SYSTEM AND METHOD FOR DETECTING TRAFFIC SIGNS

Abstract

The present disclosure provides a system (102) and a method (300) for detecting traffic signs. The system (102) receives data from a sensor (104) to represent a three-dimensional (3D) environment of a vehicle (106). The system (102) defines a region of interest (ROI) from the data to detect one or more objects. The system (102) identifies one or more clustered objects from the ROI using a clustering technique. The system (102) filters the one or more clustered objects according to one or more reflectivity values ​​corresponding to a traffic sign. Based on a predefined condition, the system (102) determines one or more vectors associated with the filtered one or more clustered objects and determines one or more data points associated with the traffic sign based on the one or more vectors.

Description

TECHNICAL AREA

[0001] The present disclosure relates generally to a field of assistance systems. In particular, the present disclosure relates to a system and a method for detecting traffic signs, e.g., using Light Detection and Ranging (LiDAR). BACKGROUND

[0002] Object tracking in vehicles, particularly in the context of advanced driver assistance systems (ADAS) and autonomous driving, involves detecting and tracking objects such as other vehicles, pedestrians, cyclists, etc., to ensure safe and efficient vehicle operation. Road signs must be recognized for safe vehicle maneuvering. These signs include various types such as speed limit signs, school zone signs, accident-prone areas, turn signals, and more. Recognizing traffic signs helps inform the driver about road conditions and traffic patterns.

[0003] Existing vehicle detection systems are unable to accurately determine the dimensions required to select a region of interest (ROI) for detecting specific objects on roads, such as traffic signs. When a vehicle detects a traffic sign, it cannot distinguish it from other objects in its vicinity. Current in-vehicle detection systems use a camera to convert images from three-dimensional (3D) to two-dimensional (2D) space and use these features to detect the traffic sign. The camera is used without secondary sensors such as Global Positioning System (GPS), Radio Detection and Ranging (RADAR), and similar technologies, resulting in inaccurate detection of the traffic sign or the detection of objects other than the traffic sign. Furthermore, existing detection systems have a limited range.

[0004] Therefore, there is a need for an advanced system and a procedure for improved detection of traffic signs. SUBJECT OF THE PRESENT DISCLOSURE

[0005] A general objective of the present disclosure is to overcome at least the problems mentioned above and to provide a system and method for detecting traffic signs, for example using Light Detection and Ranging (LiDAR).

[0006] One purpose of the present disclosure is to determine the exact position of the traffic signs on the road.

[0007] One objective of the present disclosure is to provide a system that receives a region of interest (ROI) associated with multiple objects identified on a road using a LiDAR sensor and detects data points associated with the traffic sign.

[0008] One objective of the present disclosure is to provide a system that uses an intensity filter to filter one or more clustered objects with one or more reflectance values ​​corresponding to traffic signs.

[0009] One purpose of the present disclosure is to provide a system that accurately distinguishes traffic signs from other objects on the road, such as vehicles or pedestrians. SUMMARY

[0010] This disclosure relates generally to assistance systems. In particular, this disclosure relates to a system and a method for recognizing one or more traffic signs.

[0011] One aspect of the present disclosure relates to a system for recognizing traffic signs. The system comprises a processor that is communicatively coupled to a sensor. The sensor is configured to be connected to a vehicle. The system also includes a memory that is coupled to the processor. The memory stores instructions which, when executed by the processor, cause the processor to receive data from the sensor to represent a three-dimensional environment of the vehicle. The processor is also configured to define a region of interest (ROI) from the data in order to detect one or more objects. Furthermore, the processor is configured to identify one or more clustered objects from the ROI using a clustering technique.Furthermore, the processor is configured to filter the one or more clustered objects to identify those with one or more reflectivity values ​​corresponding to a traffic sign. Additionally, the processor is configured to determine one or more vectors associated with the filtered one or more clustered objects based on a predefined condition. Finally, the processor is configured to determine one or more data points associated with the traffic sign based on these one or more vectors.

[0012] In one embodiment, the sensor can include a LiDAR (Light Detection and Ranging) sensor.

[0013] In one embodiment, the processor can use an intensity filter to filter the one or more clustered objects with one or more reflection values ​​that correspond to the traffic sign.

[0014] In one embodiment, the processor can select the one or more vectors based on the predefined condition. The predefined condition can include a maximum deviation of 10 degrees to identify the traffic sign.

[0015] In one embodiment, the processor can dynamically adjust the ROI based on the relative height of the detected cluster object(s) and avoid interference when detecting the traffic sign.

[0016] In another aspect, the present disclosure relates to a method for detecting traffic signs. The method comprises the reception of data from a sensor by a processor connected to a system to represent a three-dimensional environment of the vehicle. The method also comprises the processor defining a region of interest (ROI) from the data in order to detect one or more objects. Furthermore, the method comprises the processor using a clustering technique to identify one or more clustered objects from the ROI. Finally, the method comprises the processor filtering the one or more clustered objects to identify the one or more clustered objects with one or more reflectance values ​​corresponding to traffic signs.Furthermore, the method includes the processor determining one or more vectors associated with one or more filtered clustered objects based on a predefined condition. Additionally, the method includes the processor determining one or more data points associated with the traffic sign based on one or more vectors.

[0017] In one embodiment, the method may include filtering the one or more clustered objects with one or more reflectivity values ​​corresponding to the traffic sign by the processor using an intensity filter.

[0018] In one embodiment, the method may involve the processor determining a split of one or more vectors with the predefined condition, wherein the predefined condition includes a maximum deviation of 10 degrees to identify the traffic sign.

[0019] In one embodiment, the method can include the dynamic adjustment of the ROI by the processor, based on a relative height of the detected object(s) and to avoid interference from vehicles and pedestrians when detecting the traffic sign. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which form part of this invention, illustrate exemplary embodiments of the disclosed methods and systems, in which the same reference numerals refer to the same parts in the various drawings. The components in the drawings are not necessarily to scale, the emphasis being on clearly illustrating the principles of the present invention. In some drawings, the components are represented by means of block diagrams, which do not necessarily depict the internal circuits of the individual components. The person skilled in the art will understand that the invention of these drawings comprises the invention of electrical components, electronic components, or circuits commonly used to implement such components. Fig. Figure 1 shows an example architecture (100) representing a system (102) for detecting a traffic sign according to an embodiment of the present disclosure. Fig. Figure 2 shows an exemplary block diagram (200) of the proposed system (102) in accordance with an embodiment of the present disclosure. Fig. Figure 3 shows a flowchart of an example method (300) for detecting a traffic sign according to an embodiment of the present disclosure. Fig. Figure 4 shows a block diagram representing an exemplary computer system (700) in which or with which embodiments of the present disclosure can be used in accordance with embodiments of the present disclosure.

[0021] This will become apparent from the following more detailed description of the invention. DETAILED DESCRIPTION OF THE INVENTION

[0022] For explanatory purposes, various specific details are set forth below to enable a comprehensive understanding of the embodiments of the present disclosure. However, it will be clear that embodiments of the present disclosure can also be implemented without these specific details. Several of the features described below can each be used independently of one another or with any combination of other features. A single feature may not solve all of the problems discussed above, or may only solve some of them. Some of the problems discussed above may not be completely solved by any one of the features described here.

[0023] In one aspect, the present disclosure provides a system and a method for detecting a traffic sign. To ensure a smooth and safe journey, traffic signs on the road must be identified to allow for safe vehicle maneuvering. The present disclosure uses raw point cloud data (PCD) from Light Detection and Ranging (LiDAR) sensors. The traffic signs are detected by the LiDAR sensor. The LiDAR sensor has a large detection range, which enables accurate detection of the traffic signs. In one embodiment, the detection range of the sensor can be 100 meters (m).

[0024] In one embodiment, the system may include a processor that is communicatively coupled to a sensor configured in a vehicle. The system may include a memory that is operationally coupled to the processor. The memory stores instructions which, when executed by the processor, cause the processor to receive data from the sensor to represent a three-dimensional environment of the vehicle. The processor may be configured to define a region of interest (ROI) from the data in order to detect one or more objects. Furthermore, the processor may be configured to identify one or more clustered objects from the ROI using a clustering technique.Furthermore, the processor can be configured to filter the one or more clustered objects to identify those with one or more reflectivity values ​​corresponding to a traffic sign. Additionally, the processor can be configured to identify one or more vectors associated with the filtered one or more clustered objects based on a predefined condition. Finally, the processor can be configured to identify one or more data points associated with the traffic sign based on these one or more vectors.

[0025] Various embodiments of the present disclosure are described with reference to the Fig. 1-4 explained in more detail. 1-4.

[0026] Fig. Figure 1 shows an example architecture (100) representing a system (102) for detecting a traffic sign according to an embodiment of the present disclosure.

[0027] In one embodiment, the system (102) can include a processor (202, shown in Fig. 2) comprising a sensor (104) that is communicatively coupled to a vehicle (106). The sensor (104) is configured with a vehicle (106). In one embodiment, the sensor (104) is a Light Detection and Ranging (LiDAR) sensor. In one embodiment, the LiDAR sensor uses a remote sensing method that employs light in the form of a pulsed laser to measure variable distances of an object from a surface plane. In one embodiment, the surface plane can be the ground or the road on which the vehicle (114) is moving.

[0028] The system (102) can receive data from the sensor (104) to represent a three-dimensional (3D) environment of the vehicle (114). In one embodiment, the data received from the sensor (104) can include point cloud data (PCD). In one embodiment, the PCD can be a set of data points in a three-dimensional (3D) coordinate system. Each point represents a single spatial measurement on the surface of an object. The PCD thus represent the outer surface of the object.

[0029] In one embodiment, the system (102) can be configured to define a ROI from the data to detect one or more objects on the road. These objects may include, among others, traffic signs, other vehicles, or other objects detected on the road.

[0030] In one embodiment, the system (102) can identify one or more clustered objects from the ROI using a clustering technique. Furthermore, the system (102) can be configured to filter the one or more clustered objects to determine the one or more clustered objects with one or more reflectance values ​​corresponding to a road sign. In one embodiment, the road sign can include, among others, a speed limit sign, a school zone sign, an accident-prone area sign, a turn sign, and the like.

[0031] In one embodiment, the system (102) can be configured to determine, based on a predefined condition, one or more vectors associated with the filtered one or more clustered objects. Furthermore, the system (102) can be configured to determine, based on the one or more vectors, one or more data points associated with the traffic sign.

[0032] In one embodiment, the system (102) may be able to detect the traffic signs under all adverse conditions, such as darkness, cloud cover, and the like.

[0033] Fig. Figure 2 shows an exemplary block diagram (200) of the proposed system (102) in accordance with an embodiment of the present disclosure.

[0034] As in Fig. As shown in Figure 2, the system (102) can include one or more processors / processing devices (202), which may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuits, and / or any devices that process data based on operating instructions. Among other capabilities, the one or more processors (202) can be configured to retrieve and execute computer-readable instructions stored in the memory (204) of the system (102). The memory (204) can be configured to store one or more computer-readable instructions or routines on a non-volatile, computer-readable storage medium that can be retrieved and executed to create or share data packets via a network service. The memory (204) can include any non-volatile device, such as...volatile memory such as random access memory (RAM) or non-volatile memory such as erasable programmable read-only memory (EPROM), flash memory, and the like.

[0035] In one embodiment, the system (102) may include one or more interfaces (206). The interface(s) (206) may include a variety of interfaces, such as interfaces for data input and output (I / O) devices, storage devices, and the like. The interface(s) (206) may also provide a communication path for one or more components of the system (102). Examples of such components include a processing machine (208) and a database (210).

[0036] The processing machine(s) (208) can be implemented as a combination of hardware and programming (e.g., programmable instructions) to implement one or more functions of the processing machine(s) (208). In one embodiment of the examples described here, such combinations of hardware and programming can be implemented in various ways. For example, the programming for the processing machine(s) (208) can consist of processor-executable instructions stored on a non-volatile, machine-readable storage medium, and the hardware for the processing machine(s) (208) can include a processing resource (e.g., one or more processors) to execute such instructions. In the present examples, the machine-readable storage medium can store instructions which, when executed by the processing resource, implement the processing machine(s) (208).In such examples, the system (102) can include the machine-readable storage medium that stores the instructions and the processing resource for executing the instructions, or the machine-readable storage medium can be separate but accessible to the system (102) and the processing resource. In other examples, the processing machine(s) (208) can be implemented by electronic circuits.

[0037] In one embodiment, the processor (202) can receive data from the sensor to display a 3D environment of the vehicle (106). The processor (202) can define a region of interest (ROI) from the data to detect one or more objects. Furthermore, in one embodiment, the processor (202) can use a clustering technique to determine which of the clustered objects from the ROI to identify.

[0038] In one embodiment, the clustering technique can be performed with at least 10 points, and the minimum distance between any two points can be less than 0.5 m to become part of the cluster. In one embodiment, an output of the clustering technique can be the clustered objects present in the ROI.

[0039] Furthermore, the processor (202) can filter the one or more clustered objects to determine the one or more clustered objects with one or more reflectance values ​​corresponding to a traffic sign. In one embodiment, the processor (202) can use an intensity filter to filter the one or more clustered objects. The system (102) can estimate one or more normal vectors for all points passing through the intensity filter. In one embodiment, a plurality of endpoints above a threshold can belong to a traffic sign. The system (102) can detect the traffic sign efficiently and accurately over a distance of, for example, 100 m.

[0040] Furthermore, in one embodiment, the processor (202) can determine one or more vectors associated with the filtered one or more clustered objects based on a predefined condition. In one embodiment, the predefined condition can include a maximum deviation of 10 degrees. Additionally, based on the one or more vectors, the processor (202) can determine one or more data points associated with the traffic sign.

[0041] According to the embodiments of the present disclosure, the system (102) can receive a real-time image of the road containing one or more objects, e.g., the traffic sign. The system (102) can define the ROI, which can be a relevant measurement area. The ROI can refer to the relevant section of a measurement curve. In one embodiment, the ROI can be considered statistically. In another embodiment, the dimensions of the ROI from a received LiDAR-PCD can be set such that vehicles or pedestrians are excluded from the 3D environment of the vehicle (106) because the traffic signs are taller than other objects such as vehicles and pedestrians.

[0042] In one embodiment, the clustering technique can be performed by the system (102) taking into account at least 10 data points, wherein the minimum distance between each data point can be less than 0.5 m. The data points that are part of the cluster are considered as clustered objects.

[0043] As described here, the system (102) can include the intensity filter configured to filter the one or more bundled objects with one or more reflectance values ​​corresponding to the traffic sign. In one embodiment, the reflectance of an object can be the object's ability to reflect energy or light from its surface back into the atmosphere. The reflectance of traffic signs can be high because the signpost is located at a higher level relative to the road surface. The reflectance can be measured by measuring the visible and usable light reflected from a surface or the ground using a light source.

[0044] In one embodiment, the system (102) can be configured to estimate the one or more vectors for the data points by passing the one or more vectors through the intensity filter. After passing through the intensity filter, the system (102) performs a segregation of the one or more vectors. The one or more vectors that run parallel to the ground with a maximum deviation of 10 degrees can be separated from other vectors, thus enabling accurate detection of traffic signs.

[0045] Fig. Figure 3 shows a flowchart of an example method (300) for detecting traffic signs in accordance with an embodiment of the present disclosure.

[0046] Referring to Fig. In step (302), the method (300) includes the reception of data from a sensor by a system (102) to represent a three-dimensional environment of a vehicle (106). In step (304), the method (300) includes the definition of a region of interest (ROI) by the system (102) from the data to detect one or more objects on a road on which the vehicle is operated.

[0047] Furthermore, in step (306), the method (300) comprises identifying one or more clustered objects from the ROI by the system (102) using a clustering technique. In step (308), the method (300) comprises filtering the one or more clustered objects by the system (102) to determine the one or more clustered objects with one or more reflectance values ​​corresponding to road signs. In one embodiment, the filtering is performed using an intensity filter.

[0048] Furthermore, in step (310), the method (300) includes the determination by the system (102) of one or more vectors associated with the filtered one or more clustered objects based on a predefined condition. In one embodiment, the predefined condition may include a maximum deviation of, for example, 10 degrees, since traffic signs are generally perpendicular to the road. In step (312), the method (300) includes the determination by the system (102) of one or more data points associated with the traffic sign based on one or more vectors.

[0049] In one embodiment, the method (300) includes the dynamic adjustment of the ROI by the system (102) based on a relative height of the detected bundled object(s) and the avoidance of interference from vehicles and pedestrians when detecting the traffic sign.

[0050] Fig. Figure 4 shows an exemplary computer system (400) in which or with which embodiments of the present disclosure can be used in accordance with embodiments of the present disclosure. In one embodiment, the system (102) can be implemented as the computer system (400).

[0051] As in Fig.As shown in Figure 4, the computer system (400) can comprise an external device (410), a bus (420), main memory (430), read-only memory (440), a mass storage device (450), one or more communication ports (460), and a processor (470). A person skilled in the art will understand that the computer system (400) can comprise more than one processor and communication ports. The communication port(s) (460) can be an RS-232 port for use with a modem-based dial-up connection, a 10 / 100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fiber optic cables, a serial port, a parallel port, or other existing or future ports. The port(s) (460) can be selected according to the network, e.g., B. a local area network (LAN), a wide area network (WAN) or any network to which the computer system (400) is connected.

[0052] The main memory (430) may be random access memory (RAM) or any other dynamic device generally known in the art. The read-only memory (440) may be any static device, including but not limited to programmable read-only memory (PROM) chips for storing static information, such as boot or BIOS (Basic Input / Output System) instructions for the processor (470). The mass storage device (450) may be any current or future mass storage solution that can be used to store information and / or instructions.

[0053] The bus (420) connects the processor (470) communicatively to the other memory, storage, and communication blocks. The bus (420) can be a Peripheral Component Interconnect (PCI) / PCI Extended (PCI-X) bus, a Small Computer System Interface (SCSI), a Universal Serial Bus (USB), or similar, to connect expansion cards, drives, and other subsystems, as well as other buses, such as a Front Side Bus (FSB) that connects the processor (470) to the computer system (400).

[0054] Optionally, operator and management interfaces, such as a display device or a control unit, can also be connected to the bus (420) to support direct interaction between the operator and the computer system (400). Other operator and management interfaces can be provided via network connections connected through the communication port(s) (460). The exemplary computer system (400) described above is not intended to limit the scope of this disclosure in any way.

[0055] While the foregoing describes various embodiments of the disclosure, other and further embodiments of the invention can be developed without departing from the fundamental scope of the disclosure. The scope of the disclosure is determined by the following claims. The disclosure is not limited to the described embodiments, versions, or examples that are included to enable a person with ordinary technical knowledge to produce and use the disclosure when combined with information and knowledge available to such a person. BENEFITS OF THE PRESENT DISCLOSURE

[0056] The present disclosure makes it possible to accurately detect a traffic sign on a road.

[0057] The present disclosure avoids objects such as other vehicles and pedestrians in order to determine the position of the traffic sign with accuracy.

[0058] The present disclosure offers a cost-effective system for detecting traffic signs.

[0059] The present disclosure provides a system that assists vehicles in informing the driver about the nature of upcoming traffic.

[0060] The present disclosure provides a system that uses a Light Detection and Ranging (LiDAR) sensor for the detection of traffic signs, which has a large detection range.

[0061] The present disclosure provides a system with which traffic signs can be clearly detected with a high degree of certainty even in darker or cloudy environmental conditions.

Claims

[1] System (102) for detecting traffic signs, comprising the following: a processor (202) that is communicatively coupled to a sensor (104), wherein the sensor (104) is arranged in a vehicle (106); and a memory (204) that is operationally coupled to the processor (202), wherein the memory (204) stores instructions which, when executed by the processor (202), cause the processor (202) to: to receive data from the sensor (104) in order to represent a three-dimensional (3D) environment of the vehicle (106); to define an area of ​​interest (ROI) from the data in order to detect one or more objects on a road on which the vehicle is operated; to identify one or more clustered objects from the ROI using a clustering technique; to filter the one or more clustered objects according to one or more reflection values ​​that correspond to a traffic sign on the road; to determine one or more vectors associated with the filtered one or more clustered objects, based on a predefined condition; and to determine one or more data points associated with the traffic sign based on one or more vectors. [2] System (102) according to claim 1, wherein the sensor (104) comprises a Light Detection And Ranging (LiDAR) sensor. [3] System (102) according to claim 1, wherein the processor (202) is to filter the one or more clustered objects using an intensity filter. [4] System (102) according to claim 1, wherein the predefined condition comprises a maximum deviation of 10 degrees to identify the traffic sign. [5] System (102) according to claim 1, wherein the processor (202) is to dynamically adjust the ROI on the basis of a relative height of the detected bundled object(s). [6] Method (300) for detecting traffic signs, comprising: Receiving (302) data from a sensor (104) by a processor (202) connected to a system (102) to represent a three-dimensional environment of a vehicle operating on a road; Defining (304) a region of interest (ROI) by the processor (202) from the data in order to detect one or more objects on the street; Identifying (306) one or more clustered objects from the ROI by the processor (202) using a clustering technique; Filtering (308) by the processor (202) of one or more objects according to one or more reflection values ​​corresponding to a road sign; Determine (310), by the processor (202), one or more vectors associated with the filtered one or more clustered objects, based on a predefined condition; and Determining (312) the one or more data points associated with the traffic sign by the processor (202) based on the one or more vectors. [7] Method (300) according to claim 6, wherein the predefined condition comprises a maximum deviation of 10 degrees to identify the traffic sign. [8] Method (300) according to claim 6, comprising the dynamic adjustment of the ROI by the processor (202) on the basis of a relative height of the detected one or more clustered objects.

Images