阅读说明：本技术 用于汽车雷达跟踪的重影对象标识 (Ghost object identification for automotive radar tracking ) 是由 李鹏勃 O·S·伊波克维 K·科拉辛斯基 K·诺尔思 A·贾戈里克 于 2020-04-08 设计创作，主要内容包括：一种对由雷达设备检测到的对象进行分类的方法,包括：从由至少一个传感器检测到的传感器数据中标识两个动态对象和一个静止对象；基于每个对象之间的分隔距离和每个对象到传感器的范围的比较来确定多个置信度。所述方法还确定它们之中的最高置信度值；将最高置信度与预定义阈值进行比较；以及当最高置信度值高于预定阈值时,增加对应的重影概率,或者当最高置信度值不高于预定阈值时,减少对应的重影概率。所述方法还包括当较低置信度对象的概率高于阈值上限时将所述对象标记为重影对象,并且当较低置信度对象低于阈值下限时将重影概率设置为零。(A method of classifying an object detected by a radar device, comprising: identifying two dynamic objects and one static object from sensor data detected by at least one sensor; a plurality of confidences is determined based on a comparison of a separation distance between each object and a range of each object to the sensor. The method also determines the highest confidence value among them; comparing the highest confidence with a predefined threshold; and increasing the corresponding ghost probability when the highest confidence value is higher than a predetermined threshold, or decreasing the corresponding ghost probability when the highest confidence value is not higher than the predetermined threshold. The method also includes marking the object as a ghost object when the probability of the lower confidence object is above an upper threshold limit and setting the ghost probability to zero when the lower confidence object is below a lower threshold limit.)

1. A method of classifying an object detected by a radar device, the method comprising:

receiving sensor data at a hardware processor from at least one sensor in communication with the hardware processor and positioned such that an area surrounding the radar device is within a field of view of the at least one sensor;

detecting one or more objects in the area from sensor data;

identifying, at a hardware processor, two dynamic objects and one static object from the one or more objects;

determining a plurality of confidences based on a comparison of a separation distance between each object and a range of each object to the sensor;

comparing, at the hardware processor, the plurality of confidences to determine a highest confidence value among them;

comparing the highest confidence with a predefined threshold;

finding a dynamic object having a smaller RCS or lifetime among the two dynamic objects, and increasing a corresponding ghost probability when the highest confidence value is higher than a predetermined threshold, and decreasing the corresponding ghost probability when the highest confidence value is not higher than the predetermined threshold; and

when the probability of a lower confidence object is above an upper threshold, the object is marked as a ghost object, and when the lower confidence object is below a lower threshold, the ghost probability is set to zero.

2. The method of claim 1, further comprising:

verifying, at the hardware processor, that the two objects and the sensor are collinear by checking the azimuth angle;

marking objects that are not collinear with other objects as first objects, marking closer objects as second objects, and marking farther objects as third objects;

determining, at a hardware processor, a separation distance between each object and another object and a range from the object to the sensor; and

the separation distance between each object is compared to the range of each object to the sensor at the hardware processor.

3. A method of classifying an object detected by a radar device, the method comprising:

receiving sensor data at a hardware processor from at least a first sensor, the first sensor in communication with the hardware processor and positioned such that an area surrounding a radar device is within a field of view of the at least first sensor;

detecting one or more objects in the area from at least first sensor data;

identifying, at a hardware processor, two dynamic objects and one static object from the one or more objects;

verifying, at the hardware processor, that the two objects and the first sensor are collinear by checking the azimuth angle;

marking objects that are not collinear with other objects as first objects, marking closer objects as second objects, and marking farther objects as third objects;

determining, at a hardware processor, a first separation distance from a first object to a second object, a first range to the first object, and a second range from a first sensor to the second object;

determining, at the hardware processor, a second separation distance from the second object to a third object, a third range to the third object;

comparing, at the hardware processor, whether the first separation distance is equal to the second separation distance;

obtaining a first confidence when the first separation distance is equal to the second separation distance, and setting the first confidence to zero when the first separation distance is not equal to the second separation distance;

obtaining a second confidence when the first separation distance is equal to half of the second separation distance, and setting the second confidence to zero when the second separation distance is not equal to half of the second separation distance;

obtaining a third confidence when the first separation distance is equal to twice the third range minus the first range and minus the second range, and setting the third confidence to zero when the first separation distance is not equal to twice the third range minus the first range and minus the second range;

comparing, at the hardware processor, the first, second, and third confidences to determine a highest confidence value among them;

comparing the highest confidence with a predefined threshold;

finding a dynamic object having a smaller RCS or lifetime among the two dynamic objects, and increasing a corresponding ghost probability when the highest confidence value is higher than a predetermined threshold, and decreasing the corresponding ghost probability when the highest confidence value is not higher than the predetermined threshold; and

when the probability of a lower confidence object is above an upper threshold, the object is marked as a ghost object, and when the lower confidence object is below a lower threshold, the ghost probability is set to zero.

4. A vehicle system for performing a vehicle safety procedure based on objects in an area surrounding a vehicle, the system comprising:

a hardware processor; and

a hardware memory in communication with the hardware processor, the hardware memory storing instructions that, when executed on the hardware processor, cause the hardware processor to perform operations comprising:

receiving sensor data at a hardware processor from at least a first sensor, the first sensor in communication with the hardware processor and positioned such that the area is within a field of view of the at least first sensor;

detecting one or more objects in the area from the at least first sensor data;

identifying, at a hardware processor, two dynamic objects and one static object from the one or more objects;

determining a plurality of confidences based on a comparison of a separation distance between each object and a range of each object to the sensor;

comparing, at the hardware processor, the plurality of confidences to determine a highest confidence value among them;

comparing the highest confidence with a predefined threshold;

finding a dynamic object having a smaller RCS or lifetime among the two dynamic objects, and increasing a corresponding ghost probability when the highest confidence value is higher than a predetermined threshold, and decreasing the corresponding ghost probability when the highest confidence value is not higher than the predetermined threshold; and

when the probability of a lower confidence object is above an upper threshold, the object is marked as a ghost object, and when the lower confidence object is below a lower threshold, the ghost probability is set to zero.

5. The system of claim 4, further comprising:

verifying, at the hardware processor, that the two objects and the first sensor are collinear by checking the azimuth angle;

marking objects that are not collinear with other objects as first objects, marking closer objects as second objects, and marking farther objects as third objects;

determining, at a hardware processor, a separation distance between each object and another object and a range from the object to a first sensor; and

at the hardware processor, the separation distance between each object and the distance of each object to the sensor are compared.

Technical Field

The present disclosure relates to a system and method for detecting objects in the vicinity of a motor vehicle using a radar apparatus, for example, for detecting objects approaching the vehicle.

Background

Traffic on roads includes traffic participants such as, but not limited to, vehicles, trams, buses, pedestrians, and any other moving objects using public roads and sidewalks, or fixed objects such as benches and trash cans. Organized traffic typically has well established priorities, lanes, right of way, and traffic control intersections. Traffic may be classified by type: heavy motor vehicles (e.g., cars and trucks), other vehicles (e.g., mopeds and bicycles), and pedestrians. It is desirable to have a system and method for monitoring traffic to detect travel along a roadway.

Radar is widely used in the automotive industry to detect vehicles, pedestrians, road boundaries and other objects, etc. These targets are in close range, for example typically less than 500 meters. There may be strong reflecting surfaces and objects near the vehicle, resulting in the detection of ghost objects (ghost objects). The ghost objects detected by the radar complicate the detection by the radar apparatus, since the radar apparatus has to distinguish between real objects and ghost objects.

Ghost objects from multipath reflections are almost always present in radar detected objects, especially in urban areas. In some devices, road objects and ghost regions are used to assist in identifying ghost objects. In other devices, object velocity, range, and neighboring objects are used to identify ghost objects. In other devices, ranges of real objects, ghost objects, and candidate reflectors are used in aircraft tracking to identify ghost objects. Further, in other devices, range and bearing are used to identify ghost targets tracked by the aircraft.

However, these approaches are specific to a given application and lack a general solution. Some methods only deal with one of several multipath reflection scenarios and cannot be used in other scenarios. For example, some devices depend on road objects and assume that ghost objects are detected later than real objects, which is not always true. Other devices only deal with the simplest multipath reflection scenarios. Furthermore, in some other devices disclosed in the prior art, some other reflection configurations are discussed, but the method is not suitable for automotive radar applications and there is an opportunity to identify real objects as ghost objects, since there are more targets in automotive radar tracking than in aircraft control applications. Furthermore, the approaches employed in these examples are not uniform and difficult to integrate into automotive radar systems.

It is therefore desirable to have a system and method for detecting ghost objects that provides a multipath reflection solution for automotive radar object tracking and detection.

The background description provided herein is for the purpose of generally presenting the context of the disclosure. Work of the presently named inventors, to the extent it is described in this background section, as well as aspects of the description that may not otherwise qualify as prior art at the time of filing, are neither expressly nor impliedly admitted as prior art against the present disclosure.

Disclosure of Invention

One general aspect includes a method of classifying an object detected by a radar device. The method also includes receiving, at the hardware processor, sensor data from at least one sensor in communication with the hardware processor and positioned such that an area surrounding the radar device is within a field of view of the at least one sensor.

The method may also include detecting one or more objects in the area from the sensor data.

The method may also include identifying, at the hardware processor, two dynamic objects and one static object from the one or more objects.

The method may further include determining a plurality of confidences based on a comparison of a separation distance between each object and a range of each object to the sensor.

The method may further include comparing, at the hardware processor, the plurality of confidences to determine a highest confidence value therein.

The method may further include comparing the highest confidence level to a predetermined threshold.

The method may further comprise finding a dynamic object with less radar cross section or lifetime among the two dynamic objects.

The method may further include increasing the corresponding ghost probability when the highest confidence value is above a predetermined threshold, and decreasing the corresponding ghost probability when the highest confidence value is not above the predetermined threshold.

The method may further include marking an object with a lower confidence as a ghost object when the probability of the object is above an upper threshold and setting the ghost probability to zero when the object with the lower confidence is below a lower threshold.

Implementations may include one or more of the following features. The method can comprise the following steps: at the hardware processor, it is verified that the two objects and the sensor are collinear by checking the azimuth.

The method may further include labeling objects that are not collinear with other objects as first objects, labeling objects closer as second objects, and labeling objects further away as third objects.

The method may further include determining, at the hardware processor, a separation distance between each object and another object and a range from the object to the sensor; and

the method may also include comparing, at the hardware processor, a separation distance between each object and a range of each object to the sensor.

In other embodiments, a method of classifying an object detected by a radar device is. The method also includes receiving, at the hardware processor, sensor data from at least a first sensor in communication with the hardware processor and positioned such that an area surrounding the radar device is within a field of view of the at least first sensor.

The method may also include detecting one or more objects in the area from at least the first sensor data.

The method may also include identifying, at the hardware processor, two dynamic objects and one static object from the one or more objects.

The method may further include verifying, at the hardware processor, that the two objects and the first sensor are collinear by checking the azimuth angle.

The method may further include labeling objects that are not collinear with other objects as first objects, labeling objects closer as second objects, and labeling objects further away as third objects.

The method may also include determining, at the hardware processor, a first separation distance from the first object to the second object, a first range to the first object, and a second range from the first sensor to the second object.

The method may also include determining, at the hardware processor, a second separation distance from the second object to a third object, a third range to the third object.

The method may also include comparing, at the hardware processor, whether the first separation distance is equal to the second separation distance.

The method may further include obtaining a first confidence when the first separation distance is equal to the second separation distance, and setting the first confidence to zero when the first separation distance is not equal to the second separation distance.

The method may further include obtaining a second confidence when the first separation distance is equal to half of the second separation distance, and setting the second confidence to zero when the second separation distance is not equal to half of the second separation distance.

The method may further include obtaining a third confidence when the first separation distance is equal to twice the third range minus the first range and minus the second range, and setting the third confidence to zero when the first separation distance is not equal to twice the third range minus the first range and minus the second range.

The method may further include comparing, at the hardware processor, the first, second, and third confidences to determine a highest confidence value among them.

The method may further include comparing the highest confidence with a predefined threshold.

The method may further include finding a dynamic object having a smaller RCS or lifetime among the two dynamic objects.

The method may further include increasing the corresponding ghost probability when the highest confidence value is above a predetermined threshold, and decreasing the corresponding ghost probability when the highest confidence value is not above the predetermined threshold.

The method may further include marking an object with a lower confidence as a ghost object when the probability of the object is above an upper threshold and setting the ghost probability to zero when the object with the lower confidence is below a lower threshold.

A vehicle system for performing a vehicle safety procedure based on objects in an area surrounding a vehicle is disclosed. The vehicle system may include a hardware processor.

The system may also include a hardware memory in communication with the hardware processor, the hardware memory storing instructions that, when executed on the hardware processor, cause the hardware processor to perform operations.

This may include receiving, at the hardware processor, sensor data from at least a first sensor in communication with the hardware processor and positioned such that the area is within a field of view of the at least first sensor.

This may also include detecting one or more objects in the area from at least the first sensor data; at a hardware processor, two dynamic objects and one static object are identified from the one or more objects.

This may also include determining a plurality of confidences based on a comparison of a separation distance between each object and a range of each object to the sensor.

This may also include comparing, at the hardware processor, the plurality of confidences to determine a highest confidence value among them.

This may also include comparing the highest confidence with a predefined threshold; among the two dynamic objects, the dynamic object with the smaller RCS or lifetime is found.

This may also include increasing the corresponding ghost probability when the highest confidence value is above a predetermined threshold.

This may also include decreasing the corresponding ghost probability when the highest confidence value is not above a predetermined threshold.

This may also include marking an object with a lower confidence as a ghost object when the probability of the object is above an upper threshold.

This may also include setting the ghost probability to zero when the object with the lower confidence is below a lower threshold.

This may also include verifying, at the hardware processor, that the two objects and the first sensor are collinear by checking the azimuth angle;

this may also include marking objects that are not collinear with other objects as first objects, marking closer objects as second objects,

this may also include marking more distant objects as third objects.

This may also include determining, at the hardware processor, a separation distance between each object and another object and a range from the object to the first sensor.

Further, the separation distance between each object and the distance of each object to the sensor are compared at the hardware processor.

Other objects, features, and characteristics of the present invention, as well as the methods of operation and functions of the related elements of structure and the combination of parts and economies of manufacture, will become more apparent upon consideration of the following detailed description and the appended claims with reference to the accompanying drawings, all of which form a part of this specification. It should be understood that the detailed description and specific examples, while indicating the preferred embodiment of the disclosure, are intended for purposes of illustration only and are not intended to limit the scope of the disclosure.

Drawings

The present disclosure will become more fully understood from the detailed description and the accompanying drawings, wherein:

FIG. 1A is a schematic illustration of an exemplary overview of a vehicle having a blind spot monitoring system of the present invention in a first exemplary communication scenario;

FIG. 1B is a schematic illustration of an exemplary overview of a vehicle having a blind spot monitoring system of the present invention in a second exemplary communication scenario;

FIG. 1C is a schematic illustration of an exemplary overview of a vehicle having a blind spot monitoring system of the present invention in a third exemplary communication scenario;

FIG. 2A is a schematic illustration of an exemplary overview of a vehicle having a blind spot monitoring system of the present invention;

FIG. 2B is a schematic illustration of an exemplary blind spot monitoring system for the vehicle shown in FIG. 2A;

FIG. 3A is a schematic illustration of a first ghost object detection scene for detecting ghost objects using the blind spot monitoring system shown in FIGS. 1A-2B;

FIG. 3B is a schematic illustration of a second ghost object detection scene for detecting ghost objects using the blind spot monitoring system shown in FIGS. 1A-2B;

FIG. 3C is a schematic illustration of a third ghost object detection scene for detecting ghost objects using the blind spot monitoring system shown in FIGS. 1A-2B;

fig. 3D is a schematic diagram of a fourth ghost object detection scene for detecting ghost objects using the blind spot monitoring system shown in fig. 1A-2B.

FIG. 3E is a schematic illustration of a fifth ghost object detection scene for detecting ghost objects using the blind spot monitoring system shown in FIGS. 1A-2B;

FIG. 4 is a schematic illustration of a generic model for ghost object detection using the blind spot monitoring system shown in FIGS. 1A-2B;

FIG. 5 is an exemplary method for detecting ghost objects using the blind spot monitoring system shown in FIGS. 1A-2B;

FIG. 6 is a schematic diagram of an example computing device to perform any of the systems or methods described herein;

like reference symbols in the various drawings indicate like elements.

Detailed Description

Advanced driver safety features have received increasing attention over the past few years. To improve the transportation safety of vehicles, it is important to accurately identify objects that are close to and/or near the vehicle. This is particularly important for vehicle regions that are "blind spots" of the vehicle driver. This may include the driver's field of view being obscured by the vehicle itself (conventionally referred to as a "blind spot") and areas obscured by external objects such as other vehicles, buildings, etc. near the host vehicle.

Referring to fig. 1A-5, a vehicle 100 includes a blind spot monitoring system 110 that includes a computing device (or hardware processor) 112 (e.g., a central processing unit having one or more computing processors), the computing device 112 in communication with a non-transitory memory or hardware memory 114 (e.g., hard disk, flash memory, random access memory) capable of storing instructions executable on the computing processor(s) 112. The blind spot monitoring system 110 includes a sensor system 120. The sensor system 120 includes one or more sensors 122a-n, the sensors 122a-n being positioned at one or more zones and configured to sense one or more objects 102,102a-n in a zone proximate to the vehicle. Objects 102,102a-n may include, but are not limited to, vehicles 102a, traffic participants 102b (such as pedestrians and bicyclists), buildings/infrastructure 103b, natural objects, shrubs, trees, and the like. In addition to sensing the actual objects 102,102a-n, the sensors 122,122a-n may also detect ghost objects. The blind spot monitoring system distinguishes objects 102,102a-n and ghosted objects 104,104a-n from one another in the manner described herein.

In some implementations, the sensor 122 may be a short range radar sensor, which provides a wide field of view. The one or more sensors 122a-n may be positioned to capture data 124 associated with a particular area 10, where each sensor 122a-n captures data 124 associated with a portion of the area 10. As a result, the sensor data 124 associated with each sensor 122a-n includes sensor data 124 associated with the entire area 10. Alternatively, the sensors 122 may also include, but are not limited to, sonar, LIDAR (light detection and ranging, which may require optical remote sensing that measures characteristics of scattered light to find distance and/or other information to distant targets), HFL (high flash LIDAR), LADAR (laser detection and ranging), cameras (e.g., monocular camera, binocular camera).

Each sensor 122 is positioned at a location where the sensor 122 can capture sensor data 124 associated with objects 102,102a-n, 104a-n within their field of view. Accordingly, the sensor system 120 analyzes the sensor data 124 captured by the one or more sensors 122 a-n. The analysis of the sensor data 124 includes the sensor system 120 identifying one or more objects 102,102a-n, 104a-n and determining whether it is an object 102,102a-n or a ghost object 104,104 a-n.

Based on general analysis, there are five types of multipath reflections observed in a large amount of test data. In fig. 3A-E and 4, R is a radar, T is a real target, G is a ghost object, and S is a stationary object with a high reflection index, such as a parked car, a truck, or a metal fence, or a reflective wall. The double-line arrow means that the radar signal passes twice, and the single-line arrow means that the radar signal passes once.

In fig. 3A, a radar signal emanates from R, hits a stationary object S, and then reflects off and hits a real target T, after which the signal passes to S, and then to R, the name of the figure being RSTSR, and it represents the path of the radar signal.

In fig. 3B, a radar signal emanates from R, hits a real target T, then hits a stationary object S, after which it returns to the radar in the same path. It is called RTSTR.

In fig. 3C, the radar signal R bounces twice between the real target T and the stationary object S. It is called rtssttr.

In fig. 3D, a signal emanates from the radar, is reflected by the target T, then by the stationary object S, and finally returns to the radar R. It is called RTSR.

In fig. 3E, a signal emanates from the radar R, is reflected by the stationary object S, is then reflected by the target T and returns to the radar. It is called RSTR.

In fig. 3A and 3B, we have:

x, y and z represent distances to radar, real objects, ghost objects and reflecting stationary objects.

In fig. 3C, we have:

。

in fig. 3D, we have:

is the range of the real target.Is the range of the ghost object and,

it can be converted into:

。

in fig. 3E, we have:

we can conclude that:

is the range of stationary objects.

The five cases are different and these objects will never satisfy more than one condition. If z is not zero, 0.5z cannot equal z. For equation (3), we have:

a similar conclusion can be reached for equation (4). Only one condition will be satisfied. Thus, we can summarize equations (1) to (4):

。

in fig. 3A-E, there are always three objects, a real object, a ghost object, and a stationary object. Two of them are collinear with the radar sensor. One of them is not on the line formed by the other two objects and the radar.

The five reflection cases can be summarized as one case, as shown in fig. 4. R is a radar sensor, O₁And O₂Are two objects, O₃Or O₃' or O₃'' is a third object. We can always form a triangle with two sides of the same length. Two objects (O)₁And O₂) Located at the two corners of the triangle. Side O₁O₂Is equal to the side O₂O₃Length of (d). The remaining objects are located at O₂O₃Marginally, but at a location which may be O₃、O₃' or O₃’’。

In detail, for the reflection case shown in FIG. 3A, O₁Is a real target, O₂Is a stationary object, O₃Is a ghost object. For the case shown in FIG. 3B, O₁Is a stationary target, O₂Is a real object, O₃Is a ghost object. For the reflection case shown in FIG. 3C, O₁Is a stationary object, O₂Is a real target. O is₃' is a ghost object. O is₂Is O₂O₃And | O₂O₃I is 0.5| O₂O₃' ' ' I.. For the reflection case shown in FIG. 3D, O₃Will be the ghost object, O₁Is a real object, O₂Is a stationary object. Triangle O₁O₂O₃O of (A) to (B)₂O₃The length of the edge will beWhich can be written as. For the reflection case shown in FIG. 3E, O₁Is a stationary object. O is₃' is a ghost object, O₂Is a real target. Triangle O₁O₂O₃O of (A) to (B)₂O₃Will be of lengthCan also be written as. Then the formula would be:。

based on equation (6), a general solution is provided to identify ghost objects as shown in fig. 4. This solution can be easily implemented to identify ghost objects generated from all of the cases shown in fig. 3A-E.

FIG. 5 provides an example operational arrangement of a method 500 for detecting ghost objects 104,104a-n using the system 110 of FIGS. 1-4. At block 502, the method 500 includes receiving, at the hardware processor 112, sensor data 124 from one or more sensors 122, the one or more sensors 122 being in communication with the hardware processor 112 and positioned such that the surrounding area 10 is within a field of view of the one or more sensors 122. At block 504, the method 500 includes detecting, at the hardware processor 112, one or more objects 102,102a-n, 104a-n from the sensor data 124. At block 506, the method 500 includes identifying, at the hardware processor 112, two dynamic objects and one static object from the one or more objects 102,102a-n, 104a-n

Additionally, at block 508, the method 500 includes verifying that the two objects and the radar are collinear at the hardware processor 112 by checking the azimuth. Marking nearer objects as O₂. Marking distant objects as O_x. Marking objects that are not collinear with other objects as O₁。

At block 510, method 500 includes determining, at hardware processor 112, a slave O₁To O₂The distance of (d); RO₁And RO₂，O₁And O₂The range of (1). Further, at block 512, the method 500 includes determining, at the hardware processor 112, the RO₃', which is the object O_xThe range of (1). At block 514, method 500 includes determining, at hardware processor 112, a slave O₂To O_xAnd is marked as O₂O₃And O₂O₃’。

At block 516, method 500 includes comparing, at hardware processor 112, O₁O₂ = O₂O₃Whether or not this is true. Based on the comparison, if O₁O₂Is equal to O₂O₃Then confidence 1 (C) is obtained at block 518₁) Or if O₁O₂Is not equal to O₂O₃Then C is added at block 520₁Is set to 0.

At block 522, method 500 includes comparing, at hardware processor 112, O₁O₂ = 0.5O₂O₃Whether or not' is true. Based on the comparison, if O₁O₂Equal to 0.5O₂O₃', then a confidence level of 2 (C) is obtained at block 524 (C)₂) Or if O₁O₂Not equal to 0.5O₂O₃', then C is added at block 526₂Is set to 0.

At block 528, the method 500 includes comparing, at the hardware processor 112Whether or not this is true. Based on the comparison, if O₁O₂Is equal toThen at block 530 confidence level 3 (C) is obtained₃) Or if O₁O₂Is not equal toThen C is added at block 532₃Is set to 0.

In obtaining C₁、C₂And C₃Thereafter, the method 500 includes comparing C at the hardware processor 112₁、C₂And C₃To determine the highest confidence value among them, and then compare the highest confidence to a predefined threshold at block 534. If the highest confidence value is greater than the predefined threshold, the method 500 includes, at block 536, finding the dynamic object with the smaller RCS or lifetime among the two dynamic objects and increasing the corresponding ghost probability. If the highest confidence value is not greater than the predefined threshold, the method 500 includes, at block 538, finding the dynamic object with the smaller RCS or lifetime among the two dynamic objects and reducing the corresponding ghost probability.

Further, at block 540, the method 500 includes comparing, at the hardware processor 112, whether the ghost probability of the object with the lower confidence is above an upper threshold and marking it as a ghost object, or whether the ghost probability of the object with the lower confidence is less than a lower threshold and setting its ghost probability to zero.

FIG. 6 is a schematic diagram of an example computing device 600 that may be used to implement the systems and methods described in this document. Computing device 600 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The components shown here, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed in this document.

Computing device 600 includes a processor 610, memory 620, a storage device 630, a high-speed interface/controller 640 connected to memory 620 and high-speed expansion ports 650, and a low-speed interface/controller 660 connected to low-speed bus 670 and storage device 630. Each of the components 610, 620, 630, 640, 650, and 660 are interconnected using various buses, and may be mounted on a common motherboard or in other manners as appropriate. The processor 610 may process instructions for execution within the computing device 600, including instructions stored on the memory 620 or storage device 630, to display graphical information for a Graphical User Interface (GUI) on an external input/output device, such as display 680 coupled to high speed interface 640. In other implementations, multiple processors and/or multiple buses may be used, as appropriate, along with multiple memories and types of memory. Moreover, multiple computing devices 600 may be connected, with each device providing portions of the necessary operations (e.g., as a server bank, group of blade servers, or multi-processor system).

The memory 620 stores information within the computing device 600 non-temporarily. The memory 620 may be a computer-readable medium, volatile memory unit(s), or non-volatile memory unit(s). Non-transitory memory 620 may be a physical device for storing programs (e.g., sequences of instructions) or data (e.g., program state information) on a temporary or permanent basis for use by computing device 600. Examples of non-volatile memory include, but are not limited to, flash memory and Read Only Memory (ROM)/Programmable Read Only Memory (PROM)/Erasable Programmable Read Only Memory (EPROM)/Electrically Erasable Programmable Read Only Memory (EEPROM) (e.g., typically used for firmware, such as a boot program). Examples of volatile memory include, but are not limited to, Random Access Memory (RAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Phase Change Memory (PCM), and magnetic disks or tape.

The storage device 630 can provide mass storage for the computing device 600. In some implementations, the storage device 630 is a computer-readable medium. In various different implementations, the storage device 630 may be a floppy disk device, a hard disk device, an optical disk device, or a tape device, a flash memory or other similar solid state memory device, or an array of devices, including devices in a storage area network or other configurations. In an additional implementation, a computer program product is tangibly embodied in an information carrier. The computer program product contains instructions that, when executed, perform one or more methods, such as those described above. The information carrier is a computer-readable or machine-readable medium, such as the memory 620, the storage device 630, or memory on processor 610.

The high speed controller 640 manages bandwidth-intensive operations for the computing device 600, while the low speed controller 660 manages lower bandwidth-intensive operations. Such allocation of duties is exemplary only. In some implementations, the high-speed controller 640 is coupled to memory 620, a display 680 (e.g., through a graphics processor or accelerator), and high-speed expansion ports 650, which may accept various expansion cards (not shown). In some implementations, the low-speed controller 660 is coupled to the storage device 630 and the low-speed expansion port 670. The low-speed expansion port 670, which may include various communication ports (e.g., USB, bluetooth, ethernet, wireless ethernet), may be coupled to one or more input/output devices, such as a keyboard, a pointing device, a scanner, or a network device (such as a switch or router), for example, through a network adapter.

As shown, computing device 600 may be implemented in a number of different forms. For example, it may be implemented as a standard server 600a, or multiple times in a group of such servers 600a as a laptop computer 600b, or as part of a rack server system 600 c.

Various implementations of the systems and techniques described here can be realized in digital electronic and/or optical circuits, integrated circuits, specially designed ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

These computer programs (also known as programs, software applications or code) include machine instructions for a programmable processor, and can be implemented in a high-level procedural and/or object-oriented programming language, and/or in assembly/machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, non-transitory computer-readable medium, apparatus and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

Implementations of the subject matter and the functional operations described in this specification can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them. Furthermore, the subject matter described in this specification can be implemented as one or more computer program products, i.e., one or more modules of computer program instructions encoded on a computer-readable medium for execution by, or to control the operation of, data processing apparatus. The computer readable medium can be a machine-readable storage device, a machine-readable storage substrate, a memory device, a composition of matter effecting a machine-readable propagated signal, or a combination of one or more of them. The terms "data processing apparatus," "computing device," and "computing processor" encompass all apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, or multiple processors or computers. The apparatus can include, in addition to hardware, code that creates an execution environment for the computer program in question, e.g., code that constitutes processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them. A propagated signal is an artificially generated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, that is generated to encode information for transmission to suitable receiver apparatus.

A computer program (also known as an application, program, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.

The processes and logic flows described in this specification can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).

Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and data from a read-only memory or a random access memory or both. The essential elements of a computer are a processor for executing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto-optical disks, or optical disks. However, a computer need not have such a device. Further, the computer may be embedded in another device, e.g., a mobile telephone, a Personal Digital Assistant (PDA), a mobile audio player, a Global Positioning System (GPS) receiver, to name a few. Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic disks, such as internal hard disks or removable disks; magneto-optical disks; and CD ROM and DVD ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

To provide for interaction with a user, one or more aspects of the disclosure can be implemented on a computer having a display device, e.g., a CRT (cathode ray tube), LCD (liquid crystal display) monitor or touch screen for displaying information to the user and an optional keyboard and a pointing device, e.g., a mouse or a trackball, by which the user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback, such as visual feedback, auditory feedback, or tactile feedback; and input from the user may be received in any form, including acoustic, speech, or tactile input. Further, the computer may interact with the user by sending and receiving documents to and from the device used by the user; for example, by sending a web page to a web browser on the user's client device in response to a request received from the web browser.

One or more aspects of the present disclosure may be implemented in a computing system that includes a back-end component, e.g., as a data server; or include middleware components, such as application servers; or include a front-end component, such as a client computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the subject matter described in this specification; or any combination of one or more such back-end, middleware, or front-end 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 local area networks ("LANs") and wide area networks ("WANs"), intranets (e.g., the internet), and peer-to-peer networks (e.g., ad hoc, peer-to-peer networks).

The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. In some implementations, the server transmits data (e.g., HTML pages) to the client device (e.g., for the purpose of displaying data to and receiving user input from a user interacting with the client device). Data generated at the client device (e.g., a result of the user interaction) may be received at the server from the client device.

While this specification contains many specifics, these should not be construed as limitations on the scope of the disclosure or of what may be claimed, but rather as descriptions of features specific to particular implementations of the disclosure. Certain features that are described in this specification in the context of separate implementations can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.

Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In some cases, multitasking and parallel processing may be advantageous. Moreover, the separation of various system components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated within a single software product or packaged into multiple software products.

Many implementations have been described. Nevertheless, it will be understood that various modifications may be made without departing from the spirit and scope of the disclosure. Accordingly, other implementations are within the scope of the following claims. For example, the actions recited in the claims can be performed in a different order and still achieve desirable results.

The foregoing preferred embodiments have been shown and described for the purposes of illustrating the structural and functional principles of the present invention and illustrating the methods of employing the preferred embodiments, and are subject to change without departing from such principles. Accordingly, this invention includes all modifications encompassed within the scope of the following claims.