METHOD AND SYSTEM FOR DETECTING AN OBJECT IN A BLIND SPOT

Abstract

The present disclosure relates to a method (200) for object detection in at least one blind spot (10) in the vicinity of a vehicle (20), wherein the method comprises acquiring (202) image data of an area in the vicinity of the vehicle (20) that at least partially covers the blind spot (10); processing (206) at least partially of the image data obtained in order to locate at least one object in the image data obtained; converting (208) at least partially of the processed image data into corresponding perimeter coordinates, wherein the corresponding perimeter coordinates are defined relative to a viewpoint from which the image data are obtained; and transforming (210) at least partially of the converted perimeter coordinates into corresponding orthogonal coordinates, wherein the corresponding orthogonal coordinates refer to an orthogonal viewpoint with respect to the blind spot (10).and the detection (212) of a movement of at least a part of the object relative to the blind spot (10) based on at least a part of the transformed orthogonal coordinates. The present disclosure also relates to a system (100) for object detection in a blind spot (10) in the vicinity of a vehicle (20).

Description

[0001] The present disclosure relates to a method for object detection in the blind spot in front of a vehicle using a camera and a control unit. Furthermore, the present disclosure relates to a system for object detection in the blind spot in front of a vehicle, comprising a camera and a control unit adapted for implementing such a method.

[0002] With global population growth, the number of vehicles on the road has increased. Furthermore, traffic congestion has also increased with population growth. As traffic has grown worldwide, so has the number of traffic accidents. Various technologies are being developed to reduce the number of accidents. There has been enormous progress in the materials used for bumpers and dashboards to reduce the impact of collisions. Developments have also been made in chassis materials to absorb the impact of collisions. Similarly, there have been developments in the field of airbags. In addition, various advancements have been made in lighting technology to reduce the number of accidents.

[0003] Furthermore, there are developments aimed at avoiding collisions through near-field communication, which informs the driver of the presence of another vehicle. Similarly, sensors have been integrated into vehicles to detect other vehicles nearby or in the vicinity. Additionally, collision avoidance through inter-vehicle GPS data management has been developed and researched. Driver monitoring systems have also been developed to prevent traffic accidents. Furthermore, systems for predicting and estimating driving behavior have been developed to prevent traffic accidents.

[0004] For example, US11054835B2 discloses a collision avoidance method using lidar data that includes one or more points and determines the speed limit for each point or points. Similarly, CN105405320A discloses an early warning system for vehicle collisions using polarized light image 3D reconstruction based on Harris operator-based feature extraction.KR102605696B1 relates to a method for estimating a map-based CCTV camera position and object coordinates with precision, wherein the method comprises estimating a camera position by precisely matching a map with a road surface object in an image captured by a CCTV camera; selecting a mapped object in the image; and estimating coordinates of the selected mapped object in the image based on the estimated camera position, wherein the camera position includes information about a position, pan, and tilt of the CCTV camera.

[0005] However, there is a lack of development in the area of ​​object detection in front of a vehicle using a camera. The object can be, but is not limited to, a person, a child, a bicycle, and / or an animal. In particular, there is a lack of development in the area of ​​object detection in the blind spot in front of the vehicle. The term 'blind spot' can refer to a rectangular area that cannot be directly seen by a driver in a seated position. Furthermore, the blind spot in front of a vehicle of a certain geometry can be fixed, depending on the geometry of the specific vehicle. Additionally, the corresponding blind spot can change with a change in the geometry.

[0006] Therefore, there is a need to develop a cost-effective, safe and reliable system and method for detecting an object in a blind spot in front of a vehicle.

[0007] Therefore, one objective of the present disclosure is to provide a method for detecting an object in a blind spot in front of a vehicle, in order to at least partially overcome the known disadvantages of the prior art. Furthermore, it is an objective to develop a cost-effective and reliable system for detecting an object in a blind spot in front of a vehicle. A further objective of the present disclosure is to provide a cost-effective and safe method for detecting an object in a blind spot in front of a vehicle.

[0008] This objective is achieved by the features of claim 1. Embodiments of the method according to the present disclosure are described in claims 2 to 12.

[0009] Furthermore, the present disclosure provides a system comprising a camera configured to capture image data in front of the vehicle; and a control unit arranged and adapted within the vehicle to implement a method as described above. Embodiments of the system according to the present disclosure are described in claims 13 and 14.

[0010] Furthermore, the present disclosure relates to a computer-implemented method for object detection in a blind spot in front of a vehicle, wherein the method is implemented by a control unit located in a base station, the control unit being adapted to implement a method as described above.

[0011] Accordingly, one aspect of the present disclosure relates to a method for detecting an object in a blind spot in front of a vehicle, wherein the method may comprise: the acquisition of image data by a camera; the receipt of the acquired image data from the camera by a control unit; the processing of the received image data by the control unit to locate the object in the received image data; the conversion of the processed image data by the control unit into corresponding perimeter coordinates, wherein the corresponding perimeter coordinates relate to a point of view with respect to a position of the camera; the transformation of the converted perimeter coordinates by the control unit into corresponding orthogonal coordinates, wherein the corresponding orthogonal coordinates relate to an orthogonal point of view with respect to the blind spot;and the detection of the object in the blind spot by the control unit based on the transformed orthogonal coordinates.

[0012] In one aspect, the object can be at least one of the following: a neighboring vehicle, an animal, and an endangered road user.

[0013] In another aspect, the processing step can also include the classification of the object in the obtained image data.

[0014] According to one embodiment, the camera can be placed on top of the vehicle's windshield to capture the blind spot.

[0015] It can be advantageous that the conversion of the processed image data into the corresponding perimeter coordinates can correspond to a conversion of pixel coordinates into real world coordinates, and / or where the transformation of the converted perimeter coordinates into the corresponding orthogonal coordinates can correspond to a perspective transformation.

[0016] In another aspect, the detection of the object in the blind spot can be based on a comparison of the transformed orthogonal coordinates with coordinates of a predetermined area of ​​interest in the blind spot.

[0017] In another aspect of the present disclosure, the system for detecting an object in a blind spot in front of a vehicle may include a camera configured to capture image data in front of the vehicle; and a control unit configured in the vehicle to: - receive the captured image data from the camera, - process the received image data to locate the object in the received image data, - convert the processed image data into appropriate perimeter coordinates, optionally the appropriate perimeter coordinates relating to a viewpoint with respect to a position of the camera, - convert the converted perimeter coordinates into appropriate orthogonal coordinates, the appropriate orthogonal coordinates relating to an orthogonal viewpoint with respect to the blind spot, and - detect the entry of the object into the blind spot based on the transformed orthogonal coordinates.

[0018] The object can be at least one of the following: a neighboring vehicle, an animal, and a road user at risk.

[0019] The control unit can also be configured to classify the object in the received image data.

[0020] The camera can be placed on top of the vehicle's windshield to capture the blind spot.

[0021] The conversion of the processed image data into the corresponding perimeter coordinates can correspond to a conversion of pixel coordinates into real world coordinates, and / or the transformation of the converted perimeter coordinates into the corresponding orthogonal coordinates can correspond to a perspective transformation.

[0022] In one aspect, the detection of the object in the blind spot can be based on a comparison of at least one of the transformed orthogonal coordinates with coordinates of a predetermined area of ​​interest in the blind spot.

[0023] Another aspect of the present disclosure relates to a computer-implemented method for detecting an object in a blind spot in front of a vehicle, wherein the method is implemented by a control unit located at a base station. The method steps may include: - capturing image data from a camera; - processing the captured image data to locate the object within the captured image data; - converting the processed image data into appropriate perimeter coordinates, wherein the appropriate perimeter coordinates relate to a viewpoint with respect to a position of the camera; - converting the converted perimeter coordinates into appropriate orthogonal coordinates, wherein the appropriate orthogonal coordinates relate to an orthogonal viewpoint with respect to the blind spot; and - detecting the object's entry into the blind spot based on the transformed orthogonal coordinates.

[0024] The present disclosure also relates to a computer-implemented method for detecting the object in the blind spot in front of the vehicle, wherein the detection of the object in the blind spot can be based on a comparison of at least one of the transformed orthogonal coordinates with coordinates of a predetermined area of ​​interest in the blind spot.

[0025] The present disclosure also relates to a computer-implemented method for detecting the object in the blind spot in front of the vehicle, wherein the conversion of the processed image data into the corresponding perimeter coordinates may correspond to a conversion of pixel coordinates into real world coordinates, and / or wherein the transformation of the converted perimeter coordinates into the corresponding orthogonal coordinates may correspond to a perspective transformation.

[0026] The term “circumferential coordinates” is to be understood, in the sense of the claimed subject matter, as a coordinate system that has at least one, optionally two and / or three, non-orthogonal coordinates, coordinate lines and / or coordinate axes, optionally polar coordinates, cylindrical coordinates, spherical coordinates and / or at least one angular coordinate.

[0027] The present disclosure provides a safe, reliable, and cost-effective method and system for detecting an object in front of a vehicle. In particular, expensive systems such as lidar or radar systems are not required. Furthermore, existing cameras can be used, or an additional camera can be added to an existing camera monitor system. Thus, the method and system of the present disclosure can be used, at least partially, and / or expanded upon, the vehicle's existing equipment.

[0028] It should be noted that the features set forth individually in the following description may be combined in any technically advantageous manner, and other forms of the present disclosure may be presented. However, it is to be understood that the disclosure is not limited to the precise arrangements and instruments shown. The accompanying drawings, which are incorporated into and form part of this specification, illustrate an implementation of system, devices, and methods consistent with the present description and, together with the description, serve to explain advantages and principles consistent with the present disclosure. The figures are not necessarily drawn to scale. Identical numbers used in the figures refer to identical components.However, it is understood that the use of a number to refer to a component in a given figure is not intended to limit the component in another figure designated by the same number. The description further characterizes and specifies the present disclosure, particularly in connection with the figures.

[0029] Other aspects, advantages and outstanding features of the present disclosure will become apparent to the person skilled in the art from the following detailed description, which, in conjunction with the accompanying drawings, discloses exemplary embodiments of the disclosure, wherein: Fig. Figure 1 shows a blind spot in front of a vehicle according to one embodiment of the present disclosure. Fig. Figure 2 shows a block diagram of an object recognition system according to an embodiment of the present disclosure. Fig. Figure 3 shows a camera positioned on a vehicle according to an embodiment of the present disclosure. Fig. Figure 4 shows a camera positioned on a vehicle and the blind spot in front of the vehicle according to an embodiment of the present disclosure. Fig. Figure 5 shows an orthogonal view of a blind spot in front of a vehicle according to an embodiment of the present disclosure. Fig. Figure 6 shows a flowchart of process steps for object recognition according to an embodiment of the present disclosure. Fig. Figure 7 shows a flowchart of process steps for object recognition according to a further embodiment of the present disclosure.

[0030] The aforementioned objectives, features, and advantages of the present disclosure will become clearer from the following detailed description in conjunction with the accompanying drawings. However, various modifications to the present disclosure are possible, and the present disclosure may have different embodiments. Specific embodiments of the present disclosure, illustrated in the drawings, are described in detail below.

[0031] The following description presents numerous specific details to provide a comprehensive understanding of the present disclosure. However, it will be evident to a person skilled in the art that the present disclosure can also be practiced without these specific details. Descriptions of known components and processing techniques are omitted to avoid unnecessarily obscuring the embodiments contained herein. The examples used herein serve only to facilitate an understanding of how the embodiments contained herein can be practiced and to further enable those skilled in the art to implement them. Accordingly, the examples should not be interpreted as limiting the scope of the embodiments contained herein.

[0032] A reference in this disclosure to "an embodiment" or "an embodiment" means that a particular feature, structure, or property described in connection with the embodiment is included in at least one embodiment of the present disclosure. The appearance of the expression "in an embodiment" at various points in the disclosure does not necessarily always refer to the same embodiment, nor do separate or alternative embodiments mutually exclude other embodiments. Furthermore, various features are described that may be present in some embodiments but not in others. Additionally, various requirements are described that may be requirements for some embodiments but not for others.

[0033] Although the following description contains many specific details for illustrative purposes, any person skilled in the art will recognize that many variations and / or modifications of these details fall within the scope of the present disclosure. Similarly, although many of the features of the present disclosure are described in relation to or in conjunction with one another, a person skilled in the art will recognize that many of these features can be provided independently of other features. Accordingly, this description of the present disclosure is set forth without loss of generality and without imposing any limitations on the present disclosure.

[0034] In the drawings, the thicknesses of layers and regions may be exaggerated for clarity. When it is stated that an element or layer is "on" or "above" another element or layer, this includes both cases where another layer or element is positioned between them and cases where the element or layer is directly above the other element or layer. Generally, reference numerals denote elements throughout this disclosure. In the following description, the same reference numerals are used to denote elements that have the same function within the same concept, as illustrated in the drawings of each embodiment of this disclosure.

[0035] If a detailed description of known functions or configurations relating to the present disclosure is considered an unnecessary obfuscation of the core of the disclosure, the detailed description is omitted. Likewise, numbers (e.g., first, second, etc.) used in the description herein are merely identifiers to distinguish one element from another.

[0036] Furthermore, the terms “module” and “unit”, which refer to elements in the following description, are only given or used in combination to facilitate the writing of the revealed scripture, and the terms themselves have no different meanings or roles.

[0037] Furthermore, the use of a singular term, such as "a" or "an", is not to be interpreted as limiting the number of components or details of specific components. Additionally, various terms and / or phrases that indicate a direction or positional reference, but are not limited to "top", "bottom", "front", "back", "forward", "backward", "end", "outside", "inside", "left", "right", "vertical", "horizontal", etc., refer to one or more specific components as generally applicable from the perspective of a user during use or operation. Such terms and / or phrases are not to be understood as open to interpretation, but merely as a representative basis for describing the disclosure to a person skilled in the field.Additionally, a suffix “region”, “part”, “unit” is for a component that is specified in the following description or in consideration of the sole purpose of describing the specification, and have no meanings or roles that differ from each other.

[0038] As described below, the term Vehicle 20 refers to an automobile powered by an internal combustion engine or a battery, with or without a trailer, and driven by a driver. For example, a Vehicle 20 could be a car, a truck, a tractor, a bus, a motorcycle, or a trailer.

[0039] Fig. Figure 1 shows a vehicle with a blind spot 10 from a top view according to an embodiment of the present disclosure. The blind spot 10 can refer to a rectangular area in front of the vehicle 20 that cannot be directly seen by the driver from a seated and / or driving position. As shown in Fig. Figure 2 shows an embodiment of the present disclosure, including a block diagram of a system 100 for detecting an object in a blind spot 10 in front of the vehicle 20. The object may be, but is not limited to, a nearby vehicle, an animal, or a vulnerable road user. The object may be in motion or stationary. The vulnerable road user may be defined according to United Nations standards, the European Union's Intelligent Transport System Directives, or similar government standards for transportation.

[0040] System 100 comprises a camera 102 and a control unit 104. The camera 102 can be a conventionally known image capture device, e.g., a fisheye camera. The camera 102 can be positioned on top of a windshield of the vehicle 20, as shown in the Fig. Figures 3 to 5 show how to partially or completely capture the blind spot 10. In one embodiment, the camera 102 can be positioned in the center of the top of the windshield, as shown in Fig. Figure 3 shows. In another embodiment, two cameras 102 can be positioned on the right and left upper sides of the windshield. Furthermore, the camera 102 can be aligned with or parallel to the chassis of the vehicle 20, as shown in the Fig. 3, Fig. 4 and Fig. 5 shown. The camera 102 can be configured to detect the blind spot 10 in front of the vehicle 20, as shown in the Fig. 4 and Fig. 5 shown. Camera 102 can take pictures of the object entering the blind spot 10, as shown in the Fig. 4 and Fig. Figure 5 shows that the camera 102 can capture the image at a predefined time interval or continuously. The camera 102 can transmit the captured image data wirelessly or via a cable connection known to those skilled in the art to the control unit 104.

[0041] The control unit 104 can be configured to receive the captured image data from the camera 102. The control unit 104 can be a processor or an electronic control unit. In one embodiment, the control unit 104 can be an electronic control unit 104 of the vehicle 20. In another embodiment, the control unit 104 can be located in the vehicle 20. In another embodiment, the control unit 104 can be located at a base station. The base station can be a central location configured to receive data from a plurality of vehicles 20, in particular wirelessly. In one embodiment, the base station can be located at a cloud location.

[0042] The control unit 104 can have access to pre-stored (pre-saved) image data. In another embodiment, the control unit 104 can include a data storage unit for storing the pre-stored image data. The pre-stored image data includes information about objects with different visual attributes such as shape, size, and color, in order to recognize patterns of, for example, pedestrians, animals, vehicles, walls, trees, or the like. The pre-stored image data can be used by an artificial intelligence approach to recognize patterns of pre-stored objects. The control unit 104 can also have stored the coordinates of a predetermined area of ​​interest within the blind spot 10. In one case, the predetermined area of ​​interest can be part or all of the blind spot 10.

[0043] Furthermore, the control unit 104 can be configured to process the received image data. This processing can include classifying the object within the image data. The classification can encompass categorizing objects, such as people, animals, vehicles, and the like, and / or categorizing a hazard level, such as high or low, and / or categorizing the probability of a potential collision with the object, such as high or low probability.

[0044] Furthermore, the processing of the received image data includes the localization of the object within the image data. The object localization can provide the pixel coordinates of the object in the received image data. The control unit 104 can be configured to use an artificial intelligence approach, such as a deep learning approach and / or a neural network model, to perform the classification and localization of the object in the received image data, with the neural network model comprising multiple convolutional layers. In one embodiment, the multiple convolutional layers can include a YOLO backbone, RESNET head, segmentation, and semantic segmentation, resulting in classification and localization. The deep learning approach and neural networks are used, in particular, to determine the projection points of one or more objects, e.g.,The goal is to locate the projection points of a person, vehicle, cyclist, animal, wall, tree, or similar object on the ground. For example, the projection points of the left and right foot on the ground or the front and rear wheels of a bicycle are located. Calibration can be used to assign one or more ground positions to pixels or groups of pixels, for example, by projecting points from a top-down or bird's-eye view. By using one or more, or even all, of the object's detected projection points connected to the ground, the object's position can be determined.

[0045] In addition to the projection points, further points (for example, creating a frame of body points of a person or shape points of a vehicle) and / or features such as size, shape, color, or the like are used by the deep learning approach and / or neural network to classify the object, e.g., as a person, vehicle, or tree, and to calculate the real and complete object shape and position relative to vehicle 20. Using the projection points and / or additional features, the object can be tracked, optionally using the cosine similarity of feature vectors. Using the tracking history, an extrapolation of the trajectory can be performed to predict a possible collision with the front of vehicle 20.

[0046] Furthermore, the control unit 104 can be configured to convert the received image data into corresponding circumferential coordinates, wherein the corresponding circumferential coordinates refer to a viewpoint with respect to the position of the camera. In one embodiment, the circumferential coordinates can be coordinates of the outer edges of the object (as in Fig. (4 shown). In an embodiment where the object is a human, the circumferential coordinates can be the coordinates of limbs. The conversion of the processed image data into the corresponding circumferential coordinates can correspond to the conversion of pixel coordinates into real-world coordinates.

[0047] Furthermore, the control unit 104 can be configured to transform the converted circumferential coordinates into corresponding orthogonal coordinates, where the corresponding orthogonal coordinates refer to the orthogonal viewpoint with respect to the blind angle 10, as shown in Fig. 5 shown. For example, as in Fig. As shown in Figure 5, the object appears as a circular point directly above the blind spot 10 from the orthogonal viewpoint. The transformation of the converted circumferential coordinates into the corresponding orthogonal coordinates can correspond to a perspective transformation, where the transformed coordinates can correspond to the real 2D or 3D coordinates, with the origin of the coordinates referring, for example, to the position of the camera, a specific point on the vehicle 20, or a specific point in the vehicle 20's environment, such as a specific point on the ground. Furthermore, the control unit 104 can be configured to detect the object's entry into the blind spot 10 when comparing at least one of the transformed orthogonal coordinates with the coordinates of the predetermined area of ​​interest within the blind spot 10.

[0048] Furthermore, upon detection, the control unit 104 can be configured to notify the driver of the vehicle 20. The notification of the driver of the vehicle 20 can be, but need not be limited to, a visual notification, an audible notification, and / or a haptic notification. In another embodiment, the control unit 104 can send a signal and / or even control at least one driver assistance system and / or a function of the vehicle 20, such as braking or acceleration.

[0049] Furthermore, it shows ( Fig. 6) A flowchart of a method 200 for detecting an object in the blind spot in front of the vehicle 20 according to one embodiment. The method 200 begins with the start step 201. In the image data acquisition step 202, the camera 102 acquires the image data. In the image data acquisition step 204, the control unit 104, which is configured in a vehicle 20 and / or at a base station, receives the image data from the camera 102. Furthermore, in the image data processing step 206, the control unit 104 processes the received image data to locate the object in the received image data. In the image data conversion step 208, the control unit 104 converts the processed image data into corresponding circumferential coordinates, whereby the corresponding circumferential coordinates can refer to the viewpoint with respect to the position of the camera 102.Furthermore, in the step of transforming the converted circumferential coordinates 210, the control unit 104 converts the converted circumferential coordinates into corresponding orthogonal coordinates, whereby the corresponding orthogonal coordinates can refer to the orthogonal viewpoint with respect to the blind spot. Step 210 leads to the step of detecting an object in the blind spot 212, whereby the control unit 104 detects the object in the blind spot 10 by comparing at least one of the transformed orthogonal coordinates with the coordinates of the predetermined area of ​​interest in the blind spot 10. The procedure 200 ends with the final step 214.

[0050] Similarly, ( Fig.7) A flowchart of a method 300 for detecting the object in the blind spot in front of the vehicle 20 according to a further embodiment. The method 300 begins with the start step 301. In the step of receiving the image data 302, the control unit 104 located at the base station receives the image data from the camera 102. The base station can be a central location configured to receive data from a plurality of the vehicles 20. In one embodiment, the base station can be located at a cloud location. Furthermore, in the step of processing the received image data 304, the control unit 104 processes the received image data to locate the object in the received image data.In step 306, converting the processed image data, the control unit 104 converts the processed image data into corresponding circumferential coordinates, whereby the corresponding circumferential coordinates can refer to the viewpoint with respect to the position of the camera 102. Furthermore, in step 308, transforming the converted circumferential coordinates, the control unit 104 converts the converted circumferential coordinates into corresponding orthogonal coordinates, whereby the corresponding orthogonal coordinates can refer to the orthogonal viewpoint with respect to the blind spot 10. This step 308 leads to step 310, detecting an object in the blind spot, whereby the control unit 104 detects the object in the blind spot 10 by comparing at least one of the transformed orthogonal coordinates with the coordinates of the predetermined area of ​​interest in the blind spot 10. The procedure 300 ends with the final step 312.

[0051] Therefore, the present disclosure provides a system for detecting an object in a blind spot in front of a vehicle 20. Furthermore, the present disclosure provides a method for detecting an object in a blind spot in front of a vehicle 20.

[0052] Although the subject matter of this disclosure has been described in language specific to structural features and / or actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are disclosed as examples of the implementation of the claims, and other equivalent features and actions are intended to fall within the scope of the claims. That is, the features disclosed in the foregoing description, the claims, and the drawings may be essential, individually or in any combination, to realize this disclosure in its various embodiments. The embodiments shown here are merely examples of this disclosure and should therefore not be understood as limiting.Alternative embodiments considered by the person skilled in the art are likewise covered by the scope of protection of the present disclosure. REFERENCE MARK LIST 10 blind spots 20 vehicles 100 System 102 Camera 104 Control unit 200 methods for object recognition 201 Start of the procedure Step 202 of capturing image data Step 204 of obtaining the captured image data Step 206 of processing the received image data Step 208 of converting the processed image data Step 210 of transforming the converted circumference coordinates Step 212 of detecting an object in the blind spot 214 End of the procedure 300 computer-implemented methods for object recognition 301 Commencement of the procedure Step 302 of obtaining the image data Step 304 of processing the received image data Step 306 of converting the processed image data Step 308 of transforming the converted circumference coordinates 310 Steps of Detecting an Object in the Blind Spot 312 End of the procedure QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] US 11054835B2

[0004] CN 105405320A

[0004] KR 102605696B1

[0004]

Claims

A method (200) for object detection in at least one blind spot (10) in the vicinity of a vehicle (20), the method comprising: capturing (202) image data of at least one area in the vicinity of the vehicle (20) that at least partially covers the blind spot (10); processing (206) at least partially of the acquired image data to locate at least one object in the acquired image data; converting (208) the processed image data at least partially into corresponding perimeter coordinates, wherein the corresponding perimeter coordinates are defined relative to a viewpoint from which the image data were acquired; transforming (210) the converted perimeter coordinates at least partially into corresponding orthogonal coordinates, wherein the corresponding orthogonal coordinates refer to an orthogonal viewpoint with respect to the blind spot (10);and detecting (212) a movement of at least one part of the object relative to the blind angle (10) based at least partially on at least one part of the transformed orthogonal coordinates.; The method (200) according to claim 1, wherein (i) the blind spot is located at the front, side and / or rear of the vehicle, optionally relative to a principal direction of travel and / or a position and / or direction of the driver's cabin and / or driver's seat; (ii) the image data are acquired by at least one camera (102); (iii) the processing, conversion, transformation and / or recognition is performed at least partially by at least one control unit (104), optionally arranged at least partially in the vehicle (20) and / or at at least one base station, wherein the image data are optionally obtained from the camera (102) by the control unit (104);(iv) the perimeter coordinates are defined relative to a viewpoint in relation to the position of the camera (102) and / or the origin of the coordinates is / are defined by the viewpoint, in particular of the camera (102); (v) the object is at least one of the following: a nearby vehicle, a person, an animal, a cyclist, a pedestrian, a wall, a building, an obstacle, a plant, a tree and / or an endangered road user; and / or (vi) the movement of at least part of the object involves at least partially entering and / or exiting the blind spot (10). The method (200) according to claim 1 or 2, wherein the processing step (206) also includes the classification of the object in the obtained image data, wherein the classification optionally includes a categorization of objects, optionally a human being, an animal, a cyclist, a wall, an obstacle, a plant, a tree, a vulnerable road user, a building, a vehicle, a pedestrian and / or the like, and / or includes a categorization of a hazard level, optionally a high hazard level or a low hazard level, and / or includes a categorization of a probability of a potential collision with the object, optionally a high or low probability. The method (200) according to claim 2 or 3, wherein the control unit (104) is configured to use an artificial intelligence approach, in particular using a deep learning approach and / or a neural network model, optionally to perform the classification and / or localization of the object in the obtained image data, wherein optionally the neural network model comprises multiple convolutional layers, optionally with Yolo backbone, RESNET head, segmentation and semantic segmentation, which lead to classification and localization. The method (200) according to one of claims 2 to 4, wherein the control unit (104), particularly when using the artificial intelligence approach, is configured to find at least one projection point of one or more elements, optionally of the object, in the captured image data, optionally of at least one person, at least one vehicle, at least one cyclist, at least one animal, at least one wall, at least one tree, at least one obstacle, at least one vulnerable road user, at least one plant, at least one building and / or the like, onto the ground, wherein optionally at least one calibration is used to assign pixels or groups of pixels of the captured image data to one or more locations on the ground, optionally by projecting points from a top or bird's-eye view. The method (200) according to claim 5, wherein, in addition to the projection points, at least one further point characterizing the object and / or object features such as size, shape, color or the like is used, in particular by the control unit (104) and / or the artificial intelligence approach to classify the element and / or the object, in particular after identifying the element as the object, optionally: as a human, as an animal, as a cyclist, as a wall, as a vehicle, as a plant, as a building, as an obstacle, as a vulnerable road user, as a plant or as a tree or the like, and optionally to calculate the real and complete object shape and position relative to the vehicle (20). The method (200) according to one of the preceding claims, wherein the camera (102) is placed on top of a front windshield or a rear windshield of the vehicle (20) and / or on the A-pillar and / or on a rearview device of the vehicle (20) and / or is optionally adapted to detect the blind spot (10). The method (200) according to one of the preceding claims, wherein the step of converting (208) the processed image data into the corresponding circumferential coordinates corresponds to a conversion of pixel coordinates into real-world coordinates, and / or the step of transforming (210) corresponds to a perspective transformation which optionally provides 2D or 3D real-world coordinates of the recorded area, wherein optionally an origin of the coordinates relates to the position of the camera or a specific point of the vehicle (20) or a specific point in the environment of the vehicle (20), optionally a specific point on the ground. The method (200) according to one of the preceding claims, wherein the control unit (104) has prestored coordinates of a predetermined area of ​​interest, in particular in the blind spot (10), wherein optionally the predetermined area of ​​interest is part or all of the blind spot (10), wherein optionally the detection step (212) is based on comparing at least one of the transformed orthogonal coordinates with coordinates of the predetermined area of ​​interest in the blind spot (10) in order to detect the entry of the object into the blind spot (10). The method (200) according to one of the preceding claims, wherein, after the object is detected, the control unit (104) is configured to notify a driver or passenger of the vehicle (20), wherein the notification is optionally a visual notification, an acoustic notification and / or a haptic notification, and / or the control unit (104) sends a signal and / or even controls at least one driver assistance system and / or a function of the vehicle (20) such as braking or accelerating. The method (200) according to one of the preceding claims, wherein the control unit (104) has access to pre-stored image data, wherein optionally the control unit (104) has a data storage unit for storing the pre-stored image data, wherein optionally the pre-stored image data includes information about the objects, in particular the object features, of varied visual attributes such as shape, size and color, wherein the attributes are used to recognize patterns of the element and / or object, optionally pedestrians, plants, vulnerable road users, people, buildings, obstacles, animals, vehicles, cyclists, walls, trees and / or the like, wherein optionally the pre-stored image data is used by the control unit (104) and / or the artificial intelligence approach to recognize patterns of pre-stored objects in the acquired image data.where optionally the object is tracked by using the projection points and / or the object feature, optionally by using the cosine similarity of feature vectors, where an extrapolation of the trajectory is derived from the tracking history to predict a possible collision with, in particular, the front of the vehicle (20). The method (200) according to one of the preceding claims, wherein the method (200) is a computer-implemented method in which the control unit (104) is arranged at the base station, wherein optionally the base station is a central location configured to receive data from a plurality of the vehicles (20), in particular wirelessly, and / or the base station is located at a cloud location. A system (100) for object detection in a blind spot (10) in the vicinity of a vehicle (20), wherein the system (100) comprises: a camera (102) configured to capture image data in the vicinity of the vehicle (20); and a control unit (104) arranged on and / or encompassed by the vehicle (20) and adapted to implement a method (200) according to any one of the preceding claims. The system (100) according to claim 11, wherein the control unit (104) is configured to: - receive the captured image data from the camera (102), - at least partially process the received image data to locate at least one object in the received image data, - at least partially convert the processed image data into corresponding circumferential coordinates; wherein the corresponding circumferential coordinates refer to a viewpoint with respect to a position of the camera (102), - at least partially transform the converted circumferential coordinates into corresponding orthogonal coordinates, wherein the corresponding orthogonal coordinates refer to an orthogonal viewpoint with respect to the blind spot (10), and / or - detect the entry of at least a part of the object into the blind spot (10) based at least on at least a part of the transformed orthogonal coordinates.

Images