Person Detection Method and System Based on Point Cloud Data

Abstract

The present application discloses a personnel detection method based on point cloud data, which is applied to a system with a detection radar installed at the top of a detection space, and includes: obtaining the point cloud data of the radar; determining the activity information in at least part of the sub-spaces of the space according to the point cloud data of the radar, wherein there are multiple sub-spaces, and the sub-spaces are distributed in the space from top to bottom; when the activity information is detected in the sub-spaces in a specified combination manner, it is determined that there is a person. In this way, the accuracy of personnel detection can be increased.

Description

Technical Field

[0001] This application relates to object detection technology, in particular to a method and system for human detection based on point cloud data. Background Art

[0002] With the development of society and technology, higher requirements have been put forward for the safety of patients and the elderly in hospitals, nursing homes, etc. Falls often occur in private spaces such as restrooms. However, considering that it is not convenient to install devices such as cameras in private spaces like restrooms, relevant image recognition technologies cannot be used for detection. Although alarm devices are installed in restrooms, the premise is that the fallen person can touch the button. In some cases, this method is not reliable. In recent years, non-visual detection means such as radar have emerged to detect falls. Before performing relevant fall detection, it is first necessary to determine whether someone has entered. If there is no one in the space, there is no need to perform relevant fall detection determination. However, currently in the detection means, it is usually based on the radar reflection area to determine whether a moving object is a person. In fact, it is difficult for radar to distinguish the difference between a person and other larger animals, and it is easy to cause misjudgment. Summary of the Invention

[0003] The present invention aims to at least solve one of the technical problems existing in the prior art. For this reason, the present invention provides a method and system for human detection based on point cloud data, which can accurately determine whether someone has entered.

[0004] An embodiment of this application provides a method for human detection based on point cloud data, which is applied to a system with a detection radar installed on the top of a detection space, and includes:

[0005] Obtain the point cloud data of the radar;

[0006] According to the point cloud data of the radar, determine the activity information in at least some sub-spaces of the space, wherein there are multiple sub-spaces, and the sub-spaces are distributed from top to bottom in the space;

[0007] When the activity information is detected in the sub-spaces in a specified combination mode, it is determined that there is someone.

[0008] In some embodiments, the sub-spaces include a first space, a second space, a third space, and a fourth space that are distributed from top to bottom and do not intersect.

[0009] In some embodiments, the first space, the second space, the third space, and the fourth space have the same height.

[0010] In some embodiments, detecting the activity information in the sub-spaces in a specified combination mode includes that the first space, the second space, the third space, and the fourth space simultaneously detect the activity information, and the second space, the third space, and the fourth space simultaneously detect the activity information.

[0011] In some embodiments, determining the activity information in at least a partial subspace of the space specifically includes:

[0012] Determining the activity information in at least a partial subspace of the space;

[0013] Wherein, when the area of the point cloud data belonging to any subspace is greater than a preset value, it is determined that there is activity information in this subspace.

[0014] In some embodiments, the area of the point cloud data refers to the area of the projection of all the point clouds within the space on a horizontal plane.

[0015] In some embodiments, it further includes the following steps:

[0016] Setting the size of the preset value according to the input information of the user.

[0017] On the other hand, an embodiment of the present application provides a personnel detection system for point cloud data, including:

[0018] An acquisition unit, configured to acquire the point cloud data of a radar;

[0019] An activity determination unit, configured to determine the activity information in at least a partial subspace of the space according to the point cloud data of the radar, wherein there are multiple subspaces, and the subspaces are distributed in the space from top to bottom;

[0020] A determination unit, configured to determine that there is a person when activity information is detected in a subspace with a specified combination method. On the other hand, an embodiment of the present application provides a personnel detection system for point cloud data, including:

[0021] A memory, configured to store a program;

[0022] A processor, configured to load the program to execute the personnel detection method for the point cloud data.

[0023] In some embodiments, the detection radar uses a millimeter-wave radar.

[0024] In the embodiment of the present application, by acquiring the point cloud data of a radar, and then determining the activity information in at least a partial subspace of the space according to the point cloud data of the radar, wherein there are multiple subspaces, and the subspaces are distributed in the space from top to bottom, when activity information is detected in a subspace with a specified combination method, it is determined that there is a person; in this way, by using multiple subspaces distributed from top to bottom for activity detection, the difference between a person and an animal can be distinguished by taking advantage of the fact that the height of a person is greater than that of large animals such as birds or dogs, thereby reducing the possibility of misjudgment and improving the accuracy of system judgment. Description of the Drawings

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0026] Figure 1 is a flowchart of a personnel detection method based on cloud peak data provided by an embodiment of the present application;

[0027] Figure 2 is a schematic diagram of space division provided by an embodiment of the present application. Detailed implementation manners

[0028] To make the objectives, technical solutions and advantages of the present application clearer, the following will refer to the accompanying drawings in the embodiments of the present application and clearly and completely describe the technical solutions of the present application through the implementation manners. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0029] In the description of the present invention, the meaning of several is more than one, and the meaning of multiple is more than two. Understandings such as greater than, less than, exceeding, etc. do not include the present number, and understandings such as above, below, within, etc. include the present number. If there is a description of first and second, it is only for the purpose of distinguishing technical features and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features or implicitly indicating the sequence relationship of the indicated technical features.

[0030] In the description of the present invention, unless otherwise clearly defined, terms such as set should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific content of the technical solutions.

[0031] In the description of the present invention, the descriptions referring to terms such as "one embodiment", "some embodiments", "schematic embodiments", "examples", "specific examples", or "some examples", etc. mean that the specific features or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic descriptions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0032] Refer to Figure 1, An embodiment of the present application provides a method for detecting personnel based on point cloud data, which is applied to a system with a detection radar installed at the top of the detection space. Generally, a millimeter-wave radar is used as the detection radar. The millimeter-wave radar mainly scans the activity information in the space. The millimeter-wave radar can output point cloud data on the motion state of objects in the scanned area, including:

[0033] S1. Obtain the point cloud data of the radar. The millimeter-wave radar is a radar that operates in the millimeter-wave band for detection. The frequency band is generally 30 GHz to 300 GHz, and the wavelength is 1 to 10 mm, which is between microwave and centimeter wave, and has some advantages of both microwave radar and optoelectronic radar; the basic working principle of the millimeter-wave radar is to use a high-frequency circuit to generate electromagnetic waves with a specific modulation frequency (FMCW), and send electromagnetic waves through the antenna and receive the electromagnetic waves reflected from the target. It can simultaneously measure the distance, speed, and azimuth angle of multiple targets; the speed measurement is based on the Doppler effect, and the relative motion speed of the target with respect to the radar can be obtained by calculating the frequency change of the radar wave returned to the receiving antenna, etc., to obtain the distance of the target object. Accordingly, based on the detection data of the radar, the distance and speed of moving objects in the space can be detected. Through these, it can be determined whether there is activity information at certain positions irradiated by the radar in the space. And what the radar outputs is the point cloud generated by the motion. These point clouds contain position and distance information. Through these information, the number of point clouds at different distances can be determined. Thus, the action information appearing in different layers can be analyzed.

[0034] S2. According to the point cloud data of the radar, determine the activity information in at least some sub-spaces of the space, where there are multiple sub-spaces, and the sub-spaces are distributed in the space from top to bottom. Refer to Figure 2 , In one embodiment, the space can be evenly divided into 4 sub-spaces. The sub-spaces include a first space, a second space, a third space, and a fourth space that are distributed from top to bottom and do not intersect. The first space, the second space, the third space, and the fourth space have the same height. Generally, the floor height is about 2.5 meters to 3 meters. Assuming 2.7 meters is used as the floor height, for the four evenly divided sub-spaces, each is 0.675 meters. Generally, a person's height is greater than 1.35 meters. Therefore, when a person enters, activity information will be generated in at least the three lower sub-spaces. And if a large animal enters, although it will be confused with a person in terms of the activity area, neither a dog nor a flying bird can easily generate activity information in multiple spaces at the same time.

[0035] Accordingly, multiple sub-spaces can also be discontinuous, and they only need to be evenly distributed or distributed at a specific height. For example, the fourth space corresponds to the space at a height of 0.1 to 0.2 meters relative to the ground, the third space corresponds to the space at a height of 0.8 to 0.9 meters relative to the ground, the second space corresponds to the space at a height of 1.5 to 1.6 meters relative to the ground, and the first space corresponds to the space at a height of 2.2 to 2.3 meters relative to the ground. The division method of the sub-spaces only needs to mainly consider the average height of adults. The division method is not unique. The core is to detect whether there is activity in multiple sub-spaces in the vertical direction to determine whether there is a person.

[0036] S3. When activity information is detected in the sub-spaces of the specified combination mode, it is determined that there is a person.

[0037] Activity information is detected in the sub-spaces of the specified combination mode, including that activity information is detected simultaneously in the first space, the second space, the third space, and the fourth space, and activity information is detected simultaneously in the second space, the third space, and the fourth space. Of course, if it is desired to lower the accuracy rate, it can also be set that activity is detected simultaneously in the third space and the fourth space. Or activity information is detected simultaneously in the second space and the fourth space. In all cases, it can be determined that there is a person. Among them, it is more accurate to detect a person in three or more detection spaces.

[0038] In some embodiments, determining the activity information in at least some of the sub-spaces of the space specifically is:

[0039] Determine the activity information in at least some of the sub-spaces of the space. Some of the sub-spaces can select multiple sub-spaces to be judged in the manner of the previous embodiments.

[0040] Among them, when the area of the point cloud data belonging to any sub-space is greater than a preset value, it is determined that there is activity information in that sub-space. In connection with the prior art, it is also necessary to analyze whether there is activity information in a certain sub-space based on the area of the point cloud data. The area of the point cloud data refers to the area of the projection of all the point clouds in the space on the horizontal plane. Although the point cloud is composed of points, a certain area can be assigned to the point cloud, so that the projection area can be calculated. In addition, the size of the preset value can be set according to the input information of the user. Of course, the area of the point cloud data can also be determined by the number of point clouds in the space.

[0041] The embodiment of the present application provides a personnel detection system for point cloud data, including:

[0042] An acquisition unit, configured to acquire the point cloud data of the radar;

[0043] An activity determination unit, configured to determine the activity information in at least some of the sub-spaces of the space according to the point cloud data of the radar, where there are multiple sub-spaces, and the sub-spaces are distributed from top to bottom in the space;

[0044] A determination unit, configured to determine that there is a person when activity information is detected in a subspace with a specified combination mode.

[0045] An embodiment of the present application provides a personnel detection system for point cloud data, including:

[0046] A memory, configured to store programs;

[0047] A processor, configured to load the program to execute the personnel detection method for the point cloud data.

[0048] In the present application, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes.

[0049] Note that the above is only a preferred embodiment of the present application and the applied technical principle. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein. Various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present application. Therefore, although the present application has been described in detail through the above embodiments, the present application is not limited to the above embodiments. Without departing from the concept of the present application, it may include more other equivalent embodiments, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A method for detecting personnel based on point cloud data, characterized in that, Applied to a system with a detection radar installed at the top of a space, including: Obtain the point cloud data of the radar; Determine the activity information in at least part of the sub-spaces of the space according to the point cloud data of the radar, wherein there are multiple sub-spaces, and the sub-spaces are distributed in the space from top to bottom; When the activity information is detected in the sub-spaces in the specified combination mode, it is determined that there is a person; The sub-spaces include a first space, a second space, a third space, and a fourth space that are distributed from top to bottom and do not intersect; The detection of the activity information in the sub-spaces in the specified combination mode includes: the first space, the second space, the third space, and the fourth space simultaneously detect the activity information, or the second space, the third space, and the fourth space simultaneously detect the activity information.

2. The method for detecting a person based on point cloud data according to claim 1, wherein, The first space, the second space, the third space, and the fourth space have the same height.

3. The method for detecting a person based on point cloud data according to claim 1, wherein The determination of the activity information in at least part of the sub-spaces of the space is specifically: Determine the activity information in at least part of the sub-spaces of the space; Wherein, when the area of the point cloud data belonging to any sub-space is greater than a preset value, it is determined that there is activity information in this sub-space.

4. The method for detecting a person based on point cloud data according to claim 3, wherein, The area of the point cloud data refers to the area of the projection of all the point clouds in the space on the horizontal plane, or the area of the point cloud data is determined by the number of point clouds in the space.

5. The method for detecting a person based on point cloud data according to claim 3, wherein It further includes the following steps: Set the size of the preset value according to the input information of the user.

6. A personnel detection system for point cloud data, characterized in that, Including: A memory for storing programs; A processor for loading the program to execute the method according to any one of claims 1-5.

7. The personnel detection system for point cloud data according to claim 6, wherein The detection radar uses a millimeter-wave radar.

Images