Method and system for determining traffic mirror orientation - Patents.com

Abstract

The present disclosure provides a method and system (200) for determining an orientation of a traffic mirror (106). The method includes detecting an area of ​​the traffic mirror (106) from a real-time image of a field of view (108) of a vehicle (104). The real-time image of the field of view (108) of the vehicle (104) is captured while the vehicle (104) is moving. The method further includes identifying one or more edges of the traffic mirror (106) by processing the area of ​​the traffic mirror (106) detected in the real-time image. Thereafter, the method includes identifying a shape of the traffic mirror (106) based on an analysis of the one or more edges. Furthermore, the method includes measuring an inclination angle of the traffic mirror (106) using a predetermined angle measurement technique corresponding to the shape of the traffic mirror (106). Finally, the method includes determining an orientation of the traffic mirror (106) based on the inclination angle value of the traffic mirror (106).

Description

[Technical field]

[0001] The present disclosure relates generally to autonomous vehicles, and more particularly, to methods and systems for determining traffic mirror orientation and angle using image analysis. [Background technology]

[0002] Road mirrors or road safety mirrors are used to enhance traffic safety on roads, road intersections, and curved or bent lanes. Traffic mirrors provide better visibility to blind spots on the road and help prevent common hazards or accidents. In general, traffic mirrors benefit both drivers and pedestrians to see if there are other vehicles coming from the opposite direction.

[0003] However, to further reduce the risk of accidents, it is important that traffic mirrors are clearly visible to drivers. Moreover, for vehicles integrated with advanced driver assistance systems (ADAS) and autonomous driving (AD) mechanisms, it is also important to estimate the direction and angle of traffic mirrors to accurately predict the direction of traffic flow.

[0004] The information disclosed in the Background section of this disclosure is merely intended to enhance understanding of the general background of the invention and should not be construed as an admission or any form of suggestion that this information constitutes prior art already known to those of ordinary skill in the art. Summary of the Invention [Means for solving the problem]

[0005] Aspects of the present disclosure provide methods and systems for determining the orientation of a traffic mirror by analyzing an image of the traffic mirror.

[0006] One aspect of the present disclosure provides a method for identifying a traffic mirror orientation, comprising detecting an area of ​​the traffic mirror from a real-time image of a field of view of a vehicle. In one embodiment, the real-time image of the field of view of the vehicle is captured by an image sensor in the vehicle while the vehicle is moving. The method further comprises identifying one or more edges of the traffic mirror by processing the area of ​​the traffic mirror detected in the real-time image. Upon identifying the one or more edges, the method comprises identifying a shape of the traffic mirror based on an analysis of the one or more edges. Once the shape of the traffic mirror is identified, the method comprises measuring an installation angle of the traffic mirror using a predetermined angle measurement technique corresponding to the shape of the traffic mirror. Subsequently, the method comprises identifying an orientation of the traffic mirror based on the value of the installation angle of the traffic mirror.

[0007] Another aspect of the present disclosure provides a safety monitoring system for identifying a traffic mirror's orientation. The system includes a processor and at least one memory coupled to the processor. The at least one memory stores instructions executable by the processor and causing the processor to detect a region of the traffic mirror from a real-time image of the vehicle's field of view. In one embodiment, the real-time image of the vehicle's field of view is captured by an image sensor of the vehicle while the vehicle is moving. Further, the processor is configured to identify one or more edges of the traffic mirror by processing the region of the traffic mirror detected in the real-time image. After identifying the one or more edges, the processor identifies a shape of the traffic mirror based on an analysis of the one or more edges. Then, the processor measures an installation angle of the traffic mirror using a predetermined angle measurement technique corresponding to the shape of the traffic mirror. Finally, the processor identifies the orientation of the traffic mirror based on the value of the installation angle of the traffic mirror.

[0008] The above method and system embodiments of the present disclosure may provide several advantages. First, the method and system of the present disclosure are useful for identifying the orientation of traffic mirrors on a road. In some embodiments, the orientation and / or angle of traffic mirrors are important inputs for accurate risk prediction for advanced driver assistance systems (ADAS) and autonomous driving (AD) integrated vehicles. As a result, identifying the orientation of traffic mirrors enhances road safety and reduces the risk of road hazards or accidents.

[0009] The foregoing summary is merely illustrative and is not intended to be in any way limiting. Details of one or more implementations of the disclosure are set forth in the accompanying drawings and the following detailed description of the invention. Other aspects, features, and advantages will become apparent from the detailed description and drawings, and from the claims.

[0010] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, explain the disclosed principles. In the drawings, the leftmost digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the drawings to reference like features and components. Some embodiments of systems and / or methods according to embodiments of the present subject matter are now described, by way of example only, with reference to the accompanying drawings, in which: [Brief description of the drawings]

[0011] [Figure 1] 1 is an exemplary diagram illustrating a vehicle capturing real-time images of a traffic mirror according to one embodiment of the present disclosure. [Diagram 2] 1 illustrates a block diagram of a safety monitoring system for determining traffic mirror orientation according to one embodiment of the present disclosure. [Figure 3A] 2 illustrates a sequence of steps involved in a method for determining the orientation of a traffic mirror according to one embodiment of the present disclosure. [Figure 3B] 2 illustrates a sequence of steps involved in a method for determining the orientation of a traffic mirror according to one embodiment of the present disclosure. [Figure 3C] 2 illustrates a sequence of steps involved in a method for determining the orientation of a traffic mirror according to one embodiment of the present disclosure. [Figure 3D] 2 illustrates a sequence of steps involved in a method for determining the orientation of a traffic mirror according to one embodiment of the present disclosure. [Figure 4A] 1 illustrates an exemplary variation of the present disclosure according to an alternative embodiment of the present disclosure. [Figure 4B] 1 illustrates an exemplary variation of the present disclosure according to an alternative embodiment of the present disclosure. [Diagram 5] FIG. 1 is a flow diagram illustrating an exemplary method for determining a direction, according to one embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of exemplary systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flowcharts, state diagrams, pseudocode, or the like, may be substantially represented in a computer-readable medium and represent various processes that may be performed by such a computer or processor, whether or not a computer or processor is explicitly depicted.

[0013] In the following disclosure, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

[0014] While the disclosure is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and are described in detail below. It is to be understood, however, that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is intended to cover all modifications, equivalents and alternatives falling within the spirit and scope of the disclosure.

[0015] The terms "comprises," "comprising," "includes," or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device, or method comprising a list of components or steps may include not only those components or steps, but 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 proceeded by "including a..." does not, in the absence of more constraints, preclude the presence of other or additional elements in the system or method.

[0016] In the following detailed description of the embodiments of the present disclosure, reference is made to the accompanying drawings which form a part hereof, and which show, by way of illustration, specific embodiments in which the present disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, it being understood that other embodiments may be utilized and changes may be made without departing from the scope of the present disclosure. The following description, therefore, is not to be taken in a limiting sense.

[0017] FIG. 1 is an exemplary diagram illustrating a method for determining the direction of a traffic mirror 106 using a real-time image of the traffic mirror 106 according to an embodiment of the present disclosure. The traffic mirror 106 may be a road safety mirror or a road safety mirror that is installed at a predetermined position on the road 102 to avoid traffic collisions. Furthermore, the real-time image of the traffic mirror 106 may be an image captured in real time by the vehicle 104 while the vehicle 104 is moving on the road 102. In an embodiment, it is assumed that the safety monitoring system of the present disclosure is integrated into the vehicle 104 shown in FIG. 1. It is assumed that the vehicle 104 is moving on the road 102 and has come to an intersection where one or more other vehicles 110A and 110B pass through. It is assumed that the traffic mirror 106 is positioned at the intersection such that the traffic mirror 106 displays one or more other vehicles 110A, 110B merging and / or diverging from both sides of the road 102. It should be appreciated by those skilled in the art that the one or more other vehicles 110A, 110B shown in FIG. 1 are for representational purposes only and may include other types of obstacles and hazards on the roadway 102, including, but not limited to, potholes, pedestrians, etc.

[0018] In one embodiment, the vehicle 104 may be, but is not limited to, an autonomous or automated vehicle, an assisted driving vehicle with an advanced driver assistance system (ADAS). In order to avoid a possible collision, accident, or other type of danger, it may be necessary for the vehicle 104 to read and analyze the reflection displayed on the traffic mirror 106. In addition, in order to accurately predict the location of an incoming vehicle or danger, the vehicle 104 may need to estimate the correct direction and angle at which the traffic mirror 106 is installed on the road 102. For this purpose, the vehicle 104 may continuously capture real-time images of the traffic mirror 106 when the traffic mirror 106 appears within the field of view (FOV) 108 of an image sensor associated with the vehicle 104. In one embodiment, the vehicle 104 may capture real-time images of the traffic mirror 106 using an image sensor configured in a forward portion of the vehicle 104.

[0019] In one embodiment, to identify the orientation of the traffic mirror 106 for the reasons discussed above, the safety monitoring system on the vehicle 104 may perform one or more artificial intelligence (AI) and deep learning (DL) based operations on the real-time image of the traffic mirror 106. For example, a processor associated with the safety monitoring system may process the real-time image to detect the area of ​​the traffic mirror 106 in the real-time image. The area of ​​the traffic mirror 106 in the real-time image may be a portion of the real-time image that represents the traffic mirror 106. After detecting the area of ​​the traffic mirror 106, the processor may identify one or more edges of the traffic mirror 106 by further processing the area of ​​the traffic mirror 106 detected in the real-time image. The one or more edges of the traffic mirror 106 may represent a boundary of the traffic mirror 106 in the real-time image. After identifying the one or more edges, the processor may identify a shape of the traffic mirror 106 based on an analysis of the one or more edges. The processor may then measure the installation angle of the traffic mirror 106 using a predetermined angle measurement technique that corresponds to the shape of the traffic mirror 106. Finally, the processor may determine the orientation of the traffic mirror 106 based on the installation angle value of the traffic mirror 106. A detailed description of the various steps and processes involved in processing the real-time imagery to determine the orientation of the traffic mirror 106 is provided in further sections of this disclosure.

[0020] In one embodiment, once the direction of the traffic mirror 106 is identified, the direction of the traffic mirror 106 may be used as an input to accurately predict the position, speed, and movement of one or other vehicles 110A, 110B on the road 102. For example, in the case of an autonomous / self-driving vehicle, the direction information of the traffic mirror 106 may be used to carefully scan for an oncoming vehicle (i.e., one of the one or more other vehicles 110A, 110B) or other obstacles and estimate their position and speed. This in turn helps to reduce the processing load on the autonomous path monitoring control unit of the vehicle 104, as the control unit may easily change the driving path based on the direction of the traffic mirror 106. Alternatively, in the case of a driver-assisted or ADAS-equipped vehicle, the direction information of the traffic mirror 106 may be used to alert the driver of the vehicle 104 about the position and speed of one or more other vehicles 110A, 110B. The path of the vehicle 104 may then be appropriately changed to mitigate any risks.

[0021] FIG. 2 illustrates a block diagram of a safety monitoring system 200 for determining the orientation of a traffic mirror 106, according to one embodiment of the present disclosure.

[0022] In one embodiment, the safety monitoring system 200 may be configured within the vehicle 104 to identify the orientation of traffic mirrors 106 encountered during the movement of the vehicle 104. Alternatively, the safety monitoring system 200 may be remotely connected to the vehicle 104. In one embodiment, the safety monitoring system 200 may include, but is not limited to, a processor 202, a memory 204, and an I / O interface 206.

[0023] In one embodiment, the processor 202 may be, for example, a microcontroller or a graphics processing unit (GPU) capable of accessing the memory 204 to store information and execute instructions stored therein. Alternatively, the processor 202 may be a part of an engine control unit (ECU) in the vehicle 104. In one embodiment, the processor 202 and the memory 204 may be integrated into a single integrated circuit. In one embodiment, the memory 204 stores information accessible by the processor 202, such as instructions executable by the processor 202 and data that may be stored, retrieved, or otherwise used by the processor 202. For example, the processor 202 may execute a method for determining the orientation of the traffic mirror 106 according to some embodiments of the present disclosure based on the instructions stored in the memory 204. As an example, the data stored in the memory 204 may include, but is not limited to, a reference image of one or more traffic mirrors, a measured installation angle of the traffic mirror 106, etc. In one embodiment, the I / O interface 206 of the safety monitoring system 200 may be used to interface the safety monitoring system 200 with one or more other components of the vehicle 104 .

[0024] In one embodiment, the safety monitoring system 200 may comprise one or more functional modules including an image sensor module 208, an area detection module 210, an edge detection module 212, a shape identification module 214, an angle measurement module 216, and a user interface 218. In one embodiment, each of the above modules may be communicatively coupled to each of the other modules via a controller area network (CAN) bus. Furthermore, each of the modules may be a controller and may be supervised by a processor 202 based on instructions and data stored in a memory 204 to determine the orientation of the traffic mirror 106.

[0025] In one embodiment, the image sensor module 208 may comprise one or more image sensors. The image sensors may be externally mounted on various parts of the vehicle 104. Furthermore, the image sensors may be configured to continuously capture real-time images in a field of view (FOV) 108 in front of the vehicle 104 as long as the vehicle 104 is moving. Alternatively, the image sensors may capture real-time images only when the traffic mirrors 106 are detected in the FOV 108 of the vehicle 104. As an example, the image sensor may be a vision image sensor, such as a mono camera or a wide-angle fish-eye camera, mounted on the front bumper of the vehicle 104. In one embodiment, the image sensor module 208 may comprise other types and numbers of image sensors other than those mentioned above based on the requirements of the vehicle 104.

[0026] In one embodiment, the area detection module 210 may be configured to detect the area of ​​the traffic mirror 106 from the real-time image of the FOV 108 of the vehicle 104. As an example, the area detection module 210 may detect the area of ​​the traffic mirror 106 using one or more predefined computer vision techniques, such as single object localization or object detection. Alternatively, the area detection module 210 may use any other artificial intelligence (AI) and deep learning (DL) techniques for localizing and detecting the area of ​​the traffic mirror 106 in the real-time image. In one embodiment, the input to the area detection module 210 may be a raw real-time image captured by the image sensor module 208, and the output of the area detection module 210 may be a processed image that highlights the area of ​​the traffic mirror 106 in the real-time image. An exemplary output of the area detection module 210 is shown in image 302 of FIG. 3A.

[0027] In one embodiment, the edge detection module 212 may be configured to identify one or more edges of the traffic mirror 106 by processing the area of ​​the traffic mirror 106 detected in the real-time image. In one embodiment, the edge detection module 212 may identify the one or more edges using a pre-trained Convolutional Neural Network (CNN). Alternatively, the edge detection module 212 may use any other AI and DL techniques to identify one or more edges corresponding to the area of ​​the traffic mirror 106. An exemplary output of the edge detection module 212 is shown in image 304 of FIG. 3B.

[0028] In one embodiment, the shape identification module 214 may be configured to identify the shape of the traffic mirror 106 by analyzing one or more detected edges of the traffic mirror 106. The shape identification module 214 may identify the shape by identifying a basic geometric shape that may be formed using one or more edges identified in the real-time image. As an example, the shape of the traffic mirror 106 may be identified as one of a circle, an oval, or a polygon.

[0029] In one embodiment, the angle measurement module 216 may be configured to measure the installation angle of the traffic mirror 106 based on an analysis of the shape of the traffic mirror 106. In one embodiment, the installation angle may be the angle between the traffic mirror 106 and a horizontal axis representing the roadway 102 on which the vehicle 104 is traveling. As an example, the installation angle may be 90 degrees when the traffic mirror 106 is installed vertically and / or in an exactly vertical position on the roadway 102. The installation angle may change when the traffic mirror 106 is tilted and / or bent in a particular direction. In one embodiment, the angle measurement module 216 may use different angle measurement techniques to measure the installation angle based on the identified shape of the traffic mirror 106. As an example, the angle measurement technique used to measure the installation angle of an elliptical shaped traffic mirror 106 may be an existing technique such as, but not limited to, the "findContours" function in OpenCV®. In addition, the angle measurement module 216 may use a predefined automatic angle compensation technique to handle any irregularities in the identified shape before measuring the installation angle. As an example, one of the predetermined automatic angle compensation techniques may be to rotate the identified features by a predetermined angle in a clockwise or counterclockwise direction.

[0030] In one embodiment, the user interface 218 may be used to display and / or inform the driver or passengers in the vehicle 104 of the identified direction and angle of the traffic mirror 106. Additionally, the user interface 218 may be used to communicate audio and / or visual messages to the driver / passengers of the vehicle 104. In one variation, the user interface 218 may include one or more components, such as an instrument panel, an electronic display, and an audio system. The instrument panel may be, for example, a dashboard or center display displaying a speedometer, a tachometer, and warning light indicators. The user interface 218 may also include an electronic display, such as an infotainment or head-up display, for communicating other visual messages to the driver / passengers, and an audio system for playing audio messages, warnings, or music.

[0031] 3A-3D show a sequence of steps involved in a method for determining the orientation of a traffic mirror 106 according to one embodiment of the present disclosure.

[0032] 3A illustrates an exemplary real-time image 300 of a field of view (FOV) 108 of a vehicle 104 captured by an image sensor module 208 of the vehicle 104 while the vehicle 104 is moving and a traffic mirror 106 is detected within the FOV 108 of the vehicle 104. In one embodiment, after capturing the real-time image 300, the safety monitoring system 200 configured in the vehicle 104 may process the real-time image to detect the area of ​​the traffic mirror 106 in the real-time image 300. A cropped and / or extracted portion of the real-time image 300 comprising the area of ​​the traffic mirror 106 is shown in image 302 of FIG. 3A.

[0033] In one embodiment, once the area of ​​the traffic mirror 106 has been acquired, the safety monitoring system 200 may identify one or more edges of the traffic mirror 106, as shown in image 304 of Figure 3B. The safety monitoring system 200 may then identify a shape of the traffic mirror 106 based on an analysis of the one or more edges detected in image 304. In this example, the traffic mirror 106 is elliptical in shape, as shown in image 300 of Figure 3A, so the safety monitoring system 200 may detect a boundary of the ellipse from the one or more edges, as shown in image 306 of Figure 3C.

[0034] In one embodiment, after detecting the shape of the traffic mirror 106, the safety monitoring system 200 may measure the installation angle of the traffic mirror 106 by calculating the angle of tilt and / or rotation of the traffic mirror 106 relative to a reference horizontal axis 309 corresponding to the vehicle 104. For example, as shown in image 308 of FIG. 3D, the reference horizontal axis 309 may be an x-coordinate axis representing the plane of the road 102 and / or the vehicle 104. Furthermore, as shown in image 308, the installation angle may be calculated as the angle between the tilt axis of the detected shape (shown by a dotted line in image 308) and the reference horizontal axis 309. In image 308, the installation angle is represented by an angle "θ".

[0035] In one embodiment, once the installation angle is measured, the safety monitoring system 200 may identify the orientation of the traffic mirror 106 based on the installation angle value. In one embodiment, the orientation of the traffic mirror 106 may be identified as "right" if the installation angle value is less than 90 degrees. In an alternative embodiment, the orientation of the traffic mirror 106 may be identified as "left" if the installation angle value is between 90 degrees and 180 degrees. In this example, the orientation of the traffic mirror 106 may be identified as "right" because the installation angle "θ" is between 90 degrees and 180 degrees. The same steps may be repeated to identify the installation angle of traffic mirrors 106 of any shape and size.

[0036] In one embodiment, Figure 4A shows an alternative embodiment in which the traffic mirror 106 is tilted to the right, where the installation angle "θ" may be less than 90 degrees, as shown in image 404 of Figure 4A, and therefore the direction of the traffic mirror 106 may be identified as left.

[0037] FIG. 4B illustrates yet another embodiment of the proposed disclosure for detecting the orientation of a traffic mirror 106 having a polygonal shape (e.g., a square shape). In one embodiment, the image 406 of FIG. 4B may be a real-time image of the traffic mirror 106. The image 408 may represent a region of the traffic mirror 106 extracted from the real-time image 406. In one embodiment, for traffic mirrors that are polygonal in shape, the installation angle may be measured by performing an automatic angle compensation technique on the region of the traffic mirror 106 shown in the image 408. For example, since the region of the traffic mirror 106 in the image 408 is tilted to the right, the automatic compensation technique may rotate the region of the traffic mirror 106 in a counterclockwise direction to compensate for the tilt angle of the region of the traffic mirror 106. As an example, the image 408 may be rotated 8 degrees counterclockwise to compensate for the tilt angle, resulting in a compensated image 410. Furthermore, the installation angle of the traffic mirror 106 may be measured as the magnitude of the angle through which the image 408 is rotated. In this example, the installation angle may be measured as 8 degrees since the image 408 has been rotated 8 degrees. Finally, the orientation of the traffic mirror 106 in the image 406 may be identified as "right" since the installation angle is less than a value of 90 degrees.

[0038] In one embodiment, the process illustrated above may be used to measure the installation angle of traffic mirrors of any other size and shape.

[0039] FIG. 5 is a flow diagram illustrating an example method 500 for determining an orientation of a traffic mirror 106 according to one embodiment of the disclosure.

[0040] In one embodiment, the method 500 may be performed sequentially or in parallel with other embodiments of the present disclosure to determine the orientation of the traffic mirrors 106. For example, based on traffic requirements and size, traffic mirrors may be used in different sizes and shapes, including but not limited to oval, square, or other polygonal shapes. Thus, two or more processes may be performed simultaneously or sequentially to determine the orientation of traffic mirrors regardless of their size and shape.

[0041] Operation of the method 500 will be described with reference to the safety monitoring system 200 of Figure 1, however, it will be appreciated that other similar systems may be suitable. The method 500 begins at step 502 and may be initiated when the ignition of the vehicle 104 is turned on. Other events for initiating the start of the method 500 may also be suitable, and the method may also be initiated on demand.

[0042] In step 502, the method 500 begins by having the processor 202 in the safety monitoring system 200 detect the area of ​​the traffic mirror 106 from a real-time image of the field of view (FOV) 108 of the vehicle 104. In one embodiment, the vehicle 104 may be an autonomous vehicle or a vehicle 104 equipped with an advanced driver assistance system (ADAS). In one embodiment, the vehicle 104 may capture a real-time image of the FOV 108 of the vehicle 104, including the traffic mirror 106, using an image sensor configured in the vehicle 104. In one embodiment, the area of ​​the traffic mirror 106 may be detected using a predefined artificial intelligence (AI) technique, such as, but not limited to, a pre-trained convolutional neural network (CNN).

[0043] In step 504, the method 500 causes the processor 202 in the safety monitoring system 200 to identify one or more edges of the traffic mirror 106 by processing the area of ​​the traffic mirror 106 detected in the real-time image. In one embodiment, the one or more edges of the traffic mirror 106 may be identified using a predefined edge detection technique.

[0044] In step 506, the method 500 causes the processor 202 in the safety monitoring system 200 to identify a shape of the traffic mirror 106 based on an analysis of the identified one or more edges. In one embodiment, the shape of the traffic mirror 106 may be at least one of, but is not limited to, a circle, an ellipse, or a polygon.

[0045] In step 508, the method 500 causes the processor 202 in the safety monitoring system 200 to measure an installation angle of the traffic mirror 106. In one embodiment, the installation angle may be an installation angle of the traffic mirror 106 relative to the roadway 102. In other words, the installation angle may be a tilt angle of the traffic mirror 106 relative to the roadway 102. In one embodiment, the installation angle may be measured using a predetermined angle measurement technique that corresponds to the shape of the traffic mirror 106. In one embodiment, measuring the installation angle may further include applying an angle compensation technique to the identified shape prior to measuring the installation angle. The compensation technique may be selected based on the identified shape of the traffic mirror 106.

[0046] In step 510, the method 500 causes the processor 202 in the safety monitoring system 200 to determine a direction of the traffic mirror 106 based on a value of the installation angle of the traffic mirror 106. In one embodiment, the direction of the traffic mirror 106 may be determined as "right" if the installation angle value is less than 90 degrees or between 0 and 90 degrees. Similarly, the direction of the traffic mirror 106 may be determined as "left" if the installation angle value is between 90 and 180 degrees.

[0047] The terms "an embodiment," "embodiment," "embodiments," "the embodiment," "the embodiment," "the embodiment," "one or more embodiments," "some embodiments," and "one embodiment" mean "one or more (but not all) embodiments of the present invention," unless expressly specified otherwise.

[0048] The terms "including," "comprising," "having," and variations thereof mean "including, but not limited to," unless expressly stated otherwise. An enumerated list of items does not imply that any or all of the items are mutually exclusive, unless expressly stated otherwise.

[0049] The terms "a," "an," and "the" mean "one or more" unless expressly specified otherwise. A description of an embodiment having several components in communication with each other does not imply that all such components are required. On the contrary, a variety of optional components are described to illustrate the wide variety of possible embodiments of the present invention.

[0050] It will be apparent that where a single device or article is described herein, more than one device / article (whether they cooperate or not) may be substituted for the single device / article. Similarly, where more than one device or article is described herein (whether they cooperate or not), it will be apparent that a single device / article may be substituted for more than one device or article, or a different number of devices / articles may be substituted for the number of devices or programs illustrated. The functionality and / or features of a device may alternatively be embodied by one or more other devices not explicitly described as having such functionality / features. Thus, other embodiments of the invention need not include a device per se.

[0051] Finally, the language used herein has been selected primarily for ease of reading and teaching purposes, and not to delineate or limit the subject matter of the present invention. Accordingly, it is intended that the scope of the invention be limited not by this detailed description, but by any claims that issue on an application based hereon. Accordingly, the embodiments of the present invention are intended to illustrate, but not limit, the scope of the invention, which is set forth in the following claims.

[0052] While various aspects and embodiments have been disclosed herein, other aspects and embodiments will become apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope and spirit being indicated by the following claims. This application relates to the invention described in the claims, but also includes the following as other aspects. 1. A method for determining the orientation of a traffic mirror (106), comprising: detecting, by a processor (202), an area of ​​a traffic mirror (106) from a real-time image of a field of view (108) of a vehicle (104), the real-time image of the field of view (108) of the vehicle (104) being captured while the vehicle (104) is moving; identifying, by the processor (202), one or more edges of the traffic mirror (106) by processing the area of ​​the traffic mirror (106) detected in the real-time image; identifying, by the processor (202), a shape of the traffic mirror (106) based on an analysis of the one or more edges; measuring, by the processor (202), an inclination angle of the traffic mirror (106) using a predetermined angle measurement technique corresponding to the shape of the traffic mirror (106); determining, by the processor (202), the orientation of the traffic mirror (106) based on the installation angle value of the traffic mirror (106); A method comprising: 2. 2. The method of claim 1, wherein the vehicle (104) is an autonomous vehicle or an autonomous vehicle equipped with an advanced driver assistance system (ADAS). 3. 2. The method according to claim 1, wherein the area of ​​the traffic mirror (106) is detected using certain artificial intelligence (AI) techniques. 4. 2. The method of claim 1, wherein the shape of the traffic mirror (106) is at least one of a circle, an ellipse, or a polygon. 5. 2. The method of claim 1, wherein measuring the installation angle further comprises applying, by the processor (202), an angle compensation technique to the identified feature before measuring the installation angle. 6. 6. The method of claim 5, wherein the installation angle is measured relative to a reference horizontal axis corresponding to the vehicle (104). 7. the direction of the traffic mirror (106) is identified as "right" if the installation angle value is less than 90 degrees; the direction of the traffic mirror (106) is identified as "left" if the installation angle value is between 90 degrees and 180 degrees; The method according to claim 1. 8. A safety monitoring system (200) for determining the orientation of a traffic mirror (106), comprising: a processor (202); at least one memory (204) coupled to the processor (202) and storing instructions executable by the processor (202), the instructions causing the processor (202) to: detecting an area of ​​a traffic mirror (106) from a real-time image of a field of view (108) of a vehicle (104), the real-time image of the field of view (108) of the vehicle (104) being captured while the vehicle (104) is moving; processing the area of ​​the traffic mirror (106) detected in the real-time image to identify one or more edges of the traffic mirror (106); identifying a shape of the traffic mirror (106) based on an analysis of the one or more edges; measuring an inclination angle of the traffic mirror (106) using a predetermined angle measurement technique corresponding to the shape of the traffic mirror (106); and determining the orientation of the traffic mirror based on the value of the installation angle of the traffic mirror; A system comprising: 9. 9. The system (200) of claim 8, wherein the vehicle is an autonomous vehicle or an autonomous vehicle equipped with an advanced driver assistance system (ADAS). 10. 9. The system (200) according to claim 8, wherein the area of ​​the traffic mirror (106) is detected using certain artificial intelligence (AI) techniques. 11. 9. The system (200) of claim 8, wherein the shape of the traffic mirror (106) is at least one of a circle, an ellipse, or a polygon. 12. 9. The system (200) of claim 8, wherein measuring the installation angle further comprises applying an angle compensation technique to the identified feature prior to measuring the installation angle. 13. 13. The system (200) of claim 12, wherein the installation angle is measured relative to a reference horizontal axis corresponding to the vehicle (104). 14. the direction of the traffic mirror (106) is identified as "right" if the installation angle value is less than 90 degrees; the direction of the traffic mirror (106) is identified as "left" if the installation angle value is between 90 degrees and 180 degrees; 9. The system (200) according to claim 8. 15. A non-transitory computer-readable storage medium comprising computer-readable instructions for performing a method according to any one of 1 to 7 above. 16. A vehicle (104) comprising a safety monitoring system (200) for identifying the direction of a traffic mirror (106) according to any one of 8 to 14 above. [Explanation of symbols]

[0053] 100 Illustrative Figures 102 Road 104 vehicles 106 Traffic Mirror 108 Field of view 110 (110A, 110B) Other vehicles 200 Safety Monitoring System 202 Processor 204 Memory 206 I / O Interface 208 Image Sensor Module 210 Area Detection Module 212 Edge Detection Module 214 Shape Recognition Module 216 Angle Measurement Module 218 User Interface

Claims

1. A method for determining the orientation of a traffic mirror (106), comprising: The method comprises: detecting, by a processor (202), an area of ​​a traffic mirror (106) from a real-time image of a field of view (108) of a vehicle (104), the real-time image of the field of view (108) of the vehicle (104) being captured while the vehicle (104) is moving; identifying, by the processor (202), one or more edges of the traffic mirror (106) by processing the area of ​​the traffic mirror (106) detected in the real-time image; identifying, by the processor (202), a shape of the traffic mirror (106) based on an analysis of the one or more edges; measuring, by the processor (202), an inclination angle of the traffic mirror (106) using a predetermined angle measurement technique corresponding to the shape of the traffic mirror (106); determining, by the processor (202), the orientation of the traffic mirror (106) based on the installation angle value of the traffic mirror (106); Including, determining the installation angle further includes applying, by the processor (202), an angle compensation technique to the identified feature prior to determining the installation angle. method.

2. The method of claim 1 , wherein the vehicle (104) is an autonomous vehicle or an autonomous vehicle equipped with an advanced driver assistance system (ADAS).

3. The method of claim 1 , wherein the area of ​​the traffic mirror (106) is detected using an artificial intelligence (AI) technique.

4. The method of claim 1 , wherein the shape of the traffic mirror (106) is at least one of a circle, an ellipse, or a polygon.

5. The method of claim 1 , wherein the installation angle is measured relative to a reference horizontal axis corresponding to the vehicle (104).

6. the direction of the traffic mirror (106) is identified as "right" if the installation angle value is less than 90 degrees; the direction of the traffic mirror (106) is identified as "left" if the installation angle value is between 90 degrees and 180 degrees; The method of claim 1.

7. A safety monitoring system (200) for identifying an orientation of a traffic mirror (106), comprising: The system (200) includes: A processor (202); At least one memory (204) coupled to the processor (202) and storing instructions executable by the processor (202), the instructions causing the processor (202) to: detecting an area of ​​a traffic mirror (106) from a real-time image of a field of view (108) of a vehicle (104), the real-time image of the field of view (108) of the vehicle (104) being captured while the vehicle (104) is moving; processing the area of ​​the traffic mirror (106) detected in the real-time image to identify one or more edges of the traffic mirror (106); identifying a shape of the traffic mirror (106) based on an analysis of the one or more edges; measuring an installation angle of the traffic mirror (106) using a predetermined angle measurement technique corresponding to the shape of the traffic mirror (106); determining the orientation of the traffic mirror based on the value of the installation angle of the traffic mirror; Equipped with The system (200), wherein measuring the installation angle further comprises applying an angle compensation technique to the identified feature prior to measuring the installation angle.

8. The system (200) of claim 7, wherein the vehicle is an autonomous vehicle or an autonomous vehicle equipped with an advanced driver assistance system (ADAS).

9. The system (200) of claim 7, wherein the area of ​​the traffic mirror (106) is detected using an artificial intelligence (AI) technique.

10. The system (200) of claim 7, wherein the shape of the traffic mirror (106) is at least one of a circle, an ellipse, or a polygon.

11. The system (200) of claim 7, wherein the installation angle is measured relative to a reference horizontal axis corresponding to the vehicle (104).

12. the direction of the traffic mirror (106) is identified as "right" if the installation angle value is less than 90 degrees; the direction of the traffic mirror (106) is identified as "left" if the installation angle value is between 90 degrees and 180 degrees; The system (200) of claim 7.

13. A non-transitory computer readable storage medium comprising computer readable instructions for performing the method of any one of claims 1 to 6.

14. A vehicle (104) comprising a safety monitoring system (200) for determining the orientation of a traffic mirror (106) according to any one of claims 7 to 12.

Images