Search

KR-20260066155-A - Method and processor for recognizing fixed traffic signs

KR20260066155AKR 20260066155 AKR20260066155 AKR 20260066155AKR-20260066155-A

Abstract

The present disclosure relates to a method for recognizing a fixed traffic sign (30), wherein a point cloud (32) of an environment (22) is acquired by a LiDAR sensor (10) included in a vehicle (20), the fixed traffic sign (30) is identified within the point cloud (32), visual information (34) of the traffic sign (30) is extracted using contrast of intensity information, and intensity information is acquired by the LiDAR sensor (10). The present disclosure also relates to a processor, a LiDAR sensor (10), a computing unit (24), a vehicle (20), and a computer program product.

Inventors

  • 레이너드 앙투안
  • 나시르 우마이르
  • 아마렌드라 바라트

Assignees

  • 발레오 샬터 운트 센소렌 게엠베아

Dates

Publication Date
20260512
Application Date
20240919
Priority Date
20231011

Claims (15)

  1. In a method for recognizing a stationary traffic sign (30), A point cloud (32) of the environment (22) is obtained by a LiDAR sensor (10) included in the vehicle (20), and The fixed traffic sign (30) is identified within the above point cloud (32), and The visual information (34) of the above traffic sign (30) is extracted using contrast of intensity information, and the intensity information is obtained by the lidar sensor (10). method.
  2. In paragraph 1, The above traffic sign (30) is identified within the point cloud (32) using depth information included in the point cloud (32), method.
  3. In paragraph 1 or 2, The identification of the above fixed traffic sign (30) is, Tracking the location of the traffic sign (30) across a plurality of frames captured by the above lidar sensor (10), and Includes confirming the stopping attribute of the traffic sign (30) based on the above-mentioned captured plurality of frames, method.
  4. In any one of paragraphs 1 through 3, The identification of the above traffic sign (30) includes identifying an area within the point cloud containing the above traffic sign (30) and extracting the shape of the above traffic sign (30). method.
  5. In paragraph 4, The identification of the above traffic sign (30) is performed using the extracted shape of the above traffic sign (30). method.
  6. In any one of paragraphs 1 through 5, The above visual information (34) is extracted using the contrast of intensity information, and the intensity information is included in the point cloud (32). method.
  7. In any one of paragraphs 1 through 6, The extracted visual information (34) includes characters, letters and/or symbols, method.
  8. In any one of paragraphs 1 through 7, The visual information (34) of the above traffic sign (30) is recognized using image recognition based on the extracted visual information (34), and the recognized visual information (34) is output. method.
  9. In paragraph 8, The extraction and/or recognition of the above visual information (34) is performed using the extracted shape of the above traffic sign (30). method.
  10. In any one of paragraphs 1 through 9, The above method is performed at least partially while the vehicle (20) including the lidar sensor (10) is moving, method.
  11. In a processor for recognizing a fixed traffic sign (30), The above processor is configured to perform the steps of a method according to any one of claims 1 to 10, Processor.
  12. In the lidar sensor (10) included in the vehicle (20), The above lidar sensor (10) includes a control unit (18), and the control unit (18) includes a processor according to claim 11. LiDAR sensor.
  13. In the computing unit (24) included in the vehicle (20), The above computing unit (24) includes a processor according to claim 11, Computing unit.
  14. A vehicle (20) comprising a lidar sensor (10) according to claim 12 and/or a computing unit according to claim 13.
  15. As a computer program product containing instructions, When the above instruction is executed by a processor, it causes the processor to perform a method according to any one of claims 1 to 10. Computer program products.

Description

Method and processor for recognizing fixed traffic signs The present disclosure relates to a method and a processor for recognizing a fixed traffic sign. The present disclosure also relates to a LiDAR sensor, a computing unit, a vehicle, and a computer program product. Modern vehicles such as cars, vans, trucks, motorcycles, etc., may include sensor systems, and the data from these sensor systems is used for driver information and/or by driver assistance systems. Sensor systems are continuously being developed for various functions, such as acquiring environmental information at near and far ranges of vehicles like passenger or commercial vehicles. Based on the acquired data, a model of the vehicle environment can be generated, and responses to changes in this environment are possible. Sensor systems can also serve as sensors for driver assistance systems, particularly for support systems for autonomous or semi-autonomous vehicle control. These can be used, for example, to detect obstacles and/or other road users in the front, rear, or blind spots of the vehicle. Sensor systems can be based on different sensor principles, such as radar, ultrasound, and optical devices. For example, an important optical sensor principle for detecting a vehicle's environment is LiDAR (Light Detection and Ranging) technology. A LiDAR sensor includes an optical transmitter and an optical receiver. The transmitter emits an optical signal that can be continuous or pulsed. Additionally, the optical signal can be modulated. Electromagnetic waves in the form of laser beams in the ultraviolet, visible, or infrared ranges can be used as the optical signal in a LiDAR sensor. The light of the optical signal is received by the optical receiver after being reflected from an object within the detection area of the LiDAR sensor. The optical signal can be evaluated, for example, according to the time-of-flight method, and the spatial location and distance of the object from which the reflection occurred can be determined. Furthermore, it may be possible to determine the relative velocity. Reflected or reflected light is understood to mean any light that is reflected back, and in particular, it must include light reflected back by scattering or absorption emission. A scanning LiDAR sensor emits an optical signal moving in the scanning direction. Scanning movement can be achieved by steering the optical beam of the optical signal using a beam steering device. CN108009474A describes a method and apparatus for extracting text written on a vehicle. The extraction is based on using a stationary laser rangefinder. A method for recognizing fixed traffic signs includes the following: ● The LiDAR sensor included in the vehicle acquires the point cloud of the vehicle's environment. ● Fixed traffic signs are identified within the point cloud. ● Visual information of traffic signs is extracted using the contrast of intensity information, and this intensity information was acquired by a LiDAR sensor. Lidar sensors can provide raw data containing point clouds, which include measured values regarding the vehicle's environment, particularly depth values. To generate a point cloud, the Lidar sensor includes an optical transmitter that emits an optical signal. The optical signal is reflected from the environment of the Lidar sensor. The optical receiver of the Lidar sensor receives the reflected optical signal. The transmitted and received optical signals can be evaluated to obtain measured values. Measurements involving transmission, reception, and evaluation can be repeated. The collection of measured values for various points in the environment forms a point cloud. Pulsed Lidar sensors will emit optical signals as pulses. Each pulse of the optical signal can provide a measured value for a point. Scanning Lidar sensors will cause the optical signal to perform a scanning movement, thereby continuously scanning points in the environment. A point cloud can be understood as a set of points, each containing a corresponding coordinate in a two-dimensional or three-dimensional coordinate system. In the case of a three-dimensional point cloud, the three-dimensional coordinates can be determined, for example, by the incident direction of the reflected optical signal and the corresponding time of flight or radial distance measured for each of these points. In other words, the three-dimensional coordinate system can be a three-dimensional polar coordinate system. However, information can also be provided in an orthogonal coordinate system for each point. In addition to spatial information, namely two-dimensional or three-dimensional coordinates, the point cloud can also store additional information or measurements for individual points, such as the intensity of each received optical signal. The method provides reliable identification and recognition of traffic signs based on visual information on traffic signs. Traffic sign identification specifically refers to the ide