Mobile object detection device, mobile object detection method, program, and storage medium
The system addresses the challenge of detecting moving objects behind obstacles by analyzing electromagnetic wave reflections at multiple timings, enabling accurate tracking through data acquisition, analysis, and processing units.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- PIONEER IP
- Filing Date
- 2025-03-24
- Publication Date
- 2026-04-23
AI Technical Summary
Existing methods for detecting moving objects using electromagnetic wave reflection fail to detect objects that move behind obstacles, creating non-measurement areas where reflected waves cannot be obtained.
A system that analyzes three-dimensional distributions of electromagnetic wave reflection points at multiple timings, identifies non-measurement areas, and uses non-measurement region identification to detect moving objects, and includes measurement data acquisition, analysis, and processing units to identify and display the position of moving objects in non-measurement areas.
Enables detection of moving objects in non-measurement areas by analyzing changes in reflection point distributions over time, allowing accurate tracking of objects that move behind obstacles.
Smart Images

Figure 0007850841000001 
Figure 0007850841000002 
Figure 0007850841000003
Abstract
Description
Technical Field
[0001] The present invention relates to a moving object detection device, a moving object detection method, a program, and a storage medium.
Background Art
[0002] In recent years, while irradiating electromagnetic waves such as light, the reflected waves of the electromagnetic waves are analyzed to detect objects, people, etc. This method is often used to assist in the automatic driving of vehicles, for example, as described in Patent Document 1.
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] When detecting a moving object such as a person by analyzing the reflected wave of an electromagnetic wave, if the moving object moves to the back side of the object, the reflected wave caused by the moving object cannot be obtained, and thus the moving object cannot be detected.
[0005] An example of the problem to be solved by the present invention is to detect that a moving object has moved to the back side of an object.
Means for Solving the Problems
[0006] The invention according to claim 1 is generated by analyzing the reflected wave of the electromagnetic wave irradiated to the target area, and includes first measurement data indicating a three-dimensional distribution of the reflection points of the electromagnetic wave at a first timing, and second measurement data indicating a three-dimensional distribution of the reflection points of the electromagnetic wave at a second timing after the first timing. A measurement data acquisition unit for acquiring the data; A measurement data analysis unit that processes the first measurement data to generate first analysis data that allows the position of a moving object to be identified when the moving object is in the target area at a first timing, and processes the second measurement data to generate second analysis data that allows the position of a moving object to be identified when the moving object is in the target area at a second timing, A non-measurement area processing unit detects a moving object that is estimated to be located in the non-measurement area at the second timing, using non-measurement area identification information that can identify a non-measurement area which is a region within the target area to which the electromagnetic waves are not expected to reach, the first analysis data, and the second analysis data. This is a mobile object detection device equipped with [a specific feature / feature].
[0007] The invention described in claim 8 is a computer that, By analyzing the reflected waves of electromagnetic waves irradiated onto the target region, first measurement data showing the three-dimensional distribution of the reflection points of the electromagnetic waves at a first timing is obtained, and second measurement data showing the three-dimensional distribution of the reflection points of the electromagnetic waves at a second timing which is after the first timing. By processing the first measurement data, first analysis data is generated that allows the position of a moving object to be identified when the moving object is in the target area at the first timing, and by processing the second measurement data, second analysis data is generated that allows the position of a moving object to be identified when the moving object is in the target area at the second timing. This is a method for detecting a moving object that is estimated to be located in the non-measurement region at a second timing, using non-measurement region identification information that can identify a non-measurement region which is a region within the target area to which the electromagnetic waves are not expected to reach, the first analysis data, and the second analysis data.
[0008] The invention described in claim 9 relates to a computer, The system has a function to acquire first measurement data, which is generated by analyzing the reflected waves of electromagnetic waves irradiated onto a target region and shows the three-dimensional distribution of the reflection points of the electromagnetic waves at a first timing, and second measurement data, which shows the three-dimensional distribution of the reflection points of the electromagnetic waves at a second timing that is after the first timing. The system has a function to generate first analysis data that allows the position of a moving object to be identified when the moving object is in the target area at a first timing by processing the first measurement data, and a function to generate second analysis data that allows the position of a moving object to be identified when the moving object is in the target area at a second timing by processing the second measurement data, A function to detect a moving object that is estimated to be located in the non-measurement region at the second timing, using non-measurement region identification information that can identify the non-measurement region which is the region within the target area to which the electromagnetic waves are not expected to reach, the first analysis data, and the second analysis data, This is a program that gives it a function. The invention described in claim 10 is a storage medium that stores the above-mentioned program. [Brief explanation of the drawing]
[0009] [Figure 1] This is a diagram illustrating the operating environment of the moving object detection device according to the embodiment. [Figure 2] This figure shows an example of the functional configuration of a moving object detection device. [Figure 3] This figure shows an example of the hardware configuration of a mobile object detection device. [Figure 4] This is a flowchart illustrating an example of the processing performed by a moving object detection device. [Figure 5] This diagram illustrates the processing performed by the non-measurement area processing unit. [Modes for carrying out the invention]
[0010] Embodiments of the present invention will be described below with reference to the drawings. In all drawings, similar components are denoted by the same reference numerals, and their descriptions are omitted as appropriate.
[0011] Figure 1 is a diagram illustrating the operating environment of the moving object detection device 20 according to the embodiment. The moving object detection device 20 is a device that processes the analysis data generated by the reflection data generation device 10.
[0012] The reflection data generation device 10 is, for example, a LiDAR (Light Detection and Ranging) and has an electromagnetic wave irradiation unit, a receiving unit, and an analysis unit. The irradiation unit irradiates electromagnetic waves (for example, infrared or near-infrared (for example, with a wavelength of 905 nm)) while scanning. However, if the reflection data generation device 10 is a so-called 3D flash LiDAR, the irradiation unit does not scan when irradiating electromagnetic waves. The receiving unit receives the reflected waves of the electromagnetic waves irradiated by the irradiation unit. The analysis unit generates data showing the three-dimensional distribution of reflection points (hereinafter referred to as measurement data) using the irradiation direction and irradiation timing of the electromagnetic waves by the irradiation unit and the reception timing of the reflected waves by the receiving unit. This measurement data shows the distance from the receiving unit of the reflection data generation device 10 to the reflection point for each direction of electromagnetic wave irradiation. This measurement data also includes data showing the intensity of the reflected waves for each direction of electromagnetic wave irradiation.
[0013] In this embodiment, the reflection data generation device 10 is fixed to a stationary object. Therefore, the range in which the reflection data generation device 10 can scan electromagnetic waves does not change. Consequently, if there is no change in the target area scanned by the electromagnetic waves, neither the three-dimensional distribution of reflection points nor the intensity of the reflected waves from each of the multiple reflection points will change.
[0014] The reflection data generation device 10 uses, for example, the interior of a facility (for example, the interior of a building) as the target area for electromagnetic wave irradiation. In this case, the reflection data generation device 10 is fixed to the wall or ceiling of the facility. The reflection data generation device 10 then outputs the generated measurement data to the moving object detection device 20.
[0015] Incidentally, the reflection data generation device 10 may output data indicating the irradiation direction and irradiation timing of the electromagnetic wave by the irradiation unit, as well as the reception timing of the reflected wave by the reception unit, to the moving body detection device 20. In this case, the moving body detection device 20 generates the above-described measurement data by processing the data acquired from the reflection data generation device 10. Note that the data output from the reflection data generation device 10 to the moving body detection device 20 may include the intensity of each reflected wave.
[0016] The reflection data generation device 10 irradiates the target area with repeated electromagnetic waves. And each time the reflection data generation device 10 irradiates the electromagnetic wave, it generates measurement data.
[0017] Then, the moving body detection device 20 detects the moving body 40 existing in the target area by processing the above-described measurement data. Here, when an object 30 (for example, a shelf, a desk, and a partition, etc.) is installed in the target area, the electromagnetic wave does not reach the area located behind the object 30 as viewed from the reflection data generation device 10, that is, the area hidden by the object 30 (hereinafter, referred to as a non-measurement area). Therefore, if the moving body 40 moves to the non-measurement area, the reflected wave from the moving body 40 cannot be obtained. In contrast, the moving body detection device 20 estimates that the moving body 40 is located in the non-measurement area by processing the measurement data. Note that the non-measurement area can also be said to be an area in the target area where it is estimated that the electromagnetic wave does not reach.
[0018] FIG. 2 is a diagram showing an example of the functional configuration of the moving body detection device 20. The moving body detection device 20 shown in this figure has a measurement data acquisition unit 210, a measurement data analysis unit 220, and a non-measurement area processing unit 230.
[0019] The measurement data acquisition unit 210 acquires the measurement data generated by the reflection data generation device 10. As described above, the reflection data generation device 10 repeatedly generates measurement data. And the measurement data acquisition unit 210 acquires these multiple measurement data.
[0020] The measurement data analysis unit 220 generates analysis data by analyzing the measurement data acquired by the measurement data acquisition unit 210. The analysis data is data that allows the position of a moving object to be identified when a moving object is present in the target area, for example, data indicating the position of a moving object 40 present in the target area. The measurement data analysis unit 220 generates one analysis data for each measurement data. Hereinafter, the analysis data corresponding to the measurement data generated at the first timing (first measurement data) will be referred to as the first analysis data, and the analysis data corresponding to the measurement data generated at the second timing, which is later than the first timing (second measurement data), will be referred to as the second analysis data.
[0021] The non-measurement area processing unit 230 uses the non-measurement area identification information, first analysis data, and second analysis data that can identify the non-measurement area to detect a moving object that is estimated to be located in the non-measurement area at the second timing. Details of the processing performed by the non-measurement area processing unit 230 will be described later with reference to other figures.
[0022] The non-measurement area identification information is stored in the data storage unit 212. The non-measurement area identification information may be three-dimensional information indicating the location of the non-measurement area, or two-dimensional information indicating the location of the non-measurement area in a top view (plan view). The non-measurement area identification information may be generated by analyzing measurement data, or by processing building design drawings or layout drawings. The non-measurement area information may also be data showing the three-dimensional distribution of reflection points caused by the object 30 (i.e., data showing the location and shape of the object 30). If there are multiple non-measurement areas, the data storage unit 212 stores multiple non-measurement area identification information. The data storage unit 212 may also store other data, such as measurement data generated by the reflection data generation device 10 or analysis data generated by the moving object detection device 20.
[0023] Furthermore, the data storage unit 212 stores data necessary for detecting the moving object 40, such as measurement data (hereinafter referred to as reference data) generated by the reflection data generation device 10 when object 30 is present but the moving object 40 is not. As described above, the reflection data generation device 10 is fixed to a stationary object. Therefore, if there is no change in the target area scanned by the electromagnetic wave, the three-dimensional distribution of reflection points and the intensity of the reflected waves at each of the multiple reflection points do not change. Accordingly, the non-measurement area processing unit 230 can identify the presence or absence of the moving object 40 and its position by detecting the difference between the measurement data and the reference data. This difference, for example, represents the three-dimensional distribution of reflection points corresponding to the moving object 40.
[0024] In the example shown in this figure, the data storage unit 212 is part of the moving object detection device 20. However, the data storage unit 212 may be located outside the moving object detection device 20.
[0025] Figure 3 shows an example of the hardware configuration of the mobile object detection device 20. The mobile object detection device 20 includes a bus 1010, a processor 1020, a memory 1030, a storage device 1040, an input / output interface 1050, and a network interface 1060.
[0026] Bus 1010 is a data transmission path for the processor 1020, memory 1030, storage device 1040, input / output interface 1050, and network interface 1060 to send and receive data to and from each other. However, the method of connecting the processor 1020 and the other components to each other is not limited to bus connection.
[0027] Processor 1020 is a processor implemented in components such as the CPU (Central Processing Unit) and GPU (Graphics Processing Unit).
[0028] Memory 1030 is a main memory device implemented using RAM (Random Access Memory), etc.
[0029] The storage device 1040 is an auxiliary storage device implemented as an HDD (Hard Disk Drive), SSD (Solid State Drive), memory card, or ROM (Read Only Memory). The storage device 1040 stores program modules that implement each function of the moving object detection device 20 (for example, the measurement data acquisition unit 210, the measurement data analysis unit 220, and the non-measurement area processing unit 230). The processor 1020 reads these program modules into the memory 1030 and executes them, thereby realizing each function corresponding to the program module. The storage device 1040 also functions as a data storage unit 212.
[0030] The input / output interface 1050 is an interface for connecting the moving object detection device 20 with various input / output devices (for example, the reflection data generation device 10).
[0031] The network interface 1060 is an interface for connecting the mobile object detection device 20 to a network. This network may be, for example, a LAN (Local Area Network) or a WAN (Wide Area Network). The network interface 1060 may connect to the network via a wireless connection or a wired connection. The mobile object detection device 20 may also be connected to the reflection data generation device 10 via the network interface 1060.
[0032] Figure 4 is a flowchart illustrating an example of the processing performed by the moving object detection device 20. First, the non-measurement area processing unit 230 of the moving object detection device 20 reads non-measurement area identification information and reference data from the data storage unit 212 (step S10). Next, the measurement data acquisition unit 210, the measurement data analysis unit 220, and the non-measurement area processing unit 230 repeatedly perform the processing shown in steps S20 to S60. In the flowchart shown in this figure, the data storage unit 212 stores the analysis data generated up to that point, i.e., data indicating the position of the moving object 40 present in the target area, as a result of the processing shown in step S60. This data shows the three-dimensional distribution of reflection points corresponding to the moving object 40.
[0033] As described above, the reflection data generation device 10 generates measurement data by repeatedly irradiating the target area with electromagnetic waves. The measurement data acquisition unit 210 of the moving object detection device 20 repeatedly acquires the measurement data generated by the reflection data generation device 10 (step S20). Next, the measurement data analysis unit 220 generates analysis data (second analysis data) using the measurement data acquired in step S20 and the reference data acquired in step S10. As described above, this analysis data indicates the presence or absence of the moving object 40, and if the moving object 40 is present, it also indicates the position of the moving object 40. For example, the measurement data analysis unit 220 identifies the three-dimensional distribution of reflection points corresponding to the moving object 40, and uses the data showing the identified three-dimensional distribution as analysis data (step S30).
[0034] Next, the non-measurement area processing unit 230 determines whether or not there is a moving object 40 located in the non-measurement area (step S40). Details of this process will be described later with reference to Figure 5. The non-measurement area processing unit 230 then generates display data indicating the position of the moving object 40 and displays this display data on the display device. For example, the non-measurement area processing unit 230 displays the reflection point corresponding to the moving object 40 in a different manner from other reflection points. An example of a "different manner" here is to make at least one of the following different: color, shape, and size. The three-dimensional distribution of the reflection points displayed in a different manner indicates the three-dimensional shape of the object that caused the reflection point. Therefore, a user of the reflection data generation device 10 can recognize the three-dimensional shape of the object by looking at the data displayed by the non-measurement area processing unit 230.
[0035] The non-measurement area processing unit 230 may also use data obtained by processing the three-dimensional distribution of reflection points corresponding to the selected irradiation direction as display data. For example, the non-measurement area processing unit 230 may estimate the shape of the object using the three-dimensional distribution of reflection points and display a diagram showing that shape together with / or instead of the three-dimensional distribution of reflection points.
[0036] Next, the measurement data analysis unit 220 stores the analysis data generated in the data storage unit 212, and the non-measurement area processing unit 230 stores in the data storage unit 212 information about the moving object 40 detected by the non-measurement area processing unit 230, for example, information indicating that the moving object 40 is located in the non-measurement area at the second timing (step S60).
[0037] Figure 5 is a diagram illustrating the processing performed by the non-measurement area processing unit 230. As described above, the data storage unit 212 stores non-measurement area identification information and previously generated analysis data. The non-measurement area processing unit 230 reads the non-measurement area identification information from the data storage unit 212, and also reads the analysis data (first analysis data) based on measurement data (first measurement data) generated before the measurement data (second measurement data) that is currently being processed, from the data storage unit 212. As shown in Figure 5(A), it is assumed that the moving object 40 was detected in the first analysis data. The unit then determines whether the distance between the non-measurement area indicated by the non-measurement area identification information (the area hidden by object 30 in the figure) and the moving object 40 is within the first reference distance. As described above, if the non-measurement area identification information is 3D or 2D information of the non-measurement area, the non-measurement area processing unit 230 calculates the distance between the moving object 40 and the part of the non-measurement area closest to the moving object 40 (i.e., the shortest distance between the moving object 40 and the non-measurement area). Here, instead of the distance between the moving object 40 and the non-measured area, the distance between the moving object 40 and the object 30 may be used. In this case, this distance is calculated using the position of the reflection point corresponding to the moving object 40 and the position of the reflection point corresponding to the object 30. The first reference distance is set based on the distance that the moving object 40 can move in the time between the generation of the first measurement data and the generation of the second measurement data. If the distance between the moving object 40 and the non-measured area is within the first reference distance, there is a possibility that the moving object 40 detected in the first analysis data has moved to the back side of the object 30, i.e., the non-measured area, by the time the second measurement data is generated.
[0038] Then, as shown in Figure 5(B), if at least a portion of the moving body 40 is not detected in the second analysis data generated this time, the non-measurement area processing unit 230 estimates that at least a portion of the moving body 40 is located in the non-measurement area at this time (second timing).
[0039] Here, the measurement data generated by the reflection data generation device 10 also shows the distance to each reflection point. Therefore, the non-measurement area processing unit 230 can determine whether the reflection point corresponding to the moving body 40 is farther away than the reflection point corresponding to the object 30. Thus, the non-measurement area processing unit 230 may use the fact that the reflection point caused by the moving body 40 is farther away than the reflection point caused by the object 30 (i.e., the cause of the non-measurement area) as a necessary condition for estimating that at least a part of the moving body 40 is located in the non-measurement area at the second timing.
[0040] Subsequently, as shown in Figure 5(C), the measurement data acquisition unit 210 acquires third measurement data showing the three-dimensional distribution of the reflection points at the third timing, which is after the second timing. The measurement data analysis unit 220 then processes the three measurement data to generate analysis data (third analysis data) for the third timing. The non-measurement area processing unit 230 estimates that the moving object 40 is located in the non-measurement area at the second timing, and if the moving object 40 is detected within the second reference distance from the non-measurement area at the third timing, it estimates that the moving object 40, which was located in the non-measurement area at the second timing, has moved out of the non-measurement area at the third timing. This estimation result means that the moving object 40 detected at the first timing and the moving object 40 detected at the third timing are the same. The non-measurement area processing unit 230 then includes information indicating this estimation result in the display data.
[0041] Here, the second reference distance is set based on the distance the moving object 40 can travel in the time between the generation of the second measurement data and the generation of the third measurement data. Therefore, if the time between the generation of the first measurement data and the generation of the second measurement data is equal to the time between the generation of the second measurement data and the generation of the third measurement data, the second reference distance may be the same value as the first reference distance. Also, the moving object 40 detected at the first timing and the moving object 40 detected at the third timing may be located on the same side of the object 30 or on opposite sides.
[0042] In this way, the non-measurement area processing unit 230 can estimate that a moving object 40 is hidden in a non-measurement area. Furthermore, if there are multiple non-measurement areas, it can also identify the non-measurement area in which the moving object 40 is hidden. In addition, the non-measurement area processing unit 230 can estimate the number of moving objects 40 present in a non-measurement area by incrementing the counter by one when it estimates that a new moving object 40 has entered a non-measurement area, and conversely, by decrementing the counter by one when it estimates that a moving object 40 has left a non-measurement area.
[0043] Furthermore, the intensity of the reflected wave changes depending on the surface condition of the reflection point (for example, clothing if the moving object 40 is a person). For this reason, the non-measurement area processing unit 230 may use as a necessary condition for estimating that the moving object 40, which was located in the non-measurement area at the second timing, has moved out of the non-measurement area at the third timing, if the difference between the intensity of the reflected wave at the reflection point corresponding to the moving object 40 in the first measurement data and the intensity of the reflected wave at the reflection point corresponding to the moving object 40 in the third measurement data is below a certain standard.
[0044] Conversely, if the reflection data generation device 10 is installed in a clothing store and the moving object 40 is a person, the moving object 40 may wear clothing as merchandise in the shadow of the object 30. In such a case, the non-measurement area processing unit 230 may perform a warning process if the difference between the intensity of the reflected wave at the reflection point corresponding to the moving object 40 in the second measurement data and the intensity of the reflected wave at the reflection point corresponding to the moving object 40 in the third measurement data exceeds a certain standard. One example of this warning process is to have the display device show a predetermined message and output a predetermined sound from the speaker.
[0045] Furthermore, if the reflection data generation device 10 is installed in the store and the moving object 40 is a person, there is a possibility that the moving object 40 may take the product from behind the object 30. In such a case, the non-measurement area processing unit 230 may issue a warning if the difference between the shape of the moving object 40 identified by the second analysis data and the shape of the moving object 40 identified by the third analysis data exceeds a certain standard. An example of this warning process is as described above.
[0046] As described above, according to this embodiment, the non-measurement area processing unit 230 of the moving object detection device 20 uses non-measurement area identification information that can identify the non-measurement area, first analysis data generated at the first timing, and second analysis data generated at the second timing to detect a moving object 40 that is estimated to be located in the non-measurement area at the second timing. For example, if the moving object 40 is detected within a first reference distance from the non-measurement area in the first analysis data, and at least a part of the moving object 40 is not detected in the second analysis data, the non-measurement area processing unit 230 estimates that at least a part of the moving object 40 is located in the non-measurement area at the second timing. Therefore, it is possible to detect that the moving object 40 has moved to the back side of the object 30, i.e., to the non-measurement area.
[0047] The embodiments and examples described above with reference to the drawings are illustrative examples of the present invention, and various other configurations can also be adopted. [Explanation of Symbols]
[0048] 10 Reflection data generation device 20 Mobile object detection device 30 Object 40 Mobile Units 210 Measurement data acquisition unit 212 Data Storage Unit 220 Measurement Data Analysis Department 230 Non-measurement area processing unit
Claims
1. A measurement data acquisition unit that acquires first measurement data showing the three-dimensional distribution of the reflection points of the electromagnetic waves at a first timing, generated by analyzing the reflected waves of electromagnetic waves irradiated onto a target area, and second measurement data showing the three-dimensional distribution of the reflection points of the electromagnetic waves at a second timing which is after the first timing, A measurement data analysis unit that processes the first measurement data to generate first analysis data that allows the position of a moving object to be identified when the moving object is in the target area at the first timing, and processes the second measurement data to generate second analysis data that allows the position of a moving object to be identified when the moving object is in the target area at the second timing, The system includes a non-measurement area processing unit that uses non-measurement area identification information that can identify a non-measurement area which is an area within the target area to which the electromagnetic waves are not expected to reach, the first analysis data, and the second analysis data to detect a moving object that is estimated to be located in the non-measurement area at the second timing, The non-measurement area processing unit is a moving object detection device that estimates that at least a portion of the moving object is located in the non-measurement area at the second timing if, in the first analysis data, a moving object is detected within a first reference distance from the non-measurement area, and in the second analysis data, at least a portion of the moving object is not detected.
2. In the moving object detection device according to Claim 1, The non-measurement area processing unit is a moving object detection device that estimates that at least a part of the moving object is located in the non-measurement area at the second timing when the moving object is located far from the reflection point that causes the generation of the non-measurement area, with respect to the receiving unit that receives the reflected wave as the starting point in the first analysis data.
3. In the moving object detection device according to claim 1 or 2, The measurement data acquisition unit acquires third measurement data showing the three-dimensional distribution of the reflection point at a third timing which is after the second timing. The measurement data analysis unit processes the third measurement data to generate third analysis data that allows for the identification of the position of a moving object when the moving object is present in the target area at the third timing. The non-measurement area processing unit estimates that the moving body is located in the non-measurement area at the second timing, and when the moving body is detected within a second reference distance from the non-measurement area at the third timing, the moving body that was located in the non-measurement area at the second timing has moved out of the non-measurement area at the third timing.
4. In the moving object detection device according to claim 3, Both the first measurement data and the third measurement data include the intensity of the reflected wave from the moving body. The non-measurement area processing unit is a moving object detection device that estimates that the moving object, which was located in the non-measurement area at the second timing, has moved out of the non-measurement area at the third timing, when the difference between the intensity of the reflected wave from the moving object included in the first measurement data and the intensity of the reflected wave from the moving object included in the third measurement data is less than or equal to a standard.
5. In the moving object detection device according to claim 3, Both the first measurement data and the third measurement data include the intensity of the reflected wave from the moving body. The non-measurement area processing unit is a moving object detection device that performs a warning process when the difference between the intensity of the reflected wave from the moving object included in the first measurement data and the intensity of the reflected wave from the moving object included in the third measurement data is greater than or equal to a standard.
6. In the mobile object detection device according to any one of claims 3 to 5, The first analysis data and the third analysis data both include data that allows for the identification of the shape of the moving body. The non-measurement area processing unit is a moving object detection device that performs a warning process when the difference between the shape of the moving object identified by the first analysis data and the shape of the moving object identified by the third analysis data is greater than or equal to a standard.
7. Computers By analyzing the reflected waves of electromagnetic waves irradiated onto the target region, first measurement data showing the three-dimensional distribution of the reflection points of the electromagnetic waves at a first timing is obtained, and second measurement data showing the three-dimensional distribution of the reflection points of the electromagnetic waves at a second timing which is after the first timing. By processing the first measurement data, first analysis data is generated that allows the position of a moving object to be identified when the moving object is in the target area at the first timing, and by processing the second measurement data, second analysis data is generated that allows the position of a moving object to be identified when the moving object is in the target area at the second timing. Using non-measurement region identification information that can identify the non-measurement region which is the region within the target area to which the electromagnetic waves are not expected to reach, the first analysis data, and the second analysis data, a moving object that is estimated to be located in the non-measurement region at the second timing is detected. A method for detecting a moving object, wherein if a moving object is detected within a first reference distance from the non-measurement area in the first analysis data, and at least a portion of the moving object is not detected in the second analysis data, it is estimated that at least a portion of the moving object is located in the non-measurement area at the second timing.
8. On the computer, The system has a function to acquire first measurement data, which is generated by analyzing the reflected waves of electromagnetic waves irradiated onto a target region and shows the three-dimensional distribution of the reflection points of the electromagnetic waves at a first timing, and second measurement data, which shows the three-dimensional distribution of the reflection points of the electromagnetic waves at a second timing that is after the first timing. The system has a function to generate first analysis data that allows the position of a moving object to be identified when the moving object is in the target area at a first timing by processing the first measurement data, and a function to generate second analysis data that allows the position of a moving object to be identified when the moving object is in the target area at a second timing by processing the second measurement data, A function to detect a moving object that is estimated to be located in the non-measurement region at the second timing, using non-measurement region identification information that can identify the non-measurement region which is the region within the target area to which the electromagnetic waves are not expected to reach, the first analysis data, and the second analysis data, A program that has a function to estimate that at least a portion of the moving object is located in the non-measurement region at the second timing, if in the first analysis data a moving object is detected within a first reference distance from the non-measurement region, and in the second analysis data at least a portion of the moving object is not detected.
9. A storage medium for storing the program described in Claim 8.
Citation Information
Patent Citations
Parked vehicle detection method, detection system and parked vehicle detection apparatus
JP2004021496A
Object recognition device
JP2012123471A
Systems and Methods to Track Vehicles Proximate Perceived By an Autonomous Vehicle
US20180322650A1
Automatic driving assistance device, control method, program, and storage medium
WO2016152873A1
Object tracking method and object tracking device
WO2018003056A1