CN112837346A - Method and device for detecting in-place of moving target - Google Patents
Method and device for detecting in-place of moving target Download PDFInfo
- Publication number
- CN112837346A CN112837346A CN202110136512.0A CN202110136512A CN112837346A CN 112837346 A CN112837346 A CN 112837346A CN 202110136512 A CN202110136512 A CN 202110136512A CN 112837346 A CN112837346 A CN 112837346A
- Authority
- CN
- China
- Prior art keywords
- moving
- target
- point cloud
- points
- millimeter wave
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000001514 detection method Methods 0.000 claims abstract description 75
- 238000012545 processing Methods 0.000 claims description 33
- 230000000694 effects Effects 0.000 claims description 22
- 230000009467 reduction Effects 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 230000008685 targeting Effects 0.000 claims description 4
- 238000011065 in-situ storage Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000004044 response Effects 0.000 description 9
- 230000001960 triggered effect Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000001788 irregular Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/77—Determining position or orientation of objects or cameras using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
Abstract
The embodiment of the specification provides a method and a device for detecting the in-place of a moving target. According to the method, the millimeter wave radar is used for obtaining point cloud data of a plurality of moving points in a detection area, at least one moving target included in the detection area can be determined according to the point cloud data, then the position information of the moving target can be determined according to the attribute information of the moving points in the point cloud data, and finally whether the moving target is located in the target area or not can be judged according to the range information of the target area and the position information of the moving target. The scheme for detecting whether a moving target enters a certain target area only needs one millimeter wave radar, even if the target area changes, the scheme can continuously detect the moving target in place by changing the range information of the target area without continuously deploying the sensor in the changed target area, and therefore the operation complexity of detecting the moving target in place can be reduced.
Description
Technical Field
One or more embodiments of the present description relate to computer technology, and more particularly, to a method and apparatus for in-place detection of moving objects.
Background
In-place detection is a technique for detecting whether an active object enters a certain target area.
Currently, detection is typically accomplished by deploying sensors within the target area. However, when the above technical solution is implemented, since the sensor can only detect the target area after being deployed, once the target area changes, the sensor can only be continuously deployed again in the changed target area, and this operation of detecting the moving target in place is complicated.
Disclosure of Invention
One or more embodiments of the present specification describe a method and apparatus for in-place detection of a moving object, which can reduce the complexity of the operation of in-place detection of the moving object.
According to a first aspect, there is provided a method of in-place detection of a moving object, comprising:
acquiring range information of a target area; the target area is obtained by dividing a detection area;
acquiring point cloud data corresponding to a plurality of moving points, which is obtained by detecting the detection area by a millimeter wave radar; the point cloud data comprises the number of the moving points and attribute information of each moving point;
determining at least one moving target included in the detection area according to the number of the moving points detected by the millimeter wave radar in the detection area and the attribute information of each moving point; wherein each moving target is composed of a plurality of moving points;
for each activity goal, performing:
determining the position information of the moving target according to the attribute information of the moving point corresponding to the moving target;
and judging whether the moving target is positioned in the target area or not according to the range information of the target area and the position information of the moving target.
In one embodiment of the present description, the attribute information includes coordinates, velocity, and signal-to-noise ratio;
the determining at least one moving target included in the detection area according to the number of the moving points detected by the millimeter wave radar for the detection area and the attribute information of each moving point includes:
clustering a plurality of moving points in the detection area according to the coordinate, the speed and the signal-to-noise ratio of each moving point to obtain at least one initial point cloud cluster;
for each initial point cloud cluster, if the number of the moving points included in the initial point cloud cluster is not less than a preset first number threshold and the distance between any two moving points included in the initial point cloud cluster is less than a preset first distance threshold, determining the initial point cloud cluster as an effective point cloud cluster;
and determining the effective point cloud cluster meeting the activity target determination rule as an activity target.
In one embodiment of the present specification, the activity targeting rule comprises at least one of:
the duration of the effective point cloud cluster is not less than a preset first duration;
the number of the moving points in the effective point cloud cluster is not less than a preset second number threshold;
and the distance between the effective point cloud cluster and the effective point cloud cluster closest to the effective point cloud cluster is not less than a preset second distance threshold.
In one embodiment of the present description, the point cloud data includes a distance of each moving point to the millimeter wave radar and an azimuth angle of each moving point to the millimeter wave radar;
before the determining the position information of the moving target, further comprising: acquiring position information of the millimeter wave radar;
the determining the position information of the moving target comprises:
calculating the average distance from the moving target to the millimeter wave radar according to the distance from each moving point in the moving target to the millimeter wave radar;
calculating the average azimuth angle from the moving target to the millimeter wave radar according to the azimuth angle from each moving point in the moving target to the millimeter wave radar;
and determining the position information of the moving target according to the position information of the millimeter wave radar and the average distance and the mean square angle obtained by calculation.
In one embodiment of the present description, there are at least two target regions within the detection region;
within a preset second time length, the millimeter wave radar detects the detection area to obtain at least two frames of point cloud data corresponding to the plurality of moving points;
the determining whether the moving target is located in the target area according to the range information of the target area and the position information of the moving target includes:
judging whether the moving target is positioned in the target area or not according to the range information of the target area and the position information of the moving target in each frame;
after determining that an active target in at least one frame is located in one of the target regions, the method further includes:
within a preset second time length, judging whether the active target in at least one frame is located in another target area, if so, executing the following processing:
performing noise reduction processing on the motion points corresponding to the moving target in all the frames in the second duration;
determining new position information of the movable target;
and determining a target area where the movable target is located according to the determined new position information.
In an embodiment of the present specification, the denoising processing of the motion point corresponding to the moving target in all frames in the second duration includes:
determining a boundary band region of the two target regions; wherein the boundary belt region of the target region is formed by moving a boundary line of the target region to the inside of the target region by a preset distance;
removing the motion points located on the boundary band region in all frames within the second duration;
and/or the presence of a gas in the gas,
the point cloud data comprises a doppler value for each motion point; the Doppler value of each moving point is used for representing the change rate of the relative distance from the moving point to the millimeter wave radar;
the denoising processing of the motion points corresponding to the moving target in all the frames in the second duration includes:
calculating the average Doppler value of the moving points corresponding to the moving target in all the frames in the second time length;
and removing the moving points with Doppler values lower than the average Doppler value.
In an embodiment of the present specification, the determining new location information of the activity target includes:
clustering the motion points corresponding to the moving target after the noise reduction treatment again to obtain at least two new point cloud clusters;
and determining new position information of the moving target according to the attribute information of the moving points in the new point cloud cluster with the largest number of the moving points.
According to a second aspect, there is provided an apparatus for in-place detection of a moving object, comprising:
the first acquisition module is configured to acquire range information of a target area; the target area is obtained by dividing a detection area;
the second acquisition module is configured to acquire point cloud data corresponding to the plurality of moving points, which is obtained by detecting the detection area by the millimeter wave radar; the point cloud data comprises the number of the moving points and attribute information of each moving point;
the moving target determining module is configured to determine at least one moving target included in the detection area according to the number of the moving points detected by the millimeter wave radar in the detection area and the attribute information of each moving point; wherein each moving target is composed of a plurality of moving points;
a processing module configured to perform, for each activity goal: determining the position information of the moving target according to the attribute information of the moving point corresponding to the moving target; and judging whether the moving target is positioned in the target area or not according to the range information of the target area and the position information of the moving target.
According to a third aspect, there is provided an apparatus for in-place detection of a moving object, comprising a memory and a processor, wherein the memory stores executable code, and the processor executes the executable code to implement the method according to any embodiment of the present specification.
According to a fourth aspect, there is provided a computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform a method as described in any one of the embodiments of the present specification.
According to the method and the device for detecting the in-place of the moving target, provided by the embodiment of the specification, the millimeter wave radar is used for obtaining the point cloud data of a plurality of moving points in the detection area, at least one moving target included in the detection area can be determined according to the point cloud data, then the position information of the moving target can be determined according to the attribute information of the moving points in the point cloud data, and finally whether the moving target is located in the target area or not can be judged according to the range information of the target area and the position information of the moving target. The scheme for detecting whether a moving target enters a certain target area only needs one millimeter wave radar, even if the target area changes, the scheme can continuously detect the moving target in place by changing the range information of the target area without continuously deploying the sensor in the changed target area, and therefore the operation complexity of detecting the moving target in place can be reduced.
Drawings
In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present specification, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 illustrates a flow diagram of a method for in-place detection of a moving object in one embodiment of the present description;
FIG. 2 illustrates a flow diagram for determining an activity goal in one embodiment of the present description;
FIG. 3 illustrates a flow chart for determining location information for an active object in one embodiment of the present description;
FIG. 4 is a schematic diagram illustrating the location of a cloud of point clouds and millimeter wave radar in one embodiment of the present disclosure;
FIG. 5 illustrates a flow diagram for determining a target area in which an active target is located in one embodiment of the present description;
FIG. 6 is a schematic diagram illustrating the location of a cloud of point clouds and two target regions in one embodiment of the present disclosure;
FIG. 7 is a schematic structural diagram of an apparatus in which an apparatus for detecting the in-place of a moving object is located in one embodiment of the present disclosure;
FIG. 8 is a schematic diagram of an apparatus for in-place detection of moving objects in one embodiment of the present disclosure.
Detailed Description
The scheme provided by the specification is described below with reference to the accompanying drawings.
In the existing process of detecting the in-place of an active target, the detection is usually realized by deploying sensors in the target area. The sensor is, for example, an infrared sensor, a laser sensor, or an image sensor, and it is directly determined whether or not a moving object enters the target area by using the sensor.
However, since the sensor can only detect the target area after being deployed, once the target area changes, the sensor can only be continuously re-deployed in the changed target area, and this operation of detecting the moving target in place is complicated.
As can be seen from the analysis of the above process of detecting the moving target in place, the moving target entering the target area is directly determined only by the change of the collected signals of some of the sensors in the target area (for example, the infrared ray is blocked, the laser is blocked, and the moving target enters the image). If the target area changes, for example, a sensor is originally arranged in the target area a, and now to increase the detection of whether a moving target enters the target area B, the sensor needs to be added in the target area B, which is a complicated operation. That is, when the target area changes, it may be considered to determine whether the position information of the moving target falls within the range of the target area, so that an in-place response may be triggered.
Further, since the common defects of the above-described sensors are mainly that the detection distance is short and is easily affected by the environment (such as light, temperature, and obstacles), a sensing manner that is long in detection distance and is not easily affected by the environment, such as a sensing manner using a millimeter wave radar, can be considered. Based on this, the embodiments of the present specification are a system that detects a moving target using a millimeter wave radar and uses indirect detection that determines whether or not position information of the moving target falls within a range of a target area (i.e., a system that directly detects the moving target using an existing sensor).
Specific implementations of the concepts provided in the present specification are described below.
FIG. 1 shows a flow diagram of a method of in-place detection according to one embodiment. It is understood that the method may be performed by any device, apparatus, platform, apparatus point cloud having computing and processing capabilities. Referring to fig. 1, the method includes:
step 101: and acquiring range information of the target area.
In the present embodiment, the target area is obtained by dividing the detection area.
The detection area and the target area are both two-dimensional areas in the embodiment of the present specification, for example, the detection area may be a regular planar graph or an irregular planar graph; similarly, the target area may be a regular planar figure or an irregular planar figure. The range information of the target area, i.e., the contour shape for characterizing the target area, may be, for example, a set of coordinate information of a plurality of coordinate points, or a set of coordinate information and size information of one coordinate point.
Taking the detection region and the target region as rectangular regions for example, the range information of the detection region and the target region may include a vertex coordinate of the detection region, a length and a width of the detection region, for example, the vertex coordinate of the lower left corner of the detection region is (0, 0), the length is 4 (dimensionless unit), and the width is 2 (dimensionless unit), and if a target region is to be determined in the detection region, only one vertex coordinate, the length and the width of the target region need to be obtained.
Step 102: and acquiring point cloud data corresponding to the plurality of moving points, which is obtained by detecting the detection area by the millimeter wave radar.
In the present embodiment, the point cloud data includes the number of moving points and attribute information of each moving point.
The millimeter wave Radar (Radar) is a Radar which operates in a millimeter wave band for detection, generally, the millimeter wave refers to an electromagnetic wave with a length of 1-10 mm, and the corresponding frequency range is 30-300 GHz. The millimeter wave radar can realize accurate measurement of information such as target position, speed and the like, and has the characteristics of all-time, all-weather, low cost, low power consumption and long service life. The millimeter wave radar can distinguish and identify very small targets and can identify a plurality of targets simultaneously.
The millimeter wave radar can emit electromagnetic waves in a millimeter wave frequency range within a preset range, then the millimeter wave radar can collect echo signals, analog-to-Digital conversion is carried out on the collected echo signals, and then DSP (Digital Signal Processing) is carried out on the converted signals to obtain point cloud data.
Step 103: and determining at least one moving target included in the detection area according to the number of the moving points detected by the millimeter wave radar in the detection area and the attribute information of each moving point.
In the present embodiment, each moving object is composed of a plurality of moving points.
In some implementations, at least one activity target included within the detection region may be determined by the flowchart shown in fig. 2. Specifically, the method comprises the following steps:
the attribute information comprises coordinates, speed and signal-to-noise ratio;
step 201: and clustering the plurality of moving points in the detection area according to the coordinate, the speed and the signal-to-noise ratio of each moving point to obtain at least one initial point cloud cluster.
In this step, clustering processing is performed by using the DBSCAN algorithm as an example, and it should be understood that clustering processing performed by using the embodiments of the present specification is not limited to the DBSCAN algorithm.
The clustering process of the DBSCAN algorithm comprises the following steps:
starting from a motion point which is not divided into the initial cloud cluster and is not visited, calculating a neighborhood of which the difference between the coordinate and the speed of the motion point is within a certain threshold, wherein the threshold of the difference between the coordinate and the speed is set to be 0.15m in the embodiment, and the threshold of the difference between the speed is set to be 1m/s, namely, other motion points which are not more than 0.15m away from the plane of the point and the absolute value of the difference between the speeds is not more than 1m/s are all within the neighborhood of the point.
If the number of the motion points falling into the neighborhood range exceeds a threshold (for example, 10, the threshold can be set according to different scenes), the motion point is marked as a first point in a new point cloud cluster, otherwise, the motion point is marked as a noise point, and the state of the marked motion point is changed to be visited.
And processing the first point in the new point cloud cluster, marking all the moving points in the neighborhood of the first point as the moving points in the new point cloud cluster, and processing all the moving points in the new point cloud cluster until no new moving point is added into the new point cloud cluster. After the current cloud cluster is processed, a new point which is not visited is extracted and processed, so that the next cloud cluster or noise is discovered, the process is repeated until all the points are marked as visited, and after the processing is completed, each moving point is marked as belonging to one cloud cluster or noise point.
And calculating the sum of signal-to-noise ratios of the points of each point cloud cluster, and marking the point cloud cluster with the sum of the signal-to-noise ratios larger than a threshold (for example, 100dB, the threshold of the sum of the signal-to-noise ratios can be according to different scenes) as an initial point cloud cluster, or marking the point cloud cluster as a noise point cloud cluster.
Step 202: and for each initial point cloud cluster, if the number of the moving points included in the initial point cloud cluster is not less than a preset first number threshold value, and the distance between any two moving points included in the initial point cloud cluster is less than a preset first distance threshold value, determining the initial point cloud cluster as an effective point cloud cluster.
The determined initial cloud may still have interference factors, such as wind blowing curtains in the detection area, and may be determined as the initial cloud. However, the number of the moving points in the point cloud cluster corresponding to the moving object and the distance between any two moving points should have a certain limit (that is, the number of the moving points included in the initial point cloud cluster is not less than the preset first number threshold, and the distance between any two moving points included in the initial point cloud cluster is less than the preset first distance threshold), so that it is possible to further determine that the moving object is the moving object.
It should be noted that, with reference to fig. 4, the distance between any two motion points included in the initial cloud cluster can be calculated by the following formula:
wherein D ispFor characterizing the distance between any two moving points,/p1For characterizing the distance, l, of one of the moving points to the millimeter-wave radarp2For characterising the distance, theta, of another moving point to the millimeter-wave radarp1For characterising one of the moving points to the azimuth, theta, of a millimeter-wave radarp2For characterizing the azimuth angle of another moving point to the millimeter wave radar.
Step 203: and determining the effective point cloud cluster meeting the activity target determination rule as an activity target.
In this embodiment, the activity targeting rule includes at least one of:
1) the duration of the effective point cloud cluster is not less than a preset first duration (for example, 5 s);
2) the number of the motion points included in the effective point cloud cluster is not less than a preset second number threshold (for example, 20);
3) the distance between the effective point cloud cluster and the effective point cloud cluster closest to the effective point cloud cluster is not less than a preset second distance threshold (for example, 0.1 m).
If the effective point cloud cluster can meet any one of the three active target determination rules, the probability that the effective point cloud cluster is an active target is higher; further, if the more the number of the effective point cloud cluster can satisfy the three active target determination rules, the greater the probability that the effective point cloud cluster is an active target is.
Step 104: for each activity goal, performing: determining the position information of the moving target according to the attribute information of the moving point corresponding to the moving target; and judging whether the moving target is positioned in the target area or not according to the range information of the target area and the position information of the moving target.
In this embodiment, with reference to fig. 3 and 4, the point cloud data includes a distance from each moving point to the millimeter wave radar and an azimuth angle from each moving point to the millimeter wave radar;
before the determining the position information of the moving target, further comprising: acquiring position information of the millimeter wave radar;
the determining the position information of the moving target comprises:
step 301: and calculating the average distance from the movable target to the millimeter wave radar according to the distance from each moving point in the movable target to the millimeter wave radar.
In this step, the average distance from the moving target to the millimeter wave radar is calculated by the following formula:
wherein laFor characterizing the average distance of a moving target to the millimeter wave radar.
Step 302: calculating the average azimuth angle from the moving target to the millimeter wave radar according to the azimuth angle from each moving point in the moving target to the millimeter wave radar;
in this step, the average azimuth angle from the moving target to the millimeter wave radar is calculated by the following formula:
wherein, thetaaFor characterizing the mean azimuth angle of a moving target to the millimeter wave radar.
Step 303: determining the position information of the moving target according to the position information of the millimeter wave radar and the average distance and the mean square angle obtained by calculation
In this step, the position information of the moving object is calculated by the following formula group:
wherein, X0Abscissa, Y, for characterizing moving objects0Ordinate, X, for characterizing moving objectsRFor characterizing the transverse-axis coordinate, Y, of a millimeter-wave radarRThe method is used for representing the vertical axis coordinate of the millimeter wave radar.
In the present specification, examples are given by using (X)0，Y0) The position information of the movable target is characterized, and the accuracy of the characterization mode is high. Of course, the moving target may also be characterized by coordinates or other position information of other moving points in the moving target, which is not limited herein.
In this embodiment, when the target area is a rectangular area, the following formula group may be used to determine that the active target is located in the target area:
wherein, XaA horizontal axis coordinate, Y, for characterizing the lower left corner vertex of a target regionaThe vertical axis coordinate of the vertex of the lower left corner of the target area is used for representing, L is used for representing the length of the target area, and W is used for representing the width of the target area.
If the formula set is not satisfied, the active target is not located within the target area.
In the embodiment of the present specification, the scheme for detecting whether a moving target enters a certain target area only needs to use one millimeter wave radar, and even if the target area changes, the scheme can continue to detect the moving target in place by changing the range information of the target area without continuously relocating a sensor in the changed target area, so that the operation complexity of detecting the moving target in place can be reduced.
In some embodiments, the determining whether the moving target is located in the target area according to the range information of the target area and the position information of the moving target in step 104 includes:
and judging whether the movable target is positioned in the target area or not according to the range information of the target area and the position information of the movable target in each frame.
That is to say, for each frame of point cloud data detected by the millimeter wave radar, if there is position information of a moving target in a target area in the point cloud data of one frame, an in-place response is triggered, otherwise, no trigger is triggered. Of course, for the point cloud data of a preset number of frames detected by the millimeter wave radar, if the position information of the moving target is located in the target area in each frame of point cloud data of multiple frames exceeding the preset threshold, the in-place response is triggered, otherwise, the in-place response is not triggered.
The above embodiments describe the case when an active object enters a target area. However, in practical applications, if at least two target areas exist in the detection area, there may be a case where the active object repeatedly enters two of the target areas within a short time, and thus the in-place responses (e.g., alarm information) of the two target areas are triggered more frequently, which may affect the user experience.
The reason for this is that the above embodiment processes the point cloud data of each frame, and if there is position information of a moving target located in a target area in the point cloud data of one frame, an in-place response is triggered, that is, the sensitivity of this triggering method is high. Considering that a moving object may enter a target area by mistake, the sensitivity of the triggering method may be reduced, for example, noise reduction processing may be performed on a moving point generated within a preset time period.
With reference to fig. 5, after determining that an active target in at least one frame is located in one of the target areas in step 104, the method further includes:
step 501: and within a preset second time length, judging whether the active target in at least one frame is located in another target area, if so, executing the step 502, and if not, ending the current process.
In this step, for example, the preset second duration is 1s, the millimeter wave radar can detect 20 frames of point cloud data within 1s, and if there is at least one frame of point cloud data in which a moving object is located in the first target area, and there is also at least one frame of point cloud data in which a moving object is located in the second target area, step 502 is executed. For example, if the moving target in the 8 frames of point cloud data is located in the first target area, and the moving target in the 12 frames of point cloud data is located in the second target area, within 1s, the first target area and the second target area both detect that the moving target enters, that is, within 1s, in-place responses corresponding to the first target area and the second target area are both triggered for several times, which may affect the use experience of the user. Thus, the problem of such frequent triggering can be solved by performing step 502.
Step 502: and performing noise reduction processing on the motion points corresponding to the moving target in all the frames in the second duration.
In this step, the noise reduction processing may include at least one of the following two ways.
In a first mode
Step A1: determining a boundary band region of the two target regions.
Wherein the boundary band region of the target region is formed by moving a boundary line of the target region to the inside of the target region by a preset distance. Referring to fig. 6, for example, the two target areas are the first target area and the second target area respectively, and the boundary zone area is two ring-shaped shaded areas in fig. 6.
Step A2: removing the motion points located on the boundary band region in all frames within the second duration.
In this embodiment, by defining the boundary band region, the motion points located in the adjacent boundary region portions of the first target region and the second target region are subjected to the blurring weakening process, so that the attribute information of the motion points other than the motion points located in the boundary band region can be focused, and then preparation is made for determining the target region where the active target is located (specifically, the first target region or the second target region).
Mode two
Step B1: and calculating the average Doppler value of the moving points corresponding to the moving target in all the frames in the second time length.
Wherein the point cloud data comprises a Doppler value for each motion point; wherein the Doppler value of each moving point is used for representing the change rate of the relative distance from the moving point to the millimeter wave radar. That is to say, the doppler value of the moving point describes the motion attribute of the moving point, and the filtering of the doppler value can be beneficial to accurately determining the motion characteristic of the moving target. For example, if the doppler value of a moving point located within a first target region is generally higher than the doppler value of a moving point located within a second target region, it may be demonstrated that the moving target is more likely to be located in the first target region.
Step B2: and removing the moving points with Doppler values lower than the average Doppler value.
In this embodiment, since the doppler value of the moving point describes the motion attribute of the moving point, the moving characteristic of the moving target can be determined accurately by screening the doppler values. For further processing of noise moving points, moving points with doppler values higher than the average doppler value may be focused, i.e. moving points with doppler values lower than the average doppler value are removed.
Step 503: new location information for the active object is determined.
This step may be specifically realized as follows.
Step C1: and clustering the motion points corresponding to the moving target after the noise reduction treatment again to obtain at least two new point cloud clusters.
In this step, for example, the DBSCAN algorithm may be continuously used for clustering, which is described in detail above and will not be described herein again. It should be noted that the parameters (e.g., the threshold of the difference between the coordinates, the threshold of the difference between the speeds, the threshold of the signal-to-noise ratio, and the threshold of the number) of the clustering algorithm in this step are all more strict than those in the above first clustering, otherwise, the moving points corresponding to the moving target cannot be clustered into at least two new cloud clusters.
Step C2: and determining new position information of the moving target according to the attribute information of the moving points in the new point cloud cluster with the largest number of the moving points.
In this step, the implementation of determining the new location information of the active target is consistent with the above. For example, firstly, determining an initial point cloud cluster by using the coordinate, the speed and the signal-to-noise ratio of each moving point, then determining an effective point cloud cluster, and then determining a new moving target; next, the new moving target position information is determined by using the average distance from the new moving target to the millimeter wave radar, the average azimuth angle, and the position information of the millimeter wave radar, that is, the new position information of the moving target in step C2 is obtained.
Step 504: and determining a target area where the movable target is located according to the determined new position information.
In this embodiment, the new position information of the moving target determined in the above steps can better represent the real position information of the moving target, and the problem that the moving target frequently triggers in-place response can be effectively solved by the determined new position information, that is, the triggering result is only that the moving target is located in the first target area or the second target area.
In conclusion, the function of virtualizing the sub-sensors into a plurality of sub-sensors can be realized by using a single millimeter wave radar, when the target area changes, the virtualized sub-sensors can still accurately trigger in-place response, and the operation complexity of in-place detection on the moving target is reduced. Meanwhile, the trigger states of the virtual sub-sensors can be transmitted to an application terminal in real time for the terminal application to use and display.
As shown in fig. 7 and 8, the present specification provides an apparatus in which an apparatus for detecting in-position of a moving target is located and an apparatus for detecting in-position of a moving target. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. From a hardware level, as shown in fig. 7, for a hardware structure diagram of a device where an apparatus for performing in-place detection on an active target provided in the embodiment of the present specification is located, in addition to the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 7, the device where the apparatus is located in the embodiment may also generally include other hardware, such as a forwarding chip responsible for processing a packet, and the like. Taking a software implementation as an example, as shown in fig. 8, as a logical apparatus, the apparatus is formed by reading a corresponding computer program instruction in a non-volatile memory into a memory by a CPU of a device in which the apparatus is located and running the computer program instruction.
As shown in fig. 8, in one embodiment of the present specification, an apparatus for detecting an in-position of a moving target is provided, including:
a first obtaining module 801 configured to obtain range information of a target area; the target area is obtained by dividing a detection area;
a second obtaining module 802, configured to obtain point cloud data corresponding to a plurality of moving points, which is obtained by detecting the detection area by a millimeter wave radar; the point cloud data comprises the number of the moving points and attribute information of each moving point;
a moving target determining module 803, configured to determine at least one moving target included in the detection region according to the number of moving points detected by the millimeter wave radar for the detection region and attribute information of each moving point; wherein each moving target is composed of a plurality of moving points;
a processing module 804 configured to perform, for each activity goal: determining the position information of the moving target according to the attribute information of the moving point corresponding to the moving target; and judging whether the moving target is positioned in the target area or not according to the range information of the target area and the position information of the moving target.
In one embodiment of the apparatus set forth in the specification, the attribute information comprises coordinates, velocity, and signal-to-noise ratio;
the activity target determination module 803 is configured to perform the following processes:
clustering a plurality of moving points in the detection area according to the coordinate, the speed and the signal-to-noise ratio of each moving point to obtain at least one initial point cloud cluster;
for each initial point cloud cluster, if the number of the moving points included in the initial point cloud cluster is not less than a preset first number threshold and the distance between any two moving points included in the initial point cloud cluster is less than a preset first distance threshold, determining the initial point cloud cluster as an effective point cloud cluster;
and determining the effective point cloud cluster meeting the activity target determination rule as an activity target.
In an embodiment of the apparatus proposed in the present specification, the activity targeting rule comprises at least one of:
the duration of the effective point cloud cluster is not less than a preset first duration;
the number of the moving points in the effective point cloud cluster is not less than a preset second number threshold;
and the distance between the effective point cloud cluster and the effective point cloud cluster closest to the effective point cloud cluster is not less than a preset second distance threshold.
In one embodiment of the apparatus proposed in the present specification, the point cloud data includes a distance from each moving point to the millimeter wave radar and an azimuth angle from each moving point to the millimeter wave radar;
further comprising:
the third acquisition module is configured to acquire the position information of the millimeter wave radar;
the processing module 804, when performing the determining the location information of the active target, is configured to perform the following processes:
calculating the average distance from the moving target to the millimeter wave radar according to the distance from each moving point in the moving target to the millimeter wave radar;
calculating the average azimuth angle from the moving target to the millimeter wave radar according to the azimuth angle from each moving point in the moving target to the millimeter wave radar;
and determining the position information of the moving target according to the position information of the millimeter wave radar and the average distance and the mean square angle obtained by calculation.
In one embodiment of the apparatus proposed in the present specification, there are at least two target areas within the detection area;
within a preset second time length, the millimeter wave radar detects the detection area to obtain at least two frames of point cloud data corresponding to the plurality of moving points;
the processing module 804 is configured to perform the following processing when the determining module determines whether the moving target is located in the target area according to the range information of the target area and the position information of the moving target:
judging whether the moving target is positioned in the target area or not according to the range information of the target area and the position information of the moving target in each frame;
after determining that an active target in at least one frame is located in one of the target regions, the method further includes:
a target area determination module configured to perform the following:
within a preset second time length, judging whether the active target in at least one frame is located in another target area, if so, executing the following processing: performing noise reduction processing on the motion points corresponding to the moving target in all the frames in the second duration; determining new position information of the movable target; and determining a target area where the movable target is located according to the determined new position information.
In an embodiment of the apparatus proposed in this specification, the target region determination module, when performing the denoising processing on the moving point corresponding to the active target in all frames within the second duration, is configured to perform the following processing:
determining a boundary band region of the two target regions; wherein the boundary belt region of the target region is formed by moving a boundary line of the target region to the inside of the target region by a preset distance;
removing the motion points located on the boundary band region in all frames within the second duration;
in one embodiment of the apparatus set forth in the present specification, the point cloud data comprises a doppler value for each moving point; the Doppler value of each moving point is used for representing the change rate of the relative distance from the moving point to the millimeter wave radar;
the target area determination module, when performing the denoising processing on the moving point corresponding to the moving target in all frames in the second duration, is configured to perform the following processing:
calculating the average Doppler value of the moving points corresponding to the moving target in all the frames in the second time length;
and removing the moving points with Doppler values lower than the average Doppler value.
In an embodiment of the apparatus proposed in this specification, said target area determination module, when performing said determining new location information of the active target, is configured to perform the following processing:
clustering the motion points corresponding to the moving target after the noise reduction treatment again to obtain at least two new point cloud clusters;
and determining new position information of the moving target according to the attribute information of the moving points in the new point cloud cluster with the largest number of the moving points.
In one embodiment of the present specification, the above-mentioned apparatus for detecting the presence of a moving object may be integrated into a terminal device for detecting the presence, or may be integrated into a separate device or server connected to the terminal device for detecting the presence.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
According to an embodiment of another aspect, there is also provided an apparatus for detecting in-place of a moving target, including: at least one memory and at least one processor;
the at least one memory to store a machine readable program;
the at least one processor is configured to invoke the machine readable program to perform the method for detecting the in-place of the active target in any embodiment of the present specification.
According to an embodiment of yet another aspect, there is also provided a computer-readable medium storing instructions for causing a computer to perform the method of in-place detection of an active target as described herein. Specifically, a method or an apparatus equipped with a storage medium on which a software program code that realizes the functions of any of the above-described embodiments is stored may be provided, and a computer (or a CPU or MPU) of the method or the apparatus is caused to read out and execute the program code stored in the storage medium.
In this case, the program code itself read from the storage medium can realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code constitute a part of this specification.
Examples of the storage medium for supplying the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD + RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer via a communications network.
Further, it should be clear that the functions of any one of the above-described embodiments can be implemented not only by executing the program code read out by the computer, but also by performing a part or all of the actual operations by an operation method or the like operating on the computer based on instructions of the program code.
Further, it is to be understood that the program code read out from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion unit connected to the computer, and then causes a CPU or the like mounted on the expansion board or the expansion unit to perform part or all of the actual operations based on instructions of the program code, thereby realizing the functions of any of the above-described embodiments.
Those skilled in the art will recognize that in one or more of the examples described above, the functions described in this specification can be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium.
It is to be understood that the illustrated structure of the embodiments of the present disclosure does not constitute a specific limitation on the apparatus for detecting the in-position of the moving object. In other embodiments of the present description, the means for detecting the presence of a moving object may include more or fewer components than shown, or some components may be combined, some components may be split, or a different arrangement of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
For the information interaction, execution process, and other contents between the modules in the apparatus, the specific contents may refer to the description in the method embodiment of the present specification because the same concept is based on the method embodiment of the present specification, and are not described herein again.
The above embodiments are described in further detail for the purpose of illustrating the invention, and it should be understood that the above embodiments are only for illustrative purposes and are not intended to limit the scope of the invention, and any modification, equivalent replacement, improvement, etc. made on the basis of the technical solutions of the present invention should be included in the scope of the present invention.
Claims (10)
1. The method for detecting the in-place of the moving target is characterized by comprising the following steps:
acquiring range information of a target area; the target area is obtained by dividing a detection area;
acquiring point cloud data corresponding to a plurality of moving points, which is obtained by detecting the detection area by a millimeter wave radar; the point cloud data comprises the number of the moving points and attribute information of each moving point;
determining at least one moving target included in the detection area according to the number of the moving points detected by the millimeter wave radar in the detection area and the attribute information of each moving point; wherein each moving target is composed of a plurality of moving points;
for each activity goal, performing:
determining the position information of the moving target according to the attribute information of the moving point corresponding to the moving target;
and judging whether the moving target is positioned in the target area or not according to the range information of the target area and the position information of the moving target.
2. The method of claim 1,
the attribute information comprises coordinates, speed and signal-to-noise ratio;
the determining at least one moving target included in the detection area according to the number of the moving points detected by the millimeter wave radar for the detection area and the attribute information of each moving point includes:
clustering a plurality of moving points in the detection area according to the coordinate, the speed and the signal-to-noise ratio of each moving point to obtain at least one initial point cloud cluster;
for each initial point cloud cluster, if the number of the moving points included in the initial point cloud cluster is not less than a preset first number threshold and the distance between any two moving points included in the initial point cloud cluster is less than a preset first distance threshold, determining the initial point cloud cluster as an effective point cloud cluster;
and determining the effective point cloud cluster meeting the activity target determination rule as an activity target.
3. The method of claim 2,
the activity targeting rule comprises at least one of:
the duration of the effective point cloud cluster is not less than a preset first duration;
the number of the moving points in the effective point cloud cluster is not less than a preset second number threshold;
and the distance between the effective point cloud cluster and the effective point cloud cluster closest to the effective point cloud cluster is not less than a preset second distance threshold.
4. The method of claim 1,
the point cloud data comprises the distance from each moving point to the millimeter wave radar and the azimuth angle from each moving point to the millimeter wave radar;
before the determining the position information of the moving target, further comprising: acquiring position information of the millimeter wave radar;
the determining the position information of the moving target comprises:
calculating the average distance from the moving target to the millimeter wave radar according to the distance from each moving point in the moving target to the millimeter wave radar;
calculating the average azimuth angle from the moving target to the millimeter wave radar according to the azimuth angle from each moving point in the moving target to the millimeter wave radar;
and determining the position information of the moving target according to the position information of the millimeter wave radar and the average distance and the mean square angle obtained by calculation.
5. The method according to any one of claims 1 to 4,
at least two target regions are present within the detection region;
within a preset second time length, the millimeter wave radar detects the detection area to obtain at least two frames of point cloud data corresponding to the plurality of moving points;
the determining whether the moving target is located in the target area according to the range information of the target area and the position information of the moving target includes:
judging whether the moving target is positioned in the target area or not according to the range information of the target area and the position information of the moving target in each frame;
after determining that an active target in at least one frame is located in one of the target regions, the method further includes:
within a preset second time length, judging whether the active target in at least one frame is located in another target area, if so, executing the following processing:
performing noise reduction processing on the motion points corresponding to the moving target in all the frames in the second duration;
determining new position information of the movable target;
and determining a target area where the movable target is located according to the determined new position information.
6. The method of claim 5,
the denoising processing of the motion points corresponding to the moving target in all the frames in the second duration includes:
determining a boundary band region of the two target regions; wherein the boundary belt region of the target region is formed by moving a boundary line of the target region to the inside of the target region by a preset distance;
removing the motion points located on the boundary band region in all frames within the second duration;
and/or the presence of a gas in the gas,
the point cloud data comprises a doppler value for each motion point; the Doppler value of each moving point is used for representing the change rate of the relative distance from the moving point to the millimeter wave radar;
the denoising processing of the motion points corresponding to the moving target in all the frames in the second duration includes:
calculating the average Doppler value of the moving points corresponding to the moving target in all the frames in the second time length;
and removing the moving points with Doppler values lower than the average Doppler value.
7. The method of claim 5, wherein determining new location information for the active object comprises:
clustering the motion points corresponding to the moving target after the noise reduction treatment again to obtain at least two new point cloud clusters;
and determining new position information of the moving target according to the attribute information of the moving points in the new point cloud cluster with the largest number of the moving points.
8. Device to moving target detection that targets in place, its characterized in that includes:
the first acquisition module is configured to acquire range information of a target area; the target area is obtained by dividing a detection area;
the second acquisition module is configured to acquire point cloud data corresponding to the plurality of moving points, which is obtained by detecting the detection area by the millimeter wave radar; the point cloud data comprises the number of the moving points and attribute information of each moving point;
the moving target determining module is configured to determine at least one moving target included in the detection area according to the number of the moving points detected by the millimeter wave radar in the detection area and the attribute information of each moving point; wherein each moving target is composed of a plurality of moving points;
a processing module configured to perform, for each activity goal: determining the position information of the moving target according to the attribute information of the moving point corresponding to the moving target; and judging whether the moving target is positioned in the target area or not according to the range information of the target area and the position information of the moving target.
9. Apparatus for in-situ detection of a moving object, comprising a memory having stored therein executable code, and a processor which, when executing the executable code, implements the method of any one of claims 1 to 7.
10. Computer-readable storage medium, characterized in that a computer program is stored thereon, which, when being executed in a computer, causes the computer to carry out the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110136512.0A CN112837346A (en) | 2021-02-01 | 2021-02-01 | Method and device for detecting in-place of moving target |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110136512.0A CN112837346A (en) | 2021-02-01 | 2021-02-01 | Method and device for detecting in-place of moving target |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112837346A true CN112837346A (en) | 2021-05-25 |
Family
ID=75931386
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110136512.0A Pending CN112837346A (en) | 2021-02-01 | 2021-02-01 | Method and device for detecting in-place of moving target |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112837346A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113687429A (en) * | 2021-08-30 | 2021-11-23 | 四川启睿克科技有限公司 | Device and method for determining boundary of millimeter wave radar monitoring area |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110457407A (en) * | 2018-05-02 | 2019-11-15 | 北京京东尚科信息技术有限公司 | Method and apparatus for handling point cloud data |
| CN111199555A (en) * | 2019-12-13 | 2020-05-26 | 意诺科技有限公司 | Millimeter wave radar target identification method |
| CN111966099A (en) * | 2020-08-17 | 2020-11-20 | 深圳电目科技有限公司 | Indoor target tracking method based on radar, energy-saving method and system |
| CN112150501A (en) * | 2020-09-18 | 2020-12-29 | 浙江吉利控股集团有限公司 | Target detection method, device and equipment based on laser radar and storage medium |
-
2021
- 2021-02-01 CN CN202110136512.0A patent/CN112837346A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110457407A (en) * | 2018-05-02 | 2019-11-15 | 北京京东尚科信息技术有限公司 | Method and apparatus for handling point cloud data |
| CN111199555A (en) * | 2019-12-13 | 2020-05-26 | 意诺科技有限公司 | Millimeter wave radar target identification method |
| CN111966099A (en) * | 2020-08-17 | 2020-11-20 | 深圳电目科技有限公司 | Indoor target tracking method based on radar, energy-saving method and system |
| CN112150501A (en) * | 2020-09-18 | 2020-12-29 | 浙江吉利控股集团有限公司 | Target detection method, device and equipment based on laser radar and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113687429A (en) * | 2021-08-30 | 2021-11-23 | 四川启睿克科技有限公司 | Device and method for determining boundary of millimeter wave radar monitoring area |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11709058B2 (en) | Path planning method and device and mobile device | |
| CN111045008B (en) | Vehicle millimeter wave radar target identification method based on widening calculation | |
| CN112513679B (en) | Target identification method and device | |
| JP5145986B2 (en) | Object detection apparatus and distance measuring method | |
| CN110782465B (en) | Ground segmentation method and device based on laser radar and storage medium | |
| JP2018146486A (en) | Radar device and target height estimation method | |
| CN111913177A (en) | Method and device for detecting target object and storage medium | |
| WO2022198637A1 (en) | Point cloud noise filtering method and system, and movable platform | |
| CN115524683A (en) | Light spot extraction method, distance measurement method, laser radar and robot | |
| CN112837346A (en) | Method and device for detecting in-place of moving target | |
| KR102060286B1 (en) | Radar object detection threshold value determination method using image information and radar object information generation device using the same | |
| US20220108552A1 (en) | Method and Apparatus for Determining Drivable Region Information | |
| CN111753803B (en) | Unmanned aerial vehicle graph signal identification method based on fuzzy clustering and high-order cumulant | |
| CN114137505A (en) | Target detection method and device based on wireless radar | |
| CN113625232A (en) | Method, device, medium and equipment for suppressing multipath false target in radar detection | |
| CN113625266A (en) | Method, device, storage medium and equipment for detecting low-speed target by using radar | |
| WO2022217407A1 (en) | Signal processing method and apparatus, and readable storage medium | |
| CN112014822B (en) | Vehicle-mounted radar measurement data identification method and device, medium and electronic device | |
| CN114859380A (en) | Cliff detection method, driving device and storage medium | |
| CN115792870B (en) | Detection method and device for window shielding of laser radar | |
| WO2020103043A1 (en) | Linear object identification method, device and system and computer storage medium | |
| CN112015960A (en) | Clustering method of vehicle-mounted radar measurement data, storage medium and electronic device | |
| KR102656646B1 (en) | Method for detecting installation abnormality of sensing device and sensing device of performing the same | |
| CN115439484B (en) | Detection method and device based on 4D point cloud, storage medium and processor | |
| CN114002708A (en) | Tail wave filtering method for unmanned ship application |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |