Method and device for identifying a hazard in the vicinity of a vehicle

Abstract

Method (600) for identifying a hazard (115) in the vicinity of a vehicle (105), wherein the method (600) comprises the following steps: Reading (605) a hazard information, wherein the hazard information represents information regarding a hazard (115) approaching the vehicle (105), wherein the person information and the hazard information are provided by at least one environmental sensor of the vehicle (105); Reading (605) personal information, wherein the personal information represents information relating to a person (125) in the vicinity of the vehicle (105); and Determine (610) the hazard location (115) using the hazard location information and the person information, wherein the hazard location (115) is determined if, in step (605) of reading, the person information represents the presence of a person (125) and the hazard location information represents the absence of a hazard location (115) approaching the vehicle (105).

Description

State of the art

[0001] The present invention relates to a method for detecting a hazard in the vicinity of a vehicle, to a corresponding device and to a corresponding computer program product.

[0002] German patent DE 10 2011 018 157 A1 discloses a method for notifying a motor vehicle driver of a hazard location, whereby a current hazard situation is determined by comparing current image data. A camera is used that can detect traffic signs located at the roadside and people standing at the roadside. Depending on the camera's orientation and viewing angle, several indicators of the hazard location can be detected, such as people crossing the road, the road's course, or traffic density.

[0003] US 2011 / 0184617A1 discloses the detection of a pedestrian crossing in conjunction with a pedestrian.

[0004] DE 10 2011 081 396 A1 discloses a method by which a person in the vicinity of the vehicle can be detected. A hazard signal can be provided when an obstacle in the vehicle's path is detected.

[0005] DE 10 2009 036 433 A1 discloses a method for detecting a construction site, using traffic signs for detection.

[0006] Today's driver assistance systems, such as lane keeping assistants, may rely on lane markings to implement a function such as lane assignment in the event of an impact warning or to improve other functions.

[0007] In construction zones, original lane markings may be painted over, milled off, or otherwise removed. Since lane detection can have difficulties in these situations, the system's functionality can be adjusted to the specific construction site. For example, a function can be deactivated or the intervention level reduced.

[0008] Currently, lane information can be used to detect painted lines. Furthermore, sign recognition, sometimes combined with navigation information, can be used to detect reduced speed limits in construction zones, particularly on highways. The function can be adapted based on the type of construction zone detected. Disclosure of the invention

[0009] The approach proposed here creates a procedure for identifying a hazard in the vicinity of a vehicle, the procedure comprising the following steps: Reading in hazard information, where the hazard information represents information regarding a hazard approaching the vehicle; Reading in personal information, where the personal information represents information relating to a person in the vicinity of the vehicle; and Determine the hazard location using the hazard location information and the person information.

[0010] A hazard zone can be understood as a location in the vicinity of the vehicle where a high level of driver attention is required. For example, a hazard zone could be a construction site, an accident scene, or any other traffic situation that poses a potential danger to the driver and / or other road users. A vehicle can be understood as a motor vehicle such as a car, truck, or motorcycle. The vehicle's surroundings can be understood as an area of ​​the vehicle's lane or an adjacent area of ​​the lane. A person can be understood as, for example, a human being or a humanoid mannequin. Person information and hazard zone information can be provided, for example, by one or more of the vehicle's environmental sensors.

[0011] The present approach is based on the understanding that the presence of one or more people on or near a vehicle's lane can indicate the presence of a hazard relevant to the vehicle, such as a construction site or accident scene. It is not necessary for the person to be standing on the road. For example, a "warning dummy" is placed at the edge of the road so that it is visible but not run over. Road workers are also usually not standing directly on the road, but rather protected behind a concrete barrier or separated from the road by cones. Thus, the presence of a person in the immediate vicinity of the road can also indicate the presence of a hazard relevant to the vehicle.In particular, such personal information can be used to validate other information that can be recorded by the vehicle regarding the hazard.

[0012] By using person detection, significantly improved hazard detection can be achieved compared to conventional approaches, which can mean a safety increase for vehicle occupants and other road users, especially in the case of highway construction sites. Furthermore, precise detection of the end of a construction zone can, for example, prevent a vehicle's driver assistance function from remaining in construction mode for too long.

[0013] According to one embodiment of the present approach, the probability of the presence of the hazard point can be determined in the identification step in order to identify the hazard point. This allows the hazard point to be identified very precisely and reliably.

[0014] During the identification step, the person information can be weighted more heavily than the hazard location information to determine the probability. For example, the person information can be used to increase the probability, especially if the person information represents the presence of a person in the vicinity of the vehicle. This can prevent inaccuracies in hazard location identification caused by faulty hazard location information.

[0015] Furthermore, activation information for activating a hazard mode of the vehicle can be provided in one step of the provisioning process if the hazard is identified in the detection step. A hazard mode can be understood as an operating mode of the vehicle that can be activated in the event of a detected hazard. For example, the hazard mode can include a reduction in the vehicle's speed or another driver assistance function of the vehicle designed to improve vehicle control in the event of an impending hazard.

[0016] According to a further embodiment of the present approach, the reading step and / or the detection step can be executed repeatedly in response to the provision step. In this case, a deactivation message to deactivate the hazard mode can be output in an output step if no hazard is detected in the detection step. This allows the hazard mode to be automatically deactivated once the vehicle has left the hazard.

[0017] Furthermore, the hazard location can be determined during the detection step if, during the input step, the person information represents the presence of a person and the hazard location information represents the absence of a hazard location approaching the vehicle. This ensures that the hazard location is determined even if, apart from the presence of the person, there are no other indications of a hazard. For example, this prevents the vehicle's hazard location mode from being deactivated before the vehicle has actually left the hazard location.

[0018] Another embodiment of the approach proposed here involves reading in traffic sign information and / or marking information as hazard information during the data acquisition step. The traffic sign information can represent information regarding a traffic sign in the vicinity of the vehicle, and the marking information can represent information regarding a road marking on the vehicle's lane. A traffic sign can be understood as a sign or other display device indicating a traffic-related warning, such as a speed limit or the start of roadworks. A marking can be, for example, a road marking, a guidepost, or a guardrail. Using the traffic sign information and / or the marking information, the hazard information can be provided with a high degree of reliability.

[0019] During the data acquisition step, road information can also be imported, representing information about the road category traveled by the vehicle. In the subsequent detection step, the hazard location can then be determined using this road information. A road category can be understood as the type of road traveled by the vehicle. For example, the road category could be a highway or a city street. Based on the road category, it can be determined, for instance, to what extent the presence of a person in the vicinity of the vehicle indicates the presence of a hazard.

[0020] Finally, the present approach creates a device for detecting a hazard in the vicinity of a vehicle, wherein the device has the following features: a reading unit for reading in hazard information, wherein the hazard information represents information regarding a hazard approaching the vehicle; a reading unit for reading personal information, wherein the personal information represents information relating to a person in the vicinity of the vehicle; and an investigative unit to determine the hazard location using the hazard location information and the person information.

[0021] The approach presented here further provides a device designed to carry out or implement the steps of a variant of the method presented here in appropriate facilities. This embodiment of the invention in the form of a device also allows the problem underlying the present approach to be solved quickly and efficiently.

[0022] In this context, a device can be understood as an electrical device that processes sensor signals and outputs control and / or data signals accordingly. The device may have an interface, which can be implemented in hardware and / or software. In the case of a hardware-based interface, the interfaces can, for example, be part of a so-called system ASIC, which incorporates various functions of the device. However, it is also possible that the interfaces are separate integrated circuits or consist at least partially of discrete components. In the case of a software-based interface, the interfaces can be software modules, which, for example, are located on a microcontroller alongside other software modules.

[0023] It is also advantageous to have a computer program product with program code that can be stored on a machine-readable medium such as semiconductor memory, hard disk memory or optical memory and is used to carry out the method according to one of the embodiments described above, if the program product is executed on a computer or device.

[0024] The approach presented here is explained in more detail below using the attached drawings as examples. These show: Fig. 1 a schematic representation of a dangerous situation according to an embodiment of the present invention; Fig. 2 a representation of a person according to an embodiment of the present invention; Fig. 3 a block diagram of a device for identifying a hazard location according to an embodiment of the present invention; Fig. 4 a flowchart of a method for identifying a hazard location according to an embodiment of the present invention; Fig. 5 a flowchart of a method for identifying a hazard location according to an embodiment of the present invention; and Fig. 6 a flowchart of a method for identifying a hazard location according to an embodiment of the present invention.

[0025] In the following description of favorable embodiments of the present invention, the same or similar reference numerals are used for the elements shown in the various figures and acting similarly, without repeating these elements.

[0026] Fig. Figure 1 shows a schematic representation of a hazardous situation 100 according to an embodiment of the present invention. The hazardous situation 100 comprises a vehicle 105 traveling in the right lane of a two-lane roadway 110. The roadway 110 has lane markings 112. A hazard 115 is located at the right edge of the roadway 110. The hazard 115 is, for example, a construction site. The lane markings 112 are damaged in the area of ​​the hazard 115. Furthermore, a traffic sign 120 indicating the hazard 115 is located at the right edge. The vehicle 105 is approaching the traffic sign 120. A person 125 is on the roadway 110 in the area of ​​the hazard 115. Alternatively, the person 125 could also be at the edge or next to the roadway 110.

[0027] The vehicle 105 includes a device designed to read in information regarding the hazard 115 and information regarding the person 125 and to use this information to determine the hazard 115.

[0028] According to an embodiment of the present invention, the device is designed to read in information regarding the traffic sign 120 and / or information regarding the course of the road marking 112 in order to determine the hazard location 115.

[0029] Construction sites, especially those on busy roads, often involve continuous work, meaning road workers are present on and alongside the road. At the same time, the likelihood of people being on these roads is low.

[0030] Therefore, the presence of people can be used to infer the presence of a construction site.

[0031] According to one embodiment of the present approach, construction site detection should also function without person detection. Particularly on roads with low traffic volume, such as on holidays and weekends, these construction sites are often unused. Nevertheless, the function should react to an existing construction site, possibly with reduced performance.

[0032] For example, in a method using person detection for construction site identification, the probability of a construction site is increased by the presence of people. In this case, other criteria, such as signs or tracks, may not correspond as strictly to an original construction site situation.

[0033] Instead of real people, dolls can also be recognized, such as those used in Spain in front of a construction site to draw drivers' attention to the site.

[0034] In particular, the end of a construction zone can be delayed if people are still detected, but other criteria no longer indicate a construction zone. For example, speed limit signs are not always repeated, which can lead to a temporary switch from construction mode to normal operation. This switch is prevented by the presence of people.

[0035] Fig. Figure 2 shows a representation of a person according to an embodiment of the present invention. The person is, for example, the one described in Fig. Figure 125 shows person 125. Person 125 is represented by a mannequin and wears a protective helmet 200, a high-visibility jacket 205, and high-visibility trousers 210. Two reflective strips 215 are attached to the chest and arm areas of the jacket 205. Person 125 is shown with their right arm raised. In their right hand, person 125 holds a red flag 220 to alert the driver of the vehicle to the hazard.

[0036] Fig. Figure 3 shows a block diagram of a device 300 for detecting a hazard location according to an embodiment of the present invention. For example, the device shown in Fig. Figure 1 shows vehicle 105 equipped with device 300 for locating hazards. Device 300 comprises a reading unit 305 for reading hazard information and a reading unit 310 for reading person information. Hazard information represents information regarding a hazard approaching a vehicle, and person information represents information regarding a person in the vicinity of the vehicle. Reading units 305 and 310 are each connected to an investigation unit 315.

[0037] Investigation Unit 315 is trained to identify the hazard location using hazard location information and person information.

[0038] Fig. Figure 4 shows a flowchart of a method 400 for identifying a hazard location according to an embodiment of the present invention. Method 400 is an exemplary flowchart for identifying construction sites.

[0039] For example, while driving on a road, step 402 is continuously executed to start procedure 400. In step 405, it is then checked whether there are traffic signs, such as speed limit signs, in the vicinity of the vehicle. In a parallel step 410, the vehicle's lane alignment is checked. Furthermore, in another parallel step 415, it is checked whether there are people in the vicinity of the vehicle. Subsequently, step 420 is executed to determine the probability of the presence of a construction site based on the checks performed in steps 405, 410, and 415. For example, the checks are selected using a 2-out-of-3 decision. If step 425 indicates a high probability of the presence of a construction site, step 430 is executed to start a construction site mode.If, however, a low probability is determined in step 425, step 435 is executed to maintain a standard vehicle mode. Finally, based on either step 430 or step 435, step 440 is executed to terminate or restart procedure 400.

[0040] Fig. Figure 5 shows a flowchart of a method 500 for identifying a hazard according to an embodiment of the present invention. Method 500 is an exemplary flowchart for leaving a construction site or maintaining the construction site mode. Such a construction site mode can be established by performing the steps of the procedure described in Figure 5. Fig. The steps of procedure 500 can be summarized below as the steps of the procedure described in section 4. Fig. The procedures shown in section 4 will be carried out.

[0041] Procedure 500 is initiated with step 505, for example, when the vehicle is in construction zone mode and a condition for construction zone no longer applies. This condition could be in the form of a corresponding sign and / or a corresponding lane change. Step 510 is then executed to activate expressway detection. This determines whether the vehicle is on an expressway. If step 510 returns a negative result, step 520 is executed to end construction zone mode. If step 510 returns a positive result, step 525 checks whether people are visible in the vicinity of the vehicle. If step 525 indicates that people are visible, step 535 is executed to maintain construction zone mode. Conversely, if step 525 indicates that no people are visible, step 520 is executed.Responding to steps 520 and 535, step 540 is finally executed to complete procedure 500.

[0042] The use of highway detection is mentioned here as an example to show how the detection of people can be advantageously used when exiting a construction site.

[0043] Fig. Figure 6 shows a flowchart of a method (600) for identifying a hazard according to an embodiment of the present invention. In a first step (605), hazard information and person information are read in. Here, the hazard information represents information regarding a hazard approaching a vehicle, and the person information represents information regarding a person in the vicinity of the vehicle. In a second step (605), the hazard is identified using the hazard information and the person information.

[0044] The embodiments described and shown in the figures are only examples. Different embodiments can be combined completely or with respect to individual features. An embodiment can also be supplemented by features from another embodiment.

[0045] Furthermore, the procedural steps presented here can be repeated and carried out in a different order than described.

[0046] If an embodiment includes an “and / or” connection between a first feature and a second feature, this is to be read as meaning that the embodiment according to one embodiment has both the first feature and the second feature, and according to another embodiment either only the first feature or only the second feature.

Claims

[1] Method (600) for identifying a hazard location (115) in the vicinity of a vehicle (105), wherein the method (600) comprises the following steps: Reading (605) a hazard information, wherein the hazard information represents information regarding a hazard (115) approaching the vehicle (105), wherein the person information and the hazard information are provided by at least one environmental sensor of the vehicle (105); Reading (605) personal information, wherein the personal information represents information relating to a person (125) in the vicinity of the vehicle (105); and Determine (610) the hazard location (115) using the hazard location information and the person information, wherein the hazard location (115) is determined if, in step (605) of reading, the person information represents the presence of a person (125) and the hazard location information represents the absence of a hazard location (115) approaching the vehicle (105). [2] Method (600) according to claim 1, wherein in step (610) of determining a probability of the presence of the hazard (115) is determined in order to identify the hazard (115). [3] Method (600) according to claim 2, wherein in step (610) of determining the person information is weighted more highly than the hazard location information in order to determine the probability. [4] Method (600) according to one of the preceding claims, comprising a step of providing activation information to activate a hazard location mode of the vehicle (105) when the hazard location (115) is identified in the step (610) of determining. [5] Method (600) according to claim 4, wherein, in response to the provision step, the reading step (605) and / or the detecting step (610) is repeatedly executed, wherein in an output step, deactivation information for deactivating the hazard mode is output if no hazard (115) is detected in the detecting step (610). [6] Method (600) according to one of the preceding claims, wherein in step (605) of reading in traffic sign information and / or marking information is read in as hazard information, wherein the traffic sign information represents information regarding a traffic sign (120) in the vicinity of the vehicle (105) and the marking information represents information regarding a marking (112) of a roadway (110) of the vehicle (105). [7] Method (600) according to one of the preceding claims, wherein in step (605) of reading in road information is further read in, wherein the road information represents information relating to a road category traveled by the vehicle (105), wherein in step (610) of determining the hazard location (115) is further determined using the road information. [8] Device (300) for detecting a hazard (115) in the vicinity of a vehicle (105), wherein the device (300) has the following features: a reading unit (305) for reading in hazard information, wherein the hazard information represents information regarding a hazard (115) approaching the vehicle (105), wherein the person information and the hazard information are provided by at least one environmental sensor of the vehicle (105); a reading unit (310) for reading personal information, wherein the personal information represents information relating to a person (125) in the vicinity of the vehicle (105); and an investigation unit (315) for determining the hazard location (115) using the hazard location information and the person information, wherein the hazard location (115) is determined when the person information represents the presence of a person (125) and the hazard location information represents the absence of a hazard location (115) approaching the vehicle (105). [9] Computer program product with program code for carrying out the method (600) according to any one of claims 1 to 7, when the computer program product is executed on a device (300).

Images