CN111724558B

CN111724558B - Monitoring method, monitoring device and intrusion alarm system

Info

Publication number: CN111724558B
Application number: CN201910219254.5A
Authority: CN
Inventors: 浦世亮; 王映宇; 申琳; 沈林杰
Original assignee: Hangzhou Hikvision Digital Technology Co Ltd
Current assignee: Hangzhou Hikvision Digital Technology Co Ltd
Priority date: 2019-03-21
Filing date: 2019-03-21
Publication date: 2021-10-19
Anticipated expiration: 2039-03-21
Also published as: CN111724558A

Abstract

The application provides a monitoring method, a monitoring device and an intrusion alarm system, wherein the method is applied to a control device in the intrusion alarm system, the intrusion alarm system comprises a laser radar arranged at a preset position, the laser radar scans a peripheral three-dimensional area of a target building in a preset scanning mode corresponding to the arrangement position of the laser radar, and the method comprises the following steps: cutting and splicing the scanning data acquired by the laser radar to obtain spatial data of a peripheral three-dimensional area; calculating the distance between the reflection position of the laser radar emitted light beam and the laser radar based on the spatial data; if the distance is inconsistent with the preset distance, determining that a target tracking object exists; acquiring target space data of a target tracking object in a preset time period; if the target tracking object can be continuously detected according to the target space data, determining the identification information of the target tracking object; and generating intrusion alarm information according to the identification information. By the method and the device, the monitoring effect of the peripheral three-dimensional area of the target building can be improved.

Description

Monitoring method, monitoring device and intrusion alarm system

Technical Field

The present application relates to the field of computer technologies, and in particular, to a monitoring method, a monitoring device, and an intrusion alarm system.

Background

The intrusion alarm system can realize the detection and alarm of the target tracking object by monitoring the peripheral area of the target building, and the target tracking object can be a person or a vehicle. In the prior art, a camera can be installed at a preset position of a target building, and an intrusion alarm system can shoot a ground area around the target building through the camera and detect a target tracking object in an image recognition mode.

However, the monitoring range of the camera is limited, the intrusion alarm system based on the camera can only detect the target tracking object in the ground area, and when the target tracking object approaches a target building from the air (for example, an unmanned aerial vehicle flying at a preset height approaches a high-rise building), the existing intrusion alarm system cannot detect the target tracking object, and the monitoring effect is poor.

Disclosure of Invention

An object of the embodiments of the present application is to provide a monitoring method, a monitoring device, and an intrusion alarm system, which can improve the monitoring effect of a three-dimensional area around a target building. The specific technical scheme is as follows:

in a first aspect, an intrusion alert system is provided, comprising: a control device 1 and at least one radar 2 arranged at a preset position of a target building, wherein the radar 2 is connected with the control device 1, the preset position comprises at least one of the top, the middle and the bottom of the target building, and the radar 2 is arranged to enable the scanning range of all the radars 2 to completely cover the peripheral three-dimensional area of the target building;

the radar 2 scans the peripheral three-dimensional area of the target building in a preset scanning mode corresponding to the arrangement position of the radar to obtain spatial data of the peripheral three-dimensional area; transmitting the spatial data to the control device 1;

the control equipment 1 cuts and splices scanning data acquired by scanning the peripheral three-dimensional area by the radar 2 to obtain spatial data of the peripheral three-dimensional area; calculating a distance between a reflection position of an emission beam emitted by the radar 2 and the radar 2 based on the spatial data; if the distance is inconsistent with a preset distance, determining that a target tracking object exists in a peripheral three-dimensional area of the target building; acquiring target space data of the target tracking object within a preset time period; if the target tracking object can be continuously detected according to the target space data, carrying out target identification on the target tracking object to obtain identification information of the target tracking object; and generating intrusion alarm information of the target tracking object according to the identification information, wherein the intrusion alarm information at least comprises the identification information of the target tracking object.

Optionally, the system further includes: at least one image acquisition device 3 connected to the control device 1;

when the control device 1 detects a target tracking object, the control device 1 acquires a monitoring image containing the target tracking object through the image acquisition device 3; and carrying out image recognition on the monitoring image so as to carry out cross verification on the intrusion alarm information.

Optionally, the scanning, by the radar 2, the peripheral three-dimensional area of the target building in the preset scanning manner includes:

when the radar 2 is arranged at the top of the target building, the beam direction of the radar 2 is parallel to a preset outer vertical surface of the target building and is vertical to the ground and downward, the preset scanning mode of the radar 2 is that the preset outer vertical surface is used as a reference surface, the scanning angle is 180 degrees, the scanning is performed in a left-right mode in parallel to the preset outer vertical surface, and the scanning range of the radar 2 covers a three-dimensional area parallel to the preset outer vertical surface;

when the radar 2 is arranged in the middle of the target building, the beam direction of the radar 2 is parallel to a preset outer vertical surface of the target building and is vertical to the ground and downward, the preset scanning mode of the radar 2 is that the preset radar 2 is used as a reference point, 360 degrees are used as scanning angles, the radar 2 is parallel to the preset outer vertical surface for left-right scanning, and the scanning range of the radar 2 covers a three-dimensional area parallel to the preset outer vertical surface;

when the radar 2 is arranged at the bottom of the target building, the beam direction of the radar 2 is parallel to a preset outer vertical surface of the target building and is vertical to the ground upwards, the preset scanning mode of the radar 2 is that the preset outer vertical surface is used as a reference surface, 180 degrees are used as scanning angles, the radar is parallel to the preset outer vertical surface for left-right scanning, and the scanning range of the radar 2 covers a three-dimensional area parallel to the preset outer vertical surface.

In a second aspect, a monitoring method is provided, where the method is applied to a control device in an intrusion alarm system, the intrusion alarm system further includes at least one lidar arranged at a preset position of a target building, and the lidar scans a preset peripheral three-dimensional area of the target building in a preset scanning manner corresponding to the arrangement position of the lidar, and the method includes:

cutting and splicing the scanning data acquired by scanning the peripheral three-dimensional area by the laser radar to obtain the spatial data of the peripheral three-dimensional area;

calculating the distance between the reflection position of the laser radar emission beam and the laser radar based on the spatial data;

if the distance is inconsistent with a preset distance, determining that a target tracking object exists in a peripheral three-dimensional area of the target building;

acquiring target space data of the target tracking object within a preset time period;

if the target tracking object can be continuously detected according to the target space data, carrying out target identification on the target tracking object to obtain identification information of the target tracking object;

and generating intrusion alarm information of the target tracking object according to the identification information, wherein the intrusion alarm information at least comprises the identification information of the target tracking object.

Optionally, the performing target identification on the target tracking object to obtain the identification information of the target tracking object includes:

and inputting the target space data into a pre-trained 3D target recognition model based on deep learning, and determining the recognition information of the target tracking object.

Optionally, before the generating the intrusion alarm information of the target tracking object, the method further includes:

determining the position of the target tracking object according to the target space data;

determining a target camera corresponding to a monitoring range to which the position of the target tracking object belongs according to a pre-stored corresponding relation between the monitoring range and the camera, and sending a control signal to the target camera, so that the target camera shoots the target tracking object after receiving the control signal to obtain a monitoring image;

performing image recognition on the monitoring image, and acquiring linkage detection data of the target tracking object so as to perform cross validation on the identification information, wherein the linkage detection data comprises the identification information of the target tracking object;

and if the verification result is correct, executing the step of generating the intrusion alarm information of the target tracking object.

Optionally, the cutting and splicing of the scanning data obtained by scanning the peripheral three-dimensional region by the laser radar to obtain the spatial data of the peripheral three-dimensional region includes:

acquiring scanning data obtained by scanning the laser radar within a preset scanning range, wherein the scanning range is larger than the peripheral three-dimensional area;

extracting scanning data corresponding to spatial position information contained in the peripheral three-dimensional region from the scanning data;

for each piece of spatial position information, if the number of scanning data corresponding to the spatial position information is one, taking the scanning data as the spatial data corresponding to the spatial position information;

and if the scanning data corresponding to the spatial position information is multiple, determining the spatial data corresponding to the spatial position information according to the multiple scanning data corresponding to the spatial position information.

Optionally, after determining the identification information of the target tracking object, the method further includes:

determining the hazard level of the target tracking object corresponding to the identification information of the target tracking object according to the corresponding relation between the pre-stored identification information and the hazard level;

the generating of the intrusion alarm information of the target tracking object includes:

and generating intrusion alarm information containing the identification information of the target tracking object and the hazard level of the target tracking object.

Optionally, the intrusion alarm information includes one or more of a position of the target tracking object, identification information of the target tracking object, a degree of harm of the target tracking object, a duration of the target tracking object, spatial data of the target tracking object, and linkage detection data of the target tracking object.

In a third aspect, a monitoring apparatus is provided, where the apparatus is applied to a control device in an intrusion alarm system, the intrusion alarm system further includes at least one lidar arranged at a preset position of a target building, and the lidar scans a preset peripheral three-dimensional area of the target building in a preset scanning manner corresponding to the arrangement position of the lidar, and the apparatus includes:

the first determining module is used for cutting and splicing the scanning data acquired by the laser radar scanning the peripheral three-dimensional area to obtain the spatial data of the peripheral three-dimensional area;

the calculation module is used for calculating the distance between the reflection position of the laser radar emission beam and the laser radar based on the spatial data;

the second determination module is used for determining that a target tracking object exists in a peripheral three-dimensional area of the target building when the distance is inconsistent with a preset distance;

the first acquisition module is used for acquiring target space data of the target tracking object within a preset time period;

the identification module is used for carrying out target identification on the target tracking object to obtain identification information of the target tracking object when the target tracking object can be continuously detected according to the target space data;

and the generation module is used for generating intrusion alarm information of the target tracking object according to the identification information, wherein the intrusion alarm information at least comprises the identification information of the target tracking object.

Optionally, the identification module includes:

and the first determining submodule is used for inputting the target space data into a pre-trained 3D target recognition model based on deep learning and determining the recognition information of the target tracking object.

Optionally, the apparatus further comprises:

the third determining module is used for determining the position of the target tracking object according to the target space data;

a fourth determining module, configured to determine, according to a pre-stored correspondence between a monitoring range and a camera, a target camera corresponding to a monitoring range to which a position of the target tracking object belongs, and send a control signal to the target camera, so that the target camera shoots the target tracking object after receiving the control signal, to obtain a monitoring image;

the second acquisition module is used for carrying out image identification on the monitoring image and acquiring linkage detection data of the target tracking object so as to carry out cross validation on the identification information, and the linkage detection data comprises the identification information of the target tracking object;

and the generating module is also used for generating intrusion alarm information of the target tracking object when the verification result is correct.

Optionally, the first determining module includes:

the acquisition submodule is used for acquiring scanning data obtained by scanning the laser radar within a preset scanning range, and the scanning range is larger than the peripheral three-dimensional area;

the extraction submodule is used for extracting scanning data corresponding to the spatial position information contained in the peripheral three-dimensional region from the scanning data;

the second determining submodule is used for regarding each piece of spatial position information, and if the number of the scanning data corresponding to the spatial position information is one, the scanning data is used as the spatial data corresponding to the spatial position information;

and the third determining submodule is used for determining the spatial data corresponding to the spatial position information according to the plurality of scanning data corresponding to the spatial position information when the plurality of scanning data corresponding to the spatial position information are provided.

Optionally, the apparatus further comprises:

a fifth determining module, configured to determine, according to a correspondence between pre-stored identification information and a hazard level, a hazard level of the target tracking object corresponding to the identification information of the target tracking object;

the generation module comprises:

and the generation submodule is used for generating intrusion alarm information containing the identification information of the target tracking object and the hazard level of the target tracking object.

In a fourth aspect, a control device is provided, which includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus;

a memory for storing a computer program;

a processor for implementing the method steps of any of the second aspects when executing the program stored in the memory.

In a fifth aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when being executed by a processor, the computer program realizes the method steps of any of the second aspects.

According to the monitoring method, the monitoring device and the intrusion alarm system, the peripheral three-dimensional area can be scanned through the laser radar and the scanning mode corresponding to the arrangement position of the laser radar, and the acquired scanning data are cut and spliced to obtain the spatial data of the peripheral three-dimensional area. And then, calculating the distance between the reflection position of the laser radar emission beam and the laser radar based on the spatial data, and if the distance is inconsistent with the preset distance, determining that the target tracking object exists in the peripheral three-dimensional area of the target building. And then, acquiring target space data of the target tracking object in a preset time period, and if the target tracking object can be continuously detected according to the target space data, carrying out target identification on the target tracking object to obtain identification information of the target tracking object. And finally, generating intrusion alarm information of the target tracking object according to the identification information. The laser radar is used for scanning the peripheral three-dimensional area of the target building and detecting whether the target tracking object continuously exists or not based on the spatial data obtained by scanning, so that the monitoring effect of the peripheral three-dimensional area of the target building can be improved.

Of course, not all advantages described above need to be achieved at the same time in the practice of any one product or method of the present application.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic structural diagram of an intrusion alarm system according to an embodiment of the present application;

fig. 2a is a schematic diagram of a lidar arranged on the top of a target building according to an embodiment of the present disclosure;

fig. 2b is a schematic diagram of a lidar arranged in the middle of a target building according to an embodiment of the present disclosure;

fig. 2c is a schematic diagram of a lidar arranged at the bottom of a target building according to an embodiment of the present disclosure;

fig. 3 is a flowchart of a monitoring method according to an embodiment of the present application;

fig. 4a is a schematic diagram of a preset scanning range of a laser radar according to an embodiment of the present disclosure;

FIG. 4b is a schematic view of a peripheral three-dimensional region according to an embodiment of the present disclosure;

fig. 5 is a flowchart of a monitoring method according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of a monitoring device according to an embodiment of the present disclosure;

fig. 7 is a schematic structural diagram of a control device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

An embodiment of the present application provides an intrusion alarm system, as shown in fig. 1, the system includes: a control device 1 and at least one radar 2 arranged at a preset position of the target building, the radar 2 being connected to the control device 1. Wherein the preset position comprises at least one of the top, the middle and the bottom of the target building, and the radars 2 are arranged in such a way that the scanning ranges of all the radars 2 can completely cover the peripheral three-dimensional area of the target building.

The radar 2 scans the peripheral three-dimensional area of the target building in a preset scanning mode corresponding to the arrangement position of the radar to obtain spatial data of the peripheral three-dimensional area; transmitting the spatial data to the control device 1; the control equipment 1 cuts and splices scanning data acquired by the radar 2 scanning the peripheral three-dimensional area to obtain spatial data of the peripheral three-dimensional area; calculating the distance between the reflection position of the light beam emitted by the radar 2 and the radar 2 based on the spatial data; if the distance is inconsistent with the preset distance, determining that a target tracking object exists in a peripheral three-dimensional area of the target building; acquiring target space data of a target tracking object in a preset time period; if the target tracking object can be continuously detected according to the target space data, carrying out target identification on the target tracking object to obtain identification information of the target tracking object; and generating intrusion alarm information of the target tracking object according to the identification information, wherein the intrusion alarm information at least comprises the identification information of the target tracking object.

In implementation, the staff may determine the number of the radars 2 and the position of each radar 2 according to the peripheral three-dimensional area to be monitored of the target building and the scanning range of the radar 2, so that the scanning ranges of all the radars 2 can completely cover the peripheral three-dimensional area of the target building.

For example, when the target building is a rectangular parallelepiped office building, the peripheral three-dimensional region to be monitored of the target building may be a rectangular frame having a frame width and a preset monitoring distance, with the outer vertical surface of the target building being a bottom surface. The top of each facade can be provided with 1 radar 2 aiming at four facades of a target building, a three-dimensional area in a scanning range is scanned in a preset scanning mode corresponding to the top, and the scanning ranges of 4 radars 2 can completely cover the peripheral three-dimensional area of the target building. As shown in fig. 2a, a radar 2 provided for the embodiment of the present application is arranged on the top of a target building.

Similarly, 4 radars 2 may be arranged in the middle of the corresponding facade, as shown in fig. 2b, which is a schematic diagram of the radar 2 arranged in the middle of the target building according to the embodiment of the present application. 4 radars 2 may also be arranged at the bottom of the corresponding facade, as shown in fig. 2c, which is a schematic diagram of the radar 2 arranged at the bottom of the target building provided by the embodiment of the present application.

In a possible implementation manner, the preset position may also be the top or middle or bottom of other buildings adjacent to the target building, and the embodiment of the present application is not particularly limited.

In the embodiment of the present application, the control device 1 may be an electronic device having a calculation function. The radar 2 may be a millimeter wave radar or a laser radar. The staff can select one or more radars 2 according to actual conditions such as security level and the like to construct an intrusion alarm system.

Optionally, the intrusion alert system further comprises: at least one image acquisition device 3 connected to the control device 1; when the control device 1 detects a target tracking object, the control device 1 acquires a monitoring image containing the target tracking object through the image acquisition device 3; and carrying out image recognition on the monitoring image so as to carry out cross verification on the intrusion alarm information.

In implementation, the staff may determine the number of the image capturing devices 3 and the position of each image capturing device 3 according to the peripheral three-dimensional area to be monitored of the target building and the shooting range of the image capturing device 3, so that the shooting ranges of all the image capturing devices 3 can completely cover the peripheral three-dimensional area of the target building.

In the embodiment of the present application, the image capturing device 3 may be an electronic device having a shooting function.

Optionally, according to the difference of the arrangement positions of the radars, the scanning modes of the radars are also different, and the scanning, by the radar 2, of the peripheral three-dimensional area of the target building through the preset scanning mode includes:

when the radar 2 is arranged at the top of the target building, the light beam direction of the radar 2 is parallel to the preset outer vertical surface of the target building and is vertical to the ground and downward, the preset scanning mode of the radar 2 is that the preset outer vertical surface is used as a reference surface, the scanning angle of 180 degrees is used, the left and right scanning is performed in parallel to the preset outer vertical surface, and the scanning range of the radar 2 covers a three-dimensional area parallel to the preset outer vertical surface.

When the radar 2 is arranged on top of a target building, the scanning range of the radar 2 is shown as a shaded portion in fig. 2 a.

When the radar 2 is arranged in the middle of the target building, the light beam direction of the radar 2 is parallel to the preset outer vertical surface of the target building and is vertical to the ground and downward, the preset scanning mode of the radar 2 is that the preset radar 2 is used as a reference point, 360 degrees are used as a scanning angle, left and right scanning is performed in parallel to the preset outer vertical surface, and the scanning range of the radar 2 covers a three-dimensional area parallel to the preset outer vertical surface.

When the radar 2 is arranged in the middle of the target building, the scanning range of the radar 2 is shown by the hatched portion in fig. 2 b.

When the radar 2 is arranged at the bottom of the target building, the light beam direction of the radar 2 is parallel to the preset outer vertical surface of the target building and is vertical to the ground and upward, the preset scanning mode of the radar 2 is that the preset outer vertical surface is used as a reference surface, the scanning angle of 180 degrees is used, the left and right scanning is performed in parallel to the preset outer vertical surface, and the scanning range of the radar 2 covers a three-dimensional area parallel to the preset outer vertical surface.

In implementation, when the radar 2 is arranged at the bottom of a target building, the scanning range of the radar 2 is as shown by the shaded portion in fig. 2 c.

In the intrusion alarm system provided by the embodiment of the application, the radar can scan the peripheral three-dimensional area of the target building in a preset scanning mode corresponding to the arrangement position of the radar to obtain the spatial data of the peripheral three-dimensional area; the control device may detect a target tracking object based on spatial data of a peripheral stereoscopic region; and outputting intrusion alarm information of the target tracking object. Therefore, the monitoring and alarming of the three-dimensional perimeter intrusion process of the building can be realized, and the monitoring effect of the three-dimensional area around the target building is improved.

The embodiment of the application also provides a monitoring method, which is applied to the control equipment in the intrusion alarm system, wherein the control equipment can be electronic equipment with a computing function. The intrusion alarm system also comprises at least one laser radar arranged at a preset position of the target building, and the laser radar scans a preset peripheral three-dimensional area of the target building in a preset scanning mode corresponding to the arrangement position of the laser radar. The lidar may be a single line radar, a multi-line radar, a MEMS (Micro-Electro-Mechanical-System) radar, a solid state radar, or the like.

In the embodiment of the application, the intrusion alarm system includes 4 laser radars respectively arranged on the top of the facade of the target building, the execution process of the monitoring method is described, and other situations are similar to the monitoring method, and are not described again here.

As shown in fig. 3, a specific processing flow of a monitoring method provided in the embodiment of the present application includes:

step 301, cutting and splicing the scanning data obtained by scanning the peripheral three-dimensional area by the laser radar to obtain the spatial data of the peripheral three-dimensional area.

The scan data and the spatial data may be 3D (3 Dimensions) point cloud data, among others. The preset peripheral three-dimensional area may be a rectangular frame body with a preset monitoring distance as a frame body width, and the outer vertical surface of the target building is used as a reference surface.

In implementation, the control device may perform real-time scanning on the peripheral three-dimensional area of the target building in a preset scanning manner corresponding to the top through four laser radars installed on the top of the facade of the target building, so as to obtain scanning data corresponding to the scanning range of the laser radars. Then, the control device may cut and splice the scan data according to the scan range of the laser radar and the peripheral three-dimensional region to obtain spatial data of the peripheral three-dimensional region.

In a feasible implementation manner, the control device may scan a peripheral three-dimensional area of the target building through the laser radar according to a preset scanning period, so as to obtain spatial data of the peripheral three-dimensional area.

And 302, calculating the distance between the reflection position of the laser radar emission beam and the laser radar based on the spatial data.

The control device may store a preset distance between a reflection position of the laser radar transmission beam and the laser radar in advance.

In implementation, the control device may calculate a distance between a reflection position of the laser radar emission beam and the laser radar according to the emission time and the reception time of the laser radar emission beam. Then, the control device may compare the distance of the reflection position from the laser radar with a preset distance.

If the distance is different from the preset distance, the control device may perform step 303. If the distance coincides with the preset distance, the control apparatus may determine that the target tracking object does not exist in the peripheral stereoscopic region of the target building.

For example, when there is no target tracking object in the peripheral three-dimensional region, the reflection position of the laser radar emission beam may be the ground, and the control device may take a pre-stored distance 100m of the ground from the laser radar as the preset distance. The control device may compare the reflection position of the laser radar emission beam with a distance 95m of the laser radar with a preset distance 100m, and since the distance is different from the preset distance, the control device may perform step 303.

In a feasible implementation manner, a tracking object detection algorithm may be preset in the control device, and the tracking object detection algorithm may be a clustering algorithm, an image recognition algorithm, or the like. The control device may determine whether the target tracking object exists in the peripheral stereoscopic area of the target building according to the spatial data of the peripheral stereoscopic area and a tracking object detection algorithm.

Step 303, determining that the target tracking object exists in the peripheral three-dimensional area of the target building.

And 304, acquiring target space data of the target tracking object in a preset time period.

In implementation, the control device may acquire target space data of the target tracking object after determining that the target tracking object exists in the current peripheral stereo region. Then, the control device may calculate a distance between a reflection position of a light beam emitted from the laser radar and the laser radar based on the spatial data within a preset time period after the target tracking object is detected for the first time, and compare the distance with the preset distance to determine whether the target tracking object exists in a peripheral three-dimensional region of the target building. The control device may acquire target space data of the target tracking object when it is determined that the target tracking object exists.

Then, the control device may calculate a similarity of the target spatial data acquired within a preset time period, and if the similarity is greater than a preset similarity threshold, the control device may determine that the detected target tracking objects are the same target tracking object, that is, determine that the target tracking objects can be continuously detected. The control device may then perform step 305.

If the similarity is smaller than the similarity threshold, the control device may determine that the detected target tracking objects are not the same target tracking object, and the control device may not perform subsequent processing.

In a possible implementation manner, the control device may be preset with a target tracking algorithm, and the target tracking algorithm may be an optimized autoregressive data processing algorithm, such as a kalman filter. The control device may input target space data corresponding to the target tracking object within a preset time period into the target tracking algorithm, and determine whether the target tracking object can be continuously detected according to an output result of the target tracking algorithm. Or, the control device may obtain target space data of the target tracking object when the target tracking object is detected for the first time, and then, the control device may input the target space data into the target tracking algorithm; and then, when the control equipment detects the target tracking object within a preset time period, acquiring target space data of the target tracking object, inputting the target space data into a target tracking algorithm, and determining the target tracking object detected within the preset time period to be the same tracking object through the target tracking algorithm, namely, the target tracking object can be continuously detected.

Step 305, performing target identification on the target tracking object to obtain identification information of the target tracking object.

Wherein the identification information includes a classification to which the target tracking object belongs, for example, the identification information may be a drone or a bird or a kite.

In implementation, the control device may perform target recognition on the target tracking object according to the spatial data of the target tracking object to obtain the identification information of the target tracking object.

Optionally, the control device may determine the identification information of the target tracking object based on a pre-trained 3D target identification model based on deep learning, and the specific processing flow includes: and if the target tracking object can be continuously detected, inputting the target space data into a pre-trained 3D target recognition model based on deep learning, and determining the recognition information of the target tracking object.

In implementation, after determining that the target tracking object can be continuously detected, the control device may input the target space data of the target tracking object into a pre-trained 3D target recognition model based on deep learning, and use the obtained classification result as the recognition information of the target tracking object.

In the embodiment of the application, the control device inputs the target space data of the target tracking object into the pre-trained 3D target recognition model based on deep learning, the recognition information of the target tracking object is determined, more information of the target tracking object can be provided for workers, and the workers can take different countermeasures conveniently.

And step 306, generating intrusion alarm information of the target tracking object according to the identification information.

Wherein, the intrusion alarm information at least comprises the identification information of the target tracking object.

In implementation, the control device may generate intrusion alert information containing identification information of the target tracking object, and output the intrusion alert information. The control device can also generate intrusion alarm information including target space data of the target tracking object and identification information of the target tracking object.

In a possible implementation manner, the control device may output a window containing intrusion alarm information in a pop-up window form on a preset display screen to prompt a worker that a target tracking object capable of being continuously tracked exists.

In the embodiment of the application, the control equipment cuts and splices the scanning data acquired by the laser radar scanning peripheral three-dimensional region to obtain the spatial data of the peripheral three-dimensional region, and calculates the distance between the reflection position of the laser radar emission beam and the laser radar based on the spatial data. And then, determining whether the target tracking object exists according to the comparison result of the distance and the preset distance. And then, when the target tracking object exists and the target tracking object can be determined to be continuously detected according to the target space data of the target tracking object in the preset time period, outputting intrusion alarm information of the target tracking object, so that intelligent identification of the target tracking object can be realized, and further, three-dimensional monitoring of a target building is realized.

Compared with the prior art that the monitoring method can be found and alarm only after a building ground intrusion event occurs, the monitoring method provided by the embodiment of the application can realize monitoring and alarm of the building three-dimensional perimeter intrusion process, and the control equipment analyzes the scanning data scanned based on the laser radar, so that the accuracy and reliability of detection can be ensured. In addition, target tracking is established for the detected target tracking object, and when the target tracking object can be continuously detected, the real existence of the target tracking object is determined, so that the influence of random disturbance can be reduced, and the false alarm rate is reduced.

In the embodiment of the application, the control device cuts and splices the scanning data in various modes according to the scanning range and the peripheral three-dimensional region of the laser radar, and in a feasible implementation mode, a worker can determine the coincidence condition of the scanning data of each laser radar according to the structural parameters such as the installation position of the laser radar and determine the data processing rule for cutting and splicing the scanning data. Subsequently, the control device may determine spatial data of the peripheral three-dimensional region according to the scanning data and the data processing rule obtained by the scanning of the laser radar.

For example, the control device may set a target scanning area for each of the lidar, the scanning range of the lidar covers the target scanning area, and the target scanning areas of each of the lidar are spliced together to form a peripheral stereo area. The peripheral three-dimensional area is scanned through each laser radar, the control equipment can determine scanning data corresponding to the scanning range of the laser radar, and then the control equipment can determine the scanning data corresponding to the target scanning area in the scanning data corresponding to the scanning range so as to cut the scanning data of the laser radar. And then, the control device may use the scanning data corresponding to the target scanning area of each laser radar as the spatial data of the corresponding position of the peripheral three-dimensional area, so as to splice the scanning data of all the laser radars to obtain the spatial data of the peripheral three-dimensional area.

Optionally, the control device may further preset spatial position information of the peripheral three-dimensional region, and the control device may perform cutting and splicing on the scan data based on the spatial position information of the peripheral three-dimensional region, so as to determine the spatial data of the peripheral three-dimensional region. The specific process is as follows:

step 1, scanning data obtained by scanning the laser radar in a preset scanning range is obtained.

In implementation, the laser radar installed on the top of the outer facade of the target building may scan a spatial region within a preset scanning range to obtain scanning data corresponding to the preset scanning range, where the preset scanning range may be an actual scanning range of the laser radar. The control device may then acquire scan data from the lidar scanning.

And 2, extracting the scanning data corresponding to the spatial position information contained in the peripheral three-dimensional region from the scanning data.

In implementation, the spatial position information of the peripheral three-dimensional region may be preset by a technician, and the spatial position information of the peripheral three-dimensional region may be stored in the control device in advance. The control device may determine, after obtaining scanning data obtained by scanning of the laser radar, scanning data corresponding to spatial position information included in the peripheral three-dimensional region according to the spatial position information included in the scanning data. Then, the control device may determine, for each piece of spatial position information included in the peripheral three-dimensional region, the number of scan data corresponding to the spatial position information, and if the number of corresponding scan data is one, the control device may perform step 3; the control apparatus may perform step 4 if the number of the corresponding scan data is plural.

And 3, taking the scanning data as the space data corresponding to the space position information.

And 4, determining the spatial data corresponding to the spatial position information according to the plurality of scanning data corresponding to the spatial position information.

In an implementation, the control device may select any one of the plurality of scanning data corresponding to the spatial position information as the spatial data corresponding to the spatial position information. Alternatively, the control device may calculate an average value of a plurality of scan data corresponding to the spatial position information as the spatial data corresponding to the spatial position information.

For example, for the case shown in fig. 4a, the control device may extract scan data corresponding to spatial position information included in the peripheral solid region from among the scan data of the four laser radars. For the scanning data corresponding to the same spatial position information (x1, y1, z1) obtained by scanning the laser radar 1 and the laser radar 2, the control device may select the scanning data of the laser radar 1 as the spatial data corresponding to the spatial position information, so as to obtain the spatial data of the peripheral three-dimensional region. Fig. 4b is a schematic view of a peripheral three-dimensional area of a target building according to an embodiment of the present application.

In the embodiment of the application, the control device scans the preset area of the facade of the target building through the laser radar to obtain the spatial data within the preset scanning range, and then cuts and splices the collected spatial data to generate the spatial data of the peripheral three-dimensional area of the target building. Because laser radar's scanning range is big, through the reasonable mounted position that sets up laser radar, control device can acquire the peripheral spatial data of target building through the laser radar that the number is few, and then realizes carrying out the three-dimensional control to whole target building, and intrusion alert system based on laser radar has advantages such as installation and construction are simple, easy to maintain, all-weather work.

Optionally, the control device may be pre-stored with an initial training model, where the initial training model may be a support vector machine or a deep learning-based classification model. The control equipment can train the initial training model based on a pre-stored training set to obtain a trained 3D target recognition model based on deep learning, and the specific processing flow comprises the following steps:

step one, a pre-stored training set is obtained.

The control device may be pre-stored with a training set, where the training set includes a plurality of spatial data samples of the tracked object, and identification information of the tracked object corresponding to each spatial data sample. The identification information of the tracked object includes a drone, a bird, and a kite.

In an implementation, the control device may retrieve a pre-stored training set according to the received training instructions.

And secondly, training the pre-stored initial training model based on the training set to obtain a well-trained 3D target recognition model based on deep learning.

In implementation, the control device may input, into the initial training model, the spatial data samples of the plurality of tracked objects included in the training set and the identification information of the tracked object corresponding to each spatial data sample, so as to obtain a trained 3D target identification model based on deep learning.

In the embodiment of the application, the control device inputs the training set into the initial training model to train the initial training model to obtain a trained 3D target recognition model based on deep learning, so that the subsequent control device can input target space data of the target tracking object into the trained 3D target recognition model based on deep learning to determine recognition information of the target tracking object.

Optionally, the control device may pre-store a correspondence between the identification information and the hazard level, for example, the hazard level of the unmanned aerial vehicle is the highest in the identification information, and the hazard level of the bird in the identification information is general. The control device may determine the hazard level of the target tracking object after determining the identification information of the target tracking object. The specific treatment process comprises the following steps: and determining the hazard level of the target tracking object corresponding to the identification information of the target tracking object according to the corresponding relation between the pre-stored identification information and the hazard level.

In an implementation, the control device may determine, in the correspondence relationship between the identification information and the hazard level, the identification information that is the same as the identification information of the target tracking object, and use the hazard level corresponding to the identification information as the hazard level of the target tracking object.

Then, the control device may generate intrusion alert information containing identification information of the target tracking object and a hazard level of the target tracking object when generating the intrusion alert information.

In the embodiment of the application, the control device can determine the hazard level of the target tracking object according to the identification information of the target tracking object, and generates intrusion alarm information containing the hazard level of the target tracking object, so that more information of the target tracking object can be provided for workers, and the workers can take different countermeasures conveniently.

In a possible implementation, the control device may also be connected to an image capturing device, which may be a camera. At this time, the control device may send a control signal to the image acquisition device after being able to continuously detect the target tracking object, so as to further detect the target tracking object. In the embodiment of the present application, the image capturing device is taken as an example to describe the above process, and as shown in fig. 5, the specific processing procedure includes:

step 501, determining the position of the target tracking object according to the target space data.

In an implementation, the control device may determine spatial position information included in the target spatial data, and determine an actual position of the target tracking object in the peripheral three-dimensional region according to the spatial position information.

For example, the target spatial data is 3D point cloud data, and the 3D point cloud data includes spatial position information. As shown in fig. 4b, the control apparatus may determine that the target spatial data includes spatial position information of (x2, y2, z2), and then, the control apparatus may determine that the target tracking object is in the peripheral three-dimensional region on the left side of the target building based on the spatial position information (x2, y2, z 2).

Step 502, according to the corresponding relationship between the pre-stored monitoring range and the camera, determining a target camera corresponding to the monitoring range to which the position of the target tracking object belongs, and sending a control signal to the target camera, so that the target camera shoots the target tracking object after receiving the control signal to obtain a monitoring image.

In implementation, the control device may store a corresponding relationship between the monitoring range and the camera in advance, and after determining the position of the target tracking object, the control device may determine, according to the corresponding relationship between the monitoring range and the camera, the monitoring range to which the position of the target tracking object belongs, and the camera corresponding to the monitoring range, to obtain the target camera. Then, the control device may send a control signal to the target camera, and the target camera may shoot the target tracking object after receiving the control signal to obtain a monitoring image, and then the target camera may send the monitoring image to the control device. The control equipment can display the shot picture on a preset display screen for the staff to watch.

And 503, performing image recognition on the monitored image to acquire linkage detection data of the target tracking object so as to perform cross validation on the identification information.

The linkage detection data comprises at least one of identification information of the target tracking object, the position of the target tracking object and the hazard degree of the target tracking object.

In implementation, an image recognition algorithm may be preset in the control device, and the control device may determine the identification information of the target tracking object and the position of the target tracking object through the image recognition algorithm and the monitoring image, that is, obtain the linkage detection data of the target tracking object.

Then, the control device may compare the identification information of the target tracking object determined by image recognition of the monitored image with the identification information of the target tracking object determined by target recognition of the target spatial data, and if the two identification information are identical, the control device may determine that the verification result is correct, and then the control device may perform step 504. If the two pieces of identification information do not coincide, the control device may determine that the verification result is an error, and does not perform subsequent processing.

And step 504, generating intrusion alarm information of the target tracking object.

In the implementation, the specific processing procedure of this step is the same as that of step 306, and is not described herein again.

In a feasible implementation manner, the training set of the initial training model may include the monitoring image of the image acquisition device and the identification information of the target tracking object included in the monitoring image, and the control device may train the initial training model based on the training set including the monitoring image, so as to obtain a trained 3D target identification model based on deep learning. The control device can input the monitoring image and the target space data acquired by the image acquisition device into a trained 3D target recognition model based on deep learning to obtain the recognition information of the target tracking object. Therefore, the control equipment can realize fusion analysis of space data scanned by the laser radar and detection data of other sensors through a trained 3D target recognition model based on deep learning, and therefore the accuracy of target tracking object analysis is improved.

In the embodiment of the application, the control device may determine the position of the target tracking object after determining to continuously detect the target tracking object, further determine the target camera corresponding to the monitoring range to which the position of the target tracking object belongs, and send the control signal to the target camera to realize fixed-point detection and cross validation of the target tracking object, so that the control device may determine the authenticity of the target tracking object in a cross validation manner.

The embodiment of the present application further provides a monitoring device, the control device in intrusion alert system is applied to the device, intrusion alert system still includes at least one lidar of arranging the preset position department at target building, lidar scans the peripheral solid area of presetting of target building through the scanning mode of presetting rather than arranging the position correspondence, as shown in fig. 6, the device includes:

a first determining module 610, configured to crop and splice scanning data obtained by scanning the peripheral three-dimensional region with the laser radar, so as to obtain spatial data of the peripheral three-dimensional region;

a calculating module 620, configured to calculate a distance between a reflection position of an emission beam of the lidar and the lidar based on the spatial data;

a second determining module 630, configured to determine that a target tracking object exists in a peripheral three-dimensional region of the target building when the distance is inconsistent with a preset distance;

a first obtaining module 640, configured to obtain target space data of the target tracking object within a preset time period;

the identification module 650 is configured to perform target identification on the target tracking object to obtain identification information of the target tracking object when it is determined that the target tracking object can be continuously detected according to the target space data;

a generating module 660, configured to generate intrusion alarm information of the target tracking object according to the identification information, where the intrusion alarm information at least includes the identification information of the target tracking object.

Optionally, the identification module includes:

Optionally, the apparatus further comprises:

Optionally, the first determining module includes:

Optionally, the apparatus further comprises:

the generation module comprises:

The monitoring device provided by the embodiment of the application can scan the peripheral three-dimensional region through the scanning modes corresponding to the arrangement positions of the laser radar and the laser radar, and cut and splice the acquired scanning data to obtain the spatial data of the peripheral three-dimensional region. And then, calculating the distance between the reflection position of the laser radar emission beam and the laser radar based on the spatial data, and if the distance is inconsistent with the preset distance, determining that the target tracking object exists in the peripheral three-dimensional area of the target building. And then, acquiring target space data of the target tracking object in a preset time period, and if the target tracking object can be continuously detected according to the target space data, carrying out target identification on the target tracking object to obtain identification information of the target tracking object. And finally, generating intrusion alarm information of the target tracking object according to the identification information. The laser radar is used for scanning the peripheral three-dimensional area of the target building and detecting whether the target tracking object continuously exists or not based on the spatial data obtained by scanning, so that the monitoring effect of the peripheral three-dimensional area of the target building can be improved.

The embodiment of the present application further provides a control device, as shown in fig. 7, including a processor 701, a communication interface 702, a memory 703 and a communication bus 704, where the processor 701, the communication interface 702, and the memory 703 complete mutual communication through the communication bus 704,

a memory 703 for storing a computer program;

the processor 701 is configured to implement the following steps when executing the program stored in the memory 703:

The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.

The communication interface is used for communication between the electronic equipment and other equipment.

The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.

The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.

In yet another embodiment provided by the present application, a computer-readable storage medium is further provided, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of any one of the monitoring methods described above.

In yet another embodiment provided by the present application, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform any one of the monitoring methods in the above embodiments.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only for the preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application are included in the protection scope of the present application.

Claims

1. An intrusion alert system comprising: a control device (1) and at least one radar (2) arranged at a preset position of a target building, wherein the radar (2) is connected with the control device (1), the preset position comprises at least one of the top, the middle and the bottom of the target building, and the radar (2) is arranged in such a way that the scanning range of all the radars (2) can completely cover the peripheral three-dimensional area of the target building;

the radar (2) scans the peripheral three-dimensional area of the target building in a preset scanning mode corresponding to the arrangement position of the radar to obtain spatial data of the peripheral three-dimensional area; -sending said spatial data to said control device (1);

the control equipment (1) cuts and splices scanning data acquired by scanning the peripheral three-dimensional area by the radar (2) to obtain spatial data of the peripheral three-dimensional area; calculating a distance of a reflection position of a light beam emitted by the radar (2) from the radar (2) based on the spatial data; if the distance is inconsistent with a preset distance, determining that a target tracking object exists in a peripheral three-dimensional area of the target building; acquiring target space data of the target tracking object within a preset time period; if the target tracking object can be continuously detected according to the target space data, carrying out target identification on the target tracking object to obtain identification information of the target tracking object; and generating intrusion alarm information of the target tracking object according to the identification information, wherein the intrusion alarm information at least comprises the identification information of the target tracking object.

2. The system of claim 1, further comprising: at least one image acquisition device (3) connected to the control device (1);

when the control equipment (1) detects a target tracking object, the control equipment (1) acquires a monitoring image containing the target tracking object through the image acquisition equipment (3); and carrying out image recognition on the monitoring image so as to carry out cross verification on the intrusion alarm information.

3. The system according to claim 1, wherein the radar (2) scans the peripheral solid area of the target building by the preset scanning mode comprises:

when the radar (2) is arranged at the top of the target building, the light beam direction of the radar (2) is parallel to a preset outer vertical surface of the target building and is vertical to the ground and downward, the preset scanning mode of the radar (2) is that the preset outer vertical surface is used as a reference surface, 180 degrees are used as a scanning angle, left and right scanning is carried out in parallel to the preset outer vertical surface, and the scanning range of the radar (2) covers a three-dimensional area parallel to the preset outer vertical surface;

when the radar (2) is arranged in the middle of the target building, the light beam direction of the radar (2) is parallel to a preset outer vertical surface of the target building and is vertical to the ground and downwards, the preset scanning mode of the radar (2) is that the preset radar (2) is used as a reference point, 360 degrees are used as scanning angles, left and right scanning is carried out in parallel to the preset outer vertical surface, and the scanning range of the radar (2) covers a three-dimensional area parallel to the preset outer vertical surface;

when the radar (2) is arranged at the bottom of the target building, the light beam direction of the radar (2) is parallel to a preset outer vertical face of the target building and is vertical to the ground and faces upwards, the preset scanning mode of the radar (2) is that the preset outer vertical face is used as a reference plane, 180 degrees are used as scanning angles, left and right scanning is carried out in parallel to the preset outer vertical face, and the scanning range of the radar (2) covers a three-dimensional area parallel to the preset outer vertical face.

4. A monitoring method applied to a control device in an intrusion alert system, the intrusion alert system further including at least one lidar disposed at a preset position of a target building, the lidar scanning a preset peripheral three-dimensional area of the target building in a preset scanning manner corresponding to the arrangement position thereof, the method comprising:

5. The method according to claim 4, wherein the performing target identification on the target tracking object to obtain the identification information of the target tracking object comprises:

6. The method of claim 4, wherein before generating intrusion alert information for the target tracking object, further comprising:

7. The method according to claim 4, wherein the cropping and stitching the scanning data obtained by the lidar scanning the peripheral three-dimensional region to obtain the spatial data of the peripheral three-dimensional region comprises:

8. The method of claim 5, wherein after determining the identification information of the target tracking object, further comprising:

9. The method of claim 4, wherein the intrusion alert information includes one or more of a location of the target tracking object, identification information of the target tracking object, a degree of harm of the target tracking object, a duration of the target tracking object, spatial data of the target tracking object, and coordinated detection data of the target tracking object.

10. The utility model provides a monitoring device, its characterized in that, the device is applied to the controlgear among the intrusion alert system, intrusion alert system still includes at least one and arranges the lidar at the preset position department of target building, lidar scans the peripheral solid area of presetting of target building through the scanning mode of presetting rather than arranging the position correspondence, the device includes: