WO2023279786A1

WO2023279786A1 - Perimeter detection method and apparatus, and device and system

Info

Publication number: WO2023279786A1
Application number: PCT/CN2022/084382
Authority: WO
Inventors: 夏建东
Original assignee: 华为技术有限公司
Priority date: 2021-07-08
Filing date: 2022-03-31
Publication date: 2023-01-12

Abstract

A perimeter detection method (200) and apparatus, and a device and a system. The perimeter detection method (200) is applicable to a detection system, which comprises a radar (102) and a camera (103). The method comprises: a radar (102) entering a corresponding detection sensitivity mode according to a photographing capability of a camera (103); under the detection sensitivity, the radar (102) determining whether there is an intrusion target within a perimeter; and if there is an intrusion target within the perimeter, the camera (103) determining again whether the intrusion target is a real intrusion target. Specifically, when the camera (103) has a relatively good photographing capability, the radar enters a high detection sensitivity mode, and in this case, the overall false negative rate can be reduced by means of improving the sensitivity of the radar (102); and when the camera (103) has a relatively weak photographing capability or cannot acquire an image frame, the radar (102) enters a relatively low detection sensitivity mode, and in this case, the overall false positive rate can be reduced by means of reducing the detection sensitivity of the radar (102). By means of the perimeter detection method (200), the radar (102) can enter different detection sensitivity modes according to photographing capability of the camera (103), thereby obtaining both a low false positive rate and a low false negative rate.

Description

Perimeter detection method, device, equipment and system

This application claims the priority of the Chinese patent application submitted to the State Intellectual Property Office on July 8, 2021, with the application number 202110773755.5, and the application title is "A Radar Sensitivity Adaptive Technology for Lesion Vision Fusion", and claims the Priority of a Chinese patent application with application number 202111051346.0 and titled "Perimeter detection method, device, device and system" filed with the State Intellectual Property Office on September 8, 2021, the entire contents of which are incorporated by reference in this application .

technical field

The present application relates to the field of information technology, and more specifically, to a perimeter detection method, device, device and system.

Background technique

Perimeter protection is an important component of railway line security. In recent years, because the railway perimeter has not been warned in time after being invaded, many accidents have been caused, for example, the train was forced to stop, roll over, etc., which seriously affected the normal operation of the train. Therefore, there is a need to meet the needs of the railway industry Current solutions to ensure the safety of train operations.

As a railway perimeter protection technology, radar technology has the advantages of wide detection range, high detection sensitivity, relatively low construction and maintenance costs, and has become a mainstream technology choice.

For railway perimeter protection, it is necessary to give priority to ensuring a very low false alarm rate. Therefore, radars generally work in a higher detection sensitivity mode to reduce the false alarm rate. However, when the radar works in a higher detection sensitivity mode, it is easy to regard some non-invading targets as intrusion targets, thus generating an alarm, which will increase the false alarm rate, and frequent false alarms will make the operation and maintenance personnel tired of checking , affecting the promotion of perimeter protection systems based on radar technology.

Contents of the invention

The embodiment of the present application provides a perimeter detection method, device, equipment and system. The method enables the radar to enter the detection sensitivity mode corresponding to the camera's shooting capability according to the shooting capability of the camera. When the radar detects in the current detection sensitivity mode , can reduce the false positive rate and false negative rate.

In a first aspect, a perimeter detection method is provided, the method is applied to a detection system including a radar and a camera, and there is a communication connection between the camera and the radar. First, the radar determines the current detection sensitivity according to the shooting capability of the camera, wherein the shooting capability of the camera indicates the quality of the image frame acquired by the camera; then, the radar determines whether there is an intrusion within the perimeter under the current detection sensitivity target; finally, if there is an intrusion target within the perimeter, the camera determines whether the intrusion target is a real intrusion target.

Based on the above technical solution, the radar can enter the corresponding detection sensitivity mode according to the current shooting ability of the camera. For example, when the shooting ability of the camera is strong, the radar enters the high detection sensitivity mode. Since the shooting ability of the camera is strong and the camera will participate The second confirmation, that is, the accuracy of the second confirmation of the camera will be higher. Therefore, increasing the radar sensitivity at this time can reduce the overall false negative rate. For another example, in this solution, when the camera's shooting ability is weak or the image frame cannot be acquired, the radar enters a relatively low detection sensitivity mode. Because the camera's shooting ability is weak or even cannot be confirmed twice, the accuracy of the camera's second confirmation The rate will be low, at this time, reducing the detection sensitivity of the radar can reduce the overall false alarm rate. Therefore, the radar in this solution can enter different detection sensitivity modes according to the secondary confirmation shooting ability of the camera, and achieve a win-win situation of low false alarm rate and low false alarm rate.

It is worth mentioning that in the embodiment of the present application, the detection sensitivity mode and the detection sensitivity have the same meaning. In other words, in the embodiment of the present application, the detection sensitivity mode and the detection sensitivity can be replaced with each other. With reference to the first aspect, in some implementation manners of the first aspect, the shooting capability of the camera is determined by the camera according to a current environment and a state of the camera itself.

Based on the above technical solution, by making the camera determine the shooting capability of the camera according to the current environment and the camera's own state, the shooting capability is associated with the quality of the image frame acquired by the camera. Since the current detection sensitivity mode of the radar essentially depends on the camera The quality of the captured image frames. Therefore, by associating the shooting capability with the quality of the captured image frames of the camera, the radar can determine the current detection sensitivity mode according to the shooting capability of the camera.

In combination with the first aspect and the above implementation manners, in some implementation manners of the first aspect, the current environment includes at least one of current weather and current illumination, and the camera's own state includes the camera's functional status and at least one of the device states.

Based on the above technical solution, by making the camera determine the shooting capability of the camera according to the current weather, current light, the functional state of the camera, and the device state of the camera, the current weather, current light, the functional state of the camera, and the device state of the camera will all affect the camera The quality of the acquired image frames is affected. Therefore, the shooting capability of the camera determined by the camera according to the current weather, current lighting, functional status of the camera, and device status of the camera is closer to the real capability of the camera at the moment.

With reference to the first aspect and the above-mentioned implementation manners, in some implementation manners of the first aspect, the radar determining whether there is an intrusion target in the perimeter under the current detection sensitivity includes: the radar determining the perimeter A confidence level of an intrusion target within the perimeter; if the confidence level is greater than or equal to a first confidence level threshold under the current detection sensitivity, the radar determines that an intrusion target exists within the perimeter. It should be noted that, in this implementation manner, the "confidence level" among the confidence levels of intrusion targets in the perimeter determined by the radar is used to indicate the possibility of intrusion targets in the current perimeter.

Based on the above technical solution, only when the confidence level of intrusion targets in the perimeter is greater than the first confidence threshold under the current detection sensitivity, the radar will determine that there are intrusion targets in the perimeter, in other words, only when there are When the confidence of the intrusion target is greater than the first confidence threshold under the current detection sensitivity, the camera will determine whether the intrusion target is a real intrusion target. By setting the first confidence threshold, it is possible to filter out some Intrusion targets are non-intrusion targets, thereby reducing the workload of the camera.

With reference to the first aspect and the above implementation manners, in some implementation manners of the first aspect, the first confidence threshold under the current detection sensitivity decreases as the shooting capability of the camera increases, and the current detection sensitivity The first confidence threshold under the sensitivity increases as the shooting capability of the camera decreases.

Based on the above technical solution, by making the first confidence threshold under the current detection sensitivity decrease as the camera’s shooting ability increases, and making the first confidence threshold under the current detection sensitivity decrease with the camera’s shooting ability weakening Increase, so that the confidence threshold under the current detection sensitivity can match the current detection sensitivity.

With reference to the first aspect and the above implementation manners, in some implementation manners of the first aspect, if the radar determines that there is an intrusion target within the perimeter, the method further includes: the radar sends a notification message to the camera , the notification message instructs the camera to determine whether the intrusion target is a real intrusion target.

Based on the above technical solution, when the radar determines that there is an intrusion target in the perimeter, it sends a notification message to the camera, so that the camera can determine whether the intrusion target is a real intrusion target under the prompt of the notification message.

With reference to the first aspect and the above implementation manners, in some implementation manners of the first aspect, the notification message carries a confidence level of an intrusion target within the perimeter, and the camera determines whether the intrusion target is a real intrusion The target includes: if the confidence is greater than or equal to a preset second confidence threshold, the camera determines that the intrusion target is a real intrusion target.

Based on the above technical solution, when the confidence of the intrusion target in the perimeter is greater than or equal to the preset second confidence threshold, the camera determines that the intrusion target is a real intrusion target, thereby eliminating the step of the camera acquiring image frames and reducing the number of camera workload.

With reference to the first aspect and the above implementation manners, in some implementation manners of the first aspect, the notification message carries the confidence level of the intrusion target in the perimeter and the orientation information of the intrusion target, and the camera determines that the intrusion target Whether the intrusion target is a real intrusion target includes: if the confidence level is less than a preset second confidence threshold, the camera determines whether the intrusion target is For a real intrusion target, the image frame about the intrusion target is acquired according to the orientation information of the intrusion target.

Based on the above technical solution, when the confidence of the intrusion target in the perimeter is less than the preset second confidence threshold, by carrying the orientation information of the intrusion target in the notification message, the camera can obtain information about the intrusion based on the orientation information of the intrusion target. The image frame of the target, and then according to the image frame about the intrusion target, determine whether the intrusion target is a real intrusion target, so that when the confidence of the intrusion target in the perimeter is less than the second preset confidence threshold, the accuracy of the detection result is improved. accuracy.

With reference to the first aspect and the above implementation manners, in some implementation manners of the first aspect, the detection system further includes an alarm, and if the camera determines that the intrusion target is a real intrusion target, the method further includes: The camera controls the alarm device to output an alarm prompt, and the alarm prompt is used to prompt the intrusion target to leave the perimeter.

Based on the above technical solution, after the camera determines that the intrusion target is a real intrusion target, the camera controls the alarm to output an alarm prompt, thereby driving the intrusion target out of the perimeter through the alarm.

In a second aspect, a perimeter detection method is provided, the method comprising: the radar determines the current detection sensitivity according to the shooting capability of the camera, and the shooting capability of the camera indicates the quality of the image frame acquired by the camera; the Under the current detection sensitivity, the radar determines whether there is an intrusion target within the perimeter.

Based on the above technical solution, by making the radar enter the detection sensitivity mode corresponding to the shooting capability of the camera according to the shooting capability of the camera, for example, when the shooting capability of the camera is strong, the radar enters the high detection sensitivity mode. The camera will participate in the secondary confirmation, that is, the accuracy of the secondary confirmation of the camera will be higher. Therefore, increasing the radar sensitivity at this time can reduce the overall false negative rate. For another example, in this solution, when the camera's shooting ability is weak or the image frame cannot be acquired, the radar enters a relatively low detection sensitivity mode. Because the camera's shooting ability is weak or even cannot be confirmed twice, the accuracy of the camera's second confirmation The rate will be low, at this time, reducing the detection sensitivity of the radar can reduce the overall false alarm rate. Therefore, the radar in this solution can enter different detection sensitivity modes according to the secondary confirmation shooting ability of the camera, and achieve a win-win situation of low false alarm rate and low false negative rate.

With reference to the second aspect, in some implementation manners of the second aspect, the shooting capability of the camera is determined by the camera according to a current environment and a state of the camera itself.

In combination with the second aspect and the above implementation manners, in some implementation manners of the second aspect, the current environment includes at least one of current weather and current illumination, and the state of the camera itself includes the functional state and at least one of the device states.

With reference to the second aspect and the above-mentioned implementation manners, in some implementation manners of the second aspect, the radar determining whether there is an intrusion target in the perimeter under the current detection sensitivity includes: the radar determining the perimeter A confidence level of an intrusion target within the perimeter; if the confidence level is greater than or equal to a first confidence level threshold under the current detection sensitivity, the radar determines that an intrusion target exists within the perimeter.

With reference to the second aspect and the above implementation manners, in some implementation manners of the second aspect, the first confidence threshold under the current detection sensitivity decreases as the shooting capability of the camera increases, and the current detection sensitivity The first confidence threshold under the sensitivity increases as the shooting capability of the camera decreases.

With reference to the second aspect and the above implementation manners, in some implementation manners of the second aspect, if the radar determines that there is an intrusion target within the perimeter, the method further includes: the radar sends a notification message to the camera , the notification message instructs the camera to determine whether the intrusion target is a real intrusion target.

In a third aspect, the present application provides a detection device configured to implement the perimeter detection method in the second aspect or any possible implementation manner of the second aspect. Specifically, the apparatus may include a unit for performing the second aspect or the perimeter detection method in any possible implementation manner of the second aspect.

In a fourth aspect, a detection device is provided, and the device includes a memory and a processor. The memory is used to store instructions; the processor executes the instructions stored in the memory, so that the device executes the second aspect or the perimeter detection method in any possible implementation manner of the second aspect.

In the fifth aspect, a detection system includes a radar, a camera, and an alarm, and the radar method is used to perform the method performed by the radar in any of the above-mentioned aspects or any possible implementation of any of the above-mentioned aspects, and the camera is used for Execute the method performed by the camera in any of the above aspects or in any possible implementation of any of the above aspects, and the alarm is used to perform any of the above aspects or in any possible implementation of any of the above aspects. Executed by the alarm Methods.

In a sixth aspect, a computer-readable storage medium is provided, and the computer-readable storage medium stores instructions, and when the instructions are run on a computer, the computer is made to perform any of the above-mentioned aspects or any possible operation of any of the above-mentioned aspects. The perimeter detection method in the implementation.

In a seventh aspect, there is provided a computer program product containing instructions, which, when run on a computer, cause the computer to execute the perimeter detection method in any of the above aspects or any possible implementation of any of the above aspects.

On the basis of the implementation manners provided in the foregoing aspects, the present application may further be combined to provide more implementation manners.

Description of drawings

Fig. 1 is a schematic block diagram of a detection system provided by an embodiment of the present application;

FIG. 2 is a schematic flowchart of a perimeter detection method provided in an embodiment of the present application;

Fig. 3 is a schematic structural block diagram of a detection device provided by an embodiment of the present application;

Fig. 4 is a schematic structural block diagram of a detection device provided by an embodiment of the present application.

detailed description

The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

First, the detection system provided by the embodiment of the present application is introduced. The detection system is usually deployed near the perimeter along the perimeter, and is used to output an alarm in time after the perimeter is found to be intruded, so as to drive the intrusion target away from the perimeter in time, ensuring Perimeter security.

FIG. 1 shows a schematic diagram of a detection system provided by an embodiment of the present application. As shown in FIG. 1 , the detection system includes a management platform 101 , a radar 102 , and a camera 103 . There is a communication connection between the camera 103 and the radar 102 . The management platform 101 can control the opening and closing of the radar 102 and the camera 103 .

The workflow of the detection system when detecting whether the perimeter is intruded can be as follows:

(1) When the radar detects an intrusion target within the perimeter, the radar sends information on the intrusion target’s omnidirectional movement, lens zoom, and zoom (Pan/Tilt/Zoom, PTZ) to the camera.

(2) The camera locates the intrusion target according to the received PTZ information, obtains the image frame of the intrusion target after the positioning is completed, and further determines whether the intrusion target is a real intrusion target based on the acquired image frame through a visual algorithm .

Exemplarily, the detection system may also include an alarm 104, in this case, the above workflow may further include the following steps:

(3) If the camera is determined to be a real intrusion target, the camera controls the alarm to output an alarm prompt to prompt the intrusion target to leave the perimeter. In addition, in order to ensure that the intrusion target can be driven out of the perimeter, the control alarm will output the alarm prompt. At the same time, the camera can track the intrusion target in real time until the intrusion target leaves the perimeter.

In addition, when the camera controls the alarm to output an alarm prompt, the camera can report an alarm event to the management platform. The alarm event includes information such as the time when the alarm event occurred and the relevant image frame that triggered the alarm event. Manage and view information related to alarm events.

Since there is a camera for secondary confirmation of the detection results of the radar, even if the radar detects an intrusion target in a higher detection sensitivity mode, the false alarm rate will not increase.

However, the camera cannot participate in the secondary confirmation in all cases. For example, in the case of bad weather, the camera may only obtain image frames with low resolution, which is not enough for the camera to distinguish Whether the real intrusion target is included in the image frame, in other words, the camera cannot participate in the secondary confirmation in this case, or, in the case of a camera failure, the camera cannot obtain the image frame at all, at this time, the camera participates in the secondary confirmation Confirmation is out of the question.

To sum up, in the case where the camera cannot participate in the secondary confirmation, if the radar detects in a higher detection sensitivity mode, it may lead to an increase in the false alarm rate.

In view of this, the embodiment of the present application proposes a perimeter detection method, by making the radar enter the detection sensitivity mode corresponding to the camera's shooting capability according to the camera's shooting capability, for example, when the camera's shooting capability is strong, the radar enters a high detection Sensitivity mode, because the camera has a strong shooting ability and the camera will participate in the secondary confirmation, that is, the accuracy of the secondary confirmation of the camera will be higher. Therefore, increasing the radar sensitivity at this time can reduce the overall false negative rate. For another example, in this solution, when the camera's shooting ability is weak or the image frame cannot be acquired, the radar enters a relatively low detection sensitivity mode. Because the camera's shooting ability is weak or even cannot be confirmed twice, the accuracy of the camera's second confirmation The rate will be low, at this time, reducing the detection sensitivity of the radar can reduce the overall false alarm rate. Therefore, the radar in this solution can enter different detection sensitivity modes according to the secondary confirmation shooting ability of the camera, and achieve a win-win situation of low false alarm rate and low false alarm rate.

The perimeter detection method provided by the embodiment of the present application will be described in detail below with reference to the detection system shown in FIG. 1 , and FIG. 2 is an exemplary flow chart of the perimeter detection method 200 . It is worth mentioning that, for the sake of brevity, in the following description, the marks of management platform, camera, alarm, and radar are omitted. For example, the management platform below refers to the management platform 101, the radar refers to the radar 102, and the camera refers to the camera 103. .

Step 201 , the radar determines the current detection sensitivity according to the shooting capability of the camera, which indicates the quality of the image frames acquired by the camera.

The camera can periodically determine its own shooting ability, and send the shooting ability to the radar through the communication connection with the radar. The shooting ability represents the quality of the image frame acquired by the camera. The radar determines whether there is a When an intrusion target is detected, it can be determined in which detection sensitivity mode should be used to detect whether there is an intrusion target in the perimeter according to the shooting capability of the camera sent last time from the camera distance, and then the radar can perform step 202, that is, the radar is based on In the detection sensitivity mode determined by the shooting capability of the camera, it is determined whether there is an intrusion target within the perimeter.

In this embodiment of the present application, the detection sensitivity mode determined by the radar according to the shooting capability of the camera is referred to as the current detection sensitivity mode.

Exemplarily, the camera can determine the shooting capability of the camera according to the current environment and the camera's own state, wherein the current environment can include factors such as current weather and current illumination, and the camera's own state can include factors such as the camera's functional state and device state, The functional status of the camera may include, for example, whether the zoom function of the camera or the flashlight function is normal, and the device status of the camera may include, for example, whether the lens of the camera is worn or not.

For example, if it is a sunny day and the function of the camera and the state of the device are good, the camera can determine that the shooting capability is strong. In other words, the quality of the image frames acquired by the camera under the current environment is relatively high.

For example, it is currently nighttime, and the light is often poor at night. In this environment, the viewing distance of the camera is limited. For areas beyond the viewing distance of the camera, the camera cannot obtain clear image frames. At this time, no matter Whether the state of the camera itself is good, the camera can determine that the shooting ability is weak.

For example, it is currently rainy/snowy weather, which will cause great interference to the camera, causing the camera to fail to obtain clear image frames. At this time, regardless of whether the camera's own state is good or not, the camera can determine that the shooting ability is weak .

For example, if the lens of the camera is severely worn, the clarity of the image frame acquired by the camera using the lens will be seriously affected. In this case, regardless of whether the current environment is good or not, the camera may determine that the shooting capability is weak.

For example, the zoom function of the camera is damaged, resulting in the inability to focus, which will also affect the clarity of the image frame acquired by the camera. In this case, the camera can determine that the shooting ability is weak regardless of whether the current environment is good or not.

Exemplarily, the capability of the camera can be characterized by the following methods:

way 1

Various capabilities of the camera can be represented by several bits, for example, the capability of the camera can be represented by the information carried by two bits, "00" represents the capability of the camera is strong, "01" represents the capability of the camera is medium, "10" Indicates that the ability of the camera is weak.

Assuming that the camera determines that its shooting capability is weak, the corresponding bit is "10". Correspondingly, the radar can determine that the camera's shooting capability is weak according to the bit information from the camera.

way 2

The camera can quantify various capabilities. After quantification, the various capabilities of the camera can be distinguished in a more detailed manner. For example, the value of 0 to 1 represents the strength of the camera’s capabilities. The smaller the value, the higher the capability of the camera. The weaker and the larger the value, the stronger the capability of the camera, for example, when the shooting capability of the camera is less than or equal to 0.3, it means that the capability of the camera is weak, or, when the shooting capability of the camera is between 0.3 and 0.7 When , it means that the ability of the camera is medium, or when the shooting ability of the camera is greater than or equal to 0.7, it means that the ability of the camera is strong.

For example, for a sunny day, and the function of the camera and the state of the device are both good, the quantized capability of the camera may be 0.9.

For example, for nighttime, the quantized camera capability may be 0.5.

For example, for a rainy/snowy daytime, the quantized camera's capability may be 0.3.

For example, for daytime, but the lens of the camera is severely worn, the quantized camera's capability may be 0.3.

Assuming that it is currently a rainy/snowy day, the quantized shooting capability of the camera is 0.3. Correspondingly, the radar can determine that the shooting capability of the camera is weak according to the value from the camera.

After obtaining the shooting capability of the camera, the radar can enter the detection sensitivity mode corresponding to the shooting capability of the camera according to the shooting capability of the camera. The shooting capability is medium, and accordingly, the radar enters a medium detection sensitivity mode, or, the camera has relatively strong shooting capability, and correspondingly, the radar enters a high detection sensitivity mode.

After entering the detection sensitivity mode corresponding to the shooting capability of the camera, the camera determines whether there is an intrusion target within the perimeter in the current detection sensitivity mode.

For example, suppose the radar detects the echo signal after emitting the electromagnetic wave. However, the echo signal may be generated after the electromagnetic wave is disturbed during propagation. In this case, the radar can be in the current detection sensitivity mode, It is further determined whether the echo signal is generated after the electromagnetic wave is reflected by the target in the perimeter. In this embodiment of the present application, an object that triggers electromagnetic wave reflection is called a target.

For example, the radar determines the moving speed of the target according to the received echo signal, and can determine the strength of the received echo signal. Further, the radar determines the number of times the echo signal is received continuously. According to the moving speed of the target, The strength of the echo signal and the number of times the echo signal is received continuously determine the confidence level that the target is an intrusion target.

After obtaining the confidence that the target is an intrusion target, the radar compares the confidence that the target is an intrusion target with the first confidence threshold in the current detection sensitivity mode, if the confidence that the target is an intrusion target is greater than or equal to the current detection sensitivity mode The radar can determine that the target is an intrusion target, in other words, the radar determines that there is an intrusion target within the perimeter. It is worth mentioning that in this application, different detection sensitivity modes represent different first confidence thresholds, and the first confidence threshold in the high detection sensitivity mode is smaller than the first confidence threshold in the medium detection sensitivity mode with the first confidence threshold in low detection sensitivity mode.

For example, the shooting ability of the camera is weak, and the radar enters the low detection sensitivity mode. The first confidence threshold in this detection sensitivity mode can be 85%. Suppose the radar determines that the moving speed of the target is 2,000 based on the received echo signal. m/h, the strength of the echo signal is 5 square radar cross section (radar cross section, RCS) and the number of times the echo signal is received continuously is 10 times. Intensity and the number of times the echo signal is received consecutively, the confidence level of determining that the target is an intrusion target is 88%. In this case, since the confidence level of the target is an intrusion target is greater than the first confidence level in the low detection sensitivity mode Threshold, so the radar can determine the presence of intrusion targets within the perimeter.

For another example, the camera has a strong shooting ability, and the radar enters the high detection sensitivity mode. The confidence threshold in this detection sensitivity mode can be 60%. Suppose the radar determines that the moving speed of the target is 0.5 kilometers according to the received echo signal. / hour, the strength of the echo signal is 2 square radar cross section (radar cross section, RCS) and the number of times the echo signal is received continuously is 6 times. And the number of times the echo signal is received continuously, it can be determined that the target is an intrusion target with a confidence level of 65%. In this case, since the target is an intrusion target, the confidence level is greater than the first confidence threshold in the high detection sensitivity mode , therefore, the radar can determine the presence of intrusion targets within the perimeter. Afterwards, the radar can execute step 203 .

It should be noted that, in this embodiment of the application, the radar can also determine the confidence that the target is an intrusion target based on the distance between the target and the radar, the strength of the echo signal, and the number of times the echo signal is received continuously. Applications are not limited to this.

In step 203, the radar sends a notification message to the camera, and the notification message instructs the camera to determine whether the intrusion target is a real intrusion target.

After the radar determines that there is an intrusion target in the perimeter, it can send a notification message to the camera. The notification message instructs the radar to determine whether there is a real intrusion target in the perimeter. The camera determines that there is an intrusion target in the perimeter according to the notification message, and then performs step 204 .

Step 204, in the case that there is an intrusion target in the perimeter, the camera determines whether there is a real intrusion target in the perimeter.

Exemplarily, the camera can determine whether there is a real intrusion target in the perimeter through the following methods:

way 1

The notification message sent by the radar to the camera can carry the confidence that the target is an intrusion target, and the camera can determine whether the intrusion target is a real intrusion target based on the confidence that the target is an intrusion target and the preset second confidence threshold. For example, if the confidence that the target is an intrusion target is greater than or equal to the preset second confidence threshold, the camera determines that the intrusion target is a real intrusion target. It is worth mentioning that the preset second confidence threshold may be determined by the camera according to the degree of trust in the detection result of the radar.

For example, the confidence that the target is an intrusion target is 99%, and the preset second confidence threshold is 95%. In this case, since the confidence that the target is an intrusion target is greater than the preset second confidence threshold, therefore , the camera can determine that there is a real intrusion target within the perimeter.

way 2

The notification message sent by the radar to the camera can carry the orientation information of the intrusion target. For example, the orientation information of the intrusion target can be the PTZ information of the intrusion target. After receiving the notification message, the camera can obtain the Regarding the image frame of the intrusion target, after acquiring the image frame, the camera can determine whether there is an intrusion target in the image frame through a visual algorithm. If there is an intrusion target in the image frame, the camera can determine that the intrusion target detected by the radar is a real intrusion Target.

way 3

The notification message sent by the radar to the camera can carry the confidence level of the target as an intrusion target and the orientation information of the intrusion target. If the confidence level of the target is an intrusion target is less than the preset second confidence threshold, the camera will , to obtain the image frame about the intrusion target, after obtaining the image frame, the camera can determine whether there is an intrusion target in the image frame through a visual algorithm, if there is an intrusion target in the image frame, the camera can determine that the intrusion target detected by the radar is real intrusion target.

In the case that the detection system includes an alarm, after the camera determines that the intrusion target is a real intrusion target, it can control the alarm to output an alarm prompt to drive the intrusion target out of the perimeter. For example, the camera can perform step 205: The alarm device sends a control instruction, and the control instruction instructs the alarm device to output an alarm prompt, and the alarm device executes step 206 after receiving the control instruction from the camera.

Step 206, the alarm device outputs an alarm prompt.

It should be noted that, in this embodiment of the application, if the confidence level of the radar determining that the target is an intrusion target is less than the first confidence threshold in the current sensitivity mode, in this case, the radar can consider that the target detected by itself is not an intrusion target, in other words, the echo signal detected by the radar is generated after the electromagnetic wave is disturbed during propagation. At this time, the radar can determine that there is no intrusion target in the perimeter. The camera sends a notification message, that is, the detection is terminated.

It should also be noted that in this embodiment of the application, the radar can also determine the current detection sensitivity mode according to whether the camera is currently faulty. For example, if there is a heartbeat signal between the radar and the camera, the radar can detect the heartbeat signal between it and the camera. To determine whether the camera is currently faulty, for example, when the radar does not detect a heartbeat signal, it can be determined that the camera is currently in a faulty state, and then it can be determined that the camera is currently unable to obtain image frames. In this case, the radar can enter a low detection sensitivity mode , and the camera will not be notified for secondary confirmation.

It should also be noted that when the camera determines whether there is a real intrusion target in the perimeter through method 1, the notification message may not only carry the confidence that the target is an intrusion target, but also carry the orientation information of the intrusion target. In this case , the camera can also acquire image frames about the intrusion target, and the acquired image frames about the intrusion target can be uploaded to the alarm platform as evidence.

It should also be noted that the above only uses the method 200 as an example to introduce the perimeter detection method provided by the embodiment of the present application, but this does not constitute a limitation to the embodiment of the present application. For example, in specific implementation, only the above steps may be performed Step 201, step 202, and step 204 are not limited in this embodiment of the present application.

It should also be noted that the perimeter detection method provided in the embodiment of the present application can be applied not only to railway boundary protection, but also to any park-type and perimeter-type perimeter protection.

It should also be noted that the radar in the embodiment of the present application may be a millimeter-wave radar or other types of radar such as lidar, which is not limited in this application.

It should also be noted that the perimeter detection method provided in the embodiment of the present application can also be applied to a detection system including a vibrating optical fiber and a camera. The vibrating optical fiber can determine the current detection sensitivity according to the shooting capability of the camera, so as to achieve the same beneficial effect.

The perimeter detection method provided by the embodiment of the present application is described in detail above with reference to FIG. 1 to FIG. 2 , and the device embodiment of the present application will be described in detail below in conjunction with FIG. 3 to FIG. 4 . It should be understood that the descriptions of the method embodiments correspond to the descriptions of the device embodiments, therefore, for parts not described in detail, reference may be made to the foregoing method embodiments.

Fig. 3 is a schematic structural block diagram of a detection device 300 provided by an embodiment of the present application. The detection device 300 includes: a processing module 310 .

The processing module 310 is configured to: determine the current detection sensitivity according to the shooting capability of the camera, where the shooting capability of the camera indicates the quality of the image frames acquired by the camera;

The processing module 310 is further configured to: under the current detection sensitivity, determine whether there is an intrusion target within the perimeter.

It should be understood that the detection device 300 in the embodiment of the present application can be realized by an application-specific integrated circuit (ASIC), or can be realized by a programmable logic device (programmable logic device, PLD), and the above-mentioned PLD can be Complex programmable logical device (CPLD), field-programmable gate array (FPGA), generic array logic (GAL) or any combination thereof. When the perimeter detection method shown in FIG. 2 can be realized by software, the detection device 300 and its modules can also be software modules.

Optionally, in some embodiments, the shooting capability of the camera is determined by the camera according to the current environment and the camera's own state.

Optionally, in some embodiments, the current environment includes at least one of current weather and current lighting, and the state of the camera itself includes at least one of a function state and a device state of the camera.

Optionally, in some embodiments, the processing module is specifically configured to: determine the confidence level of an intrusion target within the perimeter; if the confidence level is greater than or equal to the first confidence level under the current detection sensitivity Threshold to determine the presence of intrusion targets within the perimeter.

Optionally, in some embodiments, the first confidence threshold under the current detection sensitivity decreases as the shooting capability of the camera increases, and the first confidence threshold under the current detection sensitivity increases with The camera's shooting ability is reduced and increased.

Optionally, in some embodiments, if the detection device 300 determines that there is an intrusion target within the perimeter, the detection device 300 further includes: a sending module 320, configured to send a notification message to the camera, the The notification message instructs the camera to determine whether the intrusion target is a real intrusion target.

The detection device 300 according to the embodiment of the present application may correspond to the implementation of the method described in the embodiment of the present application, and the above-mentioned and other operations and/or functions of each unit in the detection device 300 are to realize the corresponding flow of the method in FIG. 2 , for the sake of brevity, it is not repeated here.

Fig. 4 is a schematic structural block diagram of a detection device 400 provided by an embodiment of the present application. The detection device 400 includes: a processor 410 , a memory 420 , a communication interface 430 , and a bus 440 .

It should be understood that the processor 410 in the detection device 400 shown in FIG. 4 may correspond to the processing module 310 in the detection device 300 in FIG. 3 . The communication interface 430 in the detection device 400 may correspond to the sending module 320 in the detection device 300 .

Wherein, the processor 410 may be connected to the memory 420 . The memory 420 can be used to store the program codes and data. Therefore, the memory 420 may be a storage unit inside the processor 410, or an external storage unit independent of the processor 410, or may include a storage unit inside the processor 410 and an external storage unit independent of the processor 410. part.

Optionally, the detection device 400 may also include a bus 440 . Wherein, the memory 420 and the communication interface 430 may be connected to the processor 410 through the bus 440 . The bus 440 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (Extended Industry Standard Architecture, EISA) bus or the like. The bus 440 can be divided into address bus, data bus, control bus and so on. For ease of representation, only one line is used in FIG. 4 , but it does not mean that there is only one bus or one type of bus.

It should be understood that, in this embodiment of the present application, the processor 410 may be a central processing unit (central processing unit, CPU). The processor can also be other general-purpose processors, digital signal processors (digital signal processors, DSPs), application specific integrated circuits (application specific integrated circuits, ASICs), off-the-shelf programmable gate arrays (field programmable gate arrays, FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like. Alternatively, the processor 410 adopts one or more integrated circuits for executing related programs, so as to implement the technical solutions provided by the embodiments of the present application.

The memory 420 may include read-only memory and random-access memory, and provides instructions and data to the processor 410 . A portion of processor 410 may also include non-volatile random access memory. For example, processor 410 may also store device type information.

When the detection device 400 is running, the processor 410 executes computer-executed instructions in the memory 420 to utilize hardware resources in the detection device 400 to perform the operation steps of the above method.

It should be understood that the detection device 400 according to the embodiment of the present application may correspond to the detection device 300 in the embodiment of the present application, and may correspond to the corresponding subject performing the method shown in FIG. 2 according to the embodiment of the present application, and the detection device 400 The above-mentioned and other operations and/or functions of each module in FIG. 2 are respectively for realizing the corresponding flow of the method in FIG. 2 , and for the sake of brevity, details are not repeated here.

The present application also provides a computer-readable storage medium. The computer-readable storage medium stores computer instructions. When the computer instructions are run on the detection device, the detection device executes the perimeter detection method provided by the embodiment of the present application.

The present application also provides a computer program product, which causes the computer to execute the perimeter detection method provided in the embodiment of the present application when the computer program product is run on the computer.

The above-mentioned embodiments may be implemented in whole or in part by software, hardware, firmware or other arbitrary combinations. When implemented using software, the above-described embodiments may be implemented in whole or in part in the form of computer program products. The computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on the computer, the processes or functions according to the embodiments of the present application will be generated in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website, computer, server or data center Transmission to another website site, computer, server, or data center by wired (eg, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (eg, infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage such as a server, a data center, etc. that includes one or more sets of available media. The available media may be magnetic media (eg, floppy disk, hard disk, magnetic tape), optical media (eg, DVD), or semiconductor media. The semiconductor medium may be a solid state drive (SSD).

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the embodiments of the present application.

Those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed systems, devices and methods may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.

If the functions described above are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions for causing a memory (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disc and other media that can store program codes. .

The above is only the specific implementation of the embodiment of the present application, but the scope of protection of the embodiment of the present application is not limited thereto. Anyone familiar with the technical field can easily Any changes or substitutions that come to mind should be covered within the protection scope of the embodiments of the present application. Therefore, the protection scope of the embodiments of the present application should be based on the protection scope of the claims.

Claims

A perimeter detection method, characterized in that the method is applied to a detection system including a radar and a camera, and the camera and the radar have a communication connection, and the method includes:

The radar determines the current detection sensitivity according to the shooting capability of the camera, and the shooting capability of the camera indicates the quality of the image frame acquired by the camera;

The radar determines whether there is an intrusion target within the perimeter under the current detection sensitivity;

In the event that an intrusion target is present within the perimeter, the camera determines whether the intrusion target is an actual intrusion target.
The method according to claim 1, wherein the shooting capability of the camera is determined by the camera according to the current environment and the state of the camera itself.
The method according to claim 2, wherein the current environment includes at least one of current weather and current lighting, and the state of the camera itself includes at least one of the functional state and device state of the camera .
The method according to any one of claims 1 to 3, wherein the radar determines whether there is an intrusion target within the perimeter under the current detection sensitivity, comprising:

the radar determines a degree of confidence that an intruder target is present within the perimeter;

If the confidence level is greater than or equal to a first confidence level threshold under the current detection sensitivity, the radar determines that there is an intrusion target within the perimeter.
The method according to claim 4, characterized in that, the first confidence threshold under the current detection sensitivity decreases as the quality of the image frames acquired by the camera increases, and the current detection sensitivity under the The first confidence threshold of is increased as the shooting capability of the camera is weakened.
The method according to any one of claims 1 to 5, wherein if the radar determines that there is an intrusion target within the perimeter, the method further comprises:

The radar sends a notification message to the camera, the notification message instructs the camera to determine whether the intrusion target is a real intrusion target.
The method according to claim 6, wherein the notification message carries a degree of confidence that an intrusion target exists within the perimeter, and the camera determines whether the intrusion target is a real intrusion target, comprising:

If the confidence level is greater than or equal to a preset second confidence level threshold, the camera determines that the intrusion target is a real intrusion target.
The method according to claim 6, wherein the notification message carries the confidence level of an intrusion target in the perimeter and the orientation information of the intrusion target, and the camera determines whether the intrusion target is real Intrusion targets, including:

If the confidence is less than the preset second confidence threshold, the camera determines whether the intrusion target is a real intrusion target according to the acquired image frame about the intrusion target, and the The image frames of are obtained according to the azimuth information of the intrusion target.
The method according to any one of claims 1 to 8, wherein the detection system further comprises an alarm, and if the camera determines that the intrusion target is a real intrusion target, the method further comprises:

The camera controls the alarm device to output an alarm prompt, and the alarm prompt is used to prompt the intrusion target to leave the perimeter.
A perimeter detection method, characterized in that the method comprises:

The radar determines the current detection sensitivity according to the shooting capability of the camera, and the shooting capability of the camera indicates the quality of the image frame acquired by the camera;

Under the current detection sensitivity, the radar determines whether there is an intrusion target within the perimeter.
The method according to claim 10, wherein the shooting capability of the camera is determined by the camera according to the current environment and the state of the camera itself.
The method according to claim 11, wherein the current environment includes at least one of current weather and current lighting, and the state of the camera itself includes at least one of the functional state and device state of the camera .
The method according to any one of claims 10 to 12, wherein the radar determines whether there is an intrusion target within the perimeter under the current detection sensitivity, comprising:

the radar determines a degree of confidence that an intruder target is present within the perimeter;

If the confidence level is greater than or equal to a first confidence level threshold under the current detection sensitivity, the radar determines that there is an intrusion target within the perimeter.
The method according to claim 13, characterized in that, the first confidence threshold under the current detection sensitivity decreases as the shooting capability of the camera increases, and the first confidence threshold under the current detection sensitivity The threshold increases as the camera's shooting capability decreases.
The method according to any one of claims 10 to 14, wherein if the radar determines that there is an intrusion target within the perimeter, the method further comprises:

The radar sends a notification message to the camera, the notification message instructs the camera to determine whether the intrusion target is a real intrusion target.
A detection device, characterized in that the device comprises:

A processing module, configured to determine the current detection sensitivity according to the shooting capability of the camera, where the shooting capability of the camera indicates the quality of the image frames acquired by the camera;

The processing module is further configured to determine whether there is an intrusion target within the perimeter under the current detection sensitivity.
The device according to claim 16, wherein the shooting capability of the camera is determined by the camera according to the current environment and the state of the camera itself.
The device according to claim 17, wherein the current environment includes at least one of current weather and current lighting, and the state of the camera itself includes at least one of the functional state and device state of the camera .
The device according to any one of claims 16 to 18, wherein the processing module is specifically configured to: determine the confidence level of an intrusion target within the perimeter; if the confidence level is greater than or equal to the The first confidence threshold under the current detection sensitivity to determine that there is an intrusion target within the perimeter.
The device according to claim 19, characterized in that, the first confidence threshold under the current detection sensitivity decreases as the shooting capability of the camera increases, and the first confidence threshold under the current detection sensitivity The threshold increases as the camera's shooting capability decreases.
The device according to any one of claims 16 to 20, wherein if the device determines that there is an intrusion target within the perimeter, the device further comprises:

A sending module, configured to send a notification message to the camera, where the notification message instructs the camera to determine whether the intrusion target is a real intrusion target.
A detection device, characterized in that the detection device includes a processor and a memory, and the memory is used to store instructions, and when the instructions are executed by the processor, the detection device performs the tasks described in claims 10 to 10. The perimeter detection method described in any one of 15.
A detection system, characterized in that the detection system includes a radar, a camera and an alarm, the radar is used to perform the method performed by the radar according to any one of claims 1 to 9, and the camera is used for The method performed by the camera according to any one of claims 1 to 9 is performed, and the alarm device is used to perform the method performed by the alarm device according to any one of claims 1 to 9.
A computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions, and when the computer instructions are run on the detection device, the detection device is made to perform any one of claims 1-9. A method according to one, or, causing the detection device to execute the perimeter detection method according to any one of claims 10 to 15.
A computer program product, characterized in that, when the computer program product is run on a computer, the computer is made to execute the method according to any one of claims 1 to 9, or the computer is made to execute the method as described in The perimeter detection method according to any one of claims 10 to 15.