Search

CN-115667044-B - Method for determining reaction capability

CN115667044BCN 115667044 BCN115667044 BCN 115667044BCN-115667044-B

Abstract

The invention relates to a method for determining the reaction capacity of a vehicle user (2) in the automatic driving of a vehicle (1) from acquired image data of a driver monitoring camera. According to the invention, it is provided that, depending on the digital map data present on the vehicle side and/or on the sensor data acquired on the vehicle side, it is determined whether at least one predetermined object (O) of interest in the current vehicle environment is located in the field of view of the vehicle user (2), that, in the case of at least one detected predetermined object (O) of interest in the current vehicle environment, it is determined, depending on the acquired image data of the driver monitoring camera, at which time duration and/or frequency the vehicle user (2) is looking at the detected at least one predetermined object (O) of interest, and that, in the case of a determined time duration below a predetermined minimum time duration and/or in the case of a determined frequency of a line of sight walk below a minimum frequency, the responsiveness of the vehicle user (2) is assessed as absent.

Inventors

  • R. La arusi

Assignees

  • 梅赛德斯-奔驰集团股份公司

Dates

Publication Date
20260512
Application Date
20210401
Priority Date
20200519

Claims (10)

  1. 1. A method for determining the reaction capacity of a vehicle user (2) in the automatic driving of a vehicle (1) from acquired image data of a driver monitoring camera, characterized in that, Determining whether at least one predetermined object (O) of interest in the current vehicle environment is located in the field of view of the vehicle user (2) as a function of digital map data present on the vehicle side and/or as a function of sensor data acquired on the vehicle side, -For at least one predetermined related object (O) to be detected in the current vehicle environment, determining from the acquired image data of the driver monitoring camera, with what duration and/or frequency the vehicle user (2) is aiming his line of sight at said at least one predetermined related object (O) to be detected, and -The responsiveness of the vehicle user (2) is assessed as absent at a determined duration below a predetermined minimum duration and/or at a determined frequency below a minimum frequency of gaze migration based on the result of comparing the glance behavior of the vehicle user (2) determined according to a predetermined location or condition while driving in automated driving with the glance behavior of the vehicle user (2) determined according to a predetermined location or condition while driving in manual driving.
  2. 2. Method according to claim 1, characterized in that an object (O) is predetermined as relevant when such object (O) is in the field of view of the vehicle user (2) for a predetermined duration and/or frequency in manual driving of the vehicle (1) and is considered by the vehicle user (2) in vehicle control.
  3. 3. Method according to claim 1 or 2, characterized in that at least one other vehicle (3), traffic sign (5), light signaling device, warning light, lane marking, light reflecting column, guide rail, crash barrier and/or bridge pier located in front of, sideways and/or behind the vehicle (1) is predetermined and/or considered as relevant object (O) when determining the reaction capacity of the vehicle user (2).
  4. 4. Method according to claim 1 or 2, characterized in that the size, visibility, relative position and/or absolute position of a predetermined object (O) related to the field of view of the vehicle user (2) is ascertained and/or considered.
  5. 5. A method according to claim 1 or 2, characterized in that the viewing direction of the vehicle user (2) is determined as a line-of-sight vector (V), which is inferred to determine the field of view.
  6. 6. A method according to claim 5, characterized in that the centre point between the pupils (6) of the vehicle user (2) is predetermined as the starting point (C) of the line of sight vector (V).
  7. 7. Method according to claim 1 or 2, characterized in that the surrounding area is defined according to a predetermined shape and/or size of the relevant object (O).
  8. 8. Method according to claim 1 or 2, characterized in that for a plurality of measured objects (O), the visibility associated with a predetermined associated object (O) is evaluated in dependence on the position, size and/or material properties of the object (O).
  9. 9. A method according to claim 1 or 2, characterized in that the perception and/or the situational awareness is determined in a manner specific to the vehicle user on the basis of a glance behavior analysis.
  10. 10. Method according to claim 1 or 2, characterized in that at least one notification is output in the vehicle (1) upon determining that the vehicle user (2) is not capable of reacting, which at least one notification should be answered by the vehicle user (2) within a predetermined period of time.

Description

Method for determining reaction capability Technical Field The invention relates to a method for determining the reaction capability of a vehicle user in the automatic driving of a vehicle from acquired image data of a driver monitoring camera. Background DE 10 2015 001 686 B4 discloses a method and a device for detecting the reaction capacity of a driver during the automatic driving of a motor vehicle. In this case, a first assessment of the reaction capacity is carried out by means of camera monitoring of the driver, wherein a second assessment of the reaction capacity is carried out by detecting the operation of the operating unit by the driver. The reactive capability is classified as present when the first assessment and/or the second assessment has identified the presence of the reactive capability. In a first evaluation of the ability to respond by means of camera monitoring of the driver, at least one eye of the driver is classified as being able to respond when it opens during a minimum part of a predetermined time interval. When the operation of the operation unit is performed by a person other than the driver or performed in a periodic manner, it is not classified as being reactive. Furthermore, DE 10 2016 011 246 A1 describes a method for monitoring the state of at least one passenger of a vehicle. The method provides that the head of the passenger is illuminated by means of at least one alternately switched-on light source. The light reflected by the eyes of the passenger is detected by means of at least one sensor, wherein it is additionally checked whether the reflection varies as a function of the illumination of the light source and at least one eyelid movement and/or head movement of the passenger is detected. Disclosure of Invention The object of the present invention is to specify a method for determining the reaction capacity of a vehicle user during automatic driving of a vehicle. According to the invention, this object is achieved by a method having the features described below. Advantageous embodiments of the invention are also described below. According to the invention, a method for determining the reaction capability of a vehicle user in the automatic driving of a vehicle from acquired image data of a driver monitoring camera provides for determining whether at least one predetermined object in the current vehicle environment is located in the field of view of the vehicle user from digital map data present on the vehicle side and/or from sensor data acquired on the vehicle side. In the case of at least one detected predetermined object in the current vehicle environment, it is determined, as a function of the detected image data of the driver monitoring camera, with which duration and/or frequency the vehicle user is looking at the detected at least one predetermined object, and the reaction capacity of the vehicle user is assessed as absent when the duration of the determined duration of less than a predetermined minimum duration and/or when the frequency of the line of sight drift is determined of less than a minimum frequency. By using this method, the reaction capability of the vehicle user of the vehicle during the automatic driving in which the vehicle fully performs the driving task can be determined. Here, the vehicle user refers to a person who performs a driving task of the vehicle in manual driving. In particular, a reaction capability is ascertained to determine whether the vehicle user can react correctly in the system-dependent request for taking over the driving task, and to do so correctly with the current situation. A precondition for condition awareness is that the relevant objects and/or areas outside the vehicle, which depend on the condition, can be seen and perceived as well. In one embodiment of the method, an object is predetermined to be relevant when it is in the field of view of the vehicle user for a predetermined duration and/or frequency in the manual driving of the vehicle, i.e. when the vehicle user aims his line of sight at the object for a predetermined duration and/or frequency, and when the object is considered by the vehicle user in the control of the vehicle. If it is detected from the captured image data that the line of sight of the vehicle user is not aligned at all or is aligned relatively briefly with the predetermined relevant object, then it is interpreted that the vehicle user does not perceive the predetermined relevant object and accordingly has at least a low reaction capacity. In one possible embodiment of the method, at least one further vehicle, traffic sign, light signaling device, warning light, lane marking, light column, guidance rail, crash barrier and/or bridge pier located in front of, on the side of and/or behind the vehicle is predetermined and/or considered as relevant object when determining the reaction capacity of the vehicle user. Such objects are thus regarded as relevant and predetermined as objects of a driving s