the movement of the vehicle, the detected vehicle can be regarded as not being the non-moving vehicle V nm and can be ignored in subsequent analysis.

[0036] In the third step, the presence of at least one characteristic feature CF indicating the departure of the vehicle from the parking spot within the vehicle bounding box BB V is determined. This step can also be performed, for example, particularly, by an object detection process using an object detector OD. What can become the characteristic feature CF is an active light, for example, a headlight, a backlight, an indicator light, and particularly, the head of a person within the non-moving vehicle V nm is.

[0037] In the fourth step, based on the presence of at least one determined characteristic feature, a departure probability PL(CF, V nm ) is assigned to the identified non-moving vehicle V nm . That is, the assigned departure probability PL depends on whether the characteristic feature CF is detected at all, and the category of the characteristic feature, for example, the type of the feature, the image I, the position within the vehicle bounding box BB V etc.

[0038] Finally, non-mobile vehicle V nm Information regarding the departure probability PL is provided, for example, to the vehicle driver as output or as input for a parking function that is subsequently performed.

[0039] Vehicle bounding box BB V The determination of characteristic features CF indicating vehicle departure from a parking spot within the system, and the assignment of departure probability PL based on these, are further shown in Figure 2. With regard to the proposed method, any one of several characteristic features CF can be checked. Figure 2 illustrates the case of four characteristic features CF1 to CF4, where the first characteristic features CF1 to CF3 indicate vehicle lights, i.e., CF1 indicates taillights, CF2 indicates indicator lights, and CF3 indicates headlights, while CF4 indicates a human head.

[0040] In the first step, the vehicle bounding box BB V The object detection process OD within the system is performed here, exemplifyingly using the object detector OD, for each characteristic feature CF1 to CF4.

[0041] In the second step, case distinctions are made based on different combinations of the characteristic features CF1 to CF4 to be considered. In the illustrated embodiment, the vehicle bounding box BB V Within this context, the first case indicates a situation where any active vehicle lights are detected (CF1~CF3->t is true), but human heads are not detected (CF4->f is false); the second case indicates a situation where any vehicle lights (CF1~CF3) and human heads (CF4) are detected; the third case indicates a situation where vehicle lights (CF1~CF3) are not detected, but human heads (CF4) are detected; and finally, the fourth case indicates a situation where neither vehicle lights (CF1~CF4) nor heads (CF4) are detected, i.e., characteristic feature CF is not detected at all.

[0042] In the following third step, the detected different vehicle lights, namely the front lights (CF1), taillights (CF2), and headlights (CF3), are distinguished. In other embodiments, the second and third steps can be combined into a single method step.

[0043] In the next optional fourth step, the determined characteristic features CF1-CF4 are actually found in the non-mobile vehicle V nm and vehicle bounding box BB v Validation can be performed to verify whether or not it is associated with a non-mobile vehicle V. nm Positional, depth, and / or size information related to the determined characteristic feature CF can be taken into consideration. Validation can be performed on a single characteristic feature CF1-CF4, a combination thereof, or only selected characteristic features CF. Characteristic features CF1-CF4 and vehicle bounding box BB V If the association can be confirmed, these are non-mobile vehicle V nm This is taken into consideration when assigning the probability of departure PL to a group.

[0044] For example, validation can focus on the fact that for each characteristic feature CF considered, the ratio of the vehicle bounding box BBV to the feature bounding box BBF should be within a specific range. Otherwise, the determined characteristic feature FC may correspond to a different vehicle. Alternatively or additionally, the feature may correspond to an identified non-mobile vehicle V. nm Positional requirements can also be defined to ensure that the vehicle lights are actually distinctive, and the determined vehicle lights are preferably located within the vehicle bounding box BB V While the detected human head should be located in the lower part of the vehicle bounding box BB, the detected human head is preferably located in the vehicle bounding box BB. V It should be located at the top of. Furthermore, estimated depth information can also be taken into account; that is, the determined characteristic feature CF is the identified non-moving vehicle V. nm It should be in close proximity to it.

[0045] In the embodiment shown in Figure 2, in the fifth step, different departure probabilities PL1 to PLN are determined for each case considered in the second step regarding the case distinction of combinations of characteristic features CF1 to CF4. These departure probabilities PL1 to PLN are assigned to each combination of characteristic features CF, and ultimately, non-moving vehicle V nm Information regarding the assigned departure probability PL is provided to the vehicle driver or supplied as input to the parking function that is subsequently performed.

[0046] In this example, the departure probability PL is assigned based on the vehicle lights detected, distinguishing between different vehicle lights, and the detected human head. If no characteristic features are detected at all, this situation corresponds to a departure probability PL = 0. For example, the highest departure probability PL can be assigned to the situation where illuminated taillights are detected, because taillights are likely to be illuminated when leaving a parking spot. The second highest departure probability PL can be assigned to the situation where indicator lights are illuminated, followed by the situation where headlights are illuminated and / or a human head is detected. Needless to say, further configurations and characteristic features CF can be taken into consideration. This method can be applied to various characteristic features CF or combinations of features and their associated departure probability PL.

[0047] Optionally, information on non-moving vehicles obtained from a thermal camera (not shown) may also be taken into consideration, Non-moving vehicle V nm The probability of withdrawal PL can be determined or assigned to this.

[0048] Figure 3 shows image I(E), which represents the surrounding environment (E) of the vehicle as received from the vehicle's camera system. Multiple vehicles are shown in the image, each with a black vehicle bounding box BB attached to it. VAs shown, but as an example, it is shown for one of the vehicles. According to the method of the present invention, a white vehicle bounding box BBV is assigned a departure probability PL = 50%. In this way, the vehicle bounding box BB V Using image I(E) to which the departure probability PL has been assigned, relevant information can be output to the vehicle driver, or output to a processing unit for further processing of the acquired information. While this application relates to the invention described in the claims, it also includes the following other aspects. 1. A computer implementation method for detecting potentially available parking spots based on camera images (I) acquired from a camera system having at least one camera, - The step of receiving at least one image (I(E)) showing the surrounding environment (E) of the vehicle from the camera system, - At least one non-moving vehicle (V) located in the parking spot of the vehicle surrounding environment. nm Identify the vehicle bounding box (BB) V ) the non-moving vehicle (V) at the parking spot nm ) Steps to assign - The aforementioned vehicle bounding box (BB V A step of determining the presence of at least one characteristic feature (CF) indicating the departure of the vehicle from the parking spot within ) - Based on the presence of the at least one determined characteristic feature (CF), the identified non-mobile vehicle (V nm The steps include assigning the probability of withdrawal (PL) to ) and - The aforementioned non-mobile vehicle (V nm A method comprising the step of outputting information regarding the assigned withdrawal probability (PL) and the aforementioned withdrawal probability. 2. The aforementioned at least one non-movable vehicle (V nm The method according to item 1 above, wherein the object is identified, in particular, by performing an object detection process (OD) using an object detector. 3. By further performing a depth estimation process (d) based on the image sequence (I) received from the camera system, the at least one non-moving vehicle (V) nm The method described in item 2 above, which identifies ) 4. The aforementioned at least one non-movable vehicle (V nm The method according to any one of 1 to 3 above, wherein the step of identifying ) and / or determining the presence of the at least one characteristic feature (CF) includes using at least one neural network. 5. The method according to any one of 1 to 4 above, wherein the characteristic feature (CF) indicating the departure of the vehicle from the parking spot is a vehicle light or a person, in particular a human head. 6. Determining the presence of at least one characteristic feature (CF) is equivalent to detecting a feature, and detecting a feature bounding box (BB). F Assigning the feature to the feature, and the feature bounding box (BB F ) and the aforementioned vehicle bounding box (BB V The method according to any one of 1 to 5 above, comprising characterizing the feature as a characteristic feature (CF) when the ratio with ) is within a predetermined ratio range. 7. Determining characteristic features (CF) that have the morphology of a human head includes detecting a human head, and the detected head is the vehicle bounding box (BB) V The method according to any one of 1 to 6 above, characterized as a characteristic feature (CF) when detected at a predetermined upper part of ). 8. Determining characteristic features (CF) having the form of a vehicle light includes detecting a vehicle light, and the detected vehicle light is the vehicle bounding box (BB) V The method according to any one of 1 to 7 above, characterized as a characteristic feature (CF) when detected at a predetermined lower part of ). 9. Determining the presence of the at least one characteristic feature (CF) is the first distance from the camera system to the feature (CF) and the distance from the camera system to the non-moving vehicle (V nm A method according to any one of 1 to 8 above, comprising calculating a second distance to ) and characterizing the feature as a characteristic feature (CF) if the difference between the first distance and the second distance is less than or equal to a predetermined threshold distance. 10. Based on the presence of the at least one determined characteristic feature (CF), the identified non-mobile vehicle (V nm The method according to any one of 1 to 9 above, wherein assigning the aforementioned withdrawal probability (PL) to a particular characteristic feature (CF) or a combination of two different characteristic features (CF) includes pre-determining at least one probability value. 11. The aforementioned non-moving vehicle (V nm The vehicle bounding box (BB) outputs information regarding the vehicle bounding box (BB) and the probability of departure (PL). V The method according to any one of 1 to 10 above, further comprising displaying the camera image, which includes the ) and the departure probability (PL), to the vehicle driver. 12. The method according to any one of 1 to 11, wherein the camera system further comprises a thermal camera for measuring the temperature of features in the image received from the camera. 13. The method according to any one of 1 to 12 above, wherein the separation probability (PL) is further determined based on the measured temperature of the feature. 14. In particular, the use of any one of the methods described in 1 to 13 above in an advanced driver assistance system that performs a parking function. 15. A computer program that, when executed by a computer, includes instructions that cause the computer to perform any one of the methods described in 1 to 13 above. 16. A computer-readable (storage) medium containing instructions that can be executed by at least one processor to perform the method described in any one of the above 1 to 13, or a computer program as described in 15 above.

Claims

1. A computer implementation method for detecting potentially available parking spots based on camera images (I) acquired from a camera system having at least one camera, The above method involves the following steps: - A step of receiving at least one image (I(E)) showing the surrounding environment (E) of the vehicle from the camera system, - At least one non-moving vehicle (V) located in the parking spot of the vehicle surrounding environment ｎｍ Identify the vehicle bounding box (BB) Ｖ ) the non-moving vehicle (V ｎｍ ) Steps to assign - The aforementioned vehicle bounding box (BB Ｖ A step of determining the presence of at least one characteristic feature (CF) indicating the departure of the vehicle from the parking spot within ) - Based on the presence of at least one determined characteristic feature (CF), the identified non-mobile vehicle (V ｎｍ The steps include assigning a withdrawal probability (PL) to ) and - The non-movable vehicle (V ｎｍ A step of outputting information regarding the assigned withdrawal probability (PL) and the above-mentioned withdrawal probability, Equipped with, The step of determining the existence of at least one characteristic feature (CF) includes calculating a first distance from the camera system to the feature (CF) and a second distance from the camera system to the non-moving vehicle (V nm), and characterizing the feature as a characteristic feature (CF) if the difference between the first distance and the second distance is less than or equal to a predetermined threshold distance. method.

2. The at least one non-movable vehicle (V ｎｍ The method according to claim 1, wherein the object is identified, in particular, by performing an object detection process (OD) using an object detector.

3. By further performing a depth estimation process (d) based on the image sequence (I) received from the camera system, the at least one non-moving vehicle (V) ｎｍ The method according to claim 2, which identifies ).

4. The step of identifying said at least one non - moving vehicle (V ｎｍ ) and / or the step of determining the presence of said at least one characteristic feature (CF) comprises using at least one neural network, the method according to claim 1.

5. The method according to claim 1, wherein the characteristic feature (CF) indicating the departure of the vehicle from the parking spot is a vehicle light or a person, in particular a human head.

6. Determining the presence of at least one characteristic feature (CF) is equivalent to detecting a feature, and the feature bounding box (BB) Ｆ Assigning the feature to the feature and the feature bounding box (BB Ｆ ) and the vehicle bounding box (BB Ｖ The method according to claim 1, further comprising characterizing the feature as a characteristic feature (CF) when the ratio with ) is within a predetermined ratio range.

7. Determining characteristic features (CF) having the morphology of a human head includes detecting a human head, wherein the detected head is the vehicle bounding box (BB) Ｖ The method according to claim 1, characterized as a characteristic feature (CF) when detected at a predetermined upper part of ).

8. Determining characteristic features (CF) having the form of a vehicle light includes detecting a vehicle light, and the detected vehicle light is the vehicle bounding box (BB) Ｖ The method according to claim 1, characterized as a characteristic feature (CF) when detected at a predetermined lower part of ).

9. Based on the presence of the at least one determined characteristic feature (CF), the identified non-mobile vehicle (V ｎｍ The method according to claim 1, wherein assigning the aforementioned withdrawal probability (PL) to a particular characteristic feature (CF) or a combination of two different characteristic features (CF) is performed by pre-determining at least one probability value.

10. The aforementioned non-movable vehicle (V ｎｍ Outputting information regarding the vehicle bounding box (BB) and the probability of departure (PL) is possible. Ｖ The method according to claim 1, further comprising displaying the camera image, which includes the ) and the departure probability (PL), to the vehicle driver.

11. The method according to claim 1, wherein the camera system further comprises a thermal camera for measuring the temperature of features in the image received from the camera.

12. The method according to claim 11, wherein the separation probability (PL) is further determined based on the measured temperature of the feature.

13. The method according to any one of claims 1 to 12, used in an advanced driver assistance system that performs a parking function.

14. A computer program that, when executed by a computer, includes instructions causing the computer to perform the method according to claim 1.

15. A computer-readable (storage) medium storing a computer program according to claim 14, which includes instructions executable by at least one processor for performing the method according to any one of claims 1 to 12.

Images