Method and device for detecting ghost object in blind spot detection

Abstract

The invention relates to a ghost object detection method and device in blind spot detection. The method comprises the following steps: dividing a blind spot detection area into a first functional area and a second functional area; the threshold value of the survival cycle counter of the first functional area is set as a first threshold value, the threshold value of the survival cycle counter of the second functional area is set as a second threshold value, and the first threshold value is set to be different from the second threshold value; and respectively counting survival cycles of the object sensed by the radar sensor in the first functional area and the second functional area to obtain a first count value and a second count value, and when the first count value in the first functional area exceeds the first threshold value, judging that the object is a ghost object and filtering, and when the second count value in the second functional area exceeds a second threshold value, judging that the object is a ghost object and filtering. Wherein the first threshold value is smaller than the second threshold value. According to the invention, ghost objects can be filtered more accurately.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a ghost object detection method and a ghost object detection device in blind spot detection. Background Art

[0002] Blind Spot Detection (BSD) is a function that monitors the area adjacent to and behind the vehicle. If a moving object is detected in the warning area, a warning will be issued. Currently, in blind spot detection, if a ghost object (a ghost object refers to an object that does not actually exist) appears in the warning area, false alarms are prone to occur.

[0003] Existing ghost object filtering methods mainly focus on judging whether the object's attributes or detection quality are within a reasonable range. Generally, the object's attributes are judged by a survival cycle counter, which records the number of cycles since the object was sensed by the sensor.

[0004] Generally, for ghost objects, the number of survival cycle counters is relatively low. Therefore, in order to solve the false positives in blind spot detection, the method adopted in the prior art is to set a fixed survival cycle counter threshold for all targets and filter out ghost objects with relatively low number (i.e., short-lived appearance). Summary of the invention

[0005] Based on the above problems in the prior art, the present invention aims to provide a ghost object detection method and a ghost object detection device that can reduce the occurrence of false alarms in blind spot detection.

[0006] A method for detecting ghost objects in blind spot detection according to one aspect of the present invention comprises:

[0007] Dividing the blind spot detection area into a first functional area and a second functional area;

[0008] Setting the threshold of the survival cycle counter of the first functional area to a first threshold, setting the threshold of the survival cycle counter of the second functional area to a second threshold, and setting the first threshold to be different from the second threshold; and

[0009] In the first functional area and the second functional area, the survival period of the object sensed by the radar sensor is counted to obtain a first count value and a second count value, respectively. In the first functional area, when the first count value exceeds the first threshold, the object is judged to be a ghost object and filtered; in the second functional area, when the second count value exceeds the second threshold, the object is judged to be a ghost object and filtered.

[0010] A ghost object detection device in blind spot detection according to one aspect of the present invention comprises:

[0011] A division module, used for dividing the blind spot detection area into a first functional area and a second functional area;

[0012] a setting module, configured to set the threshold of the survival cycle counter of the first functional area to a first threshold, set the threshold of the survival cycle counter of the second functional area to a second threshold, and set the first threshold to be different from the second threshold; and

[0013] A judgment module is used to count the survival period of the object sensed by the radar sensor in the first functional area and the second functional area to obtain a first count value and a second count value respectively; when the first count value exceeds the first threshold value in the first functional area, the object is judged to be a ghost object and filtered; when the second count value exceeds the second threshold value in the second functional area, the object is judged to be a ghost object and filtered. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above and other objects and advantages of the present application will become more fully apparent from the following detailed description in conjunction with the accompanying drawings, in which the same or similar elements are represented by the same reference numerals.

[0015] Figure 1 is a schematic diagram showing the target object of the ego vehicle overtaking the vehicle.

[0016] Figure 2 is a bird's-eye view diagram showing ghost object detection in blind spot detection.

[0017] Figure 3 2 is a schematic diagram showing a ghost object detection method in blind spot detection according to an embodiment of the present invention.

[0018] Figure 4 1 is a flow chart of a method for detecting ghost objects in blind spot detection according to an embodiment of the present invention.

[0019] Figure 5 1 is a block diagram showing the structure of a ghost object detection device in blind spot detection according to one embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following describes some of the multiple embodiments of the present invention, which are intended to provide a basic understanding of the present invention, and are not intended to identify the key or decisive elements of the present invention or to limit the scope of protection. First, the inventors of the present invention have conducted in-depth research on the blind spot detection technology in the prior art and found that:

[0021] The problem with current blind spot detection technology is that the threshold of the life cycle counter for ghost object filtering cannot be too high, otherwise it will cause a delay in function activation. Assuming that the threshold of the life cycle counter is set to 5, it means that the target object must be tracked continuously and wait for 5 cycles (about 300 milliseconds) before the alarm is triggered. However, in reality, a life cycle counter of 5 cycles is not enough for many ghost objects, and it is usually necessary to set the threshold higher to better filter ghost objects.

[0022] Moreover, the inventors further discovered that there is a situation where a quick functional response is required, which is when the vehicle overtakes a target object, and a higher survival cycle counter threshold will cause an obvious activation delay problem. Figure 1 is a schematic diagram showing the target object of the ego vehicle overtaking the vehicle. Figure 1 As shown in the figure, when vehicle A overtakes target object B, because target object B is entering the warning area of ​​blind spot detection from the edge of the field of view (FOV) of vehicle A, its survival cycle counter will be close to zero. For blind spot detection, the system is required to give a warning no later than 300ms, so it can only wait for 5 cycles for the survival cycle counter to reach the threshold. Due to this system requirement, it seems impossible to set a higher threshold for the survival cycle counter.

[0023] Through the above research, the inventors found that the problem that needs to be solved is the trade-off between ghost object filtering and fast response time, that is, the currently set ghost object survival cycle counter threshold cannot be too high, otherwise it will cause delayed activation. However, in some scenarios (for example, when the vehicle overtakes the target), a quick response is required.

[0024] In order to solve the above problems and reduce the side effects caused by the fixed life cycle counter threshold in blind spot detection, the inventors proposed the inventive concept of setting the threshold of the life cycle counter in the edge area of ​​the field of view (hereinafter also referred to as "FOV") of the radar sensor and the area of ​​interest (hereinafter also referred to as "FOI") of the blind spot detection function to different values, the purpose of which is to maintain a quick response to targets at the edge of the FOV area and at the same time perform more stringent inspections on targets in other areas to filter out ghost objects.

[0025] Specifically, refer to Figure 2 The concept of the ghost object detection method in blind spot detection of the present invention is described.

[0026] Figure 2 is a bird's-eye view diagram showing ghost object detection in blind spot detection.

[0027] exist Figure 2A represents the vehicle, RF represents the field of view of the radar sensor (i.e., Radar FOV), the box shown in BSD represents the blind spot detection area, RO represents a real object located at the edge area of ​​the radar sensor's field of view, and GO represents a ghost object located in the FOI.

[0028] RO is a real object, which is located at the edge of FOV, and its survival cycle counter value is 13. There is also a ghost object GO in FOI, and its survival cycle counter value is 11. If the threshold of the survival cycle counter is set to 12 according to the prior art and the ghost object is filtered out in this case, then the activation delay problem is likely to occur for the real object entering the same FOV edge, because it must also be detected for at least 12 cycles to trigger the blind spot detection to issue an alarm.

[0029] Based on the above findings and ideas, the inventors proposed a ghost object detection method in blind spot detection of the present invention.

[0030] Figure 3 2 is a schematic diagram showing a ghost object detection method in blind spot detection according to an embodiment of the present invention.

[0031] exist Figure 3 In the figure, FOV-E represents the edge area of ​​the radar sensor field of view. In the present invention, the edge area of ​​the radar sensor field of view is separated from the entire FOI area and different parameters (ie, the threshold of the survival cycle counter) are set according to different areas.

[0032] Specifically, as an example, in the K1 area, that is, in the edge area of ​​the radar sensor's field of view, the threshold of the survival cycle counter is set to a first threshold (for example, 5 cycles), and in the K2 area, that is, in the FOI area farther from the edge area of ​​the radar sensor's field of view, the threshold of the survival cycle counter is set to a second threshold (for example, 15 cycles), wherein the first threshold is smaller than the second threshold.

[0033] In this way, by dividing the warning area of ​​blind spot detection into two areas and setting the thresholds of the life cycle counters of these two areas to different values, for example, making the threshold of the life cycle counter in the edge area of ​​the radar sensor's field of view smaller than the life cycle counter in the area of ​​interest of the blind spot detection function, it is possible to reduce the activation delay caused by setting a higher threshold in the edge area of ​​the radar sensor's field of view, especially the activation delay in the case of overtaking by the own vehicle.

[0034] Figure 4 1 is a flow chart of a method for detecting ghost objects in blind spot detection according to an embodiment of the present invention.

[0035] like Figure 4As shown, a ghost object detection method in blind spot detection according to an embodiment of the present invention comprises the following steps:

[0036] Step S100: Divide the blind spot detection area into an edge area of ​​the radar sensor field of view (FOV) and an area of ​​interest (FOI) of the blind spot detection function;

[0037] Step S200: setting a threshold of a survival cycle counter of an edge area (FOV) of a radar sensor field of view as a first threshold, setting a threshold of a survival cycle counter of an area of ​​interest (FOI) of a blind spot detection function as a second threshold, and setting the first threshold to be different from the second threshold, preferably the first threshold to be less than the second threshold; and

[0038] Step S300: Counting the survival period of the object sensed by the radar sensor in the edge area (FOV) of the radar sensor's field of view and the area of ​​interest (FOI) of the blind spot detection function to obtain a first count value and a second count value, and when the first count value exceeds a first threshold in the edge area (FOV) of the radar sensor's field of view, determining that the object is a ghost object and filtering it; and when the second count value exceeds a second threshold in the area of ​​interest (FOI) of the blind spot detection function, determining that the object is a ghost object and filtering it.

[0039] The specific threshold values ​​of the first threshold value and the second threshold value can be calibrated based on the data results of batch simulation, and the specific values ​​are not limited in the present invention.

[0040] Figure 5 1 is a block diagram showing the structure of a ghost object detection device in blind spot detection according to one embodiment of the present invention.

[0041] like Figure 5 As shown, a ghost object detection device 100 in blind spot detection according to one embodiment of the present invention includes:

[0042] A division module 110, configured to divide the blind spot detection area into a first functional area and a second functional area;

[0043] A setting module 120, configured to set the threshold of the survival cycle counter of the first functional area to a first threshold, set the threshold of the survival cycle counter of the second functional area to a second threshold, and set the first threshold to be different from the second threshold; and

[0044] The judgment module 130 is used to count the survival period of the object sensed by the radar sensor in the first functional area and the second functional area to obtain a first count value and a second count value, respectively; when the first count value exceeds the first threshold value in the first functional area, the object is judged to be a ghost object and filtered; when the second count value exceeds the second threshold value in the second functional area, the object is judged to be a ghost object and filtered.

[0045] The first functional area is an edge area of ​​the radar sensor field of view in the blind spot detection area, and the second functional area is an area of ​​interest of the blind spot detection function in the blind spot detection area.

[0046] Preferably, the first threshold is less than the second threshold. For example, as an example, the first threshold is 5 and the second threshold is 15. Here, the specific thresholds of the first threshold and the second threshold can be calibrated based on the data results of batch simulation, and the specific values ​​are not limited in the present invention.

[0047] The present invention also provides a computer-readable medium on which a computer program is stored. When the computer program is executed by a processor, the ghost object detection method in the blind spot detection is implemented.

[0048] The present invention also provides a computer device, including a storage module, a processor, and a computer program stored in the storage module and executable on the processor, wherein the processor implements the above-mentioned ghost object detection method in blind spot detection when executing the computer program.

[0049] The present invention also provides a blind spot detection system, which includes the above-mentioned ghost object detection device in blind spot detection.

[0050] As described above, according to the ghost object detection method and the ghost object detection device in blind spot detection of the present invention, by dividing the blind spot detection area into two functional areas and adopting different thresholds of the survival cycle counter, it is possible to strike a balance between ghost object filtering and fast response time, thereby greatly reducing the activation delay problem, thereby reducing the activation delay problem in blind spot detection and reducing the false alarm problem.

[0051] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Those skilled in the art can think of other feasible changes or substitutions based on the technical scope disclosed in the present application, and such changes or substitutions are all included in the protection scope of the present application. In the absence of conflict, the implementation modes of the present application and the features in the implementation modes can also be combined with each other. The protection scope of the present application shall be subject to the description of the claims.

Claims

1. A ghost object detection method in blind spot detection, characterized in that: The method includes: Dividing the blind spot detection area into a first functional area and a second functional area; Setting the threshold of the survival cycle counter of the first functional area to a first threshold, setting the threshold of the survival cycle counter of the second functional area to a second threshold, and setting the first threshold to be different from the second threshold; and In the first functional area and the second functional area, the survival period of the object sensed by the radar sensor is counted to obtain a first count value and a second count value, respectively. In the first functional area, when the first count value exceeds the first threshold, the object is judged to be a ghost object and filtered; in the second functional area, when the second count value exceeds the second threshold, the object is judged to be a ghost object and filtered.

2. The method for detecting ghost objects in blind spot detection according to claim 1, wherein: The first functional area is an edge area of ​​the radar sensor field of view in the blind spot detection area. The second functional area is an area of ​​interest of a blind spot detection function in the blind spot detection area.

3. The method for detecting ghost objects in blind spot detection according to claim 1, wherein: The first threshold is smaller than the second threshold.

4. A ghost object detection device in blind spot detection, characterized in that: The device includes: A division module, used for dividing the blind spot detection area into a first functional area and a second functional area; a setting module, configured to set the threshold of the survival cycle counter of the first functional area to a first threshold, set the threshold of the survival cycle counter of the second functional area to a second threshold, and set the first threshold to be different from the second threshold; and A judgment module is used to count the survival period of the object sensed by the radar sensor in the first functional area and the second functional area to obtain a first count value and a second count value respectively; when the first count value exceeds the first threshold value in the first functional area, the object is judged to be a ghost object and filtered; when the second count value exceeds the second threshold value in the second functional area, the object is judged to be a ghost object and filtered.

5. The ghost object detection device in blind spot detection according to claim 4, characterized in that: The first functional area is an edge area of ​​the radar sensor field of view in the blind spot detection area. The second functional area is an area of ​​interest of a blind spot detection function in the blind spot detection area.

6. The ghost object detection device in blind spot detection according to claim 5, characterized in that: The first threshold is smaller than the second threshold.

7. 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 detecting ghost objects in blind spot detection according to any one of claims 1 to 3 is implemented.

8. 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 ghost object detection method in blind spot detection according to any one of claims 1 to 3 is implemented.

9. A blind spot detection system, characterized in that: The invention comprises a ghost object detection device in blind spot detection as claimed in any one of claims 4 to 6.

Images