Fusion detection system, vehicle driving assistance system and motor vehicle

Abstract

The present application provides a fusion detection system, which comprises: at least one first detector, which gives two object identities ME ID0 and ME ID1 to an actual target detected in a to-be-detected area in a scene, and acquires signal values of each object identity ME ID0 and ME ID1; at least one second detector, which gives an object identity RD ID0 to the same target detected in the same to-be-detected area, and acquires a signal value of the object identity RD ID0; and a processing unit, which respectively compares the signal value of the object identity RD ID0 acquired by the second detector with the signal values of each object identity ME ID0 and ME ID1 acquired by the first detector, and adopts the object identity ME ID0 or ME ID1 with a smaller difference in signal value as the correct object identity. The present application also provides a vehicle driving assistance system using the fusion detection system and a motor vehicle.

Description

Technical Field

[0001] This invention relates to fusion detection systems, vehicle driving assistance systems, and motor vehicles. Background Technology

[0002] In recent years, motor vehicles equipped with driver assistance features (such as adaptive high beam, hereinafter referred to as ADB) have gained popularity among users. ADB functions mostly employ vision-based detectors (such as driving cameras / cameras) to detect the area to be detected in front of the vehicle (i.e., the field of view, FOV). Existing detectors include, for example, commercially available... Camera (hereinafter referred to as ME camera).

[0003] However, ME cameras have the following drawback: in certain application scenarios (such as nighttime applications), ME cameras may assign two object identities, ME ID0 and ME ID1, to an actual target detected in the area to be detected, even though the signal values ​​of these two object identities, ME ID0 and ME ID1, are similar to each other.

[0004] While this defect does not have a fatal impact on the decisions of the vehicle's computer (i.e., the electronic control unit, ECU), it can still potentially cause some confusion for motor vehicle users. Ideally, the detector should assign only one (not two) object identities to an actual target detected in the area to be detected. Therefore, improvements to the existing ADB (Advanced Driver Detection and Recognition) module are desired to eliminate or compensate for the aforementioned defect in the ME (Mechanical and Electrical) camera. Summary of the Invention

[0005] This invention was made to solve the above-mentioned technical problems and other potential technical problems.

[0006] According to one aspect of the present invention, a fusion detection system is provided. The fusion detection system includes: at least one first detector, which assigns two object identities, ME ID0 and ME ID1, to an actual target detected in a detection area in a scene, and acquires the signal value of each object identity ME ID0 and ME ID1; at least one second detector, which assigns one object identity RD ID0 to the same target detected in the same detection area, and acquires the signal value of the object identity RD ID0; and a processing unit, which compares the signal value of the object identity RD ID0 acquired by the second detector with the signal values ​​of each object identity ME ID0 and ME ID1 acquired by the first detector, and adopts the object identity ME ID0 or ME ID1 with the smaller difference from the signal value of the object identity RD ID0 as the correct object identity, while not adopting the other object identity ME ID0 or ME ID1 with the larger difference from the signal value of the object identity RD ID0. By adopting the above-described technical solution of the present invention, the aforementioned defects of ME cameras can be eliminated or compensated.

[0007] Specifically, the first detector can be a vision-based detector, and the second detector can be a radar-based detector. More specifically, the first detector can be a vehicle camera (such as the ME camera mentioned above), and the second detector can be a vehicle radar. By adopting the above-described technical solution of the present invention, the aforementioned technical problems can be solved with lower cost and higher reliability based on existing resources.

[0008] Specifically, if the first detector detects one target in the area to be detected while the second detector detects two targets in the same area, the detection result of the first detector is adopted, and the detection result of the second detector is not adopted. Furthermore, if the first detector assigns only one object identity to an actual target detected in the area to be detected, the detection result of the first detector is adopted. By employing the above technical solution of the present invention, it is possible to make correct judgments about targets in the area to be detected, thereby adopting the correct detection results.

[0009] According to another aspect of the present invention, a vehicle driving assistance system is provided. The vehicle driving assistance system includes the fusion detection system according to the preceding aspect. Optionally, the vehicle driving assistance system includes an adaptive high beam system, and the fusion detection system may be included in the adaptive high beam system.

[0010] According to another aspect of the present invention, a motor vehicle is provided. The motor vehicle includes the vehicle driving assistance system according to the preceding aspect. By employing the above-described technical solution of the present invention, the aforementioned technical problems can be solved with lower cost and higher reliability based on existing resources. Attached Figure Description

[0011] To facilitate understanding of the invention, it is described in more detail below based on exemplary embodiments and in conjunction with the accompanying drawings. The same or similar reference numerals are used in the drawings to denote the same or similar components. It should be understood that the drawings are merely schematic, and the dimensions and scale of the components in the drawings are not necessarily precise.

[0012] Figure 1 This is a schematic diagram of existing vehicle driver assistance functions.

[0013] Figure 2 This is a schematic diagram of a vehicle driving assistance function according to an exemplary embodiment of the present invention. Detailed Implementation

[0014] like Figure 1 As shown, existing vehicle driver assistance systems mainly include a driving camera, an ADB (Advanced Driver Assistance) module, a lighting ECU, and a vehicle controller area network (CAN) bus (not shown). The workflow of the ADB function is roughly as follows: the ME (Metal-based Driver Assistance) camera installed on the front of the vehicle detects the area to be detected in front of the vehicle (i.e., the field of view, FOV), then sends the detected objects to the ADB module, and then sends the detection list to the lighting ECU.

[0015] In certain applications (such as nighttime applications), an ME camera may assign two object identities, ME ID0 and ME ID1, to an actual target detected in the area to be detected, even though the signal values ​​of these two object identities, ME ID0 and ME ID1, are similar to each other. As a result, the two object IDs, ID0 and ID1, may be displayed on the vehicle's center console display in a real-time animated simulation.

[0016] Although this defect does not have a fatal impact on the decisions of the vehicle's computer (i.e., the electronic control unit ECU), it may still cause some inconvenience to motor vehicle users. Figure 1 The two objects ID0 and ID1 in the field of view (FOV) shown are depicted in an exaggerated manner. In reality, the two objects ID0 and ID1 can be very close to each other or even completely overlap.

[0017] Ideally, the detector assigns only one (not two) object identities to an actual target detected in the area to be detected. This way, only one object is displayed on the vehicle's center console display in a real-time animated simulation, thus matching the actual situation outside the vehicle.

[0018] Therefore, the present invention provides a fusion detection system. Figure 2 This is a schematic diagram of a vehicle driving assistance function according to an exemplary embodiment of the present invention. The vehicle driving assistance system includes an adaptive high beam system, and the fusion detection system may be included in the adaptive high beam system.

[0019] like Figure 2 As shown, a vehicle driving assistance system according to an exemplary embodiment of the present invention and Figure 1 The example area mainly involves the further addition of radar-based detectors (such as vehicle radar).

[0020] The radar can be positioned at the front or corner of the vehicle, taking into account its actual structure. Ideally, the radar's field of view (FOV) should be the same as or overlap with the existing ME camera's FOV. However, in practice, the radar's FOV may differ from that of the ME camera. Due to these differences in detection principles and FOV, discrepancies may exist between the radar's and ME camera's detection results, necessitating further analysis of the results, which will be discussed in detail later.

[0021] and Figure 1 Similarly, in some application scenarios (such as nighttime applications), a ME camera may assign two object identities, ME ID0 and ME ID1, to an actual target detected in the area to be detected.

[0022] Simultaneously, the radar assigns an object identity, such as RD ID0, to the same target detected in the same area to be detected, and acquires the signal value of the object identity RD ID0. This "signal value" can include or represent the target's range, angle, acceleration, confidence level, etc.

[0023] The processing unit (not shown) compares the signal value of the object identity RD ID0 acquired by the radar with the signal values ​​of each object identity ME ID0 and ME ID1 acquired by the ME camera, and adopts the object identity ME ID0 or ME ID1 with the smaller difference from the signal value of object identity RD ID0 as the correct object identity, while not adopting the other object identity ME ID0 or ME ID1 with the larger difference from the signal value of object identity RD ID0.

[0024] Specifically, such as Figure 2 As shown, the difference between object identity RD ID0 and object identity ME ID0 is small (visually shown as the close distance between them), while the difference between object identity RD ID0 and object identity ME ID1 is large (visually shown as the large distance between them). Therefore, in this case, object identity ME ID0 is adopted as the correct object identity, while the other object identity ME ID1 is not adopted. It should be understood that... Figure 2 The identities of the objects shown in the field of view (FOV) are exaggerated; in reality, these objects may be very close to each other or even overlap.

[0025] Furthermore, if the ME camera detects one target in the area to be detected while the radar detects two targets (ID0 and ID2) in the same area, the ME camera's detection result will be adopted, while the radar's detection result will not. This situation may be due to the difference between the detection range of the ME camera and the radar.

[0026] Furthermore, if the ME camera assigns only one object identity to an actual target detected in the area to be detected, the detection results of the ME camera are adopted, because this is exactly the desired detection result.

[0027] In summary, the judgment logic of the vehicle driving assistance function of the present invention can be listed as follows:

[0028] The IF detected only one target within the field of view (FOV) of the ME camera and identified two object identities, ME ID0 and ME ID1.

[0029] ELSE IF indicates that only one target has been detected by radar.

[0030] THEN 1. Compare the signal value of object identity RD ID0 with the signal values ​​of the two object identities ME ID0 and ME ID1 respectively.

[0031] 2. Difference ΔME ID0 = (Signal value of ME ID0 - Signal value of RD ID0) / Signal value of ME ID0

[0032] 3. Difference ΔME ID1 = (Signal value of ME ID1 - Signal value of RD ID0) / Signal value of ME ID1

[0033] 4. Output the smaller of the difference ΔME ID0 and the difference ΔME ID1 to the vehicle CAN bus.

[0034] ELSE IF indicates that two targets have been detected by radar.

[0035] THEN outputs the signal values ​​of ME ID0 and ME ID1.

[0036] ELSE detected only one target within the field of view (FOV) of the ME camera and identified an object with the identity ME ID0.

[0037] THEN outputs the ME ID0 signal value to the vehicle CAN bus.

[0038] Although the technical objectives, solutions, and effects of the present invention have been described in detail above with reference to specific embodiments, it should be understood that the above embodiments are merely exemplary and not restrictive. Any modifications, equivalent substitutions, or improvements made by those skilled in the art within the essential principles of the present invention are included within the scope of protection of the present invention.

Claims

1. A fusion detection system, characterized in that, include: At least one first detector, which assigns two object identities, ME ID0 and ME ID1, to an actual target detected in the area to be detected in a scenario, and acquires the signal value of each object identity, ME ID0 and ME ID1; At least one second detector, which assigns an object identity RD ID0 to the same target detected in the same area to be detected, and acquires the signal value of the object identity RD ID0; as well as The processing unit compares the signal value of the object identity RD ID0 obtained by the second detector with the signal values ​​of each object identity ME ID0 and ME ID1 obtained by the first detector. It then adopts the object identity ME ID0 or ME ID1 whose signal value differs less from that of object identity RD ID0, and rejects the other object identity ME ID0 or ME ID1 whose signal value differs more from that of object identity RD ID0. The comparison of the signal value of object identity RD ID0 with the signal values ​​of each object identity ME ID0 and ME ID1 includes: Calculate the difference ΔME ID0 = (signal value of ME ID0 - signal value of RD ID0) / signal value of ME ID0 and the difference ΔME ID1 = (signal value of ME ID1 - signal value of RD ID0) / signal value of ME ID1, and The object identity ME ID0 or ME ID1, which is the smaller of the difference ΔME ID0 and the difference ΔME ID1, will be adopted as the correct object identity.

2. The fusion detection system according to claim 1, wherein, The first detector is a vision-based detector, and the second detector is a radar-based detector.

3. The fusion detection system according to claim 1, wherein, The first detector is a vehicle camera, and the second detector is a vehicle radar.

4. The fusion detection system according to claim 1, wherein, If the first detector detects one target in the area to be detected while the second detector detects two targets in the same area, the detection result of the first detector shall be adopted and the detection result of the second detector shall not be adopted.

5. The fusion detection system according to claim 1, wherein, If the first detector assigns only one object identity to an actual target detected in the area to be detected, the detection result of the first detector shall be adopted.

6. A vehicle driving assistance system, characterized in that, The vehicle driving assistance system includes the fusion detection system according to any one of the preceding claims.

7. The vehicle driving assistance system according to claim 6, wherein, The vehicle driving assistance system includes an adaptive high beam system, and the fusion detection system is included in the adaptive high beam system.

8. A motor vehicle, characterized in that, The motor vehicle includes a vehicle driving assistance system as described in claim 6 or 7.

Images