Vehicle early warning method and device, vehicle, storage medium and program product

Abstract

The invention discloses a vehicle early warning method and device, a vehicle, a storage medium and a program product. According to the specific implementation scheme, the method comprises the steps that in the driving process of a vehicle, vehicle information at different time and pedestrian information in a road section where the vehicle is located are sequentially obtained; for the vehicle information at each time, determining a current vehicle state corresponding to the vehicle information; determining a vehicle early warning area corresponding to the current vehicle state according to the vehicle information; and determining a vehicle early warning state based on the vehicle information, the vehicle early warning area and the corresponding pedestrian information. The pedestrian information and the vehicle information are comprehensively considered, more reliable vehicle early warning is realized, the current vehicle state of the vehicle is determined according to the vehicle information, and the corresponding vehicle early warning area is divided for the current vehicle state, so that the vehicle can more accurately monitor the condition in the vehicle early warning area, the vehicle driving safety is improved, and the vehicle early warning efficiency is improved. The analysis process of determining the vehicle early warning state is simplified, and the risk of traffic accidents is reduced.

Description

Technical Field

[0001] The present invention relates to the field of driving technology, and particularly to a vehicle warning method, device, vehicle, storage medium, and program product. Background Art

[0002] Pedestrian collision warning means that when a vehicle is driving on ordinary roads and highways in urban and suburban areas and there is a risk of collision with surrounding pedestrians, it can warn the vehicle driver to assist the driver in avoiding or reducing the risk of collision with lateral pedestrians and improving the traffic safety of vehicles and pedestrians.

[0003] In the prior art, the main method for realizing pedestrian collision warning is to use devices such as lidar and cameras at the vehicle end to collect and analyze data of pedestrians in front, obtain the map data built-in at the vehicle end and the perceived pedestrian data, and perform pedestrian collision warning. It can be seen that the triggering analysis process for pedestrian collision warning in the prior art is relatively complex, and only the data in front or the perceivable data is analyzed, resulting in the problem of unreasonable warning areas. Summary of the Invention

[0004] The present invention provides a vehicle warning method, device, vehicle, storage medium, and program product to improve the driving safety of vehicles and reduce the risk of traffic accidents.

[0005] According to one aspect of the present invention, there is provided a vehicle warning method, including:

[0006] During the driving process of the vehicle, successively obtain the vehicle information at different times and the pedestrian information in the section where the vehicle is located;

[0007] For the vehicle information at each time, determine the current vehicle state corresponding to the vehicle information;

[0008] According to the vehicle information, determine the vehicle warning area corresponding to the current vehicle state;

[0009] Based on the vehicle information, the vehicle warning area, and the corresponding pedestrian information, determine the vehicle warning state.

[0010] According to another aspect of the present invention, there is provided a vehicle warning device, including:

[0011] An acquisition module, configured to successively obtain the vehicle information at different times and the pedestrian information in the section where the vehicle is located during the driving process of the vehicle;

[0012] A first determination module, configured to determine the current vehicle state corresponding to the vehicle information for the vehicle information at each time;

[0013] A second determination module, configured to determine a vehicle warning area corresponding to the current vehicle state according to the vehicle information;

[0014] A third determination module, configured to determine a vehicle warning state based on the vehicle information, the vehicle warning area, and the corresponding pedestrian information.

[0015] According to another aspect of the present invention, there is provided a vehicle, comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the vehicle warning method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for implementing the vehicle warning method according to any embodiment of the present invention when executed by a processor.

[0020] According to another aspect of the present invention, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the vehicle warning method according to any embodiment of the present invention.

[0021] In the technical solution of the embodiment of the present invention, during the driving process of the vehicle, vehicle information at different times and pedestrian information in the section where the vehicle is located are sequentially acquired; for the vehicle information at each time, the current vehicle state corresponding to the vehicle information is determined; according to the vehicle information, a vehicle warning area corresponding to the current vehicle state is determined; based on the vehicle information, the vehicle warning area, and the corresponding pedestrian information, a vehicle warning state is determined. By comprehensively considering pedestrian information and vehicle information and conducting a more comprehensive analysis, more reliable vehicle warning is achieved. The current vehicle state of the vehicle is determined according to the vehicle information, and a corresponding vehicle warning area is divided for the current vehicle state, enabling the vehicle to more accurately monitor the conditions within the vehicle warning area, improving the safety of vehicle driving. According to the vehicle information, the vehicle warning area, and the pedestrian information, the vehicle warning state can be determined, simplifying the analysis process for determining the vehicle warning state and reducing the risk of traffic accidents.

[0022] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0024] Figure 1 is a flowchart of a vehicle warning method provided according to Embodiment 1 of the present invention;

[0025] Figure 2 is a schematic diagram of a vehicle warning area in a reverse state provided according to Embodiment 1 of the present invention;

[0026] Figure 3 is an overall flowchart of a vehicle warning method provided according to Embodiment 1 of the present invention;

[0027] Figure 4 is a schematic diagram of a vehicle warning area in a forward state provided according to Embodiment 1 of the present invention;

[0028] Figure 5 is a schematic diagram of a circular collision model provided according to Embodiment 1 of the present invention;

[0029] Figure 6 is a flowchart of a method for determining a vehicle warning area in a forward state provided according to Embodiment 2 of the present invention;

[0030] Figure 7 is a schematic structural diagram of a vehicle warning device provided according to Embodiment 3 of the present invention;

[0031] Figure 8 is a block diagram of a vehicle provided according to Embodiment 4 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, rather than all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the description, claims and the above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0034] Embodiment 1

[0035] Figure 1 The following is a flowchart of a vehicle warning method provided for Embodiment 1 of the present invention. This embodiment is applicable to the situation of warning a vehicle during the driving process of the vehicle. This method can be executed by a vehicle warning device, which can be implemented in the form of hardware and / or software. The vehicle warning device can be configured in the vehicle, and an in-vehicle unit can be configured in the vehicle, and the in-vehicle unit can include a vehicle wireless communication device. As Figure 1 shown, the method includes:

[0036] S110. During the driving process of the vehicle, sequentially obtain the vehicle information at different times and the pedestrian information in the section where the vehicle is located.

[0037] In this embodiment, the vehicle information can be understood as the data information of the vehicle itself during the driving process of the vehicle. The vehicle information may include the speed of the vehicle, the heading angle of the vehicle, and the vehicle position information, etc. The pedestrian information can be understood as the data information generated when a pedestrian moves in the section where the vehicle is located, and may include the longitude and latitude of the pedestrian, the walking speed, and the heading angle, etc. The longitude and latitude of the pedestrian can be used to determine the current position of the pedestrian.

[0038] Specifically, when the vehicle is in motion, vehicle information at different times is obtained in real time through on-vehicle devices, and pedestrian information of pedestrians located in the section where the vehicle is located is obtained through third-party sensing devices or roadside devices, etc. The obtained vehicle information and pedestrian information are transmitted to the on-vehicle device. The section where the vehicle is located can be a part of the road where the vehicle is during the driving process, and the scope of the section where the vehicle is located is not limited here. It can be the driving section of the vehicle when the vehicle is in a turning area, or the driving section of the vehicle when the vehicle is in a straight-ahead area. An on-vehicle device is a vehicle component used to collect various vehicle information in real time and convert it into readable data. A third-party sensing device is a device located on the roadside and used to collect information such as pedestrians and road conditions in real time. The on-vehicle device can achieve information interaction between the vehicle and the outside world, including information interaction between the vehicle and various connectable devices, such as information interaction between the vehicle and other vehicles, people, or roads.

[0039] Exemplarily, when the vehicle is driving in a certain area, vehicle information at different times is obtained in real time through the on-vehicle device. Pedestrian information of pedestrians located in the vehicle driving section is obtained through the third-party sensing device. Using the roadside wireless communication device, after parsing the pedestrian information, it is filled into a standard Spatial Situation Message (SSM message). After the SSM message is verified and encrypted, it is broadcast outward through the PC5 port at a frequency of 10 hz. At this time, the on-vehicle device can receive the pedestrian information. The roadside wireless communication device can achieve information interaction between itself and the outside world, and its working principle is the same as that of the vehicle-mounted wireless communication device. The SSM message is a sensor sharing message and is a standard information format that can be directly received by other wireless communication devices.

[0040] S120. For the vehicle information at each time, determine the current vehicle state corresponding to the vehicle information.

[0041] In this embodiment, the current vehicle state can be understood as a dynamic information representing the vehicle driving state during the vehicle driving process, and different states of the vehicle can be judged according to information such as the vehicle driving trajectory and the change of the vehicle head direction.

[0042] Specifically, during the vehicle driving process, vehicle information at each time is obtained, and combined with the road condition information obtained through the roadside wireless communication device, the current vehicle state corresponding to the vehicle information at each time is obtained. When the vehicle is driving forward in the road in the direction of the vehicle head, the current vehicle state is the forward state; when the vehicle is driving backward in the road in the direction of the vehicle tail, the current vehicle state is the reverse state.

[0043] S130. According to the vehicle information, determine the vehicle warning area corresponding to the current vehicle state.

[0044] In this embodiment, during the vehicle driving process, the area that may cause the risk of vehicle collision is set as the vehicle warning area. When a target that may cause a collision, such as a pedestrian, appears in this vehicle warning area, the vehicle can provide a warning signal for the driver.

[0045] Specifically, for different current vehicle states, the vehicle warning area can be determined for the vehicle according to the vehicle information. When the current vehicle state is the forward state, the corresponding vehicle warning area can be located in the area in front of the vehicle head. When the current vehicle state is the reverse state, the corresponding vehicle warning area can be located in the area at the rear of the vehicle and behind the vehicle tail.

[0046] S140. Determine the vehicle warning state based on the vehicle information, the vehicle warning area, and the corresponding pedestrian information.

[0047] In this embodiment, the vehicle warning state can be understood as the information provided by the vehicle for the driver in the case of a possible collision. The vehicle warning state can be a triggered state or an untriggered state.

[0048] Specifically, when the current vehicle state is the forward state, it is necessary to specifically determine how to set the vehicle warning state according to the vehicle information and the pedestrian information. When the current vehicle state is the reverse state, if the pedestrian information indicates that the position of the pedestrian is within the vehicle warning area corresponding to the forward state, the vehicle warning state is set to the triggered state.

[0049] The technical solution of the embodiment of the present invention is as follows: during the driving process of the vehicle, the vehicle information at different times and the pedestrian information in the road section where the vehicle is located are sequentially obtained; for the vehicle information at each time, the current vehicle state corresponding to the vehicle information is determined; according to the vehicle information, the vehicle warning area corresponding to the current vehicle state is determined; the vehicle warning state is determined based on the vehicle information, the vehicle warning area, and the corresponding pedestrian information. By comprehensively considering the pedestrian information and the vehicle information and conducting a more comprehensive analysis, more reliable vehicle warning is achieved. The current vehicle state of the vehicle is determined according to the vehicle information, and the corresponding vehicle warning area is divided for the current vehicle state, so that the vehicle can more accurately monitor the conditions within the vehicle warning area, improving the safety of vehicle driving. According to the vehicle information, the vehicle warning area, and the pedestrian information, the vehicle warning state can be determined, simplifying the analysis process for determining the vehicle warning state and reducing the risk of traffic accidents.

[0050] Based on the above embodiment, a variant embodiment of the above embodiment is proposed. Here, it should be noted that for the sake of brief description, only the differences from the above embodiment are described in the variant embodiment.

[0051] In one embodiment, when the current vehicle state is in a reverse state, determining the vehicle warning area corresponding to the current vehicle state according to the vehicle information includes:

[0052] Parse the lateral center line and the longitudinal center line of the vehicle from the vehicle information, where the lateral center line is perpendicular to the driving direction of the vehicle;

[0053] Obtain a fifth line segment, and the length of the fifth line segment is the path length along the driving direction of the vehicle starting from the lateral center line;

[0054] Set a sixth line segment, and the length of the sixth line segment is a calibration value set along the direction perpendicular to the driving direction of the vehicle starting from the longitudinal center line;

[0055] Take the polygonal area formed by the fifth line segment and the sixth line segment excluding the vehicle as the first danger area;

[0056] Determine the symmetric polygonal area of the first danger area with the longitudinal center line as the axis of symmetry as the second danger area;

[0057] Merge the first danger area and the second danger area as the vehicle warning area of the vehicle in the reverse state.

[0058] In this embodiment, the lateral center line can be understood as the projection line on the top view of the vehicle. The lateral center line is located in the middle of the top view of the vehicle and is perpendicular to the driving direction of the vehicle. Similarly, the longitudinal center line can be understood as the projection line on the top view of the vehicle. The longitudinal center line is located in the middle of the top view of the vehicle and is parallel to the driving direction of the vehicle. The fifth line segment can be understood as the line segment starting from the lateral center line and along the driving direction of the vehicle. The sixth line segment can be understood as starting from the longitudinal center line and set along the direction perpendicular to the driving direction of the vehicle. The length of the sixth line segment is the calibration value. The fifth line segment and the sixth line segment can be used to form the vehicle warning area. The first danger area can be understood as the vehicle warning area on one side of the vehicle. The second danger area can be understood as the vehicle warning area on the other side of the vehicle. In the top view, the first danger area and the second danger area are axisymmetric areas.

[0059] Specifically, determine the lateral center line and longitudinal center line of the vehicle. Determine the path length along the vehicle driving direction starting from any point on the lateral center line as the fifth line segment. The length of the fifth line segment can be a set value or related to the vehicle information. Determine the calibration value along the vertical direction of the vehicle driving direction starting from any point on the longitudinal center line as the length of the sixth line segment. Take the polygon area except the vehicle formed by the fifth line segment and the sixth line segment as the first dangerous area. Taking the longitudinal center line as the axis of symmetry, determine the symmetric polygon area of the first dangerous area as the second dangerous area. Combine the first dangerous area and the second dangerous area as the vehicle warning area of the vehicle in the reverse state.

[0060] Exemplarily, Figure 2 is a schematic diagram of a vehicle warning area in the reverse state provided by Embodiment 1 of the present invention. As Figure 2 shown, the black area is the vehicle warning area in the reverse state. rear_lat_dis_threshold represents the sixth line segment, and its length is the lateral distance from the longitudinal center line to the edge of the vehicle warning area, which is a calibration value. Alert_length represents the fifth line segment, and its length is the longitudinal distance from the edge of the vehicle warning area to the lateral center line.

[0061] Optionally, the obtaining of the fifth line segment includes:

[0062] Parse the vehicle speed of the vehicle from the vehicle information;

[0063] Set a first candidate length, where the first candidate length is a calibration value set along the vehicle driving direction starting from the lateral center line;

[0064] Take the product of the vehicle speed and the set time as the second candidate length, where the set time includes the time related to the vehicle information;

[0065] Take the length with the larger value among the first candidate length and the second candidate length as the length of the fifth line segment.

[0066] In this embodiment, the first candidate length can be understood as a calibration value set along the vehicle driving direction starting from the lateral center line. The second candidate length can be a value calculated from the vehicle speed and the set time, which can represent the driving route length of the vehicle within the set time.

[0067] Exemplarily, as Figure 2As shown, rear_lon_lowest_dis_threshold represents the first candidate length, which is the minimum longitudinal distance from the edge of the dangerous area to the lateral center line and is a calibrated value. hv_speed represents the vehicle speed. The set time can be set to 3 seconds, then the length of the fifth line segment Alert_length = max(rear_lon_lowest_dis_threshold, hv_speed * 3).

[0068] In one embodiment, when the current vehicle state is the forward state, the vehicle warning area includes a danger warning area and a risk warning area. Determining the vehicle warning state based on the vehicle information, the vehicle warning area, and the corresponding pedestrian information includes:

[0069] Parsing the pedestrian position information and the pedestrian heading angle of the pedestrian from the pedestrian information;

[0070] Parsing the vehicle heading angle of the vehicle from the vehicle information;

[0071] When the pedestrian position information indicates that the pedestrian is located in the danger warning area corresponding to the forward state, setting the vehicle warning state to the triggered state;

[0072] When the pedestrian position information indicates that the pedestrian is located in the risk warning area corresponding to the forward state, calculating the deviation value between the pedestrian heading angle and the vehicle heading angle. When the deviation value is within the preset range, setting the vehicle warning state to the triggered state; otherwise, setting the vehicle warning state to the untriggered state;

[0073] When the pedestrian position information indicates that the pedestrian is neither located in the danger warning area nor in the risk warning area, calculating the pedestrian heading angle and the vehicle heading angle according to the circular collision model, and determining the vehicle warning state according to the calculation result.

[0074] In this embodiment, the circular collision model can be understood as a model for judging whether a vehicle and a pedestrian will collide. In the case of possible collision, the circular collision model can output the collision time between the vehicle and the pedestrian.

[0075] Specifically, when the current vehicle state is the forward state, the vehicle warning area includes a danger warning area and a risk warning area. Obtain the pedestrian position information, and determine whether the pedestrian is located in the danger warning area according to the pedestrian position information. If so, set the vehicle warning state to the triggered state; otherwise, determine whether the pedestrian is located in the risk warning area. When the pedestrian is located in the risk warning area, calculate the deviation value between the pedestrian's heading angle and the vehicle's heading angle. When the deviation value is within the preset range, during the vehicle's travel, the heading angle deviation between the vehicle and the pedestrian is small, and there is a risk of collision, so set the vehicle warning state to the triggered state; when the deviation value is not within the preset range, during the vehicle's travel, the heading angle deviation between the vehicle and the pedestrian is large, and there is no risk of collision, so set the vehicle warning state to the untriggered state. When the pedestrian is neither located in the danger warning area nor in the risk warning area, a circular collision model can be used to calculate the collision time when the vehicle and the pedestrian may collide, and determine the triggering situation of the vehicle warning state according to the collision time.

[0076] Exemplarily, Figure 3 is the overall flowchart of a vehicle warning method provided in Embodiment 1 of the present invention. First, determine whether the vehicle is moving forward. If the vehicle is moving forward, the current vehicle state is the forward state. Then, determine whether the pedestrian is within the danger warning area. If so, trigger the vehicle warning state, such as setting a pedestrian collision warning event; if not, continue to determine whether the pedestrian is within the risk area. If so, determine the vehicle warning state according to the deviation value of the heading angles of the vehicle and the pedestrian. If not, determine the vehicle warning state according to the circular collision model. Figure 4 is a schematic diagram of a vehicle warning area in the forward state provided in Embodiment 1 of the present invention. Determining the vehicle warning state according to the deviation value of the heading angles of the vehicle and the pedestrian may include: as Figure 4 shown, if the pedestrian is within the risk warning area on the right side of the vehicle's driving direction and the deviation value of the heading angle between the pedestrian and the vehicle is within the range of [-3π / 4, -π / 4], or the pedestrian is within the risk warning area on the left side of the vehicle's driving direction and the deviation value of the heading angle between the pedestrian and the vehicle is within the range of [π / 4, 3π / 4], then set the vehicle warning state to the triggered state; otherwise, set the vehicle warning state to the untriggered state.

[0077] Optionally, calculating the pedestrian's heading angle and the vehicle's heading angle according to the circular collision model, and determining the vehicle warning state according to the calculation result includes:

[0078] Parse the vehicle center point of the vehicle and the longitudinal and lateral edges of the vehicle from the vehicle information;

[0079] Determine the diagonal line segment of the rectangle formed by the longitudinal edge and the lateral edge;

[0080] Taking the center point of the vehicle as the center of a circle and half of the diagonal line segment as the radius, construct a circular vehicle model;

[0081] Taking the center of gravity of the pedestrian indicated by the pedestrian position information as the center of a circle and a preset length as the radius, construct a circular pedestrian model, where the preset length is set according to the volume of the pedestrian;

[0082] Predict whether the circular vehicle model and the circular pedestrian model will be externally tangent according to the pedestrian heading angle and the vehicle heading angle;

[0083] If so, calculate the external tangent time. When the external tangent time is less than a preset threshold, set the vehicle warning state to the triggered state; otherwise, set the vehicle warning state to the untriggered state. The external tangent time includes the predicted value of the collision time between the vehicle and the pedestrian;

[0084] If not, set the vehicle warning state to the untriggered state.

[0085] In this embodiment, the circular vehicle model can be understood as a circle that includes the vehicle, and its center of the circle is the center point of the vehicle. The circular pedestrian model can be understood as a circle that includes the pedestrian, and its radius can be set to a preset length. The preset length is an empirical value and needs to consider the volume of the pedestrian to ensure that the pedestrian is included in the circular pedestrian model under normal walking conditions.

[0086] Exemplarily, Figure 5 is a schematic diagram of a circular collision model provided in Embodiment 1 of the present invention. Taking the center point of the vehicle as the center of a circle and the diagonal formed by the length and width of the vehicle as the radius r 1 constitute a circular vehicle model that includes the vehicle. Taking a preset length width as the radius r 2 , and taking the center of gravity of the pedestrian as the center of a circle, construct a circular pedestrian model. Calculate the distance difference d between the centers of the circular vehicle model and the circular pedestrian model, and perform trajectory prediction according to the speeds and heading angles of the pedestrian and the vehicle at this time to determine whether there are two external tangencies between the circular vehicle model and the circular pedestrian model. The judgment formula for external tangency is d = r 1 +r 2 . If not, then set the vehicle warning state to the untriggered state. If so, calculate the time t of the first external tangency as the collision time TTC between the two. If TTC is less than the preset threshold ttc_threshold, set the vehicle warning state to the triggered state; otherwise, set the vehicle warning state to the untriggered state. The calculation formula for the external tangent time is (r 1 +r 2 ) 2 =Distance(t) 2 , specifically including: assuming that the center coordinates of the circular vehicle model are (x 1 ,y1 ), radius r1, the velocity vector of the vehicle (v x1 , v y1 ). Similarly, the center of the pedestrian circular model (x 2 , y 2 ), radius r2, the velocity vector of the pedestrian (v x2 , v y2 ). After the vehicle and the pedestrian move for time t, the center coordinates of the vehicle circular model are (x 1 + v x1 × t, y 1 + v y1 × t), and the center coordinates of the pedestrian circular model are (x 2 + v x2 × t, y 2 + v y2 × t). Assuming that there is an external tangent situation between the vehicle circular model and the pedestrian circular model, then according to d = r 1 + r 2 , square both sides of the equation to get:

[0087] ((x 1 + v x1 × t) - (x 2 + v x2 × t)) 2 + ((y 1 + v y1 × t) - (y 2 + v y2 × t)) 2 = (r 1 + r 2 ) 2 . Rearrange it into the form of a quadratic equation of one variable at 2 + bt + c = 0 to get: a = (v x1 - v x2 ) 2 + (v y1 - v y2 ) 2 , b = 2 × ((x 1 - x 2 )(v x1 - v x2 ) + (y 1 - y 2 )(v y1 - v y2 ))), c = (x 1 - x 2 ) 2 + (y 1 - y 2 ) 2 - (r 1 + r 2) 2 Then analyze the result: When a = 0, then v x1 = v x2 , v y1 = v y2 , which means that the driving directions of the vehicle and the pedestrian are the same, and there is no collision risk; when a ≠ 0, calculate △ = b 2 - 4ac. When △ < 0, the equation has no solution, and there is no collision risk between the vehicle and the pedestrian. When △ ≥ 0, calculate and at t 1 > 0 and t 2 > 0, there is a collision risk between the vehicle and the pedestrian, and the time to collision TTC = t 1 .

[0088] In one embodiment, when the current vehicle state is in a reverse state, determining the vehicle warning state based on the vehicle information, the vehicle warning area, and the corresponding pedestrian information includes:

[0089] Parse the pedestrian position information of the pedestrian from the pedestrian information;

[0090] When the pedestrian position information indicates that the pedestrian is located in the vehicle warning area corresponding to the reverse state, set the vehicle warning state to the triggered state; otherwise, set the vehicle warning state to the untriggered state.

[0091] Exemplarily, when the current vehicle state is in a reverse state, obtain the pedestrian position information, and determine whether the pedestrian is located in the vehicle warning area as shown in Figure 2 . If so, it means that there is a collision risk between the vehicle and the pedestrian, that is, set the vehicle warning state to the triggered state; otherwise, set the vehicle warning state to the untriggered state.

[0092] Embodiment Two

[0093] Figure 6 The following is a flowchart of a method for determining a vehicle warning area in a forward state provided by the second embodiment of the present invention. This embodiment is directed to the method for determining the vehicle warning area corresponding to the forward state according to the vehicle information in the above embodiment. Among them, the vehicle warning area corresponding to the forward state includes a danger warning area and a risk warning area. As shown in Figure 6 , the method includes:

[0094] S210. During the driving process of the vehicle, sequentially obtain the vehicle information at different times and the pedestrian information in the section where the vehicle is located.

[0095] S220. For the vehicle information at each time, determine the current vehicle state corresponding to the vehicle information.

[0096] S2301. Parse the longitudinal center line, vehicle width, and vehicle longitudinal edges of the vehicle from the vehicle information. The vehicle longitudinal edges are the edge positions of the vehicle parallel to the driving direction of the vehicle, and the longitudinal center line is parallel to the driving direction of the vehicle.

[0097] Exemplarily, as Figure 4 shown, determine the projection line of the vehicle top view, and use the line located at the middle position of the vehicle top view and parallel to the driving direction of the vehicle as the longitudinal center line of the vehicle. As Figure 4 shown in, approximate the vehicle top view as a rectangle, where vehicle_width represents the vehicle width, and the rectangular edge consistent with the driving direction of the vehicle is used as the vehicle longitudinal edge.

[0098] S2302. Obtain a first line segment, where the length of the first line segment is the path length starting from the head position of the vehicle along the driving direction of the vehicle.

[0099] In this embodiment, the first line segment can be understood as a line segment starting from the head position of the vehicle along the driving direction of the vehicle, and the length of the line segment is related to vehicle information, vehicle driver information, etc.

[0100] Specifically, determine the path length starting from any point on the straight line perpendicular to the driving direction of the vehicle where the head position is located along the driving direction of the vehicle as the first line segment. This path length can be calculated based on information such as vehicle speed, driver reaction time, and vehicle deceleration.

[0101] Optionally, the obtaining of the first line segment includes:

[0102] Parse the vehicle speed of the vehicle from the vehicle information;

[0103] Set an empirical value and a preset value for the vehicle according to the vehicle information;

[0104] Calculate the product of the vehicle speed and the empirical value, add it to the preset value, and use the calculation result as the first line segment.

[0105] In this embodiment, the empirical value can be understood as set according to information related to the vehicle, such as the size and deceleration of the vehicle. The preset value can be understood as a value related to the vehicle driver, and can include the driver's reaction time, etc.

[0106] Exemplarily, determine the vehicle speed hv_speed of the vehicle, and set the reaction time reaction_time left for the driver, which is a preset value. The preset value can be an optimal value obtained through multiple tests. Set empirical values according to information such as the size of the vehicle, including the activation time brake_active_time of the vehicle's braking action, the deceleration growth time decel_growth_time of the vehicle, and the preset braking deceleration brake_acc of the vehicle. Then, the length of the first line segment longitude_safe_dis can be calculated according to the formula:

[0107]

[0108] S2303. Set a second line segment. The length of the second line segment is a calibrated value set from the longitudinal edge of the vehicle, towards the outside of the vehicle, along the vertical direction of the vehicle's driving direction.

[0109] In this embodiment, the second line segment starts from any point on the longitudinal edge of the vehicle, and is a line segment towards the two outsides of the vehicle, along the vertical direction of the vehicle's driving direction. The length of the second line segment is a calibrated value.

[0110] Exemplarily, as Figure 4 shown, front_lat_safedis_margin_threshold represents the second line segment. It can be seen that its length is the longitudinal distance between the longitudinal edge of the vehicle and the edge of the danger warning area.

[0111] S2304. Take the sum of the vehicle width and the two second line segments set for the longitudinal edges on both sides of the vehicle as the third line segment.

[0112] Exemplarily, as Figure 4 shown, the third line segment is represented as front_dangerous_lat_width. It can be seen that the third line segment includes the vehicle width vehicle_width and the two second line segments front_lat_safedis_margin_threshold on both sides of the vehicle.

[0113] S2305. Take the rectangular area at the front position of the vehicle formed by the first line segment and the third line segment as the danger warning area of the vehicle in the forward state.

[0114] Exemplarily, as Figure 4As shown, a third line segment front_dangerous_lat_width and a first line segment longitude_safe_dis are combined to form a rectangular area, which is located at the front of the vehicle and is symmetric about the longitudinal center line of the vehicle. This rectangular area is used as the dangerous warning area in the forward state.

[0115] S2306. Set a fourth line segment, and the length of the fourth line segment is a calibrated value set along the vertical direction of the vehicle driving direction starting from the longitudinal edge of the dangerous warning area.

[0116] In this embodiment, the fourth line segment can be understood as a line segment set along the vertical direction of the vehicle driving direction starting from any point on the edge of the dangerous area, and the length of the fourth line segment is a calibrated value.

[0117] Exemplarily, as Figure 4 in which front_risk_lat_width_threshold represents the fourth line segment, it can be seen that its length is the longitudinal distance between the edge of the dangerous area and the edge of the adjacent risk area.

[0118] S2307. The rectangular area formed by the first line segment and the fourth line segment and adjacent to the longitudinal edge of the dangerous warning area is used as the first risk warning area of the vehicle in the forward state.

[0119] In this embodiment, the first risk warning area can be understood as a risk warning area located on one side of the vehicle and adjacent to the dangerous warning area.

[0120] Specifically, the rectangular area formed by the first line segment and the fourth line segment and adjacent to the longitudinal edge of the dangerous area is used as the first risk warning area, and the first risk warning area is located in front of the vehicle.

[0121] Exemplarily, as Figure 4 shown, the rectangular area located in the right front of the vehicle can be used as the first risk warning area.

[0122] S2308. Taking the longitudinal center line as the axis of symmetry, determine the symmetric rectangular area of the first risk warning area as the second risk warning area.

[0123] Exemplarily, as Figure 4 shown, the second risk warning area can be located in the left front of the vehicle. The first risk warning area and the second risk warning area are symmetric about the longitudinal center line of the vehicle, and both the first risk warning area and the second risk warning area are adjacent to the dangerous warning area.

[0124] S2309. Both the first risk warning area and the second risk warning area are used as the risk warning areas of the vehicle in the forward state.

[0125] Exemplarily, as Figure 4 shown, both the first risk warning area and the second risk warning area are used as the risk warning areas of the vehicle in the forward state. It can be seen that the vehicle warning area of the vehicle in the forward state is symmetric about the longitudinal center line and is located in the forward area of the vehicle's travel direction.

[0126] S240. Determine the vehicle warning state based on the vehicle information, the vehicle warning area, and the corresponding pedestrian information.

[0127] In the technical solution of the embodiment of the present invention, the longitudinal center line, the vehicle width, and the longitudinal edges of the vehicle are parsed from the vehicle information. The longitudinal edges of the vehicle are the edge positions of the vehicle parallel to the travel direction of the vehicle, and the longitudinal center line is parallel to the travel direction of the vehicle; a first line segment is obtained, and the length of the first line segment is the path length along the travel direction of the vehicle starting from the head position of the vehicle; a second line segment is set, and the length of the second line segment is a calibration value set from the longitudinal edge of the vehicle to the outside of the vehicle along the vertical direction of the travel direction of the vehicle; the sum of the vehicle width and the two second line segments set for the longitudinal edges on both sides of the vehicle is used as a third line segment; the rectangular area at the head position of the vehicle formed by the first line segment and the third line segment is used as the danger warning area of the vehicle in the forward state; a fourth line segment is set, and the length of the fourth line segment is a calibration value set from the longitudinal edge of the danger warning area along the vertical direction of the travel direction of the vehicle; the rectangular area adjacent to the longitudinal edge of the danger warning area formed by the first line segment and the fourth line segment is used as the first risk warning area of the vehicle in the forward state; the symmetric rectangular area of the first risk warning area is determined with the longitudinal center line as the axis of symmetry and used as the second risk warning area; both the first risk warning area and the second risk warning area are used as the risk warning areas of the vehicle in the forward state. The method for determining the vehicle warning area corresponding to the current vehicle state according to the vehicle information in the case where the current vehicle state is the forward state is refined. The vehicle warning area includes a danger warning area and a risk warning area, realizing a more comprehensive division of the warning area, making the vehicle warning more accurate, and improving the driving safety of the vehicle.

[0128] Embodiment III

[0129] Figure 7 is a schematic structural diagram of a vehicle warning device provided in Embodiment III of the present invention. As Figure 7 shown, the device includes:

[0130] An acquisition module 310, configured to sequentially acquire vehicle information at different times and pedestrian information in the road section where the vehicle is located during the driving process of the vehicle;

[0131] A first determination module 320, configured to determine a current vehicle state corresponding to the vehicle information for the vehicle information at each time;

[0132] A second determination module 330, configured to determine a vehicle warning area corresponding to the current vehicle state according to the vehicle information;

[0133] A third determination module 340, configured to determine a vehicle warning state based on the vehicle information, the vehicle warning area, and the corresponding pedestrian information.

[0134] The vehicle warning method, device, vehicle, storage medium, and program product provided by the embodiments of the present invention, during the driving process of the vehicle, the acquisition module sequentially acquires vehicle information at different times and pedestrian information in the road section where the vehicle is located; for the vehicle information at each time, the first determination module determines the current vehicle state corresponding to the vehicle information; according to the vehicle information, the second determination module determines the vehicle warning area corresponding to the current vehicle state; based on the vehicle information, the vehicle warning area, and the corresponding pedestrian information, the third determination module determines the vehicle warning state. Through the cooperation of each module, considering pedestrian information and vehicle information comprehensively, and analyzing more comprehensively, more reliable vehicle warning is achieved. The current vehicle state of the vehicle is determined according to the vehicle information, and a corresponding vehicle warning area is divided for the current vehicle state, so that the vehicle can more accurately monitor the conditions in the vehicle warning area, improving the safety of vehicle driving. According to the vehicle information, the vehicle warning area, and the pedestrian information, the vehicle warning state can be determined, simplifying the analysis process of determining the vehicle warning state and reducing the risk of traffic accidents.

[0135] In one embodiment, when the current vehicle state is a forward state, the vehicle warning area includes a danger warning area and a risk warning area. The second determination module 330 includes:

[0136] A first parsing unit, configured to parse the longitudinal center line, vehicle width, and vehicle longitudinal edge of the vehicle from the vehicle information. The vehicle longitudinal edge is the edge position of the vehicle parallel to the driving direction of the vehicle, and the longitudinal center line is parallel to the driving direction of the vehicle;

[0137] A first acquisition unit, configured to acquire a first line segment, and the length of the first line segment is the path length along the driving direction of the vehicle starting from the front position of the vehicle;

[0138] A first setting unit for setting a second line segment, the length of the second line segment being a calibration value set from the longitudinal edge of the vehicle, outward from the vehicle, in a direction perpendicular to the vehicle's traveling direction;

[0139] A first calculation unit for taking the sum of the vehicle width and two second line segments set for the longitudinal edges on both sides of the vehicle as a third line segment;

[0140] A first forming unit for taking the rectangular area at the front of the vehicle formed by the first line segment and the third line segment as the danger warning area of the vehicle in the forward state;

[0141] A second setting unit for setting a fourth line segment, the length of the fourth line segment being a calibration value set from the longitudinal edge of the danger warning area in a direction perpendicular to the vehicle's traveling direction;

[0142] A second forming unit for taking the rectangular area adjacent to the longitudinal edge of the danger warning area formed by the first line segment and the fourth line segment as the first risk warning area of the vehicle in the forward state;

[0143] A first determining unit for determining a symmetric rectangular area of the first risk warning area with the longitudinal center line as the axis of symmetry as the second risk warning area;

[0144] A first merging unit for taking both the first risk warning area and the second risk warning area as the risk warning area of the vehicle in the forward state.

[0145] In one embodiment, the first obtaining unit is specifically configured to:

[0146] Parse the vehicle speed of the vehicle from the vehicle information;

[0147] Set an empirical value and a preset value for the vehicle according to the vehicle information;

[0148] Calculate the product of the vehicle speed and the empirical value, add the result to the preset value, and take the calculation result as the first line segment.

[0149] In one embodiment, in the case where the current vehicle state is a reverse state, the second determining module 330 includes:

[0150] A second parsing unit for parsing the lateral center line and the longitudinal center line of the vehicle from the vehicle information, the lateral center line being perpendicular to the traveling direction of the vehicle;

[0151] A second acquisition unit, configured to acquire a fifth line segment, where the length of the fifth line segment is the path length starting from the horizontal center line along the vehicle traveling direction;

[0152] A third setting unit, configured to set a sixth line segment, where the length of the sixth line segment is a calibration value set along the vertical direction of the vehicle traveling direction starting from the vertical center line;

[0153] A third formation unit, configured to use the polygonal area formed by the fifth line segment and the sixth line segment except the vehicle as a first dangerous area;

[0154] A second determination unit, configured to determine a symmetric polygonal area of the first dangerous area with the vertical center line as the axis of symmetry as a second dangerous area;

[0155] A second merging unit, configured to merge the first dangerous area and the second dangerous area as the vehicle warning area of the vehicle in the reverse state.

[0156] In one embodiment, the second acquisition unit is specifically configured to:

[0157] Parse the vehicle speed of the vehicle from the vehicle information;

[0158] Set a first candidate length, where the first candidate length is a calibration value set along the vehicle traveling direction starting from the horizontal center line;

[0159] Use the product of the vehicle speed and the set time as a second candidate length, where the set time includes the time related to the vehicle information;

[0160] Use the length with the larger value among the first candidate length and the second candidate length as the length of the fifth line segment.

[0161] In one embodiment, when the current vehicle state is the forward state, the vehicle warning area includes a danger warning area and a risk warning area. The third determination module 340 includes:

[0162] A third parsing unit, configured to parse the pedestrian position information and the pedestrian heading angle of the pedestrian from the pedestrian information;

[0163] A fourth parsing unit, configured to parse the vehicle heading angle of the vehicle from the vehicle information;

[0164] A fourth setting unit, configured to set the vehicle warning state to the trigger state when the pedestrian position information indicates that the pedestrian is located in the danger warning area corresponding to the forward state;

[0165] A fifth setting unit, configured to calculate a deviation value between the pedestrian's heading angle and the vehicle's heading angle when the pedestrian position information indicates that the pedestrian is located in the risk warning area corresponding to the forward state, and set the vehicle warning state to the triggered state when the deviation value is within a preset range, otherwise set the vehicle warning state to the untriggered state;

[0166] A second calculation unit, configured to calculate the pedestrian's heading angle and the vehicle's heading angle according to a circular collision model and determine the vehicle warning state according to the calculation result when the pedestrian position information indicates that the pedestrian is neither located in the danger warning area nor in the risk warning area.

[0167] In one embodiment, the second calculation unit is specifically configured to:

[0168] Parse the vehicle center point of the vehicle and the longitudinal and lateral edges of the vehicle from the vehicle information;

[0169] Determine the diagonal line segment of the rectangle formed by the longitudinal edge and the lateral edge;

[0170] Construct a vehicle circular model with the vehicle center point as the center and half of the diagonal line segment as the radius;

[0171] Construct a pedestrian circular model with the pedestrian center of gravity indicated by the pedestrian position information as the center and a preset length as the radius, where the preset length is set according to the volume of the pedestrian;

[0172] Predict whether the vehicle circular model and the pedestrian circular model will be externally tangent according to the pedestrian's heading angle and the vehicle's heading angle;

[0173] If so, calculate the external tangent time, and set the vehicle warning state to the triggered state when the external tangent time is less than a preset threshold, otherwise set the vehicle warning state to the untriggered state, where the external tangent time includes the predicted value of the collision time between the vehicle and the pedestrian;

[0174] If not, set the vehicle warning state to the untriggered state.

[0175] In one embodiment, in the case where the current vehicle state is the reverse state, the third determination module 340 is specifically configured to:

[0176] Parse the pedestrian position information of the pedestrian from the pedestrian information;

[0177] Set the vehicle warning state to the triggered state when the pedestrian position information indicates that the pedestrian is located in the vehicle warning area corresponding to the reverse state; otherwise set the vehicle warning state to the untriggered state.

[0178] The vehicle warning device provided by the embodiment of the present invention can execute the vehicle warning method provided by any embodiment of the present invention. Through the cooperation and collaborative work among various modules, the warning of the vehicle is completed, and it has the corresponding functional modules and beneficial effects for executing the method.

[0179] Embodiment 4

[0180] According to an embodiment of the present invention, the present invention also provides a vehicle, a computer-readable storage medium, and a computer program product.

[0181] Figure 8 is a block diagram of a vehicle provided according to Embodiment 4 of the present invention. This vehicle can implement the vehicle warning method described in the embodiments of the present invention. The vehicle is intended to represent various forms of digital computers, such as, for example, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The vehicle can also represent various forms of mobile devices, such as, for example, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0182] As Figure 8 shown, the vehicle 410 includes at least one processor 411 and a memory communicatively connected to the at least one processor 411, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 411 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or the computer program loaded from the storage unit 418 into the random access memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the vehicle 410 can also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other through a bus 414. The input / output (I / O) interface 415 is also connected to the bus 414.

[0183] Multiple components in the vehicle are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, a mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a magnetic disk, an optical disc, etc.; and a communication unit 419, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 419 allows the vehicle to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0184] The processor 411 may be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 411 executes the various methods and processes described above, such as the vehicle warning method.

[0185] In some embodiments, the vehicle warning method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed onto the vehicle 410 via the ROM 412 and / or the communication unit 419. When the computer program is loaded into the RAM 413 and executed by the processor 411, one or more steps of the vehicle warning method described above may be executed. Alternatively, in other embodiments, the processor 411 may be configured to execute the vehicle warning method by any other suitable means (e.g., by means of firmware).

[0186] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0187] The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0188] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0189] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a vehicle that has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the vehicle. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0190] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0191] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0192] In some embodiments, a computer program product includes a computer program that, when executed by a processor, implements the vehicle warning method provided by the embodiments of the present invention.

[0193] The technical solution of the embodiments of the present invention, through a vehicle warning method, device, vehicle, storage medium and program product, sequentially obtains vehicle information at different times and pedestrian information in the section where the vehicle is located during the driving process of the vehicle; for the vehicle information at each time, determines the current vehicle state corresponding to the vehicle information; determines the vehicle warning area corresponding to the current vehicle state according to the vehicle information; and determines the vehicle warning state based on the vehicle information, the vehicle warning area and the corresponding pedestrian information. By comprehensively considering pedestrian information and vehicle information and analyzing more comprehensively, more reliable vehicle warning is achieved. The current vehicle state of the vehicle is determined according to the vehicle information, and a corresponding vehicle warning area is divided for the current vehicle state, enabling the vehicle to more accurately monitor the conditions within the vehicle warning area, improving the safety of vehicle driving. According to the vehicle information, the vehicle warning area and the pedestrian information, the vehicle warning state can be determined, simplifying the analysis process for determining the vehicle warning state and reducing the risk of traffic accidents.

[0194] It should be understood that various forms of the processes shown above can be used, with steps reordered, added or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0195] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A vehicle early warning method, characterized in that: include: During the driving process of the vehicle, sequentially obtaining vehicle information at different times and pedestrian information on the road section where the vehicle is located; For each vehicle information at each time, determining a current vehicle state corresponding to the vehicle information; Determining a vehicle warning area corresponding to the current vehicle state according to the vehicle information; The vehicle warning state is determined based on the vehicle information, the vehicle warning area and the corresponding pedestrian information.

2. The method according to claim 1, characterized in that In the case where the current vehicle state is a forward state, the vehicle warning area includes a danger warning area and a risk warning area, and determining the vehicle warning area corresponding to the current vehicle state according to the vehicle information includes: parsing the longitudinal centerline, vehicle width and longitudinal edge of the vehicle from the vehicle information, wherein the longitudinal edge of the vehicle is an edge position of the vehicle parallel to the driving direction of the vehicle, and the longitudinal centerline is parallel to the driving direction of the vehicle; Acquire a first line segment, where the length of the first line segment is the length of a path starting from the front position of the vehicle and along the driving direction of the vehicle; Setting a second line segment, wherein the length of the second line segment is a calibration value set from the longitudinal edge of the vehicle to the outer side of the vehicle along a direction perpendicular to the driving direction of the vehicle; The sum of the vehicle width and two second line segments set for the longitudinal edges of the vehicle on both sides of the vehicle is used as a third line segment; Using a rectangular area at the front position of the vehicle formed by the first line segment and the third line segment as a danger warning area of ​​the vehicle in a forward state; Setting a fourth line segment, wherein the length of the fourth line segment is a calibration value set along a vertical direction of the vehicle driving direction starting from the longitudinal edge of the danger warning area; Using a rectangular area formed by the first line segment and the fourth line segment and adjacent to a longitudinal edge of the danger warning area as a first risk warning area of ​​the vehicle in a forward state; Taking the longitudinal center line as the axis of symmetry, determining a symmetrical rectangular area of ​​the first risk warning area as a second risk warning area; The first risk warning area and the second risk warning area are both used as risk warning areas of the vehicle in the forward state.

3. The method according to claim 2, characterized in that The obtaining of the first line segment comprises: parsing a vehicle speed of the vehicle from the vehicle information; According to the vehicle information, setting an experience value and a preset value for the vehicle; The product of the vehicle speed and the empirical value is calculated, added to the preset value, and the calculation result is used as the first line segment.

4. The method according to claim 1, characterized in that In the case where the current vehicle state is a reversing state, determining the vehicle warning area corresponding to the current vehicle state according to the vehicle information includes: parsing a transverse centerline and a longitudinal centerline of the vehicle from the vehicle information, wherein the transverse centerline is perpendicular to a driving direction of the vehicle; Acquire a fifth line segment, wherein the length of the fifth line segment is the length of a path starting from the transverse center line and along the driving direction of the vehicle; Setting a sixth line segment, wherein the length of the sixth line segment is a calibration value set in a direction perpendicular to the vehicle travel direction starting from the longitudinal center line; taking a polygonal area formed by the fifth line segment and the sixth line segment, excluding the vehicle, as a first dangerous area; Taking the longitudinal center line as the axis of symmetry, determining a symmetrical polygonal area of ​​the first danger zone as the second danger zone; The first danger zone and the second danger zone are combined as a vehicle warning zone of the vehicle in a reversing state.

5. The method according to claim 4, characterized in that The obtaining of the fifth line segment comprises: parsing a vehicle speed of the vehicle from the vehicle information; Setting a first candidate length, where the first candidate length is a calibrated value set along the vehicle travel direction starting from the transverse centerline; The product of the vehicle speed and a set time is used as a second candidate length, wherein the set time includes a time related to the vehicle information; The length with a larger value between the first candidate length and the second candidate length is used as the length of the fifth line segment.

6. The method according to claim 1, characterized in that In the case where the current vehicle state is a forward state, the vehicle warning area includes a danger warning area and a risk warning area, and determining the vehicle warning state based on the vehicle information, the vehicle warning area and the corresponding pedestrian information includes: parsing pedestrian position information and pedestrian heading angle of the pedestrian from the pedestrian information; parsing a vehicle heading angle of the vehicle from the vehicle information; When the pedestrian position information indicates that the pedestrian is located in the danger warning area corresponding to the forward state, setting the vehicle warning state to a trigger state; When the pedestrian position information indicates that the pedestrian is located in the risk warning area corresponding to the forward state, calculating the deviation value between the pedestrian heading angle and the vehicle heading angle, and when the deviation value is within a preset range, setting the vehicle warning state to a triggered state, otherwise setting the vehicle warning state to a non-triggered state; When the pedestrian position information indicates that the pedestrian is neither located in the danger warning area nor in the risk warning area, the pedestrian heading angle and the vehicle heading angle are calculated according to the circular collision model, and the vehicle warning state is determined according to the calculation result.

7. The method according to claim 6, characterized in that The calculating the pedestrian heading angle and the vehicle heading angle according to the circular collision model, and determining the vehicle warning state according to the calculation result, includes: parsing a vehicle center point of the vehicle, and a longitudinal edge and a lateral edge of the vehicle from the vehicle information; Determine a diagonal line segment of a rectangle formed by the longitudinal edge and the transverse edge; Constructing a circular model of the vehicle with the center point of the vehicle as the center of the circle and half of the diagonal line segment as the radius; Constructing a circular model of the pedestrian with the center of gravity of the pedestrian indicated by the pedestrian position information as the center of the circle and a preset length as the radius, wherein the preset length is set according to the volume of the pedestrian; Predicting whether the circular model of the vehicle and the circular model of the pedestrian will be circumscribed according to the pedestrian heading angle and the vehicle heading angle; If yes, calculate the circumference time, and when the circumference time is less than a preset threshold, set the vehicle warning state to a triggered state, otherwise set the vehicle warning state to a non-triggered state, wherein the circumference time includes a predicted value of the collision time between the vehicle and the pedestrian; If not, the vehicle warning state is set to an untriggered state.

8. The method according to claim 1, characterized in that: In the case where the current vehicle state is a reversing state, determining the vehicle warning state based on the vehicle information, the vehicle warning area and the corresponding pedestrian information includes: parsing pedestrian position information of the pedestrian from the pedestrian information; When the pedestrian position information indicates that the pedestrian is located in the vehicle warning area corresponding to the reversing state, the vehicle warning state is set to a triggered state; otherwise, the vehicle warning state is set to a non-triggered state.

9. A vehicle warning device, characterized in that: include: An acquisition module, used to sequentially acquire vehicle information at different times and pedestrian information on a road section where the vehicle is located during the driving process of the vehicle; A first determination module is used to determine the current vehicle state corresponding to the vehicle information at each time; A second determination module is used to determine a vehicle warning area corresponding to the current vehicle state according to the vehicle information; The third determination module is used to determine the vehicle warning state based on the vehicle information, the vehicle warning area and the corresponding pedestrian information.

10. A vehicle, characterized in that: The vehicle comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the vehicle warning method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the vehicle warning method according to any one of claims 1 to 8 when executed.

12. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the vehicle early warning method according to any one of claims 1 to 8 is implemented.

Images