Method and system for filtering misinformation objects in lateral traffic warning assistance

Abstract

The invention relates to a method for filtering a misinformation object in transverse traffic warning assistance. The method comprises the following steps: step S100, obtaining an object detected by a vehicle radar and the position and speed of a target; step S200, selecting a target, judging whether the target is a parallel target parallel to the vehicle or a crossing target crossing in front of or behind the vehicle according to the speed of the target, if the target is the parallel target, going to step S300, and if the target is the crossing target, going to step S400; step S300, setting a first object filtering area by taking the position of the parallel target as a reference, and going to step S500; step S400, setting a second object filtering area by taking the position of the crossing target as a reference; and step S500, taking the objects of which the object positions fall into the first object filtering area or the second object filtering area as misinformation objects and filtering the misinformation objects. According to the invention, the accuracy of the transverse traffic warning auxiliary function can be improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a method for filtering false alarm objects in lateral traffic warning assistance and a system for filtering false alarm objects in lateral traffic warning assistance. Background Art

[0002] Front Cross Traffic Alert (FCTA) is an assist feature that helps the driver in reduced visibility or when negotiating intersections at low speeds. The feature is only active when the vehicle is moving forward. If there is a risk of an imminent collision, FCTA will provide collision warnings and automatic braking measures to avoid or mitigate a frontal collision with a target vehicle or motorcycle crossing the vehicle's path.

[0003] FCTA is generally implemented by two front corner radars installed at the corners of the front bumper to monitor cross traffic in front of the vehicle. This function will respond to cross traffic targets in front and will not process responses to longitudinally moving targets.

[0004] One of the related challenges is that the corner radar needs to correctly process the lateral target output to activate the FCTA function. However, when the ego vehicle is driving on a normal road, the front corner radar often mistakes stationary objects or parallel objects or metal guardrails as crossing targets, resulting in false alarms of the FCTA function. Summary of the invention

[0005] In view of the above problems, the present invention aims to provide a method and system capable of effectively filtering out false alarm objects in front cross traffic warning assistance.

[0006] A method for filtering false positive objects in a lateral traffic warning aid according to one aspect of the present invention comprises the following steps:

[0007] Step S100: Acquire the positions and speeds of multiple objects and multiple targets detected by the vehicle radar;

[0008] Step S200: Select one target from the multiple targets, and determine whether the target is a parallel target parallel to the vehicle or a crossing target that crosses in front of or behind the vehicle according to the speed of the target. If the target is a parallel target, proceed to step S300; if the target is a crossing target, proceed to step S400;

[0009] Step S300: setting a first object filtering area based on the position of the parallel target, and proceeding to S500;

[0010] Step S400: setting a second object filtering area based on the position of the crossing target, and proceeding to S500; and

[0011] Step S500: Filter out objects among the multiple objects whose positions fall within the first object filtering area or the second object filtering area as false alarm objects.

[0012] A system for filtering false positive objects in a lateral traffic warning assistance according to one aspect of the present invention comprises:

[0013] An acquisition module, for acquiring positions and speeds of multiple objects and multiple targets detected by a vehicle radar;

[0014] A judgment module, selecting a target from the multiple targets, and judging whether the target is a parallel target parallel to the ego vehicle or a crossing target crossing in front of the ego vehicle according to the speed of the target;

[0015] a setting module, which sets a first object filtering area based on the position of the parallel object or sets a second object filtering area based on the position of the crossing object; and

[0016] The filtering module filters out objects among the multiple objects whose positions fall within the first object filtering area or the second object filtering area as false alarm objects.

[0017] A computer readable medium according to one aspect of the present invention stores a computer program thereon, and when the computer program is executed by a processor, the method for filtering false alarm objects in lateral traffic warning assistance is implemented.

[0018] A computer device according to one aspect of the present invention comprises a storage module, a processor and a computer program stored on the storage module and executable on the processor, wherein the processor implements the method for filtering false alarm objects in lateral traffic warning assistance when executing the computer program.

[0019] A front lateral traffic warning assistance system according to one aspect of the present invention includes the system for filtering false alarm objects in the lateral traffic warning assistance.

[0020] According to the method for filtering false alarm objects in lateral traffic warning assistance and the system for filtering false alarm objects in lateral traffic warning assistance of the present invention, false alarm objects in lateral traffic warning assistance can be filtered out, and false alarms of front cross traffic alert assistant (FCTA) and rear cross traffic alert assistant (RCTA) can be reduced, thereby improving the accuracy of the lateral traffic warning assistance function. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 The flowchart is a schematic diagram showing a method for filtering false alarm objects in a lateral traffic warning assistance according to an embodiment of the present invention.

[0022] Figure 2This is a schematic diagram showing that a first target filter area is set for a parallel object based on the position of the parallel object.

[0023] Figure 3 It is a schematic diagram showing that a second object filter area is set for a crossing object based on the position of the crossing object.

[0024] Figure 4 The present invention is an embodiment of a method for filtering false positive objects in a cross traffic warning assistant.

[0025] Figure 5 This is a schematic block diagram showing a system for filtering false alarm objects in cross traffic warning assistance according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The following describes some of the various embodiments of the present invention, which are intended to provide a basic understanding of the present invention, but are not intended to identify the key or decisive elements of the present invention or to limit the scope of protection.

[0027] For the purpose of brevity and illustration, the principles of the present invention are described herein mainly with reference to its exemplary embodiments. However, those skilled in the art will readily recognize that the same principles are equally applicable to all types of methods for filtering false alarm objects in lateral traffic warning assistance and systems for filtering false alarm objects in lateral traffic warning assistance, and these same principles can be implemented therein, and any such changes do not depart from the true spirit and scope of the present patent application.

[0028] The inventors of the present invention have found through research that corner radars or millimeter wave radars are prone to ghost detection. Ghost objects are mainly caused by multiple reflection effects that are often detected in scenes with high reflection intensity. For the FCTA function, if a ghost object occurs and it has a great tendency to cross or even collide with the test vehicle at a close distance, it will cause a false alarm of the FCTA. For example, in the corner radar test project, false alarms (i.e., false positives) are often reported when the test vehicle passes by a parallel moving vehicle or drives along a metal fence. The inventors' research and measurements have shown that ghost objects mainly come from original parallel objects.

[0029] Based on the above findings of the inventors, it is proposed to filter out false alarms caused by stationary objects or parallel objects or metal guardrails based on the relative relationship (parallel relationship and crossing relationship) between at least two objects.

[0030] Specifically, the inventors found that in the prior art, ghost objects are usually filtered by measuring their quality indicators (such as movement probability, obstacle probability, and existence probability). However, in the above case, ghost objects often have relatively high quality, and the threshold of the quality indicator cannot distinguish between real objects and ghost objects. Based on this situation, the present invention proposes that in the case of parallel targets, if there are crossing objects or ghost objects that will cause a collision risk with the vehicle, and they are on the same side as the parallel targets, we will filter out these crossing objects or ghost objects based on the relative relationship between the crossing objects or ghost objects and the parallel targets. As a result, it is possible to filter out false alarm objects caused by inaccurate corner radar perception, thereby reducing false alarms of the FCTA function.

[0031] First, a method for filtering false alarm objects in a cross traffic warning assistance according to an embodiment of the present invention is described.

[0032] Figure 1 The flowchart is a schematic diagram showing a method for filtering false alarm objects in a lateral traffic warning assistance according to an embodiment of the present invention.

[0033] like Figure 1 As shown, a method for filtering false alarm objects in lateral traffic warning assistance according to an embodiment of the present invention includes:

[0034] Step S100: Acquire the positions and speeds of multiple objects and multiple targets detected by the vehicle radar;

[0035] Step S200: selecting a target from the plurality of targets, and judging whether the target is a parallel target parallel to the vehicle or a crossing target crossing ahead of the vehicle according to the speed of the target, and if the target is a parallel target, proceeding to step S300, and if the target is a crossing target, proceeding to step S400;

[0036] Step S300: for a parallel target, a first object filtering area is set based on the position of the parallel target, and then the process proceeds to S500;

[0037] Step S400: setting a second object filtering area based on the position of the crossing target, and proceeding to S500; and

[0038] Step S500: Filter out objects among the multiple objects whose positions fall within the first object filtering area or the second object filtering area as false alarm objects.

[0039] In step S200, the vehicle may also be configured to determine that the target is a parallel target if the ratio of the lateral speed to the longitudinal speed (Vy / Vx) of the target is not greater than 1, and otherwise determine that the target is a crossing target.

[0040] Figure 2 is a schematic diagram showing setting a first object filtering area for a parallel target based on the position of the parallel target. Figure 2 In the figure, the X axis represents the longitudinal direction and the Y axis represents the transverse direction (the longitudinal direction and transverse direction described in other parts of the present invention are also the same as those in the figure). Figure 2 direction shown). Figure 2 Here, i represents a target, j represents an object (j is an object to be filtered as a false alarm object in step S500), and e represents an own vehicle.

[0041] In step S300, for relatively parallel targets, such as Figure 2 As shown, a target i parallel to the vehicle is selected, and then a first filter area K1 is defined according to the target i. The following describes the method for determining the first filter area K1.

[0042] First, determine the longitudinal extent of the first filter area K1. Figure 2 M1 and M2 on the right side of the middle vertical axis are used to limit the minimum and maximum longitudinal distances of target i, respectively.

[0043] The longitudinal extent of the first filter area K1 is Figure 2 The "①+②+③" in the formula is determined. Among them, Figure 2 ② in the figure is a first extended front distance (ExtendFront) EF1. The first extended front distance EF1 is equivalent to the vehicle length of the target i as an example. Figure 2 ③ in the figure is the first rear extension distance (ExtendBack) EB1, wherein the first rear extension distance EB1 represents the distance that the target i extends backward from the center of the rear bumper. Figure 2 ① in the figure is determined by the longitudinal speed of target i. As an example, it can be set to the distance that target i travels forward in 2 seconds.

[0044] Secondly, determine the lateral range of the first filtering area K1. The lateral range of the first filtering area K1 is set to extend 5m and 35m respectively according to the center of the rear bumper of the target i, that is, Figure 2 From the center of the rear bumper of target i to the opposite side of the position of vehicle e ( Figure 2 In the case of determining the first filtering area K1, it is also necessary to additionally determine whether there is a gap between the object and the target and whether they are on the same side. This will be Figure 4 Specific instructions are given in .

[0045] Further, in Figure 2A longitudinal unrestricted area D represented by a dotted line can also be set. As an example, the longitudinal unrestricted area D can be set to an area 5m to the left and 5m to the right of the center of the target i bumper in the lateral direction. The longitudinal unrestricted area D indicates that in this area, for the filtered object j, there are no upper and lower limits of the longitudinal range.

[0046] Thus, by setting the first filtering area K1, in step S500, the object j whose position falls within the first object filtering area K is filtered as a false alarm object. Furthermore, in step S500, the object j whose position falls within the longitudinal unrestricted area D is filtered as a false alarm object. Figure 2 The example in FIG. 1 shows the case where target i is on the left side of vehicle e. The same is true for the case where target i is on the right side of vehicle e.

[0047] Figure 3 is a schematic diagram showing setting a second object filtering area for a crossing target based on the position of the crossing target. Figure 3 In the figure, the X axis represents the vertical direction and the Y axis represents the horizontal direction. Figure 3 Here, i represents the target, j represents the filtered object, and e represents the ego vehicle.

[0048] In step S400, for a crossing target perpendicular to the vehicle, Figure 3 As shown, a target i crossing the front of the vehicle is selected, and then, based on the target i, a second filtering area K2 is defined.

[0049] First, select a target i, for example, the absolute longitudinal velocity Vx of target i + the longitudinal reference velocity VxvRef(ego) of the vehicle is less than 1.0 and the longitudinal distance of target i is greater than 2m (in Figure 3 In the figure, it is expressed as 2m forward from the center of the rear bumper of the vehicle. Figure 3 In the left figure, the horizontal M3 and M4 are used to limit the minimum horizontal distance and maximum horizontal distance of target i, respectively. Figure 3 In the right figure of , the horizontal M5 and M6 are used to limit the minimum horizontal distance and the maximum horizontal distance of the target i, respectively. Then, according to the target i, the longitudinal range of the second object filtering area K2 is defined as extending from the target i to the front by the second front extension distance (ExtendFront) EF2, wherein the second front extension distance EF2 can be set to 3.5m as an example. According to the rear bumper center of the target i, the lateral range of the second object filtering area K2 is further defined from the rear bumper center of the target i to the left ( Figure 3 ) or to the right ( Figure 3 As shown in the right figure in FIG. 1 , the second rear extension distance (ExtendBack) EB2 is extended, wherein the second rear extension distance EB2 can be set to 3m as an example. Figure 3 The second object filtering area K2 is indicated by a shaded box in FIG. Figure 3 The example in FIG. 1 shows the case where target i is on the left side of vehicle e. The same is true for the case where target i is on the right side of vehicle e.

[0050] Next, an embodiment of a method for filtering false alarm objects in a cross traffic warning assistance of the present invention is described.

[0051] Figure 4 The present invention is an embodiment of a method for filtering false positive objects in a cross traffic warning assistant.

[0052] like Figure 4 As shown, an embodiment of the method for filtering false positive objects in the lateral traffic warning assistance of the present invention comprises the following steps:

[0053] Step S1: Get the target and object list;

[0054] Step S2: Determine whether the object to be filtered is activated and whether the target is valid. If it is valid, continue to step S3, otherwise jump to step S16.

[0055] Step S3: Calculate the longitudinal speed Vx of the target, calculate the front extension distance (Extend Front) and the rear extension distance (Extend Back), wherein the front extension distance = the length of the target, and the rear extension distance = the front extension distance / 2+0.5*the longitudinal speed Vx of the target;

[0056] Step S4: Determine whether the target is a parallel target or a crossing target, that is, determine whether the lateral speed (Vy) of the target / the longitudinal speed (Vx) of the target is not greater than 1 and determine whether the period of the target being detected by the radar is greater than the period of the object being detected by the radar (this is because the longer the detection period, the higher the target credibility). If it is determined to be yes (Y), it is a parallel target and proceed to step S5. If it is determined to be no (N), it is a crossing target and proceed to step S11.

[0057] Step S5: Calculate the maximum and minimum values ​​of the longitudinal range, where the maximum value = front extension distance (ExtendFront) + rear extension distance (ExtendBack) +

[0058] TargetVxSpeed2.0f, minimum value = target length (Dx) + extended distance (ExtendBack), where "TargetVxSpeed2.0f" refers to the distance the target travels forward in 2 seconds;

[0059] Step S6: Calculate whether the target and the object are on the same side. If they are on the same side, proceed to step S7. The calculation of whether the target and the object are on the same side may be performed by determining whether the lateral coordinates of the target and the object are both positive or both negative.

[0060] Step S7: Calculate the gap between the object and the target, which can be used to determine the relative position relationship between the two, for example, whether the target to be filtered is blocked by the reference target. This can be calculated based on the horizontal distance between the two, that is, the difference between the absolute values ​​of the horizontal coordinates of the two (corresponding to Figure 2 In the case of , both target i and object j are located on the left side of the vehicle, then object j is blocked by target i);

[0061] Step S8: Calculate the lateral distance difference (dyDiff) between the target and the object, where the lateral distance difference between the target and the object = the target lateral coordinate (Dy) - the object lateral coordinate (Dy);

[0062] Step S9: Perform the following two judgments. If the judgment meets any of the two conditions, proceed to step S10: Determine whether the lateral distance difference (dyDiff) between the target and the object is less than 5m (i.e., determine whether it is located at Figure 2 The target is within the longitudinal unrestricted area D in the vertical range, and there is no longitudinal distance limit in this range), or the lateral distance difference (dyDiff) between the target and the object is less than 35m and the object is in the longitudinal range, and the object and the target are on the same side, and there is a gap between the object and the target (i.e., whether it is located in Figure 2 In the case of the first filtering area K1 in the example, it is also necessary to additionally satisfy that there is a gap between the object and the target and they are located on the same side);

[0063] Step S10: filtering the object as a false positive object;

[0064] Step S11: Set the front extension distance (ExtendFront) = 3.5m, the rear extension distance (ExtendBack) = 3m;

[0065] Step S12: Calculate the maximum and minimum values ​​of the target range, wherein the maximum value = the horizontal coordinate of the target (Dy) + the rear extension distance (ExtendBack), and the minimum value = the horizontal coordinate of the target (Dy);

[0066] Step S13: Calculate whether it is within the longitudinal range, that is, the longitudinal coordinate of the object (Dx)> the longitudinal coordinate of the target (Dx) and the longitudinal coordinate of the object (Dx)< the longitudinal coordinate of the target (Dx)+the front extension distance (ExtendFront);

[0067] Step S14: Calculate whether the object is within the lateral range, that is, the lateral coordinate (Dy) of the object > the minimum value of the target range and < the maximum value of the target range;

[0068] Step S15: Determine whether the object is within the longitudinal range and the object is within the lateral range at the same time, if so (Y), jump to step S10; and

[0069] Step S16: End.

[0070] Figure 5 This is a schematic block diagram showing a system for filtering false alarm objects in cross traffic warning assistance according to an embodiment of the present invention.

[0071] like Figure 5 As shown, a system for filtering false alarm objects in a lateral traffic warning assistance according to an embodiment of the present invention includes:

[0072] An acquisition module 100 is used to acquire the positions and speeds of multiple objects and multiple targets detected by the vehicle radar;

[0073] A judgment module 200 selects a target from the multiple targets and judges whether the target is a parallel target parallel to the vehicle or a crossing target crossing ahead of the vehicle according to the speed of the target;

[0074] A setting module 300 is used to set a first object filtering area based on the position of the parallel object or to set a second object filtering area based on the position of the crossing object, wherein the position information comes from the acquisition module 100; and

[0075] The filtering module 400 filters out objects among the multiple objects whose positions fall within the first object filtering area or the second object filtering area as false alarm objects.

[0076] In the judgment module 200 , if the ratio of the lateral speed to the longitudinal speed of the target is not greater than 1, the target is judged to be a parallel target; otherwise, the target is judged to be a crossing target.

[0077] In the case of a parallel target, in the setting module 300, an area extending forward and backward by a first predetermined distance and a second predetermined distance in the longitudinal direction based on the parallel target, respectively, and extending in the opposite direction of the vehicle position by a third predetermined distance in the transverse direction based on the parallel target is set as the first object filtering area. Specifically, the following settings are performed in the setting module 300:

[0078] Setting the maximum value in the longitudinal direction and the minimum value in the transverse direction of the first object filtering area, wherein the maximum value in the longitudinal direction is the longitudinal coordinate of the parallel target plus the first specified distance, the second specified distance, and the distance traveled by the parallel target for 2 seconds, and the minimum value in the longitudinal direction is the sum of the longitudinal coordinate of the parallel target plus the second specified distance;

[0079] determining that the parallel target and one of the plurality of objects are located on the same side of the vehicle in a lateral direction;

[0080] An area located between the maximum value and the minimum value in the longitudinal direction and within the third prescribed distance from the parallel object in the lateral direction with respect to the parallel object as a reference is set as the first object filtering area.

[0081] The first specified distance is the aforementioned front extension distance (ExtendFront), which can be set to the length of the target. The second specified distance is the aforementioned rear extension distance (ExtendBack), which can be set to the sum of half of the first specified distance and the distance that the parallel target travels for 0.5 seconds. The third specified distance is greater than 5m and less than 35m.

[0082] In the case of parallel targets, as another example, in the setting module 300, an area extending 5 m to the left and right respectively in the horizontal direction based on the parallel target is further used as a longitudinal unrestricted area. In the filtering module 400, objects among the multiple objects whose positions fall within the longitudinal unrestricted area are further filtered as false alarm objects.

[0083] In the case of a crossing target, in the setting module 300, an area extending forward by a fourth prescribed distance in the longitudinal direction based on the crossing target and extending to the left and right by a fifth prescribed distance in the transverse direction based on the crossing target is set as the second object filtering area.

[0084] Specifically, the following settings are performed in the setting module 300:

[0085] Setting the maximum and minimum values ​​of the second object filtering area in the horizontal direction;

[0086] Setting an area extending forward by the fourth prescribed distance in the longitudinal direction based on the crossing target and extending left by the fifth prescribed distance in the transverse direction based on the crossing target and located between the maximum value and the minimum value as the second object filtering area; and

[0087] Another area extending forward by the fourth prescribed distance in the longitudinal direction based on the crossing target and extending rightward by the fifth prescribed distance in the transverse direction based on the crossing target and located between the maximum value and the minimum value is also set as the second object filtering area.

[0088] Among them, the maximum value of the second object filtering area in the horizontal direction is the sum of the horizontal coordinates of the crossing target and the fifth specified distance, the minimum value of the second object filtering area in the horizontal direction is the horizontal coordinates of the crossing target, the fourth specified distance is 3.5m, and the fifth specified distance is 3m.

[0089] In the above embodiments, the application of the present invention to the front cross traffic alert assist (FCTA) is taken as an example for explanation. Similarly, the present invention can also be applied to the rear cross traffic alert assist (RCTA) by slightly adjusting parameters.

[0090] As described above, according to the method for filtering false alarm objects in lateral traffic warning assistance and the system for filtering false alarm objects in lateral traffic warning assistance of the present invention, it is possible to filter out false alarm objects in lateral traffic warning assistance, reduce false alarms of front cross traffic alert assistant (FCTA) and rear cross traffic alert assistant (RCTA), and thus improve the accuracy of the lateral traffic warning assistance function.

[0091] The above examples mainly illustrate the method for filtering false alarm objects in the lateral traffic warning assistance and the system for filtering false alarm objects in the lateral traffic warning assistance of the present invention. Although only some of the specific embodiments of the present invention are described, it should be understood by those skilled in the art that the present invention can be implemented in many other forms without departing from its subject matter and scope. Therefore, the examples and embodiments shown are regarded as illustrative rather than restrictive, and the present invention may cover various modifications and substitutions without departing from the spirit and scope of the present invention as set forth in the appended claims.

Claims

1. A method for filtering false alarm objects in lateral traffic warning assistance, characterized in that: The following steps are involved: Step S100: Acquire the positions and speeds of multiple objects and multiple targets detected by the vehicle radar; Step S200: Select one target from the multiple targets, and determine whether the target is a parallel target parallel to the vehicle or a crossing target that crosses in front of or behind the vehicle according to the speed of the target. If the target is a parallel target, proceed to step S300; if the target is a crossing target, proceed to step S400; Step S300: setting a first object filtering area based on the position of the parallel target, and proceeding to S500; Step S400: setting a second object filtering area based on the position of the crossing target, and proceeding to S500; as well as Step S500: Filter out objects among the multiple objects whose positions fall within the first object filtering area or the second object filtering area as false alarm objects.

2. The method for filtering false positive objects in lateral traffic warning assistance according to claim 1, characterized in that: In the step S200, if the ratio of the lateral speed to the longitudinal speed of the target is not greater than 1, the target is determined to be a parallel target, otherwise it is a crossing target.

3. The method for filtering false positive objects in lateral traffic warning assistance according to claim 1, characterized in that: In the step S300, an area that extends forward and backward by a first specified distance and a second specified distance in the longitudinal direction based on the parallel target, respectively, and extends laterally by a third specified distance in the opposite direction of the vehicle's position based on the parallel target is set as the first object filtering area.

4. The method for filtering false positive objects in lateral traffic warning assistance according to claim 3, characterized in that: In the step S300, an area extending 5 m to the left and right in the horizontal direction based on the parallel target is further regarded as a longitudinal unrestricted area. In the step S500, objects among the multiple objects whose positions fall within the longitudinal unrestricted area are further filtered out as false alarm objects.

5. The method for filtering false positive objects in lateral traffic warning assistance according to claim 4, characterized in that: The step S300 includes: Setting the maximum value in the longitudinal direction and the minimum value in the transverse direction of the first object filtering area, wherein the maximum value in the longitudinal direction is the longitudinal coordinate of the parallel target plus the first specified distance, the second specified distance, and the distance traveled by the parallel target for 2 seconds, and the minimum value in the longitudinal direction is the sum of the longitudinal coordinate of the parallel target plus the second specified distance; determining that the parallel target and one of the plurality of objects are located on the same side of the vehicle in a lateral direction; An area located between the maximum value and the minimum value in the longitudinal direction and within the third prescribed distance from the parallel object in the lateral direction with respect to the parallel object as a reference is set as the first object filtering area.

6. The method for filtering false positive objects in lateral traffic warning assistance according to claim 5, characterized in that: The first specified distance is the length of the target, The second specified distance is the sum of half of the first specified distance and the distance that the parallel target travels in 0.5 seconds. The third specified distance is greater than 5m and less than 35m.

7. The method for filtering false positive objects in lateral traffic warning assistance according to claim 1, characterized in that: In the step S400, an area extending forward by a fourth prescribed distance in the longitudinal direction based on the crossing target and extending leftward and rightward by fifth prescribed distances in the transverse direction based on the crossing target is set as the second object filtering area.

8. The method for filtering false positive objects in lateral traffic warning assistance according to claim 7, characterized in that: The step S400 includes: Setting the maximum and minimum values ​​of the second object filtering area in the horizontal direction; Setting an area extending forward by the fourth prescribed distance in the longitudinal direction based on the crossing target and extending left by the fifth prescribed distance in the transverse direction based on the crossing target and located between the maximum value and the minimum value as the second object filtering area; and Another area extending forward by the fourth prescribed distance in the longitudinal direction based on the crossing target and extending rightward by the fifth prescribed distance in the transverse direction based on the crossing target and located between the maximum value and the minimum value is also set as the second object filtering area.

9. The method for filtering false positive objects in lateral traffic warning assistance according to claim 8, characterized in that: The maximum value of the second object filtering area in the horizontal direction is the sum of the horizontal coordinate of the crossing object and the fifth specified distance. The minimum value of the second object filtering area in the horizontal direction is the horizontal coordinate of the crossing object. The fourth prescribed distance is 3.5 m, and the fifth prescribed distance is 3 m.

10. A system for filtering false positive objects in a lateral traffic warning aid, characterized in that: include: An acquisition module, for acquiring positions and speeds of multiple objects and multiple targets detected by a vehicle radar; A judgment module, selecting a target from the multiple targets, and judging whether the target is a parallel target parallel to the ego vehicle or a crossing target crossing in front of the ego vehicle according to the speed of the target; A setting module, which sets a first object filtering area based on the position of the parallel target or sets a second object filtering area based on the position of the crossing target; as well as The filtering module filters out objects among the multiple objects whose positions fall within the first object filtering area or the second object filtering area as false alarm objects.

11. The system for filtering false positive objects in lateral traffic warning assistance according to claim 10, characterized in that: In the judgment module, if the ratio of the lateral speed to the longitudinal speed of the target is not greater than 1, the target is judged to be a parallel target; otherwise, the target is judged to be a crossing target.

12. The system for filtering false positive objects in lateral traffic warning assistance according to claim 10, characterized in that: In the setting module, an area that extends a first specified distance and a second specified distance forward and backward respectively in the longitudinal direction based on the parallel target and extends a third specified distance in the opposite direction of the vehicle position in the transverse direction based on the parallel target is set as the first object filtering area.

13. The system for filtering false positive objects in lateral traffic warning assistance according to claim 10, characterized in that: In the setting module, an area extending 5m to the left and right in the horizontal direction based on the parallel target is further regarded as a longitudinal unrestricted area. In the filtering module, objects among the multiple objects whose positions fall within the longitudinal unrestricted area are further filtered as false alarm objects.

14. The system for filtering false positive objects in lateral traffic warning assistance according to claim 12, characterized in that: The following settings are made in the setting module: Setting the maximum value in the longitudinal direction and the minimum value in the transverse direction of the first object filtering area, wherein the maximum value in the longitudinal direction is the longitudinal coordinate of the parallel target plus the first specified distance, the second specified distance, and the distance traveled by the parallel target for 2 seconds, and the minimum value in the longitudinal direction is the sum of the longitudinal coordinate of the parallel target plus the second specified distance; determining that the parallel target and one of the plurality of objects are located on the same side of the vehicle in a lateral direction; An area located between the maximum value and the minimum value in the longitudinal direction and within the third prescribed distance from the parallel object in the lateral direction with respect to the parallel object as a reference is set as the first object filtering area.

15. The system for filtering false positive objects in lateral traffic warning assistance according to claim 14, characterized in that: The first specified distance is the length of the target, The second specified distance is the sum of half of the first specified distance and the distance that the parallel target travels in 0.5 seconds. The third specified distance is greater than 5m and less than 35m.

16. The system for filtering false positive objects in the lateral traffic warning assistance according to claim 10, characterized in that: In the setting module, an area that extends forward by a fourth prescribed distance in the longitudinal direction based on the crossing target and extends to the left and right by fifth prescribed distances in the transverse direction based on the crossing target is set as the second object filtering area.

17. The system for filtering false positive objects in lateral traffic warning assistance according to claim 16, characterized in that: The following settings are made in the setting module: Setting the maximum and minimum values ​​of the second object filtering area in the horizontal direction; Setting an area extending forward by the fourth prescribed distance in the longitudinal direction based on the crossing target and extending left by the fifth prescribed distance in the transverse direction based on the crossing target and located between the maximum value and the minimum value as the second object filtering area; as well as Another area extending forward by the fourth prescribed distance in the longitudinal direction based on the crossing target and extending rightward by the fifth prescribed distance in the transverse direction based on the crossing target and located between the maximum value and the minimum value is also set as the second object filtering area.

18. The system for filtering false positive objects in lateral traffic warning assistance according to claim 17, characterized in that: The maximum value of the second object filtering area in the horizontal direction is the sum of the horizontal coordinate of the crossing object and the fifth specified distance. The minimum value of the second object filtering area in the horizontal direction is the horizontal coordinate of the crossing object. The fourth prescribed distance is 3.5 m, and the fifth prescribed distance is 3 m.

19. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for filtering false alarm objects in lateral traffic warning assistance according to any one of claims 1 to 9 is implemented.

20. A computer device comprising a storage module, a processor, and a computer program stored in the storage module and executable on the processor, characterized in that: When the processor executes the computer program, the method for filtering false alarm objects in lateral traffic warning assistance according to any one of claims 1 to 9 is implemented.

21. A front cross traffic warning auxiliary system, characterized in that: A system for filtering false positive objects in lateral traffic warning assistance comprising the system described in claims 10 to 18.

Images