WO2022257647A1

WO2022257647A1 - Camera detection method and apparatus, storage medium, and electronic device

Info

Publication number: WO2022257647A1
Application number: PCT/CN2022/090626
Authority: WO
Inventors: 周燃; 徐文渊; 冀晓宇; 程雨诗
Original assignee: Oppo广东移动通信有限公司; 浙江大学
Priority date: 2021-06-10
Filing date: 2022-04-29
Publication date: 2022-12-15
Also published as: CN113240053A

Abstract

A camera detection method and apparatus, a storage medium, and an electronic device. The method comprises: acquiring a network data packet in a space to be detected (S310); matching a first feature of the network data packet that changes over time with a second feature of the space that changes over time (S320); and according to the matching result of the first feature and the second feature, determining whether a camera is present in the space (S330). A camera can effectively be detected, and the detection result is highly accurate.

Description

Camera detection method, device, storage medium and electronic equipment

This application claims the priority of the Chinese patent application with the application date of June 10, 2021, the application number 202110649875.4, and the title of "camera detection method, device, storage medium and electronic equipment". The entire content of the Chinese patent application is incorporated by reference incorporated in this article.

technical field

The present disclosure relates to the technical field of information security, and in particular to a camera detection method, a camera detection device, a computer-readable storage medium, and electronic equipment.

Background technique

With the development of electronic equipment and communication technology, cameras are more and more widely used in various industries. However, some criminals install cameras in hotel rooms, bathrooms, dressing rooms, rental houses and other places to take sneak shots, which greatly infringes on people's privacy and personal safety.

Most of the above-mentioned cameras are of the pinhole type, and if they are installed in wire holes, routers, set-top boxes, gaps in walls, etc., they will be very hidden and difficult to be found. Therefore, how to effectively detect the camera is a technical problem to be solved urgently in the industry.

Contents of the invention

The disclosure provides a camera detection method, a camera detection device, a computer-readable storage medium, and electronic equipment.

According to the first aspect of the present disclosure, there is provided a camera detection method, including: acquiring network data packets in the space to be detected; The second feature is matched; according to the matching result of the first feature and the second feature, it is determined whether there is a camera in the space to be detected.

According to a second aspect of the present disclosure, there is provided a camera detection device, including a processor and a memory; the processor is used to execute the following program modules stored in the memory: a data acquisition module configured to acquire data in the space to be detected A network data packet; a feature matching module configured to match the first feature of the network data packet over time with the second feature of the space to be detected over time; the detection result determination module is configured to Based on the matching result of the first feature and the second feature, it is determined whether there is a camera in the space to be detected.

According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the camera detection method of the above-mentioned first aspect and possible implementations thereof are implemented.

According to a fourth aspect of the present disclosure, there is provided an electronic device, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the executable instructions to Execute the camera detection method of the above first aspect and its possible implementation.

Description of drawings

FIG. 1 shows a system architecture diagram of an operating environment in this exemplary embodiment;

FIG. 2 shows a schematic structural diagram of an electronic device in this exemplary embodiment;

FIG. 3 shows a flow chart of a camera detection method in this exemplary embodiment;

Fig. 4 shows a flow chart of determining a second feature in this exemplary embodiment;

FIG. 5 shows a schematic diagram of a camera detection interface in this exemplary embodiment;

FIG. 6 shows a schematic diagram of matching network data packets and flashlight working hours in this exemplary embodiment;

Fig. 7 shows a flow chart of determining the camera position in this exemplary embodiment;

Fig. 8 shows a flow chart of prompting the position of the camera in this exemplary embodiment;

FIG. 9 shows a schematic structural diagram of a camera detection device in this exemplary embodiment;

Fig. 10 shows a schematic structural diagram of another camera detection device in this exemplary embodiment.

Detailed ways

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided in order to give a thorough understanding of embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details being omitted, or other methods, components, devices, steps, etc. may be adopted. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different network and/or processor means and/or microcontroller means.

The flowcharts shown in the figures are illustrative only and do not necessarily include all steps. For example, some steps can be decomposed, and some steps can be combined or partly combined, so the actual execution sequence may be changed according to the actual situation.

In a solution in the related art, for a camera configured with a supplementary light source such as infrared, whether there is a camera is determined by detecting whether there is a light source of a specific wavelength in a room. However, the detection of light sources is easily affected by ambient light, and it is difficult to ensure accuracy; moreover, this method cannot achieve effective detection when the camera is not equipped with a supplementary light source, or when there is an occluded object in front of the camera.

In view of the above problems, exemplary embodiments of the present disclosure firstly provide a camera detection method. Fig. 1 shows a system architecture diagram of the operating environment of this exemplary embodiment. Referring to FIG. 1 , the system architecture 100 may include a data capture device 110 and a data analysis device 120 . Wherein, the data capture device 110 may be a device with a network communication function, such as a mobile phone, a tablet computer, a personal computer, and the like. The data capture device 110 is located in the space to be detected, and is used to capture network data packets in the space to be detected. The space to be tested includes but is not limited to hotel rooms, bathrooms, changing rooms, and rental houses. The data capture device 110 and the data analysis device 120 may be connected through a wired or wireless communication link, so that the data capture device 110 sends the captured network data packets to the data analysis device 120 . The data analysis device 120 may be another terminal connected to the data capture device 110, or a background server that provides camera detection services. The data analysis device 120 is configured to analyze network data packets to detect whether there is a camera in the space to be detected.

In one embodiment, the system architecture 100 may further include a change construction device 130 for actively constructing changes in the space to be detected. For example, the change configuration device 130 may be a flashlight device, which constructs the light and dark changes of the space to be detected by flashing light in the space to be detected. The change configuration device 130 may also be a projection device, which constructs pattern and texture changes of the space to be tested by projecting the space to be tested. The change construction device 130 may include a camera module, which is used to collect images of the space to be detected while constructing changes in the space to be detected, and the image may be sent to the data analysis device 120 for assisting the detection of the camera.

In one embodiment, any two or more of the data capture device 110, the data analysis device 120, and the change construction device 130 may be integrated into one device. For example, based on a mobile phone equipped with a flashlight, the functions of the data capture device 110 and the change construction device 130 can be realized, which can construct changes in the space to be detected by controlling the work of the flashlight, and at the same time capture network data packets, and convert the network data packets Send it to the background server for analysis to realize camera detection; or, the mobile phone can also realize the function of data analysis device 120 at the same time, and analyze locally after capturing network data packets to realize camera detection.

Exemplary embodiments of the present disclosure also provide an electronic device for performing the above camera detection method. The electronic device may be the data analysis device 120 described above.

Taking the mobile terminal 200 in FIG. 2 as an example below, the structure of the above-mentioned electronic device will be exemplarily described. Those skilled in the art will appreciate that, in addition to components specifically intended for mobile purposes, the configuration in Fig. 2 can also be applied to equipment of a stationary type.

As shown in Figure 2, the mobile terminal 200 may specifically include: a processor 210, an internal memory 221, an external memory interface 222, a USB (Universal Serial Bus, Universal Serial Bus) interface 230, a charging management module 240, a power management module 241, battery 242, antenna 1, antenna 2, mobile communication module 250, wireless communication module 260, audio module 270, speaker 271, receiver 272, microphone 273, earphone interface 274, sensor module 280, display screen 290, camera module 291, flashlight 292, motor 293, button 294 and SIM (Subscriber Identification Module, Subscriber Identification Module) card interface 295, etc.

Processor 210 can include one or more processing units, for example: processor 210 can include AP (Application Processor, application processor), modem processor, GPU (Graphics Processing Unit, graphics processing unit), ISP (Image Signal Processor, image signal processor), controller, encoder, decoder, DSP (Digital Signal Processor, digital signal processor), baseband processor and/or NPU (Neural-Network Processing Unit, neural network processor), etc.

The encoder can encode (i.e. compress) the image or video data, for example, encode the image or video of the space to be detected to form the corresponding code stream data, so as to reduce the bandwidth occupied by data transmission; the decoder can compress the image or video code stream data to decode (that is, decompress) to restore image or video data. The mobile terminal 200 may support one or more encoders and decoders. In this way, the mobile terminal 200 can process images or videos in multiple encoding formats, such as: JPEG (Joint Photographic Experts Group, Joint Photographic Experts Group), PNG (Portable Network Graphics, portable network graphics), BMP (Bitmap, bitmap), etc. Image format, MPEG (Moving Picture Experts Group, moving picture expert group) 1, MPEG2, H.263, H.264, HEVC (High Efficiency Video Coding, high efficiency video coding) and other video formats.

In one implementation manner, the processor 210 may include one or more interfaces, and form connections with other components of the mobile terminal 200 through different interfaces.

The internal memory 221 may be used to store computer-executable program codes including instructions. The internal memory 221 may include volatile memory and non-volatile memory. The processor 210 executes various functional applications and data processing of the mobile terminal 200 by executing instructions stored in the internal memory 221 .

The external memory interface 222 can be used to connect an external memory, such as a Micro SD card, to expand the storage capacity of the mobile terminal 200. The external memory communicates with the processor 210 through the external memory interface 222 to implement a data storage function, such as storing images, videos and other files.

The USB interface 230 is an interface conforming to the USB standard specification, and can be used to connect a charger to charge the mobile terminal 200 , and can also be connected to earphones or other electronic devices.

The charging management module 240 is configured to receive charging input from the charger. While the charging management module 240 is charging the battery 242, it can also supply power to the device through the power management module 241; the power management module 241 can also monitor the state of the battery.

The wireless communication function of the mobile terminal 200 can be realized by the antenna 1, the antenna 2, the mobile communication module 250, the wireless communication module 260, a modem processor, a baseband processor, and the like. Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals. The mobile communication module 250 can provide 2G, 3G, 4G, 5G and other mobile communication solutions applied on the mobile terminal 200 . The wireless communication module 260 can provide WLAN (Wireless Local Area Networks, wireless local area network) (such as Wi-Fi (Wireless Fidelity, wireless fidelity) network), BT (Bluetooth, Bluetooth), GNSS (Global Navigation) applied on the mobile terminal 200 Satellite System, Global Navigation Satellite System), FM (Frequency Modulation, frequency modulation), NFC (Near Field Communication, short-range wireless communication technology), IR (Infrared, infrared technology) and other wireless communication solutions.

The mobile terminal 200 can realize a display function and display a user interface through the GPU, the display screen 290 and the AP. For example, when the user performs camera detection, the mobile terminal 200 may display an interface of a camera detection App (Application, application program) on the display screen 290 .

The mobile terminal 200 can realize the shooting function through the ISP, camera module 291 , encoder, decoder, GPU, display screen 290 and AP. For example, the user can enable the image or video capture function in the camera detection App, and at this time, the image of the space to be detected can be collected through the camera module 291 .

The mobile terminal 200 can implement audio functions through an audio module 270 , a speaker 271 , a receiver 272 , a microphone 273 , an earphone interface 274 , and an AP.

The sensor module 280 may include a depth sensor 2801, a pressure sensor 2802, a gyroscope sensor 2803, an air pressure sensor 2804, etc., so as to realize corresponding sensing and detection functions. Wherein, the depth sensor 2801 can collect the depth data of the space to be detected, and the gyro sensor 2803 can collect the pose data of the mobile terminal 200, and these two kinds of data can assist in realizing the positioning of the camera.

The flashlight 292 is used to increase the exposure of the space to be detected, so as to change its light and dark state. The flashlight 292 can be matched with the camera module 291 to form a specific relative positional relationship with the cameras in the camera module 291 . The flashlight 292 can work alone, and can also perform supporting work when the camera module 291 captures an image, such as flashing according to the shutter time. In addition, the flash light 292 can also serve as a reminder, for example, flashing reminders when a call comes in or the battery is too low.

The motor 293 can generate vibration prompts, and can also be used for touch vibration feedback and the like. The keys 294 include a power key, a volume key and the like.

The mobile terminal 200 may support one or more SIM card interfaces 295 for connecting SIM cards to implement functions such as calling and mobile communication.

The camera detection method in this exemplary embodiment will be described below. The application scenarios of this method include but are not limited to: the user is in a hotel room, uses the mobile phone to open the camera detection App and grabs the network data packets, then executes the camera detection method of this exemplary embodiment, and displays the detection result in the App; or the mobile phone The network data packets are captured and uploaded to the server, and the server executes the camera detection method of this exemplary embodiment, and returns the detection results to the mobile phone for display.

Figure 3 shows an exemplary flow of a camera detection method, which may include:

Step S310, acquiring network data packets in the space to be detected;

Step S320, matching the first time-varying feature of the network data packet with the time-varying second feature of the space to be detected;

Step S330, according to the matching result of the first feature and the second feature, determine whether there is a camera in the space to be detected.

Based on the above method, the change of the space to be detected is constructed, and the change of the obtained network data packet is matched with the change of the space to be detected, so as to detect whether there is a camera in the space to be detected. On the one hand, since the camera sends video data packets in a differential manner, which is correlated with changes in the space to be detected, it is highly accurate to detect the camera by matching the characteristics of changes in the network data packets and the space to be detected. On the other hand, this solution is suitable for detecting almost all cameras that need to be connected to the Internet, not limited to the detection of cameras equipped with supplementary light sources, and this solution is less affected by environmental lighting and other factors, and has lower requirements for the scene, which is conducive to reducing Cases of underreporting. On the other hand, this solution detects based on changes in the space to be detected, and will not make false alarms for nearby cameras outside the space to be detected, and has high reliability.

Each step in Fig. 3 is described in detail below.

Referring to FIG. 3, in step S310, network data packets in the space to be detected are acquired.

The data capture device located in the space to be detected can capture network data packets, including but not limited to wireless local area network network data packets, Bluetooth network data packets, mobile network data packets, and the like. Relevant software or settings can be used on the data capture device to capture network data packets. Taking the capture of network data packets of wireless LAN as an example, setting the network card of the data capture device to promiscuous mode can capture all network data packets flowing through, no matter where their destination addresses are.

The captured network data packets include data packets sent by all network devices within a certain range. If there is a camera in the space to be detected, the captured network data packets also include video data packets sent by the camera. In subsequent processing, the video data packets of the camera can be identified from the network data packets and detected. Therefore, this exemplary embodiment can realize the detection of the camera under the condition that there are cameras and other network devices in the space to be detected.

In an implementation manner, in order to eliminate the influence of other network devices, the user may be guided to actively shut down other network devices. For example, when the user starts the camera detection service on the data capture device, a prompt message may be displayed to prompt the user to turn off known network devices in the space to be detected, such as smart appliances, or to turn off the network connection function of these network devices. Thus, it is ensured that the captured network data packets are mainly video data packets sent by the camera, and the efficiency of subsequent processing and the accuracy of camera detection are improved.

After the data capture device captures the network data packets, the data analysis device can obtain the network data packets from the data capture device for subsequent processing. If the data capture device and the data analysis device are two devices, the data capture device can send network data packets to the data analysis device through the network; if the data capture device and the data analysis device are one device, the The inter-process communication realizes the sending of network data packets.

Continuing to refer to FIG. 3 , in step S320 , the above-mentioned first feature of the network data packet changing over time is matched with the second feature of the space to be detected changing over time.

Among them, the first feature refers to the feature of the network data packet changing with time, the second feature refers to the feature of the space to be detected changing with time, and the first and second are used here to distinguish different subjects of the feature.

The first feature of the network data packet may be a feature of one or more indicators of the network data packet changing over time. Indicators include but are not limited to: the size of a single data packet, the time interval between adjacent data packets, the number of data packets per unit time, etc., which generally belong to the information of the network communication layer and can be obtained without decrypting the network data packets. The network data packet itself includes a time stamp, and the data capture device can also record time information when capturing network data packets, so it is easy to correspond the above indicators with time to analyze the changes of the indicators over time, and obtain the first a feature.

The present disclosure does not limit the specific form of the first feature, for example, it may be a sequence formed by multiple time-index arrays.

In this exemplary embodiment, the change of the space to be detected refers to the change of the space to be detected that can cause a significant change in the image captured by the camera. When performing camera detection, active actions can be applied to the space to be detected to cause strong changes in light and shade, patterns, textures, etc., including but not limited to: switching flashlights, or switching lights and curtains in the space to be detected, causing Light and dark changes in the space to be detected; projecting or moving patterns in the space to be detected that have a large contrast with the space to be detected, such as projecting cartoon animations on the walls of the space to be detected, or moving a cartoon poster in and out of the space to be detected multiple times space, resulting in pattern and texture changes in the space to be detected.

The above-mentioned second feature can be obtained by recording the time point at which the space to be detected changes.

The present disclosure does not limit the specific form of the second feature, for example, it may be a sequence formed by multiple time points when the space to be detected changes.

How to obtain the second feature will be specifically exemplified below.

In an implementation manner, the space to be detected is changed by switching the flash lamp above, and the second feature can be determined according to the working time of the flash lamp. Referring to Figure 4, the camera detection method may include:

Step S410, obtaining the working time of the flashlight for flashing or illuminating the space to be detected;

Step S420, determining the second characteristic of the time-varying space to be detected according to the working time of the flashlight.

It should be noted that, when using a flashlight to construct the change of the space to be detected, the flashlight can be flashed, or the flashlight can be kept on for a period of time for illumination (such as a flashlight function on a mobile phone). The working time of the flashlight can be sent to the data analysis device by the flashlight device (such as the above-mentioned variable configuration device), or the working time of the flashlight can be obtained directly when the data analysis device controls the operation of the flashlight. The working time of the flash includes the start time and end time of each flash or illumination, or includes the start time and duration of each flash or illumination, and the end time can be calculated. The start time and end time of each flash or illumination are taken as the time points when the space to be detected changes, and the sequence formed by them can be used as the above-mentioned second feature.

The work of the flashlight can be controlled automatically by the system or manually by the user. In one embodiment, step S410 may include:

In response to the operation of the flashlight control in the camera detection interface, the flashlight is controlled to flash or illuminate the space to be detected, and the working time of the flashlight is obtained.

FIG. 5 shows a schematic diagram of a camera detection interface 500, which may be a user interface in a camera detection App. In the camera detection interface 500, a flashlight control 510 is provided, and the user can click, press and hold the control 510 to flash once, and the system records the working time of the flashlight. It should be understood that the flashlight control 510 can also implement a function similar to a light switch, for example, when the user clicks or long presses the flashlight control 510, the flashlight is triggered to turn on and remains on, and when the user clicks or long presses the flashlight again, the flashlight is turned off, and the system records the working time of the flashlight.

In one embodiment, when the user first uses the camera detection App or the flash function in the camera detection App for the first time, the user needs to allow the camera detection App to obtain the permission to use the flash light. After the user agrees, the App can call related system services to Control the flash and obtain data such as the working time of the flash.

In one embodiment, when the user does not change the space to be detected by means of the change structure device, for example, by manually switching curtains, lights, moving cartoon posters, etc., the data analysis device cannot obtain the occurrence of the space to be detected from the change structure device. time of change. Based on this, camera detection methods can include:

In response to the operation of the time control in the camera detection interface, the second characteristic of the time-varying space to be detected is determined.

Wherein, the time control is used to enable the user to manually record the time when the space to be detected changes. In the camera detection interface, relevant prompt information can be displayed to prompt the user to operate the time control when manually constructing changes in the space to be detected. For example, the prompt information can be "Please turn on and off the main light of the room several times, and Click the xx button every time the light is turned on or off". The system records the time when the user operates the time control as the time when the space to be detected changes, and then the second feature can be obtained.

When the space to be detected changes, the picture captured by the camera also changes. The camera usually uses differential encoding or transmission to process the picture, so when the picture changes, the video data packets sent by the camera will also change, for example, the size or number of video data packets increases significantly.

It can be seen from the above that when there is a camera in the space to be detected, the change of the space to be detected should be correlated with the change of the video data packets sent by the camera. In this exemplary embodiment, by matching the above-mentioned first feature and the second feature, it is determined whether the network data packet is related to the change in the space to be detected.

In one embodiment, step S320 may include:

A pre-trained machine learning model is used to process the first feature and the second feature, and output a matching result.

For example, the first sample features of a large number of network data packets changing over time and the corresponding second sample features of the test scene changing over time can be obtained in the test scene; a first sample feature and a corresponding second sample feature The sample features form a sample data group; a part of the sample data group is obtained when the actual structure of the test scene is changed, and the first sample feature is correlated with the second sample feature, and its labeled data (Ground truth) is 1; The first sample feature and the second sample feature in another part of the sample data group have no correlation, and its label data is 0; use the sample data group and its label data to train the initially constructed machine learning model, such as neural network When the network model reaches the preset accuracy rate, the trained machine learning model is obtained. In actual detection, the above-mentioned first feature and second feature are input into the machine learning model, and a result of whether the two match is output.

In another embodiment, the above-mentioned first feature includes the first time point when the network data packet changes, and the number of the first time point may be multiple; the above-mentioned second feature includes the second time point when the space to be detected changes , the number of second time points can also be multiple. Thus, step S320 may include:

The first time point is matched with the second time point.

Wherein, matching the first time point and the second time point is to determine whether there is a correlation between the two time points in time distribution.

For example, extract the time stamp and data packet size from the network data packet, and by fitting the relationship between the data packet size and time, the fitted mutation point can be determined as the first time point; record the occurrence of the space to be detected The changed time point, that is, the second time point; pair the first time point with the second time point to obtain multiple time point pairs, and each time point pair includes a first time point and a corresponding second time point ; If the difference between the first time point and the second time point in each time point pair does not exceed the preset time difference threshold (can be set according to experience, such as 1 second, 3 seconds, etc.), then determine the first time point Matching with the second time point is successful.

Considering that there may be a certain delay in sending video data packets from the camera, time compensation may be performed on the first time point or the second time point as a whole. For example, determine the time compensation value according to the time difference between the first first time point and the first second time point; then add the time compensation value to all the second time points; The time points are paired, and it is judged whether the difference between the first time point and the second time point in each time point pair does not exceed the time difference threshold, so as to obtain a matching result.

FIG. 6 shows a schematic diagram of matching the time when the size of the network data packet changes (that is, the first time point) and the time when the flashlight works (that is, the second time point). It can be seen that although the first time point is not completely consistent with the second time point, the two show a strong correlation. After pairing the first time point with the second time point, calculate the time difference threshold for each time point pair whose time difference is less than 3 seconds, and it can be determined that the first time point and the second time point are successfully matched.

In yet another implementation manner, the first feature and the second feature may be used as two variables for correlation analysis. For example, the first feature may be the size of the network data packet at different times, and the second feature may be whether the flashlight is turned on at different times (the value is 1 if the flashlight is turned on, and the value is 0 if it is not turned on). Then, the statistical method of correlation analysis is used to analyze the two variables, and the probability value of the correlation is output. If the probability value reaches the preset probability threshold (such as 70%, 80%, etc.), the first feature and the second feature are determined. The match was successful.

Continuing to refer to FIG. 3 , in step S330 , according to the matching result of the first feature and the second feature, it is determined whether there is a camera in the space to be detected.

Wherein, when the first feature is successfully matched with the second feature, it is determined that there is a camera in the space to be detected, and when the match between the first feature and the second feature is unsuccessful, it is determined that there is no camera in the space to be detected. Furthermore, the corresponding detection results can be displayed in the camera detection interface.

It can be seen from the above that only when the camera is located in the space to be detected and takes pictures of the space to be detected, the video data packet sent by it will respond to the change of the space to be detected, so that the first feature matches the second feature. When the camera is located outside the space to be detected and does not take pictures of the space to be detected, even if the signal of the video data packet it sends passes through the space to be detected and is captured by the data capture device, the video data packet will not be detected The spatial change produces a response, the first feature does not match the second feature, and this exemplary embodiment does not misjudge that there is a camera. Therefore, in this exemplary embodiment, the detection range can be accurately locked in the space to be detected, so as to ensure the accuracy of the detection result.

In one embodiment, the network data packets captured in step S310 may include multiple different types of data packets, for example, data packets sent by multiple network devices in the space to be detected. Network data packets from different sources can be grouped according to the header information of the network data packets. The header information includes but is not limited to: IP address (Internet Protocol, network protocol address), MAC address (Media Access Control, media access control address, That is, physical address), encoding information, communication protocol information, etc. For example, network data packets may be grouped according to their destination IP addresses, and network data packets with the same destination IP address are grouped into one group. Furthermore, the time-varying first features of each group of network data packets can be analyzed separately to obtain multiple sets of first features, and each set of first features is matched with the time-varying second features of the space to be detected, when at least When a group of first features and second features are successfully matched, it is determined that a camera exists in the space to be detected.

In one embodiment, in addition to matching the first feature and the second feature, other features of the network data packet may also be analyzed to detect whether it is a video data packet sent by the camera. Specifically, the camera detection method may include:

Match format signatures of network packets to preset format signatures.

Correspondingly, in step S330, it may be determined whether there is a camera in the space to be detected according to the matching result of the first feature and the second feature, and the matching result of the format feature of the network data packet and the preset format feature.

Wherein, the format feature of the network data packet is a feature related to data format, communication protocol, etc., including but not limited to port, traffic, MAC address, etc. When the camera sends a video data packet, it needs to be based on a specific data format, communication protocol, etc., so that the video data packet has a specific format feature, that is, the above-mentioned preset format feature. After the network data packet is captured, the format feature can be obtained by parsing it, and it can be matched with the preset format feature to detect whether the network data packet is a video data packet sent by the camera from the aspect of data format.

In one embodiment, the format characteristics of the network data packet can be input into another pre-trained machine learning model (different from the machine learning model matching the first feature and the second feature), through the processing and identification of the machine learning model , output whether it matches the preset format features.

In this exemplary embodiment, the final detection result may be determined in combination of the matching result of the first feature and the second feature, and the matching result of the format feature of the network data packet and the preset format feature. Specifically, the matching results of the above two aspects can be set as an "or" relationship, that is, when any of the matching results is a successful match, it is determined that there is a camera, thereby further reducing the situation of false positives; the matching results of the above two aspects can also be set as " and ", that is, when both matching results are successful, it is determined that there is a camera, thereby further reducing false positives. The present disclosure does not limit this.

When constructing changes in the space to be detected, the methods adopted can be divided into the following two types:

The first is the overall change in the structure of the space to be detected, such as switching lights, curtains, etc., which will cause changes in the light and shade of the entire space;

The second is to construct local changes in the space to be detected, such as turning on a flashlight or projecting a cartoon animation for a certain area.

If the second method is adopted, the position of the camera can be further detected. The following uses a local change in the structure of the flashlight as an example for illustration. It should be understood that the principle of the solution is the same when the flashlight is replaced by other local changes in the structure.

In one embodiment, the flash can be made to flash in the space to be detected in various poses, so that the local area covered by the flash is different in different poses, and the working time of the flash in the various poses can be obtained. Among them, INS (Inertia Navagation System, inertial navigation system) can be configured in the change structure equipment, such as the above-mentioned gyroscope sensor, etc., to measure the pose change of the device, and output the absolute position of the device based on an initial or reference pose posture. Alternatively, a camera module can be configured in the changing structure equipment, and by collecting images of the space to be detected under different poses, visual positioning is performed to output the pose of the device. Correspondingly, as shown in FIG. 7, the camera detection method may include:

Step S710, determining the second feature corresponding to each pose according to the working time of the flashlight in each pose;

Step S720, matching the first feature with the second feature corresponding to each pose;

Step S730, when the first feature is successfully matched with the second feature corresponding to at least one pose, it is determined that there is a camera in the space to be detected.

Wherein, the first feature is successfully matched with the second feature corresponding to at least one pose, indicating that the change of the network data packet is related to the change of the local area of the space to be detected corresponding to the pose, and it can be determined that there is a camera in the space to be detected, and The camera can capture pictures of the local area.

Further, as shown in FIG. 7, the camera detection method may also include:

Step S740, determining the position of the camera according to the above at least one pose.

The above at least one pose is called a suspicious pose. For example, it is possible to analyze the network data packets obtained under suspicious poses, and combine the principle of radio orientation to determine the orientation of the camera, and the deviation does not exceed 20 degrees.

In one embodiment, the camera detection method may also include:

Obtain multiple images collected in the space to be detected, and determine the corresponding relationship between the image and the pose of the flash;

According to the above suspicious poses and the corresponding relationship between images and poses, the position of the camera is estimated.

Among them, the relative positional relationship between the camera used to collect images and the flashlight is fixed. Through pre-calibration, the pose transformation relationship between the two can be determined, so that the pose of the camera when collecting images is converted into the pose of the flashlight, and the image and flashlight can be realized. Pose correspondence. The camera and the flashlight can also be a camera module provided in conjunction with each other. For example, the structural device can be changed to a mobile phone, and the camera module on the mobile phone includes an RGB camera and a flashlight. To simplify the calculation, the pose of the camera can also be equated to the pose of the flash.

In the above suspicious pose, the local area covered by the flash is the local area that the camera can capture, and it is presumed that the camera is located in the opposite direction of this local area. Therefore, according to the correspondence between the image and the pose, the image corresponding to the opposite direction of the local area is found. For example, after determining the suspicious pose, rotate the suspicious pose by 180 degrees to obtain the reverse pose, acquire an image corresponding to the reverse pose, and determine that the camera is located in the area where the image is located.

In one embodiment, the user holds the mobile phone to perform flash and image acquisition in different areas of the space to be detected, and the mobile phone can create map data for the space to be detected based on the collected images and its own pose, such as a 3D point cloud. map; after the suspicious pose is determined, the image corresponding to the suspicious pose can be found in the collected images. The area where these images are located is the local area that the camera can capture; furthermore, the area where the image is located is determined in the map data, that is, the camera For the local area that can be photographed, according to the position relationship, the area in the opposite direction is further determined as the area where the camera may be located, so as to realize the estimation of the position of the camera.

In one embodiment, when the user holds the mobile phone to perform flash and image acquisition in different areas of the space to be detected, guidance information can be presented, so that the user can aim at different areas of the space to be detected in a reasonable posture to perform flash and image acquisition. For example, the user's preferred mobile phone collects images of the entire space to be detected and uploads them to the server. The server creates map data for the space to be detected by executing the SLAM (Simultaneous Localization And Mapping) algorithm. Furthermore, based on the map data, the server plans a reasonable way to construct spatial flash changes for the user, guides the user to a suitable position (usually the central position) in the space to be detected, starts flashing from a certain direction, and guides the user to move clockwise. Or turn it counterclockwise, and every time it turns to a suitable angle, a prompt message "Please stay at this position and flash" will be displayed, so as to realize a reasonable and comprehensive detection of the entire space to be detected.

In one implementation manner, as shown in FIG. 8, after determining the position of the camera, the following steps may also be performed:

Step S810, according to the position of the camera, determine the candidate image where the camera is located in the above multiple images;

Step S820, prompting the position of the camera according to the candidate image.

Wherein, the candidate image may be an image corresponding to the above reverse pose, or a corresponding image may be found according to the area where the camera may be located in the map data as the candidate image. Candidate images or local areas in candidate images (that is, the local area where the camera is located) can be displayed on the camera detection interface, and related text prompt information can also be displayed at the same time, such as "cameras may exist in the following areas", so that users can further Find cameras in the space to be detected.

Furthermore, it is also possible to detect whether there is a suspicious light source in the candidate image, or prompt the user to re-point the camera to the area of the candidate image, and the system detects whether there is a suspicious light source, thereby locking the position of the camera more precisely.

In one embodiment, the area where the camera may be located may be marked in the map data of the space to be detected, and relevant text prompt information may be displayed, so as to facilitate further searching by the user.

Exemplary embodiments of the present disclosure also provide a camera detection device, which can be configured in the above analysis device. Referring to FIG. 9, the camera detection device 900 may include:

The data acquisition module 910 is configured to acquire network data packets in the space to be detected;

The feature matching module 920 is configured to match the above-mentioned first feature of the network data packet that changes with time with the second feature of the space to be detected that changes with time;

The detection result determining module 930 is configured to determine whether there is a camera in the space to be detected according to the matching result of the first feature and the second feature.

In one embodiment, the data acquisition module 910 is further configured to:

Obtain the working time of the flash for flashing or illuminating the space to be detected;

The second feature of the time-varying space to be detected is determined according to the working time of the flashlight.

In one embodiment, the working time of the flashlight includes the working time of the flashlight in various postures.

The data acquisition module 910 is configured to:

The second feature corresponding to each pose is determined according to the working time of the flashlight in each pose.

The detection result determination module 930 is configured to:

When the first feature is successfully matched with the second feature corresponding to at least one pose, it is determined that a camera exists in the space to be detected.

In one embodiment, the detection result determination module 930 is further configured to:

The position of the camera is determined according to the above at least one pose.

In one embodiment, the data acquisition module 910 is further configured to:

Obtain multiple images collected in the space to be detected, and determine the corresponding relationship between the image and the pose of the flashlight.

The detection result determination module 930 is configured to:

The position of the camera is determined according to the at least one pose and the corresponding relationship between the image and the pose.

After determining the position of the camera, determine the candidate image where the camera is located in the above multiple images according to the position;

Prompt camera location based on candidate images.

In an implementation manner, the candidate image is an image corresponding to a reverse pose after at least one pose is rotated by 180 degrees.

In one embodiment, the data acquisition module 910 is configured to:

In one embodiment, the feature matching module 920 is configured to:

In one embodiment, the feature matching module 920 is further configured to:

Obtaining the first sample characteristics of network data packets changing over time and the corresponding second sample characteristics of the experiment scenario changing over time in the test scenario;

Forming one of the first sample features and one of the corresponding second sample features into a sample data set to obtain a plurality of the sample data sets;

Obtain the label data of the sample data set, if the first sample feature in the sample data set is correlated with the second sample feature, the label data is 1, if the sample data set The first sample feature has no correlation with the second sample feature, and the label data is 0;

The machine learning model is trained by using the sample data set and its labeled data.

In one embodiment, the feature matching module 920 is further configured to:

Matching the format characteristics of the network data packet with the preset format characteristics;

The detection result determination module 930 is configured to:

According to the matching result of the first feature and the second feature, and the matching result of the format feature of the network data packet and the preset format feature, it is determined whether there is a camera in the space to be detected.

In one embodiment, the detection result determination module 930 is configured to:

If the matching result of the first feature and the second feature is a matching result, and the matching result of the format feature of the network data packet and the preset format feature is also a successful match, it is determined that there is a camera in the space to be detected.

In one embodiment, the first feature includes the first time point when the network data packet changes; the second feature includes the second time point when the space to be detected changes; The second feature of the space to be detected changes with time for matching, including:

The first time point is matched with the second time point.

In one embodiment, the above-mentioned matching of the first time point and the second time point includes:

pairing the first time point with the second time point to obtain a plurality of time point pairs, each time point pair including a first time point and a corresponding second time point;

If the difference between the first time point and the second time point in each time point pair does not exceed the time difference threshold, it is determined that the first time point and the second time point are successfully matched.

In one embodiment, the above-mentioned matching of the first time point and the second time point further includes:

Time compensation is performed on the first time point or the second time point before pairing the first time point with the second time point.

In one embodiment, the above-mentioned matching of the first feature of the network data packet changing over time with the second feature of the space to be detected changing over time includes:

Taking the first feature and the second feature as two variables, the correlation analysis is performed to obtain the probability value of the correlation. If the probability value of the correlation reaches the probability threshold, it is determined that the first time point and the second time point are successfully matched.

Exemplary embodiments of the present disclosure also provide another camera detection device. Referring to FIG. 10 , the camera detection device 1000 may include a processor 1010 and a memory 1020 . Wherein, the memory 1020 stores the following program modules:

The data acquisition module 1010 is configured to acquire network data packets in the space to be detected;

The feature matching module 1020 is configured to match the above-mentioned first feature of the network data packet that changes with time with the second feature of the space to be detected that changes with time;

The detection result determining module 1030 is configured to determine whether there is a camera in the space to be detected according to the matching result of the first feature and the second feature.

The processor 1010 is used to execute the above program modules.

In one embodiment, the data acquisition module 1021 is further configured to:

The data acquisition module 1021 is configured to:

The detection result determination module 1023 is configured to:

In one embodiment, the detection result determination module 1023 is further configured to:

In one embodiment, the data acquisition module 1021 is further configured to:

The detection result determination module 1023 is configured to:

Prompt camera location based on candidate images.

In one embodiment, the data acquisition module 1021 is configured to:

In one embodiment, the feature matching module 1022 is configured to:

In one embodiment, the feature matching module 1022 is further configured to:

The detection result determination module 1023 is configured to:

In one embodiment, the detection result determination module 1023 is configured to:

The first time point is matched with the second time point.

The details of each part of the above device have been described in detail in some implementations of the method, and thus will not be repeated here.

Exemplary embodiments of the present disclosure also provide a computer-readable storage medium, which can be realized in the form of a program product, which includes program code. When the program product is run on the electronic device, the program code is used to make the electronic device The steps described in the "Exemplary Methods" section above in this specification according to various exemplary embodiments of the present disclosure are performed. In one embodiment, the program product can be implemented as a portable compact disk read only memory (CD-ROM) and include program code, and can run on an electronic device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program, and the program may be used by or in combination with an instruction execution system, apparatus or device.

A program product may take the form of any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

A computer readable signal medium may include a data signal carrying readable program code in baseband or as part of a carrier wave. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages—such as Java, C++, etc., as well as conventional procedural programming Language - such as "C" or similar programming language. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server to execute. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider). business to connect via the Internet).

It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. Actually, according to the exemplary embodiment of the present disclosure, the features and functions of two or more modules or units described above may be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided to be embodied by a plurality of modules or units.

Those skilled in the art can understand that various aspects of the present disclosure can be implemented as a system, method or program product. Therefore, various aspects of the present disclosure can be embodied in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which can be collectively referred to herein as "circuit", "module" or "system". Other embodiments of the present disclosure will be readily apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any modification, use or adaptation of the present disclosure, and these modifications, uses or adaptations follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field not disclosed in the present disclosure . The specification and embodiments are to be considered as exemplary only, with the true scope and spirit of the disclosure indicated by the appended claims.

It should be understood that the present disclosure is not limited to the precise constructions which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

A camera detection method, characterized in that, comprising:

Obtain network data packets in the space to be detected;

Matching the first feature of the network data packet changing with time with the second feature of the space to be detected changing with time;

According to the matching result of the first feature and the second feature, it is determined whether there is a camera in the space to be detected.
The method according to claim 1, further comprising:

Acquiring the working time of the flashlight for flashing or illuminating the space to be detected;

The second characteristic of the space to be detected changing with time is determined according to the working time of the flashlight.
The method according to claim 2, characterized in that, the working time of the flash light includes the working time of the flash light in various postures; the determination of the space to be detected over time according to the working time of the flash light Variations in secondary characteristics, including:

determining the second feature corresponding to each pose according to the working time of the flashlight in each pose;

The determining whether there is a camera in the space to be detected according to the matching result of the first feature and the second feature includes:

When the first feature is successfully matched with the second feature corresponding to at least one pose, it is determined that a camera exists in the space to be detected.
The method according to claim 3, wherein when the first feature is successfully matched with the second feature corresponding to at least one pose, the method further comprises:

The position of the camera is determined according to the at least one pose.
The method according to claim 4, characterized in that the method further comprises:

Acquiring multiple images collected from the space to be detected, and determining the correspondence between the images and the pose of the flashlight;

The determining the position of the camera according to the at least one pose includes:

The position of the camera is determined according to the at least one pose and the corresponding relationship between the image and the pose.
The method according to claim 5, wherein after determining the position of the camera, the method further comprises:

According to the position of the camera, determine the candidate image where the camera is located in the plurality of images;

Prompting the position of the camera according to the candidate image.
The method according to claim 6, wherein the candidate image is an image corresponding to a reverse pose after the at least one pose is rotated by 180 degrees.
The method according to claim 2, wherein said obtaining the working time of the flashlight for flashing or illuminating the space to be detected comprises:

In response to the operation of the flashlight control in the camera detection interface, the flashlight is controlled to flash or illuminate the space to be detected, and the working time of the flashlight is acquired.
The method according to claim 1, further comprising:

In response to the operation of the time control in the camera detection interface, the second feature of the time-varying space to be detected is determined.
The method according to claim 1, wherein the matching of the first feature of the network data packet changing over time with the second feature of the space to be detected changing over time comprises:

The first feature and the second feature are processed by using a pre-trained machine learning model, and a matching result is output.
The method according to claim 10, characterized in that the method further comprises:

Obtaining the first sample characteristics of network data packets changing over time and the corresponding second sample characteristics of the experiment scenario changing over time in the test scenario;

Forming one of the first sample features and one of the corresponding second sample features into a sample data set to obtain a plurality of the sample data sets;

Obtain the label data of the sample data set, if the first sample feature in the sample data set is correlated with the second sample feature, the label data is 1, if the sample data set The first sample feature has no correlation with the second sample feature, and the label data is 0;

The machine learning model is trained by using the sample data set and its labeled data.
The method according to claim 1, further comprising:

Matching the format feature of the network data packet with the preset format feature;

The determining whether there is a camera in the space to be detected according to the matching result of the first feature and the second feature includes:

According to the matching result of the first feature and the second feature, and the matching result of the format feature of the network data packet and the preset format feature, it is determined whether there is a camera in the space to be detected.
The method according to claim 12, wherein, according to the matching result of the first feature and the second feature, and the matching result of the format feature of the network data packet and the preset format feature , to determine whether there is a camera in the space to be detected, including:

If the matching result of the first feature and the second feature is a matching result, and the matching result of the format feature of the network data packet and the preset format feature is also a successful match, then determine the space to be detected There is a camera in memory.
The method according to claim 1, wherein the first feature includes a first time point when the network data packet changes; the second feature includes a second time point when the space to be detected changes ; The matching of the first feature of the network data packet changing over time with the second feature of the space to be detected changing over time includes:

Match the first time point with the second time point.
The method according to claim 14, wherein the matching the first time point and the second time point comprises:

pairing the first time point with the second time point to obtain a plurality of time point pairs, each time point pair including one of the first time point and a corresponding one of the second time point;

If the difference between the first time point and the second time point in each time point pair does not exceed a time difference threshold, it is determined that the first time point and the second time point are successfully matched.
The method according to claim 15, wherein the matching the first time point and the second time point further comprises:

Before pairing the first time point with the second time point, time compensation is performed on the first time point or the second time point.
The method according to claim 1, wherein the matching of the first feature of the network data packet changing over time with the second feature of the space to be detected changing over time comprises:

Taking the first feature and the second feature as two variables, performing a correlation analysis to obtain a probability value of the correlation, and if the probability value of the correlation reaches a probability threshold, determine the first time point The matching with the second time point is successful.
A camera detection device is characterized in that it includes a processor and a memory, and the processor is used to execute the following program modules stored in the memory:

A data acquisition module configured to acquire network data packets in the space to be detected;

A feature matching module configured to match the first feature of the network data packet that changes with time with the second feature of the space to be detected that changes with time;

The detection result determining module is configured to determine whether there is a camera in the space to be detected according to the matching result of the first feature and the second feature.
A computer-readable storage medium on which a computer program is stored, wherein the computer program implements the method according to any one of claims 1 to 17 when executed by a processor.
An electronic device, characterized in that it comprises:

processor; and

a memory for storing executable instructions of the processor;

Wherein, the processor is configured to execute the method according to any one of claims 1 to 17 by executing the executable instructions.