A non-cooperative method for indoor people counting, positioning and external intrusion detection

Abstract

The present invention relates to the field of smart home security technology, and discloses a non-cooperative indoor personnel counting, positioning and external intrusion detection method, the specific steps of which are: installing a transmitter and a receiver in each room according to the distribution of objects in the room; relearning by using a learning mechanism to adapt to the current environment; after learning is completed, continuously monitoring the signal strength of the current room; calculating the difference between the signal strength before and after the change, and comparing the difference with the set detection threshold; if the threshold is exceeded, it can be judged that there are people in the area or there is an intrusion by others; and uploading the judgment result to the mobile phone of the corresponding person. The present invention takes indoor people as the research object, and can realize the acquisition of the number and location information of indoor people in an indoor environment. Even if the relevant personnel are unwilling to "cooperate", this function can be realized, and the activity area of ​​the monitored person and whether there is an abnormality can be understood more accurately; it can also warn others of intrusion and protect the property safety of the home in real time.

Description

Technical Field

[0001] The present invention relates to the field of smart home security technology, and in particular to a non-cooperative indoor personnel counting, positioning and external intrusion detection method. Background Art

[0002] With the rapid development of Internet of Things technology and the increasing demand for indoor security monitoring, real-time monitoring of people at home is increasingly accepted by ordinary families. As the backbone of the family, young and middle-aged groups are increasingly inclined to adopt remote monitoring methods, regularly checking indoor conditions during work breaks, and the primary concern is the detection of the number and location information of indoor people. When there are elderly people and children at home, remote monitoring can be used to locate and count people in the room, and when no one is at home, intrusion detection can be achieved. At present, the mainstream remote monitoring methods include infrared, image and video detection technologies, which can realize real-time detection of information related to indoor people, but due to the characteristics of light propagation along a straight path and personal privacy issues, such methods have certain limitations, and there are many doors and windows in the home, the amount of data transmission is huge, and the cost is high; in addition, because the elderly and children have a repulsive psychology to carry electronic devices, they do not have the conditions to carry corresponding devices for intruders, and electronic devices are independently powered and need to be charged frequently. Summary of the invention

[0003] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a non-cooperative indoor personnel counting, positioning and external intrusion detection method, which solves the problem of realizing the number and position of indoor personnel and external personnel intrusion detection in a complex indoor environment, and at the same time can provide guardians with remote monitoring of indoor conditions.

[0004] To achieve the above object, the present invention adopts the following technical solution:

[0005] A non-cooperative indoor people counting, positioning and external intrusion detection method, the specific steps are:

[0006] Install transmitters and receivers in each room according to the distribution of objects in the room;

[0007] Use learning mechanisms to relearn to adapt to the current environment;

[0008] After learning is completed, the signal strength of the current room is continuously monitored;

[0009] Calculate the difference between the signal strength before and after the change, and compare the difference with the set detection threshold;

[0010] If the threshold is exceeded, it can be determined that there are people in the area or someone else is intruding;

[0011] The judgment result is uploaded to the mobile phone of the corresponding personnel.

[0012] Furthermore, the learning mechanism is divided into three categories: a direct learning mechanism without abnormal data, a learning mechanism with individual abnormal data, and a learning mechanism with partial abnormal data.

[0013] Furthermore, the direct learning mechanism for data without abnormalities: directly collects signal strength data, and when the amount of information in the signal strength data reaches a certain statistical requirement, takes the average of the signal strength data, and determines the detection threshold in a static environment based on the maximum and minimum values ​​of the signal strength data.

[0014] Furthermore, the learning mechanism for the existence of individual abnormal data: according to the empirical value, the data error value of the signal strength in the indoor static environment is set to be within ±5dB, and it is determined whether the collected signal strength data has data with a signal strength exceeding ±5dB. If so, the data is abnormal data and is eliminated; then, when the amount of information in the signal strength data reaches a certain statistical requirement, the average of the signal strength data is taken, and the detection threshold in the static environment is determined according to the maximum and minimum values ​​of the signal strength data.

[0015] Furthermore, the learning mechanism for the existence of some abnormal data; according to the empirical value, the data error value of the signal strength in the indoor static environment is set to be within ±5dB. After determining that the signal strength data is abnormal, first check whether there are related electrical appliances working. If so, record the data information of the environment when the appliance is working, and directly collect the signal strength data. When the amount of information of the signal strength data reaches a certain statistical requirement, take the average of the signal strength data, and determine the detection threshold in the static environment according to the maximum and minimum values ​​of the signal strength data; if no electrical appliance is working, it is determined that there is human interference in the learning process and re-learning is required.

[0016] Furthermore, the data information of the clear working environment of the electrical appliance is recorded, specifically, only the corresponding threshold value and average value information under different working conditions of the electrical appliance in the current area is stored.

[0017] Furthermore, after the system learning is completed, the signal strength of the current room is continuously monitored. The specific steps are:

[0018] Obtain the corresponding threshold information in the current environment: obtain the working status of the current electrical appliances by communicating with other smart power nodes in the room, and retrieve the corresponding signal strength data stored in the external memory according to different states;

[0019] The current signal strength measurement value is subtracted from the signal strength data retention value. If the difference in signal strength data exceeds the threshold continuously, it is determined that there is a person in the current environment.

[0020] Furthermore, the specific steps of uploading the judgment result to the mobile phone of the corresponding person are as follows:

[0021] The independent local area network of each room uses RS485 wired method to realize the overall data sharing of the room. After all the data are collected, the GSM / GPRS function of the SIM800 module carried by the main node is used to upload the collected data information to the guardian's mobile phone. The guardian determines the number of people in the home, the area where the people are located, and whether there is any danger or intrusion.

[0022] Furthermore, the communication signal strength of the transmitter and the receiver is described using an RSSI value, and the larger the RSSI value, the stronger the communication signal strength of the transmitter and the receiver; when communication data is transmitted based on a relevant communication protocol, the RSSI value is recorded in the packet header of the transmitted communication data packet; the RSSI is defined as follows:

[0023]

[0024] In formula (1), 1mW is often used. The value of is defined as follows:

[0025]

[0026] In formulas (1)-(2), the meanings of the symbols are as follows:

[0027] The energy of the electromagnetic wave sent by the transmitter

[0028] The energy of the electromagnetic wave received by the receiver

[0029] Send Gain

[0030] Receive gain

[0031] wavelength

[0032] The distance between the sender and receiver.

[0033] Furthermore, a system for non-cooperative indoor personnel counting, positioning and external intrusion detection method is implemented, including a receiver and a transmitter installed in each room, the receivers in all rooms are connected in series through an RS485 bus, and the two ends of the SIM800 module are respectively connected to a CPU controller and one of the receivers at the two ends; the CPU controller communicates with the RS485; the CPU controller is also connected to a key module and a storage unit.

[0034] The beneficial effects of the present invention are as follows: the present invention takes indoor people as the research object, and can realize the acquisition of the number and location information of indoor people in the indoor environment. Even if the relevant people are unwilling to "cooperate", this function can be realized. Compared with the existing active methods, it is a rare passive method. By obtaining relevant information, on the basis of ensuring sufficient privacy of the monitored person, it is also possible to more accurately understand the activity area of ​​the monitored person and whether there is any abnormality; at the same time, it can also warn others of intrusion and protect the property safety of the home in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Attached Figure 1 It is a schematic diagram of installing the transmitter and the receiver in the room of the present invention;

[0036] Attached Figure 2 is a flow chart of the learning mechanism in the present invention;

[0037] Attached Figure 3 This is a flow chart of a single detection in the present invention;

[0038] Attached Figure 4 This is the overall system block diagram of the present invention. DETAILED DESCRIPTION

[0039] Below, the present invention is further described in conjunction with the accompanying drawings and specific embodiments:

[0040] Based on the existing cooperative personnel detection system, the present invention uses the common network parameter in the mainstream Internet of Things system: Received Signal Strength Indication (RSSI) to realize personnel detection. A specific solution is designed for the implementation of the present invention by integrating the characteristics of RSSI, the characteristics of the Internet of Things, and the characteristics of the working environment of the Internet of Things. The received signal strength RSSI (Received Signal Strength Indicator) is both the signal strength of the wireless communication device during the data exchange process and the energy evaluation parameter of the radio signal received by the communication module. RSSI is compatible with protocol clusters such as IEEE802.11 and IEEE802.15. The larger the RSSI value, the stronger the communication signal strength between the transmitting end and the receiving end of the communication system. When data is transmitted based on the relevant communication protocol, RSSI is usually recorded in the packet header of the transmitted data packet.

[0041] The definition of RSSI is as follows:

[0042]

[0043] In formula (1), 1mW is often used. The value of is defined as follows:

[0044]

[0045] In formulas (1)-(2), the meanings of the symbols are as follows:

[0046] : The energy of the electromagnetic wave sent by the transmitter

[0047] : The energy of the electromagnetic wave received by the receiving end

[0048] : Send gain

[0049] : Receive gain

[0050] :wavelength

[0051] : The distance between the receiving end and the sending end

[0052] It can be seen from formula (2) that when the electromagnetic wave energy sent by the transmitter, the transmission gain and other parameters are fixed, the distance between the two is determined according to the electromagnetic wave energy received by the receiver; similarly, if the distance is constant, whether there is an obstruction between the two is determined according to the energy of the receiver. This is also the basic principle and feasibility support of the present invention.

[0053] like Figure 1 As shown, corresponding Zigbee local area networks are arranged in different rooms, and transmitters and receivers are installed at corresponding positions in each room. By placing the transmitter and the receiver separately, a corresponding communication link can be formed in each room, and the presence of objects or personnel in the room area can be sensed based on the strength of the communication signal of the signal link.

[0054] The principle of placing the transmitter and receiver is to minimize the interference of objects in the room on the communication signal. Generally, the transmitter is placed on the roof where there is less possibility of obstruction, and then the receiver is placed in a corner at the same height or slightly lower than the person's height based on the person's height.

[0055] like Figure 4 As shown, the system for implementing the detection method of the present invention includes a receiver and a transmitter installed in each room. The receivers of all rooms are connected in series through the RS485 bus. The two ends of the SIM800 module are respectively connected to the CPU controller and one of the two receivers; the CPU controller communicates with the RS485 bus; the CPU controller is also connected to the key module and the storage unit, and the CPU controller is a CC25830 module. The receivers of all rooms are connected in series through the RS485 bus, which can reduce costs. The independent local area network of each room is used to realize the data sharing of the whole room by RS485 wired mode. After all data are collected, the GSM / GPRS function of the SIM800 module carried by the main node is used to upload it to the mobile phone of the relevant personnel, and the relevant personnel determine the number of people in the home, the area where the people are located, and whether there is danger or intrusion.

[0056] When the system is installed for the first time or when there is a major change in the location of items in the home, the learning mechanism is used to relearn to adapt to the current environment. After waiting for the learning to be completed, the communication signal strength in the current room is continuously monitored. When a person appears, the signal transmitted in the corresponding area will be blocked, thereby causing the signal strength at the receiving end to change. By comparing the signal strength difference before and after the change with the set threshold, it is determined whether there is a person in the area. The method of the present invention can also determine whether there is an intrusion by others.

[0057] The learning mechanisms are divided into three categories: direct learning mechanism without abnormal data, learning mechanism with individual abnormal data, and learning mechanism with partial abnormal data.

[0058] Direct learning mechanism without abnormal data: directly collect signal strength data, and when the amount of information in the signal strength data reaches a certain statistical requirement, take the average of the signal strength data, and determine the detection threshold in a static environment based on the maximum and minimum values ​​of the signal strength data.

[0059] There is a learning mechanism for individual abnormal data: according to the empirical value, the data error value of the signal strength in the indoor static environment is set to be within ±5dB, and it is determined whether the collected signal strength data has data with a signal strength exceeding ±5dB. If so, the data is abnormal data and is eliminated; then, when the amount of information in the signal strength data reaches a certain statistical requirement, the average of the signal strength data is taken, and the detection threshold in the static environment is determined according to the maximum and minimum values ​​of the signal strength data.

[0060] There is a learning mechanism for some abnormal data; according to the empirical value, the data error value of the signal strength in the indoor static environment is set to be within ±5dB. After determining that the signal strength data is abnormal, first check whether there are related electrical appliances working. If so, record the data information of the environment when the appliance is working, and directly collect the signal strength data. When the amount of information in the signal strength data reaches a certain statistical requirement, take the average of the signal strength data, and determine the detection threshold in the static environment based on the maximum and minimum values ​​of the signal strength data; if no electrical appliance is working, it is determined that there is human interference in the learning process and re-learning is required.

[0061] like Figure 2 As shown, the learning process of the system of the present invention is:

[0062] S1: Initializing the system of the present invention;

[0063] S2: All transmitters and receivers in the room collect communication signal strength information;

[0064] S3: Determine whether the collected communication information strength data meets the statistical requirements. If not, continue collecting; if satisfied, proceed to the next step;

[0065] S4: Determine whether the collected communication signal strength data contains abnormal data. If not, calculate the alarm threshold under the environment and store the alarm threshold information of the communication signal strength under the environment. If there is abnormal data, proceed to the next step:

[0066] S5: Determine the type of abnormal data. If there is individual abnormal data, delete the abnormal data, calculate the alarm threshold in the environment, and store the alarm threshold information of the communication signal strength in the environment; if there is partial abnormal data or the data is abnormal in stages, use the smart socket to obtain the working status of the electrical appliances in the room, and determine whether it is human intervention. If it is human intervention, re-collect the communication signal strength information; if it is not human intervention, calculate the alarm threshold of the working status of the electrical appliance, and store the alarm threshold information of the communication signal strength in the environment.

[0067] The data obtained by the system through learning needs to be stored in the EEPROM storage unit.

[0068] Considering that human bodies move slowly, the real-time requirements for communication signal strength detection are low, and a circular scanning method is used to detect the personnel situation in the current area in real time. Figure 3 The figure shows the detection flow chart of the present invention. After the system of the present invention starts to run, it must first obtain the corresponding threshold information in the current environment: obtain the working status of the current electrical appliances by communicating with other intelligent power consumption nodes in the room, and retrieve the corresponding data retained in the EEPROM memory according to different states; subtract the current signal measurement value from the retained value, and if the difference value exceeds the threshold continuously, it is determined that there are people in the current environment.

[0069] For those skilled in the art, various other corresponding changes and deformations can be made according to the technical solutions and concepts described above, and all of these changes and deformations should fall within the protection scope of the claims of the present invention.

Claims

1. A non-cooperative indoor people counting, positioning and external intrusion detection method, characterized in that: The specific steps are: Install transmitters and receivers in each room according to the distribution of objects in the room; Use learning mechanisms to relearn to adapt to the current environment; The learning mechanisms are divided into three categories: direct learning mechanism without abnormal data, learning mechanism with individual abnormal data, and learning mechanism with partial abnormal data; The direct learning mechanism without abnormal data: directly collect signal strength data, and when the amount of information of the signal strength data reaches a certain statistical requirement, take the average of the signal strength data, and determine the detection threshold in a static environment according to the maximum and minimum values ​​of the signal strength data; The learning mechanism for the presence of individual abnormal data: according to the empirical value, the data error value of the signal strength is set within ±5dB in the indoor static environment, and it is determined whether the collected signal strength data has data with a signal strength exceeding ±5dB. If so, the data is abnormal data and is removed; Then, when the amount of information of the signal strength data reaches a certain statistical requirement, the average of the signal strength data is taken, and the detection threshold in a static environment is determined according to the maximum and minimum values ​​of the signal strength data; The learning mechanism with partial abnormal data: according to the empirical value, the data error value of the signal strength in the indoor static environment is set to be within ±5dB. After judging that the signal strength data is abnormal, first check whether there are related electrical appliances working. If so, record the data information of the environment when the appliance is working, directly collect the signal strength data, and when the information amount of the signal strength data reaches a certain statistical requirement, take the average of the signal strength data, and determine the detection threshold in the static environment according to the maximum and minimum values ​​of the signal strength data; if no electrical appliance is working, it is determined that there is human interference in the learning process, and re-learning is required; After learning is completed, the signal strength of the current room is continuously monitored; Calculate the difference between the signal strength before and after the change, and compare the difference with the set detection threshold; If the threshold is exceeded, it can be determined that there are people in the room or someone has invaded; Upload the judgment results to the mobile phone of the corresponding personnel; The communication signal strength of the transmitter and the receiver is described using the RSSI value. The larger the RSSI value, the stronger the communication signal strength of the transmitter and the receiver. When the communication data is transmitted based on the relevant communication protocol, the RSSI value is recorded in the packet header of the transmitted communication data packet. The RSSI is defined as follows: In formula (1), The value is 1mW. The value of is defined as follows: In formulas (1)-(2), the meanings of the symbols are as follows: The energy of the electromagnetic wave sent by the transmitter The energy of the electromagnetic wave received by the receiver Send Gain Receive gain wavelength The distance between the receiver and the transmitter; The distance between the transmitter and the receiver is constant, and whether there is any shielding between the two is determined according to the energy of the electromagnetic waves received by the receiving end.

2. A non-cooperative indoor personnel counting, positioning and external intrusion detection method as claimed in claim 1, characterized in that: The data information recorded about the working clear environment of the appliance specifically stores only the corresponding threshold and average value information under different working conditions of the appliance in the current area.

3. A non-cooperative indoor personnel counting, positioning and external intrusion detection method as claimed in claim 1, characterized in that: After the learning mechanism completes learning, it continues to monitor the signal strength in the current room. The specific steps are: Obtain the corresponding threshold information in the current environment: obtain the working status of the current electrical appliances by communicating with other smart power nodes in the room, and retrieve the corresponding signal strength data stored in the external memory according to different states; The current signal strength measurement value is subtracted from the signal strength data retention value. If the difference in signal strength data exceeds the threshold continuously, it is determined that there is a person in the current environment.

4. A non-cooperative indoor personnel counting, positioning and external intrusion detection method as claimed in claim 1, characterized in that: The specific steps of uploading the judgment result to the mobile phone of the corresponding personnel are as follows: The independent local area network of each room uses RS485 wired method to realize the overall data sharing of the room. After all the data are collected, the GSM / GPRS function of the SIM800 module carried by the main node is used to upload the collected data information to the guardian's mobile phone. The guardian determines the number of people in the home, the area where the people are located, and whether there is any danger or intrusion.

Images