CN111274336A - Target track processing method and device, storage medium and electronic device - Google Patents
Target track processing method and device, storage medium and electronic device Download PDFInfo
- Publication number
- CN111274336A CN111274336A CN201911311545.3A CN201911311545A CN111274336A CN 111274336 A CN111274336 A CN 111274336A CN 201911311545 A CN201911311545 A CN 201911311545A CN 111274336 A CN111274336 A CN 111274336A
- Authority
- CN
- China
- Prior art keywords
- target
- track
- area
- preset
- target track
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides a target track processing method, a target track processing device, a storage medium and an electronic device, wherein the method comprises the following steps: inputting a target track in a target map; determining a location of the target trajectory in the target map; judging whether the target track is an effective track or not based on the position of the target track in the target map; and when the target track is determined to be an effective track, the target track is reserved, and/or when the target track is determined to be an ineffective track, the target track is deleted. The method and the device solve the problem that whether the formed track needs to be terminated cannot be determined in the related technology, and further achieve the purpose of accurately and effectively determining the track to be terminated.
Description
Technical Field
The present invention relates to the field of communications, and in particular, to a method, an apparatus, a storage medium, and an electronic apparatus for processing a target trajectory.
Background
The security of the modern society is more and more taken attention by the public, and the security products are also endlessly produced, and the security technology is rapidly developed.
Among them, the millimeter-wave radar-based area surveillance technology is a hot spot in recent years. The traditional security terminal equipment is mainly a visible light camera, but the visible light camera cannot work at night; although there are drawbacks to infrared cameras that complement visible light cameras, this undoubtedly increases cost and operational difficulty. In addition, the optical sensor is also influenced by weather, and the monitoring effect cannot be satisfactory in heavy fog days or rainy and snowy days. The millimeter wave radar actively transmits electromagnetic waves and receives signals with the same frequency, so that the millimeter wave radar has very high detection probability for moving objects or objects with large RCS (radar reflection area), and has lower detection probability (the detection probability is not zero) for static objects. The millimeter wave radar can work 24 hours all day long and is less influenced by weather. Therefore, there is a strong demand for millimeter-wave radar-based monitoring products in the market today.
In addition, the millimeter wave radar can monitor various targets, further extract the targets which are interesting to the user from the various targets, and terminate/filter the targets which are not interesting to the user or false targets as soon as possible. One of the purposes of trace termination is to filter objects. For example, in a park, if a 3 rd wind is accidentally blown up and trees shake to form a target track with low speed and small range of motion, the track termination method needs to terminate the track caused by the tree shake in time. If a small dog is going through the garden, the trajectory should also be terminated in time since it is not the target of the user's attention (whether the user is a person or a car). If the track is formed by the pedestrian, the radar outputs the track information of the pedestrian to the camera, and the camera takes pictures or records the pictures according to the track space position information provided by the radar.
However, no effective solution has been proposed in the related art as to how to determine whether a formed trace is to be terminated.
Disclosure of Invention
The embodiment of the invention provides a method and a device for processing a target track, a storage medium and an electronic device, which are used for at least solving the problem that whether the formed track needs to be terminated cannot be determined in the related technology.
According to an embodiment of the present invention, there is provided a method for processing a target trajectory, including: inputting a target track in a target map; determining a location of the target trajectory in the target map; judging whether the target track is an effective track or not based on the position of the target track in the target map; and when the target track is determined to be an effective track, the target track is reserved, and/or when the target track is determined to be an ineffective track, the target track is deleted.
According to another embodiment of the present invention, there is provided an apparatus for processing a target trajectory, including: the input module is used for inputting a target track in a target map; a determination module for determining a location of the target trajectory in the target map; the judging module is used for judging whether the target track is an effective track or not based on the position of the target track in the target map; and the processing module is used for reserving the target track when the target track is determined to be an effective track, and/or deleting the target track when the target track is determined to be an ineffective track.
According to a further embodiment of the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored, wherein the computer program is arranged to perform the steps in the above-mentioned method embodiments when executed.
According to yet another embodiment of the present invention, there is also provided an electronic device, including a memory in which a computer program is stored and a processor configured to execute the computer program to perform the steps in the above method embodiments.
According to the method and the device, whether the target track is the effective track or not can be determined according to the position of the target track in the target map, the aim of effectively filtering false track information by means of map information is achieved, the problem that whether the formed track needs to be terminated or not cannot be determined in the related technology is effectively solved, and the aim of accurately and effectively determining the track to be terminated is achieved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention to a proper form. In the drawings:
FIG. 1 is a schematic diagram of a map according to an embodiment of the invention;
fig. 2 is a block diagram of a hardware structure of a mobile terminal of a target trajectory processing method according to an embodiment of the present invention;
FIG. 3 is a flow chart of a method of processing a target trajectory according to an embodiment of the present invention;
FIG. 4 is a flow chart of a vector map based trajectory termination method according to an embodiment of the present invention;
FIG. 5 is a detailed flowchart of a method for ending a track based on a vector map according to an embodiment of the present invention;
fig. 6 is a block diagram of a target trajectory processing apparatus according to an embodiment of the present invention.
Detailed Description
The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The present invention may be referred to in terms of the following techniques:
in the related technology, monitoring technology based on radar is increasingly emphasized in the security field, the radar obtains measurement information of a moving target with high detection probability, a background target tracking algorithm quickly and accurately starts a real target track based on radar measurement input information, confirms the identity and motion information of the real moving target, filters false tracks and end target tracks in time, and then outputs the accurate target identity and motion information to other links. Wherein, the measurement information that the millimeter wave radar can obtain the target includes: distance, angle, radial velocity (RadialSpeed), radar reflection area (RCS). The millimeter wave radar can set a measurement period (signal transceiving period) as required, and the measurement period is generally set to 0.1 second, i.e. the operating frequency is 10 HZ.
The target track ending link is one of core links of a target tracking algorithm, and a corresponding method is called a track ending method. The purpose of the track ending link is to end the false track in time and eliminate the target track escaping from the tracking range, such as eliminating false alarm formed by trees. In addition, the inputs to the trajectory termination loop are the known map and target trajectory, with no output.
The map refers to a rasterized map. The node attributes in the map are allowed to be different, and the map node attributes involved in the embodiment of the present invention may include: 1) an unknown region; 2) a tree region; 3) a tree shadow area; 4) a building area; 5) a building block area; 6) an open area; 7) a motor vehicle drivable region; 8) a human drivable region; 9) an area that cannot be detected; 10) a high quality measurement area; 11) a low quality measurement region. The simple local map shown in fig. 1, wherein a region denoted by "1" represents an unknown region, a region denoted by 2 represents a building region, a region denoted by 3 represents a building blocking region, a region denoted by 4 represents a tree region, a region denoted by 5 represents a tree shadow region, a region denoted by 6 represents a human travelable region, a region denoted by 7 represents a vehicle travelable region, a region denoted by 8 represents an open region, and a region denoted by 9 represents a region that cannot be detected by a radar.
The node motion has directionality, that is, a vector map, for example, a grid (the side length is 1 meter) with coordinates (CartX is 10, CartY is 40) in a map, the motion direction is a unidirectional driving area, the direction is 0 degrees (0 degrees is defined as north), and the allowable error is 45 degrees, which means that if a moving object exists in the grid with coordinates (CartX is 10, CartY is 40), the speed direction of the moving object must be north, and the allowable direction error is 45 degrees. For another example, if there is no requirement for the direction of movement in a grid with coordinates (CartX-10 and CartY-20) in the map, it indicates that there is a target that allows movement in any direction at this point.
The state X of the target trajectory is a vector of four rows and one column, and is composed of [ X, vx, y, vy ], and the vector elements represent a rectangular coordinate position X, a velocity component vx, a rectangular coordinate position y, and a velocity component vy in a two-dimensional space, respectively.
The state covariance matrix PX of the target trajectory is a matrix of four rows and four columns.
The scheme in the embodiment of the invention can be applied to scenes such as parks, construction sites, intersections, roads, garden entrances and exits, gates and the like. Referring to fig. 1, assuming that fig. 1 describes a garden entrance/exit indication diagram, if a target track exists in a building area suddenly, a target tracking algorithm considers a virtual false track at this time and deletes the virtual false track. If the track of a person enters the building area from the open area, the pedestrian is considered to enter the building, and the track of the pedestrian is deleted. If a target track is traced by a pedestrian in the tree area and the target track moves in a small range at a low speed for a long time, the target track is considered to be a false track formed by tree shaking, and the false track is deleted as soon as possible.
The invention is illustrated below with reference to examples:
the method provided by the embodiment of the application can be executed in a mobile terminal, a computer terminal or a similar operation device. Taking the example of running on a mobile terminal, fig. 2 is a hardware structure block diagram of the mobile terminal of a target trajectory processing method according to an embodiment of the present invention. As shown in fig. 2, the mobile terminal 20 may include one or more (only one shown in fig. 2) processors 202 (the processor 202 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 204 for storing data, and optionally may also include a transmission device 206 for communication functions and an input-output device 208. It will be understood by those skilled in the art that the structure shown in fig. 2 is only an illustration, and is not a limitation to the structure of the mobile terminal. For example, the mobile terminal 20 may also include more or fewer components than shown in FIG. 2, or have a different configuration than shown in FIG. 2.
The memory 204 can be used for storing computer programs, for example, software programs and modules of application software, such as a computer program corresponding to the target trajectory processing method in the embodiment of the present invention, and the processor 202 executes various functional applications and data processing by running the computer programs stored in the memory 204, so as to implement the above-mentioned method. Memory 204 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 204 may further include memory located remotely from the processor 202, which may be connected to the mobile terminal 20 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission means 206 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal 20. In one example, the transmission device 206 includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 206 can be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
In this embodiment, a method for processing a target track that can be executed on the mobile terminal is provided, and fig. 3 is a flowchart of the method for processing a target track according to the embodiment of the present invention, as shown in fig. 3, the flowchart includes the following steps:
step S302, inputting a target track in a target map;
step S304, determining the position of the target track in the target map;
step S306, judging whether the target track is an effective track or not based on the position of the target track in the target map;
step S308, when the target track is determined to be an effective track, the target track is reserved, and/or when the target track is determined to be an ineffective track, the target track is deleted.
The terminal, the server, or the processor with similar processing capability may perform the above operations.
In the above embodiment, before inputting the target track in the target map, the processes of initializing and loading the target map need to be executed, specifically as shown in fig. 4, where the process of inputting the target track in fig. 4 corresponds to the above S302, and the process of determining the track ending in fig. 4 corresponds to the above S306-S308, where the initialization process is a necessary preprocessing link for opening up a map storage space, a target track storage space, and the like. It only needs to be executed once. The loading of the target map provides a reliable and accurate monitoring area map for the target tracking program. The map can be loaded, a map of the known environment can be drawn manually, and a program can be imported, and the map can be generated on line (without any manual auxiliary operation). The method for generating the map on line is to accumulate radar measurement for a period of time, and construct and update the environmental map in real time based on the existing environmental target type knowledge base. The advantage of manually drawing the known environment is that the map is highly accurate and does not require additional time (relative to the time required to generate the environment map on-line); the disadvantage is that the labor cost is high, and when the environment information is changed, a new map needs to be imported again. The method for generating the map on line has the advantages that no manual auxiliary operation is needed; the disadvantage is that it is less accurate than manually drawn maps and requires additional time to build the map when the procedure is initiated. Target tracking cannot be performed during map construction. In addition, the contents of the manually-introduced map and the online generated map may have a large difference, for example, in the manually-introduced map, there are many undetected areas, and in the online generated map, there are many unknown areas.
It should be noted that the map is rasterized and each map node is assigned the correct attributes.
The structure describing the map is as follows:
in the above embodiment, when the target track is input, the ID, the category, the state, the measurement in the latest period of time, and the area attribute of the input target track are included, which are specifically as follows:
by the embodiment, whether the target track is the effective track or not can be determined according to the position of the target track in the target map, the aim of effectively filtering false track information by means of map information is achieved, the problem that whether the formed track needs to be terminated or not cannot be determined in the related technology is effectively solved, and the aim of accurately and effectively determining the track to be terminated is further achieved.
In an optional embodiment, determining whether the target track is a valid track based on the position of the target track in the target map includes: judging whether the type of an area where a target object generating the target track is located is changed or not based on the position of the target track in the target map; under the condition that the target object is determined not to be changed, judging whether the target track is an effective track or not based on the type of the area where the target object is located; and under the condition that the change is determined, judging whether the target track is an effective track or not based on the types before and after the change of the area where the target object is located. In the present embodiment, the determination of whether or not the type of the area in which the target object is located is changed is actually a determination of whether or not the target object enters another type of area from one type of area, where the type of area is actually determined based on the map node attribute described above.
In an optional embodiment, the determining whether the target track is an effective track based on the type of the area where the target object is located includes: judging whether the type of the area where the target object is located is at least one of the following preset types: forbidden region, undetectable region, shielded region; determining the target track as an invalid track under the condition that the type of the area where the target object is located is determined to be at least one of the preset types; and when the type of the area where the target object is located is determined to be other than the preset type, judging whether the preset characteristic of the target track meets a preset condition corresponding to the type of the target object, if so, determining that the target track is an effective track, and if not, determining that the target track is an ineffective track. In this embodiment, when determining whether the type of the region in which the target object is located is at least one of a forbidden region, a non-detectable region, and a shielding region, the type determination may be performed in parallel, that is, whether the type of the region in which the target object is located is the forbidden region, the non-detectable region, and the shielding region is determined at the same time, or the determination may be performed by using one type by one type.
In an optional embodiment, determining whether the predetermined characteristic of the target trajectory satisfies a predetermined condition corresponding to the category of the target object includes: judging whether the smoothness of the target track meets a preset smoothness threshold value; judging whether the range of the area where the target track is located meets a preset range threshold value or not; judging whether the volatility of the radar scattering cross section RCS of the target track meets a first preset fluctuation threshold value or not; judging whether the fluctuation of the radial speed of the target track meets a second preset fluctuation threshold value or not; and judging whether the number of the measuring points of the target track meets a preset number value or not. In the present embodiment, the predetermined conditions corresponding to different types of target objects are actually different, for example, the predetermined conditions corresponding to pedestrians and vehicles are different due to different types of movement, speeds of movement, and the like of the pedestrians and vehicles. Further, the predetermined condition is actually configured in advance (manually configured or automatically configured), and of course, the predetermined condition may be adjusted at any time.
In an optional embodiment, the determining whether the target track is an effective track based on the type of the area where the target object is located before and after the change includes: judging whether the type of the target object before and after the change of the area meets at least one of the following preset conditions: the area where the target object is located is changed from a drivable area to a non-drivable area, the area where the target object is located is changed from a drivable area to an undetectable area, and the area where the target object is located is changed from a drivable area to a shielded area; when the judgment result is satisfied, judging whether the target track is an effective track or not based on the number of times of changing the type of the area where the target object is located; and when the judgment result is that the target track is not satisfied, judging whether the target track is an effective track or not based on the measurement quality before and after the change of the area where the target object is located. In this embodiment, when determining whether the type of the area where the target object is located before and after the change satisfies the predetermined condition, it may be determined whether the area where the target object is located is changed from the drivable area to the non-drivable area, whether the area where the target object is located is changed from the drivable area to the non-detectable area, and whether the area where the target object is located is changed from the drivable area to the shielding area, or, of course, it may be determined one by one, for example, it may be determined whether the area where the target object is located is changed from the drivable area to the non-detectable area, if the determination result is no, it may be determined whether the area where the target object is located is changed from the drivable area to the shielding area, of course, the order of the above sequential determination may not be limited to the above determination order. In the present embodiment, a high-quality measurement area (corresponding to an area where measurement quality is high) refers to an area where the target detection probability is high, and the area is generally a road, an open field, or the like. The low-quality measurement area (corresponding to an area with low and high measurement quality) refers to a map with a relatively low target detection probability, such as a radar detection boundary area, a tree-sheltered area, and the like. The track termination threshold corresponding to the high-quality measurement area is relatively loose, namely, one track is easier to reserve. Conversely, a low quality measurement region is more likely to terminate a trace.
In an optional embodiment, the determining whether the target track is a valid track based on the number of times of the change of the area type of the target object includes: when the number of times of changing the type of the region where the target object is located is determined to reach a preset number threshold, determining that the target track is an invalid track; and when the change frequency of the type of the area where the target object is located is determined not to reach the preset frequency threshold value, performing first adjustment on preset conditions corresponding to the type of the target object, and determining whether the target track is an effective track by judging whether the preset characteristics of the target track meet the adjusted preset conditions. In this embodiment, the threshold comparison determination is performed by counting in order to overcome accidental errors. For example, when a person walks along a building, due to the measurement error of the radar sensor and the map construction error, the track of the person is sometimes in the area of the building and sometimes in an open area, and for the situation, the misjudgment of track ending brought by the fact that the person walks along the boundary area can be overcome through counting. Alternatively, the first adjustment may be performed by increasing a condition threshold corresponding to the predetermined condition, i.e., a threshold for tightening the trajectory termination determination (e.g., smoothness, volatility, M/N, etc.), so that the trajectory is more likely to be terminated.
In an optional embodiment, the determining whether the target track is an effective track based on the measurement quality before and after the change of the area where the target object is located includes: when the measurement quality of the area where the target object is located is determined to be lower than the measurement quality before the change, performing first adjustment on a preset condition corresponding to the category of the target object, when the preset characteristic of the target track is determined to meet the preset condition after the adjustment, determining the target track to be an effective track, and when the preset characteristic of the target track is determined not to meet the preset condition after the adjustment, determining the target track to be an invalid track; and when the measurement quality of the area where the target object is located after being changed is determined to be higher than the measurement quality before being changed, performing second adjustment on a preset condition corresponding to the category of the target object, when the preset characteristic of the target track is determined to meet the preset condition after being adjusted, determining the target track to be an effective track, and when the preset characteristic of the target track is determined not to meet the preset condition after being adjusted, determining the target track to be an invalid track. Optionally, the first adjustment in this embodiment corresponds to the first adjustment in the foregoing embodiment; optionally, the second adjustment in this embodiment corresponds to decreasing the condition threshold corresponding to the predetermined condition, that is, the threshold for determining the termination of the trajectory (e.g., smoothness, fluctuation, M/N, etc.) is relaxed, so that the trajectory becomes not easy to terminate.
The track termination method of the present invention is generally described below with reference to the accompanying drawings:
as shown in fig. 5, the flow of the track termination method based on the vector map includes the following steps:
step 1 (corresponding to the reference numeral "1" in fig. 5, and the subsequent steps are similar): and (5) initializing. Initializing content includes setting a smoothness threshold, a motion region threshold, an RCS volatility threshold, and the like. And skipping to the step 2.
Step 2: and loading a map. The external map may be loaded manually or the map may be obtained automatically by an algorithm. And skipping to the step 3.
And 3, step 3: and inputting a target track. And inputting the target track needing to be judged as a parameter to the track termination function for judgment. Jump to step 4.
And 4, step 4: the location and category are extracted. The positions are the position sequence of the target track in the map within the latest period of time, the categories are the categories of the targets (pedestrians or automobiles), and the thresholds of the steps of 20 th, 21 th, 22 th and the like are determined based on the categories of the targets. For example, the radial velocity threshold of the vehicle trajectory is greater than the radial velocity threshold of the pedestrian, and the RCS threshold of the vehicle trajectory is also greater than the RCS threshold of the pedestrian. And skipping to the step 5.
And 5, step 5: and judging whether the position of the track is changed. Based on the position sequence of the trajectory, it is determined whether the position of the target trajectory in the map has changed now (corresponding to the determination described above of whether the type of area in which the target object is located has changed, and it is also noted that the type of target object needs to be distinguished, e.g., person and car, i.e., person and car correspond to different maps and therefore different thresholds). If the change occurs, step 10 is skipped, and if the change does not occur, step 6 is skipped.
And 6, step 6: the current position. The current position of the target trajectory in the map (the type of the target object needs to be distinguished) is extracted. And 7, jumping to the step.
And 7, step 7: whether in the forbidden region. If so, jumping to the 26 th step, and otherwise, jumping to the 8 th step.
And 8, step 8: whether it is in an undetectable area. If so, jumping to step 26, and otherwise, jumping to step 9.
Step 9: whether in the shielded area. If so, jumping to step 26, otherwise, jumping to step 20.
Step 10: the front and rear positions are extracted. The position of the target trajectory before the change and the position after the change in the map are extracted (please note the difference between the person and the vehicle). Jump to step 11.
And 11, step 11: from the travelable area to the forbidden area. And (5) jumping to the 16 th step when the target track enters the no-driving area from the driving area, otherwise jumping to the 12 th step.
Step 12: from travelable to undetectable. And (4) jumping to the 16 th step when the target track enters the undetectable area from the drivable area, otherwise jumping to the 13 th step.
Step 13: from the travelable area to the shielded area. And (4) jumping to the 16 th step when the target track enters the shielding area from the travelable area, and otherwise jumping to the 14 th step.
Step 14: from a high quality measurement region to a low quality measurement region. And jumping to the 18 th step from the high-quality measurement area to the low-quality measurement area, and otherwise, jumping to the 15 th step. The high quality measurement area refers to an area with high target detection probability, and the area is usually a road, an open field, and the like. The low-quality measurement area refers to a map with a low target detection probability, such as a radar detection boundary area, a tree shielding area and the like. The track ending threshold corresponding to the high-quality measurement area is loose, namely, a track is easier to keep. Conversely, a low quality measurement region is more likely to terminate a trace.
Step 15: from a low quality measurement region to a high quality measurement region. And jumping to the 19 th step from the low-quality measurement area to the high-quality measurement area, or jumping to the 20 th step.
Step 16: and (6) counting. The number of times the target track appears in the terminating area (or referred to as the number of times the type of the area corresponding to the target track is changed) is counted. Jump to step 17.
Step 17: the threshold is exceeded. If the counting value exceeds the threshold value, jumping to the 26 th step, otherwise jumping to the 18 th step. The judgment of threshold comparison is carried out through counting, so as to overcome accidental errors. For example, when a person walks along a building, due to the measurement error of the radar sensor and the map construction error, the track of the person is sometimes in the building area and sometimes in an open area, and for the situation, the misjudgment of track ending caused by the fact that the person walks along the boundary area can be overcome through counting.
Step 18: the conditions are strict. The threshold values (smoothness, volatility, M/N) for the trajectory termination judgment are tightened, so that the trajectory is more easily terminated. Jump to step 20.
Step 19: the conditions are loose. The threshold for determining the termination of the trajectory (smoothness, volatility, M/N) is relaxed, making the trajectory less susceptible to termination. Jump to step 20.
Step 20: and judging the smoothness. If the track is smooth, the smooth track ending condition is not met, and the step 21 is jumped, otherwise, the step 26 is jumped. The smoothness judgment is mainly used for deleting false tracks formed by false alarm of trees and tracks formed by shaking of trees, wherein the tracks move at low speed in a small range and jump violently, and the tracks need to be deleted. If the track is a pedestrian track, the track is approximately a straight line, and the smoothness is much better compared with the shaking track of trees in spite of accidental fluctuation.
Step 21: and judging the motion area. Judging the range of the track motion area, if the target speed is larger and the motion area is smaller, jumping to the 26 th step, otherwise jumping to the 22 nd step. If the trajectory is a pedestrian trajectory, the movement speed is generally more than 0.8m/s according to the data analysis result. Therefore, the route traveled by the track can be judged based on the track existence time, and if the route is less than the threshold value, the track is considered as a false track.
Step 22: and (5) judging RCS volatility. And judging whether the RCS fluctuation of the track is abnormal or not, if the fluctuation is severe, jumping to the 26 th step, and if not, jumping to the 23 rd step. The purpose of judging the RCS volatility is the same as that of judging the track smoothness. If the RCS fluctuation is large, the false track caused by the tree or accidental measurement interference is considered, and deletion is given.
Step 23: and judging the fluctuation of the Radial Speed. And judging whether Radial Speed fluctuation of the track is abnormal or not, if the fluctuation is severe, jumping to the 26 th step, and if not, jumping to the 24 th step.
Step 24: and judging M/N. And judging whether the number of the measuring points of the track meets M/N, if so, skipping to the 26 th step, and if not, skipping to the 25 th step. The M/N determination is to determine the target trajectory from a time perspective, and if the target trajectory is a pedestrian trajectory, the detection probability is inevitably greater than that of the false trajectory, so it can be assumed that M is 5/N is 6, that is, in 6 consecutive frames of measurement, 5 frames of measurement cannot detect the target measurement, and the target trajectory is deleted.
Step 25: and ending the judgment of the track ending, wherein the track is still the target track and is reserved.
Step 26: and finishing the judgment of the track ending, wherein the track is still a false track or a target track needing to be deleted, and deleting is carried out, namely the target track is ended.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, but may also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solution of the present invention or portions thereof contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g. a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
In this embodiment, a device for processing a target track is further provided, where the device is used to implement the foregoing embodiments and preferred embodiments, and details are not repeated for what has been described. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 6 is a block diagram of a target trajectory processing apparatus according to an embodiment of the present invention, as shown in fig. 6, the apparatus including:
an input module 62 for inputting a target trajectory in a target map;
a determining module 64 for determining a location of the target trajectory in the target map;
a determining module 66, configured to determine whether the target track is a valid track based on a position of the target track in the target map;
a processing module 68, configured to retain the target track when determining that the target track is an effective track, and/or delete the target track when determining that the target track is an ineffective track.
In an alternative embodiment, the determining module 66 may determine whether the target track is a valid track by: judging whether the type of the area where the target object generating the target track is located is changed or not based on the position of the target track in the target map; under the condition that the target object is not changed, judging whether the target track is an effective track or not based on the type of the area where the target object is located; and in the case of determining that the change occurs, judging whether the target track is an effective track or not based on the types before and after the change of the area where the target object is located.
In an optional embodiment, the determining module 66 may determine whether the target track is a valid track based on the type of the area where the target object is located by: judging whether the type of the area where the target object is located is at least one of the following preset types: forbidden region, undetectable region, shielded region; determining the target track to be an invalid track under the condition that the type of the area where the target object is located is determined to be at least one of the preset types; and when the type of the area where the target object is located is determined to be other types except the preset type, judging whether the preset characteristics of the target track meet preset conditions corresponding to the type of the target object, if so, determining that the target track is an effective track, and if not, determining that the target track is an invalid track.
In an alternative embodiment, the determining module 66 may determine whether the predetermined characteristic of the target trajectory satisfies a predetermined condition corresponding to the category of the target object by: judging whether the smoothness of the target track meets a preset smoothness threshold value; judging whether the range of the area where the target track is located meets a preset range threshold value or not; judging whether the fluctuation of the radar scattering cross section RCS of the target track meets a first preset fluctuation threshold value or not; judging whether the fluctuation of the radial speed of the target track meets a second preset fluctuation threshold value or not; and judging whether the number of the measuring points of the target track meets a preset number value or not.
In an optional embodiment, the determining module 66 may determine whether the target track is an effective track based on the type of the target object before and after the change of the area where the target object is located, as follows: judging whether the type of the target object before and after the change of the area meets at least one of the following preset conditions: the area where the target object is located is changed from a drivable area to a forbidden area, the area where the target object is located is changed from a drivable area to a non-detectable area, and the area where the target object is located is changed from a drivable area to a shielding area; when the judgment result is satisfied, judging whether the target track is an effective track or not based on the number of times of changing the type of the area where the target object is located; and when the judgment result is not satisfied, judging whether the target track is an effective track or not based on the measurement quality before and after the change of the area where the target object is located.
In an optional embodiment, the determining module 66 may determine whether the target track is a valid track based on the number of times of the change of the area type of the target object, as follows: when the number of times of changing the type of the area where the target object is located is determined to reach a preset number threshold, determining that the target track is an invalid track; and when the number of times of changing the type of the area where the target object is located is determined not to reach the preset time threshold value, performing first adjustment on preset conditions corresponding to the type of the target object, and determining whether the target track is an effective track by judging whether preset characteristics of the target track meet the adjusted preset conditions.
In an optional embodiment, the determining module 66 may determine whether the target track is an effective track based on the measurement quality before and after the change of the area where the target object is located by: when the measurement quality of the area where the target object is located is determined to be lower than the measurement quality before the change, performing first adjustment on a preset condition corresponding to the category of the target object, when the preset characteristic of the target track is determined to meet the preset condition after the adjustment, determining the target track to be an effective track, and when the preset characteristic of the target track is determined not to meet the preset condition after the adjustment, determining the target track to be an invalid track; and when the changed measurement quality of the area where the target object is located is determined to be higher than the measurement quality before the change, performing second adjustment on a preset condition corresponding to the category of the target object, when the preset characteristic of the target track is determined to meet the preset condition after the adjustment, determining the target track to be an effective track, and when the preset characteristic of the target track is determined not to meet the preset condition after the adjustment, determining the target track to be an invalid track.
In an alternative embodiment, the determining module 66 may perform the first adjustment on the predetermined condition corresponding to the category of the target object by: and increasing the condition threshold corresponding to the preset condition.
In an alternative embodiment, the determining module 66 may perform the second adjustment on the predetermined condition corresponding to the category of the target object by: and reducing the condition threshold corresponding to the preset condition.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.
Embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, where the computer program is arranged to, when executed, perform the steps in any of the above-mentioned method embodiments.
Optionally, in this embodiment, the computer-readable storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.
The scheme in the embodiment can be suitable for various environments such as an open environment (such as an airport), a complex environment (such as a park, a road, a gate and a garden) and the like, and has strong adaptability; when the specific processing is carried out, the map information is used, the accuracy of judging the false track is high, and the real-time performance of terminating the target track is high; in addition, the embodiment of the invention can be suitable for judging the tracks of pedestrians and vehicles, and allows multi-thread parallel calculation during calculation.
It will be apparent to those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and alternatively, they may be implemented in program code that is executable by a computing device, such that it may be stored in a memory device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that shown or described herein, or separately fabricated into individual integrated circuit modules, or multiple ones of them fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the principle of the present invention shall be included in the protection scope of the present invention.
Claims (12)
1. A method for processing a target track, comprising:
inputting a target track in a target map;
determining a location of the target trajectory in the target map;
judging whether the target track is an effective track or not based on the position of the target track in the target map;
and when the target track is determined to be an effective track, the target track is reserved, and/or when the target track is determined to be an ineffective track, the target track is deleted.
2. The method of claim 1, wherein determining whether the target trajectory is a valid trajectory based on the position of the target trajectory in the target map comprises:
judging whether the type of the area where the target object generating the target track is located is changed or not based on the position of the target track in the target map;
under the condition that the target object is determined not to be changed, judging whether the target track is an effective track or not based on the type of the area where the target object is located;
and under the condition that the change is determined, judging whether the target track is an effective track or not based on the types before and after the change of the area where the target object is located.
3. The method of claim 2, wherein determining whether the target track is an effective track based on the type of the area where the target object is located comprises:
judging whether the type of the area where the target object is located is at least one of the following preset types: forbidden region, undetectable region, shielded region;
determining the target track as an invalid track under the condition that the type of the area where the target object is located is determined to be at least one of the preset types;
and when the type of the area where the target object is located is determined to be other than the preset type, judging whether the preset characteristic of the target track meets a preset condition corresponding to the type of the target object, if so, determining that the target track is an effective track, and if not, determining that the target track is an invalid track.
4. The method of claim 3, wherein determining whether the predetermined characteristic of the target trajectory satisfies a predetermined condition corresponding to the category of the target object comprises:
judging whether the smoothness of the target track meets a preset smoothness threshold value;
judging whether the range of the area where the target track is located meets a preset range threshold value or not;
judging whether the volatility of the radar scattering cross section RCS of the target track meets a first preset fluctuation threshold value or not;
judging whether the fluctuation of the radial speed of the target track meets a second preset fluctuation threshold value or not; and the number of the first and second groups,
and judging whether the number of the measuring points of the target track meets a preset number value or not.
5. The method of claim 2, wherein determining whether the target track is an effective track based on the type of the target object before and after the change of the area comprises:
judging whether the type of the target object before and after the change of the area meets at least one of the following preset conditions: the area where the target object is located is changed from a drivable area to a non-drivable area, the area where the target object is located is changed from the drivable area to a non-detectable area, and the area where the target object is located is changed from the drivable area to a shielding area;
when the judgment result is satisfied, judging whether the target track is an effective track or not based on the number of times of changing the type of the area where the target object is located;
and when the judgment result is not satisfied, judging whether the target track is an effective track or not based on the measurement quality before and after the change of the area where the target object is located.
6. The method of claim 5, wherein determining whether the target track is a valid track based on the number of times the type of the area where the target object is located is changed comprises:
when the number of times of changing the type of the area where the target object is located is determined to reach a preset number threshold, determining that the target track is an invalid track;
and when the change frequency of the type of the area where the target object is located is determined not to reach the preset frequency threshold value, performing first adjustment on preset conditions corresponding to the type of the target object, and determining whether the target track is an effective track by judging whether preset characteristics of the target track meet the adjusted preset conditions.
7. The method of claim 5, wherein determining whether the target trajectory is an effective trajectory based on the quality of measurements before and after the change of the area in which the target object is located comprises:
when the measurement quality of the area where the target object is located is determined to be lower than the measurement quality before the change, performing first adjustment on a preset condition corresponding to the category of the target object, when the preset characteristic of the target track is determined to meet the preset condition after the adjustment, determining the target track to be an effective track, and when the preset characteristic of the target track is determined not to meet the preset condition after the adjustment, determining the target track to be an invalid track;
and when the measurement quality of the area where the target object is located is determined to be higher than the measurement quality before the change, performing second adjustment on a preset condition corresponding to the category of the target object, when the preset characteristic of the target track is determined to meet the preset condition after the adjustment, determining the target track to be an effective track, and when the preset characteristic of the target track is determined not to meet the preset condition after the adjustment, determining the target track to be an invalid track.
8. The method of claim 6 or 7, wherein first adjusting the predetermined condition corresponding to the category of the target object comprises:
and increasing the condition threshold corresponding to the preset condition.
9. The method of claim 7, wherein second adjusting the predetermined condition corresponding to the category of the target object comprises:
and reducing the condition threshold corresponding to the preset condition.
10. An apparatus for processing a target trajectory, comprising:
the input module is used for inputting a target track in a target map;
a determination module for determining a location of the target trajectory in the target map;
the judging module is used for judging whether the target track is an effective track or not based on the position of the target track in the target map;
and the processing module is used for reserving the target track when the target track is determined to be an effective track, and/or deleting the target track when the target track is determined to be an ineffective track.
11. A computer-readable storage medium, in which a computer program is stored, wherein the computer program is arranged to perform the method of any of claims 1 to 9 when executed.
12. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and wherein the processor is arranged to execute the computer program to perform the method of any of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911311545.3A CN111274336B (en) | 2019-12-18 | 2019-12-18 | Target track processing method and device, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911311545.3A CN111274336B (en) | 2019-12-18 | 2019-12-18 | Target track processing method and device, storage medium and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111274336A true CN111274336A (en) | 2020-06-12 |
| CN111274336B CN111274336B (en) | 2023-05-09 |
Family
ID=70998706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911311545.3A Active CN111274336B (en) | 2019-12-18 | 2019-12-18 | Target track processing method and device, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111274336B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111896941A (en) * | 2020-06-15 | 2020-11-06 | 浙江大华技术股份有限公司 | Target track determination method and device for radar data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017185688A1 (en) * | 2016-04-26 | 2017-11-02 | 深圳大学 | Method and apparatus for tracking on-line target |
| CN107516321A (en) * | 2017-07-04 | 2017-12-26 | 深圳大学 | A kind of video multi-target tracking and device |
| CN108344992A (en) * | 2017-12-20 | 2018-07-31 | 北京华航无线电测量研究所 | A kind of multi-object tracking method for vehicle-mounted millimeter wave radar |
| WO2019019943A1 (en) * | 2017-07-28 | 2019-01-31 | 阿里巴巴集团控股有限公司 | Method for tracing track of target in cross regions, and data processing method, apparatus and system |
| CN109446662A (en) * | 2018-10-31 | 2019-03-08 | 百度在线网络技术（北京）有限公司 | Generation method and device, the computer equipment and storage medium of vehicle simulation track |
| CN109829405A (en) * | 2019-01-22 | 2019-05-31 | 深圳大学 | Data correlation method, device and the storage medium of video object |
-
2019
- 2019-12-18 CN CN201911311545.3A patent/CN111274336B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017185688A1 (en) * | 2016-04-26 | 2017-11-02 | 深圳大学 | Method and apparatus for tracking on-line target |
| CN107516321A (en) * | 2017-07-04 | 2017-12-26 | 深圳大学 | A kind of video multi-target tracking and device |
| WO2019019943A1 (en) * | 2017-07-28 | 2019-01-31 | 阿里巴巴集团控股有限公司 | Method for tracing track of target in cross regions, and data processing method, apparatus and system |
| CN108344992A (en) * | 2017-12-20 | 2018-07-31 | 北京华航无线电测量研究所 | A kind of multi-object tracking method for vehicle-mounted millimeter wave radar |
| CN109446662A (en) * | 2018-10-31 | 2019-03-08 | 百度在线网络技术（北京）有限公司 | Generation method and device, the computer equipment and storage medium of vehicle simulation track |
| CN109829405A (en) * | 2019-01-22 | 2019-05-31 | 深圳大学 | Data correlation method, device and the storage medium of video object |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111896941A (en) * | 2020-06-15 | 2020-11-06 | 浙江大华技术股份有限公司 | Target track determination method and device for radar data |
| CN111896941B (en) * | 2020-06-15 | 2023-06-13 | 浙江大华技术股份有限公司 | Target track determination method and device for radar data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111274336B (en) | 2023-05-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018177026A1 (en) | Device and method for determining road edge | |
| US9086484B2 (en) | Context-based target recognition | |
| CN108279671B (en) | Terahertz-based environment sensing method and device and computer readable storage medium | |
| CN110456321B (en) | Method for filtering false alarm of radar, terminal equipment and storage medium | |
| CN110940979A (en) | Obstacle detection method, apparatus, device, and storage medium | |
| CN109377694B (en) | Monitoring method and system for community vehicles | |
| EP4020428A1 (en) | Method and apparatus for recognizing lane, and computing device | |
| CN114037966A (en) | High-precision map feature extraction method, device, medium and electronic equipment | |
| CN111929672A (en) | Method and device for determining movement track, storage medium and electronic device | |
| CN113255444A (en) | Training method of image recognition model, image recognition method and device | |
| CN112447060A (en) | Method and device for recognizing lane and computing equipment | |
| CN111324686B (en) | Target measurement track acquisition method and device, storage medium and electronic device | |
| Qing et al. | A novel particle filter implementation for a multiple-vehicle detection and tracking system using tail light segmentation | |
| CN111274336A (en) | Target track processing method and device, storage medium and electronic device | |
| CN111429791B (en) | Identity determination method, identity determination device, storage medium and electronic device | |
| DE102021212632A1 (en) | Testing of the environment sensors and/or environment perception of a vehicle | |
| CN112818780A (en) | Defense area setting method and device for aircraft monitoring and identifying system | |
| CN112634610A (en) | Natural driving data acquisition method and device, electronic equipment and storage medium | |
| CN111479217B (en) | Method and system for positioning unmanned vehicle in tunnel and electronic equipment | |
| Subash | Automatic road extraction from satellite images using extended Kalman filtering and efficient particle filtering | |
| Jiang et al. | Research on the human vehicle recognition system based on deep learning fusion remove haze algorithm | |
| Tian | Identification of Weather Conditions Related to Roadside LiDAR Data | |
| CN117710417A (en) | Multi-path multi-target tracking method and equipment for single-camera and readable storage medium | |
| CN115327539A (en) | Road guardrail detection method and device | |
| CN116363870A (en) | Target fusion method, device, terminal and storage medium based on radar |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |