CN107590439B - Target person identification and tracking method and device based on monitoring video - Google Patents
Target person identification and tracking method and device based on monitoring video Download PDFInfo
- Publication number
- CN107590439B CN107590439B CN201710711592.1A CN201710711592A CN107590439B CN 107590439 B CN107590439 B CN 107590439B CN 201710711592 A CN201710711592 A CN 201710711592A CN 107590439 B CN107590439 B CN 107590439B
- Authority
- CN
- China
- Prior art keywords
- mac address
- address information
- acquiring
- information
- monitoring video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The invention discloses a target person identification and tracking method and device based on a monitoring video, and relates to the technical field of communication, wherein the method comprises the following steps: acquiring a monitoring video image acquired by a monitoring device, acquiring MAC address information of a mobile phone acquired by a WIFI hotspot, and acquiring sound signal data acquired by pickup equipment; associating the monitoring video image, the MAC address information and the sound signal data according to the first time information, the second time information and the third time information; and identifying and tracking the target person based on the associated monitoring video image, the MAC address information and the sound signal data. The method, the device and the storage medium of the invention provide an automatic identification and tracking mode for the target person, improve the efficiency and accuracy of identification and tracking of the target person, and can help police, security personnel and the like to quickly find suspect.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a target person identification and tracking method and device based on a monitoring video.
Background
Video monitoring is an important component of a security system, and generally comprises a front-end camera, a transmission cable and a video monitoring platform. Currently, a video monitoring system can monitor key departments or places in real time. Because the video monitoring system can realize real-time monitoring of people or things, the public security, traffic, security or other departments can perform operations such as on-site playback, security guard, suspect identification, related personnel tracking and the like according to the image data acquired by the video monitoring system. However, the conventional video monitoring system can only collect image data, and only can identify image features when performing operations such as field playback, security guard, suspect identification, related personnel tracking and the like, and an automatic identification and tracking means is lacked.
Disclosure of Invention
In view of the above, the present invention provides a target person identification and tracking method and device based on a surveillance video.
According to one aspect of the invention, a target person identification and tracking method based on a surveillance video is provided, which comprises the following steps: acquiring a monitoring video image acquired by a monitoring device and first time information of acquiring the monitoring video image; acquiring MAC address information of the mobile phone acquired by the WIFI hotspot and second time information for acquiring the MAC address information; acquiring sound signal data acquired by pickup equipment and third time information for acquiring the sound signal data; associating the monitoring video image, the MAC address information and the sound signal data according to the first time information, the second time information and the third time information; the monitoring device, the WIFI hotspot and the sound pickup equipment are arranged in the same area; and identifying and tracking a target person based on the associated monitoring video image, the MAC address information and the sound signal data.
Optionally, the identifying and tracking a target person based on the associated surveillance video image, the MAC address information, and the sound signal data comprises: acquiring a plurality of monitoring video images associated with the MAC address information; respectively acquiring other MAC address information associated with the plurality of monitoring video images, and generating a plurality of MAC address information sets corresponding to the plurality of monitoring video images; and calculating the intersection of the multiple MAC address information sets, selecting target MAC address information from the intersection, and acquiring identity information corresponding to the target MAC address information.
Optionally, determining characteristics of the target person, and based on obtaining a plurality of monitored video images including the target person, wherein the characteristics of the target person include: clothing, height, gender; respectively acquiring MAC address information associated with a plurality of monitored video images containing the target person to generate a plurality of MAC address information sets; calculating the intersection of a plurality of MAC address information sets, acquiring target MAC address information from the intersection based on a selection rule, and acquiring identity information corresponding to the target MAC address information and the running tracks of the target MAC address information.
Optionally, the identifying and tracking a target person based on the associated surveillance video image, the MAC address information, and the sound signal data comprises: judging whether abnormal MAC address information and corresponding abnormal persons exist or not based on the incidence relation between the monitoring video image and the MAC address information, and if so, giving an alarm; the rule for judging whether the abnormal MAC address information exists comprises the following steps: whether MAC address information with frequency larger than a frequency threshold appears in a set area or not and whether the MAC address information is in a blacklist or not; the set region includes: banks, shopping malls, stations.
Optionally, identity information is obtained from an operator client system according to the MAC address information, where the identity information includes: sex, age, height; and positioning a target person corresponding to the MAC address information in the monitoring video image based on the identity information.
Optionally, acquiring sound signal data associated with the monitoring video image, extracting a voiceprint feature vector from the sound signal data, calculating a voiceprint similarity between the voiceprint feature vector and voiceprint data stored in a preset voiceprint library, and if the voiceprint similarity is greater than a set threshold, acquiring identity information corresponding to the voiceprint data; and/or judging whether a face exists in the monitoring video image, if so, extracting the face image from the monitoring video image and comparing the face image with a face image sample stored in a preset face library, and if the comparison is successful, acquiring identity information corresponding to the face image sample; and positioning a target person corresponding to the MAC address information in the monitoring video image based on the identity information.
Optionally, it is determined that, in the same time period, a plurality of adjacent WIFI hotspots receive a WIFI signal detection packet sent by the mobile phone, where the detection packet includes: the MAC address information and the RSSI (received signal strength indicator) of the wireless signal transmission of the mobile phone; determining the distance between the mobile phone and each WIFI hotspot according to the RSSI; calculating position coordinate information of the mobile phone according to the coordinates of the WIFI hotspots and the respective distances between the mobile phone and the WIFI hotspots; and displaying the position of the mobile phone on the electronic map based on the position coordinate information.
According to another aspect of the present invention, there is provided a target person identification and tracking device based on surveillance video, including: the video acquisition module is used for acquiring a monitoring video image acquired by a monitoring device and acquiring first time information of the monitoring video image; the WIFI hotspot acquisition module is used for acquiring the MAC address information of the mobile phone acquired by the WIFI hotspot and acquiring second time information of the MAC address; the sound signal acquisition module is used for acquiring sound signal data acquired by pickup equipment and third time information for acquiring the sound signal data; the information association module is used for associating the monitoring video image, the MAC address information and the sound signal data according to the first time information, the second time information and the third time information; the monitoring device, the WIFI hotspot and the sound pickup equipment are arranged in the same area; and the identification tracking module is used for identifying and tracking a target person based on the associated monitoring video image, the MAC address information and the sound signal data.
Optionally, the identification tracking module includes: the target identity confirming unit is used for acquiring a plurality of monitoring video images associated with the MAC address information; respectively acquiring other MAC address information associated with the plurality of monitoring video images, and generating a plurality of MAC address information sets corresponding to the plurality of monitoring video images; and calculating the intersection of the multiple MAC address information sets, selecting target MAC address information from the intersection, and acquiring identity information corresponding to the target MAC address information.
Optionally, the identification tracking module includes: a target track determination unit, configured to determine characteristics of a target person, and obtain a plurality of surveillance video images including the target person based on the characteristics, where the characteristics of the target person include: clothing, height, gender; respectively acquiring MAC address information associated with a plurality of monitored video images containing the target person to generate a plurality of MAC address information sets; calculating the intersection of a plurality of MAC address information sets, acquiring target MAC address information from the intersection based on a selection rule, and acquiring identity information corresponding to the target MAC address information and the running tracks of the target MAC address information.
Optionally, the identification tracking module includes: an abnormal person determining unit, configured to determine whether there is abnormal MAC address information and a corresponding abnormal person based on an association relationship between the monitored video image and the MAC address information, and if so, issue an alarm; the rule for judging whether the abnormal MAC address information exists comprises the following steps: whether MAC address information with frequency larger than a frequency threshold appears in a set area or not and whether the MAC address information is in a blacklist or not; the set region includes: banks, shopping malls, stations.
Optionally, the identification tracking module includes: a target positioning unit, configured to obtain identity information from an operator client system according to the MAC address information, where the identity information includes: sex, age, height; and positioning a target person corresponding to the MAC address information in the monitoring video image based on the identity information.
Optionally, the target positioning unit is configured to obtain sound signal data associated with the monitored video image, extract a voiceprint feature vector from the sound signal data, calculate a voiceprint similarity between the voiceprint feature vector and voiceprint data stored in a preset voiceprint library, and if the voiceprint similarity is greater than a set threshold, obtain identity information corresponding to the voiceprint data; and/or judging whether a face exists in the monitoring video image, if so, extracting the face image from the monitoring video image and comparing the face image with a face image sample stored in a preset face library, and if the comparison is successful, acquiring identity information corresponding to the face image sample; and positioning a target person corresponding to the MAC address information in the monitoring video image based on the identity information.
Optionally, the target location unit is configured to determine that, in the same time period, a plurality of adjacent WIFI hotspots receive a WIFI signal detection packet sent by the mobile phone, where the detection packet includes: the MAC address information and the RSSI (received signal strength indicator) of the wireless signal transmission of the mobile phone; determining the distance between the mobile phone and each WIFI hotspot according to the RSSI; calculating position coordinate information of the mobile phone according to the coordinates of the WIFI hotspots and the respective distances between the mobile phone and the WIFI hotspots; and displaying the position of the mobile phone on the electronic map based on the position coordinate information.
According to another aspect of the present invention, there is provided a target person identification and tracking device based on surveillance video, including: a memory; and a processor coupled to the memory, the processor configured to execute the surveillance video-based target person identification tracking method as described above based on instructions stored in the memory.
According to still another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions, which when executed by a processor, implement the target person identification and tracking method based on surveillance video as described above.
The target person identification and tracking method and device based on the surveillance video, disclosed by the invention, have the advantages that the surveillance video image, the MAC address information and the sound signal data are associated and used for identifying and tracking the target person, an automatic identification and tracking mode for the target person is provided, the efficiency and the accuracy of identifying and tracking the target person are improved, and the method and device can help public security personnel, security personnel and the like to quickly find suspect.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart illustrating an embodiment of a surveillance video-based target person identification and tracking method according to the present invention;
FIG. 2 is a block diagram of an embodiment of a surveillance video based target person identification and tracking device according to the present invention;
FIG. 3 is a block diagram of an identification tracking module in an embodiment of a surveillance video-based target person identification tracking device according to the present invention;
fig. 4 is a block diagram of another embodiment of a target person identification and tracking device based on surveillance video according to the present invention.
Detailed Description
The present invention now will be described more fully hereinafter with reference to the accompanying drawings, in which exemplary embodiments of the invention are shown. The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, 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 invention. The technical solution of the present invention is described in various aspects below with reference to various figures and embodiments.
The terms "first", "second", and the like in the present invention are used only for descriptive distinction and have no other special meaning.
Fig. 1 is a schematic flowchart of an embodiment of a target person identification and tracking method based on surveillance video according to the present invention, as shown in fig. 1:
The WIFI hotspot can be a wireless router, the mobile phone can be a smart mobile phone and the like, the MAC address is also called a physical address and a hardware address, is used for defining the position of the network equipment, consists of a string of English and numeric character strings, and has global uniqueness. The MAC address of the mobile phone is the network card address of the mobile phone.
And 103, acquiring sound signal data collected by the sound pickup equipment and third time information of the collected sound signal data. The sound pickup equipment is a microphone and the like.
And 104, associating the monitoring video image, the MAC address information and the sound signal data according to the first time information, the second time information and the third time information.
The monitoring device, the WIFI hotspot and the sound pickup equipment are arranged in the same area, namely the installation position is close, and the monitoring or acting range is basically the same. For example, the monitoring device, the WIFI hotspot and the sound pickup equipment are all installed at a fixed position on the station square. The monitoring video images, the MAC address information and the sound signal data can be periodically uploaded to the background server by the monitoring device, the WIFI hotspot and the pickup equipment.
And if the time indicated by the first time information, the second time information and the third time information is the same or the interval of the phase difference is within a set time difference range, for example, the time difference is 2 seconds, and the like, associating the monitoring video image, the MAC address information and the sound signal data, generating an associated file and storing the associated file on a background server. The associated file can be various, such as an xml file and the like.
And 105, identifying and tracking the target person based on the associated monitoring video image, the MAC address information and the sound signal data.
There are many applications for identifying and tracking a target person. In one embodiment, a plurality of surveillance video images associated with MAC address information are acquired, other MAC address information associated with the plurality of surveillance video images is acquired, respectively, and a plurality of sets of MAC address information corresponding to the plurality of surveillance video images are generated. And calculating the intersection of the multiple MAC address information sets, selecting target MAC address information from the intersection, and acquiring identity information corresponding to the target MAC address information.
For example, a public security organization surveys a case of theft together, and a public security personnel already obtains the mobile phone information of a suspect and knows the MAC address of the mobile phone. And calling the associated file stored on the background server by the public security personnel, searching by taking the MAC address as an entrance, and acquiring a plurality of monitoring video images associated with the MAC address of the mobile phone of the suspect.
Based on the plurality of retrieved monitoring video images, the associated files stored on the background server are continuously called for retrieval, and other MAC addresses associated with the plurality of monitoring video images are respectively obtained, namely the MAC addresses of the mobile phones carried by the persons in each monitoring video image are obtained, and the MAC addresses of other persons who appear in the same place with the suspect can be obtained.
And generating a plurality of MAC address information sets corresponding to the plurality of monitoring video images, calculating the intersection of the plurality of MAC address information sets, and selecting a target MAC address from the intersection. Other people who are closely connected with the suspect can be obtained through the operation of taking the intersection, and the suspect conspire, the victim, the witness and the like can be found. Identity information corresponding to the MAC address of the mobile phone carried by the suspect, the victim, the witness and the like can be obtained through the client information of the operator, and the identity of the suspect, the victim, the witness and the like can be obtained.
In one embodiment, determining characteristics of a target person, and acquiring a plurality of surveillance video images including the target person, the characteristics of the target person include: clothing, height, gender, etc. And respectively acquiring MAC address information associated with a plurality of monitored video images containing the target person to generate a plurality of MAC address information sets. And calculating the intersection of the multiple MAC address information sets, selecting target MAC address information from the intersection based on a selection rule, and acquiring identity information corresponding to the target MAC address information and the running tracks of the multiple target MAC address information.
For example, the public security organization investigates the theft case, determines that there are 3 suspects according to the information provided by the masses and the victims, and preliminarily confirms the characteristics of the 3 criminal suspects, such as clothing, height, sex, and the like. And searching a plurality of monitoring video images containing the characteristics of the criminal suspect from the background server according to the characteristics of the suspect.
And determining the MAC address information set contained in each monitoring video image by utilizing the association between the monitoring video image and the MAC address, and calculating the intersection of a plurality of MAC address information sets. Since the characteristics of the criminal suspect are not clear, when a plurality of surveillance video images including the characteristics of the criminal suspect are searched from the background server, surveillance video images including other persons having the same characteristics as the suspect may be selected, and the MAC address information in the transaction set may be less than 2. And selecting target MAC address information from the intersection, wherein the selection rule can be that one or more pieces of MAC address information are selected from the intersection to serve as the target MAC address information, or MAC address information which is not in the intersection but has the highest frequency of occurrence is selected to serve as the target MAC address information. And acquiring identity information corresponding to the target MAC address information, and calculating the running tracks of the target MAC address information according to the selected monitoring video image and the target MAC address information. The motion trail of the suspect can be obtained.
In one embodiment, whether abnormal MAC address information and corresponding abnormal persons exist is judged based on the incidence relation between the monitoring video image and the MAC address information, and if the abnormal MAC address information and the corresponding abnormal persons exist, an alarm is given. The rule for judging whether the abnormal MAC address information exists comprises the following steps: whether the MAC address information appears in the set area with the frequency larger than the frequency threshold value, whether the MAC address information is in a blacklist, and the like. The set area includes: banks, shopping malls, stations, etc.
For example, if a security department of a bank finds that a MAC address appears very frequently in a certain bank branch within 2 days based on an associated file stored in a background server, the MAC address is determined to be abnormal MAC address information, and the identity information of an abnormal person is determined based on the MAC address information to perform security investigation. And judging whether abnormal MAC address information exists or not and whether corresponding abnormal persons can be automatically completed by the system or not based on the incidence relation between the monitoring video image and the MAC address information.
There may be various methods for obtaining the identity information corresponding to the MAC address. For example, identity information is obtained from the operator client system according to the MAC address information, and the identity information includes: sex, age, height, etc. And positioning a target person corresponding to the MAC address information in the monitoring video image based on the identity information. For example, a suspect is located in a surveillance video image based on identity information, and a clear image can be obtained.
Voiceprint recognition is one of the biometric identification techniques, also known as speaker recognition, and has two categories, namely speaker identification and speaker verification. Identification techniques may be required to narrow criminal investigation, and validation techniques may be required for banking transactions. Voiceprint recognition is the conversion of acoustic signals into electrical signals, which are then recognized by a computer.
Acquiring sound signal data associated with a monitoring video image, extracting a voiceprint feature vector from the sound signal data, calculating the voiceprint similarity between the voiceprint feature vector and voiceprint data stored in a preset voiceprint library, and acquiring identity information corresponding to the voiceprint data if the voiceprint similarity is greater than a set threshold value. The voiceprint data stored in the preset voiceprint library can be the voiceprint data of the criminal suspect, and the voiceprint data of the criminal suspect is correspondingly provided with identity information.
Face recognition is a biometric technology for identifying the identity of a person based on facial feature information of the person, and is a series of related technologies, generally called face recognition and face recognition, for automatically detecting and tracking the face in an image and further performing face recognition on the detected face.
And judging whether a face exists in the monitoring video image, if so, extracting the face image from the monitoring video image and comparing the face image with a face image sample stored in a preset face library, and if the comparison is successful, acquiring identity information corresponding to the face image sample. The recognition algorithm of the human face can be various algorithms. The face image samples stored in the preset face library can be face image samples of the criminal suspect, and the face image samples of the criminal suspect are correspondingly provided with identity information.
In one embodiment, it is determined that, in the same time period, a plurality of adjacent WIFI hotspots receive a WIFI signal detection packet sent by a mobile phone, where the detection packet includes: MAC address information, mobile phone wireless signal transmission strength RSSI and the like. Determining the distance between the mobile phone and each WIFI hotspot according to the RSSI, calculating the position coordinate information of the mobile phone according to the coordinates of the WIFI hotspots and the respective distances between the mobile phone and the WIFI hotspots, and displaying the position of the mobile phone on the electronic map based on the position coordinate information.
And positioning in real time based on the position information of the WIFI hotspot and the distance between the mobile phone and the WIFI signal hotspot. If the area of the hall is not large and the interference to the WIFI hotspots is less, the positioning of the mobile phone can be realized by at least 2 WIFI hotspots. And under the condition that the area of the hall is large, 3-dimensional spatial positioning is generally needed, and at the moment, 3 WIFI hotspots distributed at different heights are needed at least to realize the spatial positioning.
The target person identification and tracking method based on the surveillance video in the embodiment associates the surveillance video image, the MAC address information and the sound signal data, provides an automatic identification and tracking mode for the target person, improves the efficiency and accuracy of identification and tracking of the target person, and can help public security, security personnel and the like to quickly find suspect.
As shown in fig. 2, the present invention provides a target person identification and tracking device 20 based on surveillance video, including: the system comprises a video acquisition module 21, a MAC address acquisition module 22, a sound signal acquisition module 23, an information association module 24 and an identification tracking module. The video obtaining module 21 obtains a surveillance video image collected by the surveillance device and first time information of the collected surveillance video image. The MAC address obtaining module 22 obtains MAC address information of the mobile phone collected by the WIFI hotspot and second time information of the collected MAC address. The sound signal acquisition module 23 acquires sound signal data collected by the sound pickup apparatus and third time information of the collected sound signal data. The information association module 24 associates the monitored video image, the MAC address information, and the sound signal data according to the first time information, the second time information, and the third time information. The monitoring device, the WIFI hotspot and the sound pickup equipment are arranged in the same area. The recognition and tracking module 25 recognizes and tracks the target person based on the associated surveillance video image, MAC address information, and sound signal data.
As shown in fig. 3, the identification tracking module 25 includes: an object identity confirming unit 251, an object trajectory confirming unit 252, an abnormal person determining unit 253, and an object locating unit 254. The target identity confirming unit 251 acquires a plurality of surveillance video images associated with the MAC address information, respectively acquires other MAC address information associated with the plurality of surveillance video images, and generates a plurality of MAC address information sets corresponding to the plurality of surveillance video images. The target identity confirmation unit 251 calculates an intersection of the plurality of MAC address information sets, selects target MAC address information from the intersection, and acquires identity information corresponding to the target MAC address information.
The target trajectory determination unit 252 determines characteristics of a target person and acquires a plurality of surveillance video images including the target person, the characteristics of the target person including: clothing, height, gender, etc. The target trajectory confirmation unit 252 acquires MAC address information associated with a plurality of surveillance video images including a target person, respectively, and generates a plurality of MAC address information sets. The target trajectory determination unit 252 calculates an intersection of the plurality of MAC address information sets, selects target MAC address information from the intersection based on a selection rule, and obtains identity information corresponding to the target MAC address information and a plurality of running trajectories of the target MAC address information.
The abnormal person determination unit 253 determines whether there is abnormal MAC address information and a corresponding abnormal person based on the association relationship between the monitored video image and the MAC address information, and if so, issues an alarm. The rule for judging whether the abnormal MAC address information exists comprises the following steps: whether the MAC address information appears in the set area with the frequency larger than the frequency threshold value, whether the MAC address information is in a blacklist, and the like. The set area includes: banks, shopping malls, stations, etc.
The target location unit 254 obtains identity information from the operator client system according to the MAC address information, the identity information including: gender, age, height and the like, and a target person corresponding to the MAC address information is positioned in the monitoring video image based on the identity information.
The target positioning unit 254 obtains sound signal data associated with the monitored video image, extracts a voiceprint feature vector from the sound signal data, calculates a voiceprint similarity between the voiceprint feature vector and voiceprint data stored in a preset voiceprint library, and obtains identity information corresponding to the voiceprint data if the voiceprint similarity is greater than a set threshold.
The target positioning unit 254 determines whether a face exists in the monitored video image, and if so, extracts a face image from the monitored video image and compares the face image with a face image sample stored in a preset face library, and if the comparison is successful, acquires identity information corresponding to the face image sample. The target locating unit 254 locates a target person corresponding to the MAC address information in the monitored video image based on the identity information.
Target locating unit 254 determines that, in the same time period, a plurality of adjacent WIFI hotspots receive a WIFI signal detection packet sent by a mobile phone, where the detection packet includes: MAC address information and mobile phone wireless signal transmission strength RSSI. The target positioning unit 254 determines the distance between the mobile phone and each WIFI hotspot according to the RSSI, and calculates the position coordinate information of the mobile phone according to the coordinates of the plurality of WIFI hotspots and the respective distances between the mobile phone and the plurality of WIFI hotspots; and displaying the position of the mobile phone on the electronic map based on the position coordinate information.
Fig. 4 is a block diagram of another embodiment of a target person identification and tracking device based on surveillance video according to the present invention. As shown in fig. 4, the apparatus may include a memory 41, a processor 42, a communication interface 43, and a bus 44. The memory 41 is used for storing instructions, the processor 42 is coupled to the memory 41, and the processor 42 is configured to execute the target person identification and tracking method based on the surveillance video based on the instructions stored in the memory 41.
The memory 41 may be a high-speed RAM memory, a nonvolatile memory (NoN-volatile memory), or the like, and the memory 41 may be a memory array. The processor 42 may be a central processing unit CPU or one or more integrated circuits configured to implement the surveillance video-based target person identification tracking of the present invention.
In one embodiment, the present invention provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement surveillance video-based target person identification tracking as in any of the above embodiments.
The target person identification and tracking method, device and storage medium based on the surveillance video in the embodiments associate the surveillance video image, the MAC address information and the sound signal data, identify and track the target person, provide an automatic identification and tracking mode for the target person, improve the efficiency and accuracy of identifying and tracking the target person, and provide help for public security, security personnel and the like to quickly find suspect.
The method and system of the present invention may be implemented in a number of ways. For example, the methods and systems of the present invention may be implemented in software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustrative purposes only, and the steps of the method of the present invention are not limited to the order specifically described above unless specifically indicated otherwise. Furthermore, in some embodiments, the present invention may also be embodied as a program recorded in a recording medium, the program including machine-readable instructions for implementing a method according to the present invention. Thus, the present invention also covers a recording medium storing a program for executing the method according to the present invention.
The description of the present invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to practitioners skilled in this art. The embodiment was chosen and described in order to best explain the principles of the invention and the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use contemplated.
Claims (4)
1. A target person identification and tracking method based on a surveillance video is characterized by comprising the following steps:
acquiring a monitoring video image acquired by a monitoring device and first time information of acquiring the monitoring video image;
acquiring MAC address information of the mobile phone acquired by the WIFI hotspot and second time information for acquiring the MAC address information;
acquiring sound signal data acquired by pickup equipment and third time information for acquiring the sound signal data;
associating the monitoring video image, the MAC address information and the sound signal data according to the first time information, the second time information and the third time information; the monitoring device, the WIFI hotspot and the sound pickup equipment are arranged in the same area;
identifying and tracking a target person based on the associated surveillance video image, the MAC address information, and the sound signal data, comprising:
acquiring a plurality of monitoring video images associated with the MAC address information; respectively acquiring other MAC address information associated with the plurality of monitoring video images, and generating a plurality of MAC address information sets corresponding to the plurality of monitoring video images; calculating the intersection of a plurality of MAC address information sets, selecting target MAC address information from the intersection, and acquiring identity information corresponding to the target MAC address information;
judging whether abnormal MAC address information and corresponding abnormal persons exist or not based on the incidence relation between the monitoring video image and the MAC address information, and if so, giving an alarm; the rule for judging whether the abnormal MAC address information exists comprises the following steps: whether MAC address information with frequency larger than a frequency threshold appears in a set area or not and whether the MAC address information is in a blacklist or not; the set region includes: banks, shopping malls, stations;
determining the characteristics of a target person, and acquiring a plurality of monitoring video images containing the target person, wherein the characteristics of the target person comprise: clothing, height, gender;
respectively acquiring MAC address information associated with a plurality of monitored video images containing the target person to generate a plurality of MAC address information sets;
calculating the intersection of a plurality of MAC address information sets, acquiring target MAC address information from the intersection based on a selection rule, and acquiring identity information corresponding to the target MAC address information and a running track of the target MAC address information;
acquiring identity information from an operator client system according to the MAC address information, wherein the identity information comprises: sex, age, height;
positioning a target person corresponding to the MAC address information in the monitoring video image based on the identity information;
the method further comprises the following steps:
acquiring sound signal data associated with the monitoring video image, extracting a voiceprint characteristic vector from the sound signal data, calculating the voiceprint similarity between the voiceprint characteristic vector and voiceprint data stored in a preset voiceprint library, and acquiring identity information corresponding to the voiceprint data if the voiceprint similarity is greater than a set threshold value; and/or the presence of a gas in the gas,
and judging whether a face exists in the monitoring video image, if so, extracting the face image from the monitoring video image and comparing the face image with a face image sample stored in a preset face library, and if the comparison is successful, acquiring identity information corresponding to the face image sample.
2. The method of claim 1, further comprising:
determining that a plurality of adjacent WIFI hotspots receive a WIFI signal detection packet sent by the mobile phone in the same time period, wherein the detection packet comprises: the MAC address information and the RSSI (received signal strength indicator) of the wireless signal transmission of the mobile phone;
determining the distance between the mobile phone and each WIFI hotspot according to the RSSI;
calculating position coordinate information of the mobile phone according to the coordinates of the WIFI hotspots and the respective distances between the mobile phone and the WIFI hotspots;
and displaying the position of the mobile phone on an electronic map based on the position coordinate information.
3. A target person identification tracking device based on surveillance video, characterized by comprising:
the video acquisition module is used for acquiring a monitoring video image acquired by a monitoring device and acquiring first time information of the monitoring video image;
the WIFI hotspot acquisition module is used for acquiring the MAC address information of the mobile phone acquired by the WIFI hotspot and acquiring second time information of the MAC address;
the sound signal acquisition module is used for acquiring sound signal data acquired by pickup equipment and third time information for acquiring the sound signal data;
the information association module is used for associating the monitoring video image, the MAC address information and the sound signal data according to the first time information, the second time information and the third time information; the monitoring device, the WIFI hotspot and the sound pickup equipment are arranged in the same area;
the identification tracking module is used for identifying and tracking a target person based on the associated monitoring video image, the MAC address information and the sound signal data;
wherein the identification tracking module comprises:
the target identity confirming unit is used for acquiring a plurality of monitoring video images associated with the MAC address information; respectively acquiring other MAC address information associated with the plurality of monitoring video images, and generating a plurality of MAC address information sets corresponding to the plurality of monitoring video images; calculating the intersection of a plurality of MAC address information sets, selecting target MAC address information from the intersection, and acquiring identity information corresponding to the target MAC address information;
an abnormal person determining unit, configured to determine whether there is abnormal MAC address information and a corresponding abnormal person based on an association relationship between the monitored video image and the MAC address information, and if so, issue an alarm; the rule for judging whether the abnormal MAC address information exists comprises the following steps: whether MAC address information with frequency larger than a frequency threshold appears in a set area or not and whether the MAC address information is in a blacklist or not; the set region includes: banks, shopping malls, stations;
the identification tracking module comprises:
a target track determination unit, configured to determine characteristics of a target person, and obtain a plurality of surveillance video images including the target person based on the characteristics, where the characteristics of the target person include: clothing, height, gender; respectively acquiring MAC address information associated with a plurality of monitored video images containing the target person to generate a plurality of MAC address information sets; calculating the intersection of a plurality of MAC address information sets, acquiring target MAC address information from the intersection based on a selection rule, and acquiring identity information corresponding to the target MAC address information and a running track of the target MAC address information;
a target positioning unit, configured to obtain identity information from an operator client system according to the MAC address information, where the identity information includes: sex, age, height; positioning a target person corresponding to the MAC address information in the monitoring video image based on the identity information;
the target positioning unit is used for acquiring sound signal data associated with the monitoring video image, extracting a voiceprint feature vector from the sound signal data, calculating voiceprint similarity between the voiceprint feature vector and voiceprint data stored in a preset voiceprint library, and acquiring identity information corresponding to the voiceprint data if the voiceprint similarity is greater than a set threshold value; and/or judging whether a face exists in the monitoring video image, if so, extracting the face image from the monitoring video image and comparing the face image with a face image sample stored in a preset face library, and if the comparison is successful, acquiring identity information corresponding to the face image sample.
4. The apparatus of claim 3,
the target positioning unit is configured to determine that, in the same time period, a plurality of adjacent WIFI hotspots receive a WIFI signal detection packet sent by the mobile phone, where the detection packet includes: the MAC address information and the RSSI (received signal strength indicator) of the wireless signal transmission of the mobile phone; determining the distance between the mobile phone and each WIFI hotspot according to the RSSI; calculating position coordinate information of the mobile phone according to the coordinates of the WIFI hotspots and the respective distances between the mobile phone and the WIFI hotspots; and displaying the position of the mobile phone on an electronic map based on the position coordinate information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710711592.1A CN107590439B (en) | 2017-08-18 | 2017-08-18 | Target person identification and tracking method and device based on monitoring video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710711592.1A CN107590439B (en) | 2017-08-18 | 2017-08-18 | Target person identification and tracking method and device based on monitoring video |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107590439A CN107590439A (en) | 2018-01-16 |
| CN107590439B true CN107590439B (en) | 2020-12-15 |
Family
ID=61042364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710711592.1A Active CN107590439B (en) | 2017-08-18 | 2017-08-18 | Target person identification and tracking method and device based on monitoring video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107590439B (en) |
Families Citing this family (41)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108366342A (en) * | 2018-03-12 | 2018-08-03 | 宁波亿拍客网络科技有限公司 | A kind of perception information correlating method |
| CN108710827B (en) * | 2018-04-18 | 2019-04-16 | 特斯联（北京）科技有限公司 | A kind of micro- police service inspection in community and information automatic analysis system and method |
| CN108663970B (en) * | 2018-05-28 | 2021-01-12 | 杭州南威电力有限公司 | Electric power operation safety monitoring system |
| CN108897996B (en) * | 2018-06-05 | 2022-05-10 | 北京市商汤科技开发有限公司 | Identification information association method and device, electronic equipment and storage medium |
| CN108764369B (en) * | 2018-06-07 | 2021-10-22 | 深圳市公安局公交分局 | Figure identification method and device based on data fusion and computer storage medium |
| CN108898079A (en) * | 2018-06-15 | 2018-11-27 | 上海小蚁科技有限公司 | A kind of monitoring method and device, storage medium, camera terminal |
| CN109215486B (en) * | 2018-07-18 | 2021-11-26 | 平安科技（深圳）有限公司 | Electronic map marking and displaying method and device, terminal equipment and storage medium |
| CN109215184A (en) * | 2018-07-24 | 2019-01-15 | 石数字技术成都有限公司 | Face registration, verification method, face registration system and the application in gate inhibition |
| CN110766101B (en) * | 2018-07-26 | 2023-10-20 | 杭州海康威视数字技术股份有限公司 | Method and device for determining movement track |
| CN109063655A (en) * | 2018-08-07 | 2018-12-21 | 深圳市携网科技有限公司 | Feature matching method, device, computer equipment and storage medium |
| CN109063654A (en) * | 2018-08-07 | 2018-12-21 | 深圳市携网科技有限公司 | Retinue tracking, device, computer equipment and storage medium |
| CN109033440A (en) * | 2018-08-15 | 2018-12-18 | 武汉烽火众智数字技术有限责任公司 | A kind of video investigation multidimensional trajectory analysis method |
| CN111079477A (en) * | 2018-10-19 | 2020-04-28 | 北京奇虎科技有限公司 | Monitoring analysis method and monitoring analysis system |
| CN110198432B (en) * | 2018-10-30 | 2021-09-17 | 腾讯科技（深圳）有限公司 | Video data processing method and device, computer readable medium and electronic equipment |
| CN109522860B (en) * | 2018-11-27 | 2021-07-13 | 武汉虹旭信息技术有限责任公司 | Internet of things application analysis system and method based on multiple tracks |
| CN109524012B (en) * | 2018-11-28 | 2022-06-17 | 深圳力维智联技术有限公司 | Audio security control center, intelligent audio sensor, monitoring method and system |
| CN111277788B (en) * | 2018-12-04 | 2023-04-04 | 北京声迅电子股份有限公司 | Monitoring method and monitoring system based on MAC address |
| CN111277745B (en) * | 2018-12-04 | 2023-12-05 | 北京奇虎科技有限公司 | Target person tracking method and device, electronic equipment and readable storage medium |
| WO2020114132A1 (en) * | 2018-12-06 | 2020-06-11 | 西安光启未来技术研究院 | Information associativity processing method, apparatus, and system |
| CN111294732A (en) * | 2018-12-06 | 2020-06-16 | 深圳光启超材料技术有限公司 | Video tracking method and system, and storage medium |
| CN109614949A (en) * | 2018-12-23 | 2019-04-12 | 广东腾晟信息科技有限公司 | The method of judgement identification human body from image |
| CN109839614B (en) * | 2018-12-29 | 2020-11-06 | 深圳市天彦通信股份有限公司 | Positioning system and method of fixed acquisition equipment |
| CN109816906B (en) * | 2019-01-03 | 2022-07-08 | 深圳壹账通智能科技有限公司 | Security monitoring method and device, electronic equipment and storage medium |
| CN110246292B (en) * | 2019-04-26 | 2022-08-12 | 平安科技（深圳）有限公司 | Household video monitoring method, device and storage medium |
| CN111856399B (en) * | 2019-04-26 | 2023-06-30 | 北京嘀嘀无限科技发展有限公司 | Positioning identification method and device based on sound, electronic equipment and storage medium |
| CN110163167B (en) * | 2019-05-27 | 2021-02-05 | 福州外语外贸学院 | Directional real-time tracking method and system in waiting hall |
| CN110705410A (en) * | 2019-09-23 | 2020-01-17 | 广州轨道交通建设监理有限公司 | Information matching verification method, device, medium and terminal equipment |
| CN110717425A (en) * | 2019-09-26 | 2020-01-21 | 深圳市商汤科技有限公司 | Case association method and device, electronic equipment and storage medium |
| CN110751116B (en) * | 2019-10-24 | 2022-07-01 | 银河水滴科技(宁波)有限公司 | Target identification method and device |
| CN110909613A (en) * | 2019-10-28 | 2020-03-24 | Oppo广东移动通信有限公司 | Video character recognition method and device, storage medium and electronic equipment |
| JP6905773B2 (en) * | 2019-12-18 | 2021-07-21 | 株式会社デジタル・Ａｉ | Watching band monitoring system, watching band monitoring device, watching band monitoring method and watching band monitoring program |
| CN111601254A (en) * | 2020-04-16 | 2020-08-28 | 深圳市优必选科技股份有限公司 | Target tracking method and device, storage medium and intelligent equipment |
| JP7286586B2 (en) * | 2020-05-14 | 2023-06-05 | 株式会社日立エルジーデータストレージ | Ranging system and ranging sensor calibration method |
| CN112347306A (en) * | 2020-09-29 | 2021-02-09 | 浙江大华技术股份有限公司 | PTZ camera monitoring and tracking method, device and system and computer equipment |
| CN112699720B (en) * | 2020-10-10 | 2023-10-20 | 杭州翔毅科技有限公司 | Monitoring method, equipment, storage medium and device based on character information set |
| CN112637548B (en) * | 2020-11-12 | 2023-11-24 | 佳都科技集团股份有限公司 | Information association early warning method and device based on camera |
| CN112668605A (en) * | 2020-12-01 | 2021-04-16 | 深圳力维智联技术有限公司 | Single-point fusion information acquisition method and device based on biological and physical characteristics |
| CN113949842A (en) * | 2021-03-31 | 2022-01-18 | 紫光智云(江苏)物联网科技有限公司 | Suspected target track tracking and positioning system |
| CN113977603B (en) * | 2021-10-29 | 2023-07-18 | 连云港福润食品有限公司 | Worker production specification monitoring robot based on target detection, identification and tracking |
| CN114299944B (en) * | 2021-12-08 | 2023-03-24 | 天翼爱音乐文化科技有限公司 | Video processing method, system, device and storage medium |
| CN117082457B (en) * | 2023-08-24 | 2024-04-02 | 唐山东道网络科技有限公司 | Personnel positioning management method and system for safety monitoring |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104317918A (en) * | 2014-10-29 | 2015-01-28 | 深圳先进技术研究院 | Composite big-data GIS (geographic information system) based abnormal behavior analysis and alarm system |
| CN105022835A (en) * | 2015-08-14 | 2015-11-04 | 武汉大学 | Public safety recognition method and system for crowd sensing big data |
| CN106548193A (en) * | 2016-09-28 | 2017-03-29 | 厦门市杜若科技有限公司 | A kind of method and system of the mark-remaining information that tracing object is shown |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150161877A1 (en) * | 2013-11-06 | 2015-06-11 | Vringo Labs Llc | Systems And Methods For Event-Based Reporting and Surveillance and Publishing Event Information |
-
2017
- 2017-08-18 CN CN201710711592.1A patent/CN107590439B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104317918A (en) * | 2014-10-29 | 2015-01-28 | 深圳先进技术研究院 | Composite big-data GIS (geographic information system) based abnormal behavior analysis and alarm system |
| CN105022835A (en) * | 2015-08-14 | 2015-11-04 | 武汉大学 | Public safety recognition method and system for crowd sensing big data |
| CN106548193A (en) * | 2016-09-28 | 2017-03-29 | 厦门市杜若科技有限公司 | A kind of method and system of the mark-remaining information that tracing object is shown |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107590439A (en) | 2018-01-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107590439B (en) | Target person identification and tracking method and device based on monitoring video | |
| JP7040463B2 (en) | Analysis server, monitoring system, monitoring method and program | |
| JP4924607B2 (en) | Suspicious behavior detection apparatus and method, program, and recording medium | |
| AU2020309090B2 (en) | Image processing methods and apparatuses, electronic devices, and storage media | |
| US10824713B2 (en) | Spatiotemporal authentication | |
| CN108540752B (en) | Method, device and system for identifying target object in video monitoring | |
| CN108540755B (en) | Identity recognition method and device | |
| CN109656973B (en) | Target object association analysis method and device | |
| CN108540750A (en) | Based on monitor video and the associated method, apparatus of electronic device identification and system | |
| CN107888715B (en) | Method, device and equipment for binding MAC address and human face features | |
| CN103714631A (en) | ATM intelligent monitoring system based on human face recognition | |
| CN111814510B (en) | Method and device for detecting legacy host | |
| CN109839614B (en) | Positioning system and method of fixed acquisition equipment | |
| CN110555918A (en) | Attendance management method and attendance management equipment | |
| CN110765823A (en) | Target identification method and device | |
| CN109963113B (en) | Method and device for monitoring interested target | |
| CN104376619A (en) | Monitoring method and equipment | |
| CN110246292B (en) | Household video monitoring method, device and storage medium | |
| CN113343913A (en) | Target determination method, target determination device, storage medium and computer equipment | |
| EP3035225B1 (en) | Information processing device, authentication system, authentication method, and program | |
| JP2012083997A (en) | Authentication system and determination method for authentication reliability | |
| CN110717428A (en) | Identity recognition method, device, system, medium and equipment fusing multiple features | |
| CN111476070A (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| CN114067403A (en) | Old people self-help money depositing and withdrawing obstacle recognition method and device | |
| Wang et al. | Adaptive room-level localization system with crowd-sourced WiFi data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |