Target tracking method, system and tracking device based on distributed soft bus

Abstract

Embodiments of the present application provide a target tracking method and system based on a distributed soft bus and a tracking device. The method comprises: S1. obtaining and storing characteristic information of a target device itself; S2. the target device searching for a tracking device through a soft bus; S3. sorting signal measurement values of all received tracking devices to find a tracking device with the strongest signal as a current tracking device; S4. naming the current tracking device as a first tracking device and sending characteristic information of the target device to the first tracking device; and S5. the first tracking device tracking the target device in real time, collecting and matching target characteristic information of the target device. The above embodiments form an ad hoc network between the target device and the tracking device and between the tracking devices through a soft bus, so that information interaction between the target device and the tracking devices can be completed without the aid of a third party. By sending the characteristic information stored by the target device itself to the tracking device, the cost of manual selection and the cost of errors are reduced.

Description

Technical Field

[0001] This application relates to the field of intelligent control technology, and more particularly to a target tracking method, system and tracking device based on a distributed soft bus. Background Technology

[0002] In industrial manufacturing, some equipment requires real-time monitoring to ensure its proper functioning, as malfunctions can disrupt the entire production process and even lead to catastrophic consequences. However, some scenarios are unsuitable for real-time human observation due to fatigue from 24-hour monitoring. With the development of intelligent systems, monitoring of these devices can be accomplished using cameras. However, some equipment is mobile, such as unattended warehouse robots or mining machines in mines, where a single camera cannot fully cover and track all monitored targets. In such cases, multiple cameras working together are necessary for monitoring.

[0003] In existing technologies, such as the patent application "Adaptive Coal Mining Machine Follow-up Tracking Multi-Camera Video Stitching Method" (Publication No. CN112215925A), the tracking of moving targets generally uses simple camera tracking, manually selecting the target, and then using the SIFT feature matching algorithm to track the target. Its disadvantages are that it first requires manually selecting the features of the target device in the image, which places certain technical requirements on the operator and is inefficient. Furthermore, when the target object is not within the camera's range, the camera needs to continuously execute the target recognition algorithm, reducing camera performance and increasing its power consumption. At the same time, there is no interconnection between different cameras, and simply using camera tracking makes it impossible to accurately identify targets that are small and have large deformations in the image.

[0004] Application content

[0005] This application provides a target tracking method, system, and tracking device based on a distributed soft bus to solve the problem that existing technologies cannot perform target tracking well.

[0006] To address the aforementioned technical problems, this application provides a target tracking method based on a distributed soft bus, the method comprising:

[0007] S1. Acquire and store the characteristic information of the target device itself;

[0008] S2. The target device searches for and tracks the device via a soft bus;

[0009] S3. Sort all received signal measurements from tracking devices and find the tracking device with the strongest signal as the current tracking device;

[0010] S4. Name the current tracking device as the first tracking device, and send its own feature information to the first tracking device;

[0011] S5. The first tracking device tracks the target device in real time and collects and matches the target feature information of the target device.

[0012] As one embodiment, the method further includes:

[0013] S6. The target device detects that the signal of another tracking device is enhanced and exceeds that of the first tracking device, and names the other tracking device as the second tracking device, and the second tracking device is used as the current tracking device.

[0014] As one embodiment, the method further includes:

[0015] S7. The first tracking device detects whether the target device has entered the monitoring area of ​​the second tracking device;

[0016] S8. The first tracking device detects that the target device has entered the monitoring area of ​​the second tracking device, and the first tracking device enters sleep mode.

[0017] As one embodiment, the method further includes:

[0018] The first tracking device and the second tracking device communicate with each other via a soft bus, sending the target feature information of the target device collected in real time by the first tracking device and the self-feature information sent by the target device to the second tracking device.

[0019] The second tracking device fuses the target device's own feature information received with the target feature information collected in real time by the first tracking device, and the resulting fused feature information is used as the reference feature information for the second tracking device.

[0020] Secondly, in order to solve the technical problems of this application, embodiments of this application also provide a target tracking system based on a distributed soft bus, the system specifically including:

[0021] The system comprises a target device and several tracking devices, wherein the target device and the tracking devices form a self-organizing network via a soft bus, and the tracking devices themselves form a self-organizing network.

[0022] The target device acquires and stores its own characteristic information, and searches for and tracks other devices via a soft bus;

[0023] Sort all received signal measurements from tracking devices and select the tracking device with the strongest signal as the current tracking device.

[0024] The target device names the current tracking device as the first tracking device and sends its own feature information to the first tracking device;

[0025] The first tracking device tracks the target device in real time and collects and matches the target feature information of the target device.

[0026] As an embodiment of this application, preferably, when the target device detects that the signal of another tracking device is enhanced and exceeds that of the first tracking device, the other tracking device is named the second tracking device, and the second tracking device is used as the current tracking device.

[0027] As an embodiment of this application, preferably, the system further includes:

[0028] The first tracking device and the second tracking device communicate with each other via a soft bus, sending the target feature information of the target device collected in real time by the first tracking device and the self-feature information sent by the target device to the second tracking device.

[0029] The second tracking device fuses the target device's own feature information received with the target feature information collected in real time by the first tracking device, and the resulting fused feature information is used as the reference feature information for the second tracking device.

[0030] Thirdly, in order to solve the technical problems of this application, embodiments of this application also provide a tracking device, the tracking device comprising:

[0031] A communication module is used to form an ad hoc network with several other tracking devices via a soft bus, wherein the target device to be tracked forms an ad hoc network with the several tracking devices;

[0032] The receiving module is used to receive the target device's own characteristic information sent by the target device to be tracked. The target device searches for the tracking device through the soft bus, sorts the signal measurement values ​​of all received tracking devices, and finds the tracking device with the strongest signal as the current tracking device. The target device names the current tracking device as the first tracking device.

[0033] The tracking module is used to collect and match target feature information of the target device.

[0034] As an embodiment of this application, preferably, when the target device detects that the signal of another tracking device has increased and surpassed that of the first tracking device, the other tracking device is named the second tracking device, and the second tracking device is used as the current tracking device, wherein the tracking device further includes:

[0035] The sending module is used to send the target feature information of the target device collected in real time and the self-feature information sent by the target device to the second tracking device. The second tracking device fuses the self-feature information and target feature information of the target device received, and the resulting fused feature information is used as the reference feature information of the second tracking device.

[0036] To address the aforementioned technical problems, in a fourth aspect, embodiments of this application also provide a computer storage medium storing computer instructions that, when executed by at least one processor, implement the steps of the target tracking method as described above.

[0037] The above-described target tracking method, system, and device based on a distributed soft bus enable the target device and tracking devices, as well as the tracking devices themselves, to form a self-organizing network through the soft bus, allowing for information exchange without the need for remote terminals or backend servers. By sending the target device's stored feature information to the tracking devices, manual selection is eliminated, reducing the costs associated with manual selection and errors. Selecting tracking devices based on signal strength causes other tracking devices with weaker signals to enter a dormant state, reducing the overall computational demands and power consumption of the tracking equipment, while also ensuring the absence of tracking vulnerabilities. Furthermore, the target device's proactive discovery and notification of information sharing among the tracking devices significantly improves tracking accuracy. Attached Figure Description

[0038] The following is a brief introduction to the accompanying drawings used in the description of the embodiments of this application:

[0039] Figure 1 This is a schematic diagram of a target tracking system based on a distributed soft bus according to an embodiment of this application;

[0040] Figure 2 This is a schematic diagram illustrating another embodiment of the target tracking method based on a distributed soft bus in this application;

[0041] Figure 3 This is a schematic diagram illustrating another embodiment of the target tracking method based on a distributed soft bus in this application;

[0042] Figure 4 This is a schematic diagram illustrating an implementation of a target tracking method based on a distributed soft bus according to an embodiment of this application;

[0043] Figure 5 This is a flowchart illustrating another embodiment of a target tracking method based on a distributed soft bus according to this application;

[0044] Figure 6 This is a flowchart illustrating another embodiment of a target tracking method based on a distributed soft bus according to this application;

[0045] Figure 7 This is a flowchart illustrating another embodiment of a target tracking method based on a distributed soft bus according to this application;

[0046] Figure 8 This is a schematic diagram of the structure of a tracking device based on a distributed soft bus, according to another embodiment of this application. Detailed Implementation

[0047] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the specific implementation methods of this application will be described below with reference to the accompanying drawings. The accompanying drawings described below are merely some embodiments of this application. For those skilled in the art, other drawings and other implementation methods can be obtained based on these drawings without creative effort. Adjustments and improvements made without departing from the concept of this application are all within the protection scope of this application.

[0048] To keep the drawings concise, the figures in this application only schematically show the parts relevant to this application, and they do not represent the actual structure of the product. Furthermore, to make the drawings concise and easy to understand, some figures only schematically show parts of components with the same structure or function; in reality, there may be more or fewer components with the same structure or function.

[0049] In this application, unless otherwise expressly specified and limited, ordinal numbers, such as "first," "second," etc., are used only to distinguish and describe related objects, and should not be construed as indicating or implying the relative importance or order between related objects; furthermore, they do not represent the number of related objects. "And / or" is used to describe the relationship between related objects, which includes any relationship between the related objects; for example, "a and / or b" includes: "a alone," "b alone," or "a and b." The terms "installation" and "connection" should be interpreted broadly; for example, "installation" can be direct installation or installation via other components; "connection" can be direct connection or connection via other components. The term "relative arrangement" includes parallel relative or relative at a certain angle, the angle of which is not limited and is determined according to the number of objects in the relative arrangement.

[0050] In the embodiments shown in the accompanying drawings, the directional indications (such as up, down, left, right, front, and back) are relative rather than absolute when describing the structure and movement of the various components, and are not intended to limit the direction of the product during actual use.

[0051] like Figure 1As shown in the embodiment of this application, a target tracking system based on a distributed soft bus is disclosed. This embodiment includes multiple tracking devices (such as camera modules) and target devices. The target tracking based on the distributed soft bus selects the tracking device by the signal strength to track and monitor the target device in real time.

[0052] In a specific implementation scenario, the tracking device can be a camera equipped with the OpenHarmony system. Such camera devices have the ability to acquire images, perform real-time calculations, and connect to networks. The various tracking devices are connected through a distributed soft bus to form a self-organizing network.

[0053] In a specific implementation scenario, the target device can be an industrial control device equipped with the OpenHarmony system, such as a coal mining machine in a coal mine operation or a robot in a warehouse patrol operation, or other equipment that needs to be monitored in real time. It has real-time computing, network connection, and storage capabilities. The target device and the tracking device are connected through a distributed soft bus to form a self-organizing network.

[0054] like Figure 5 As shown, one embodiment of this application provides a target tracking method based on a distributed soft bus, the method comprising:

[0055] S1. Acquire and store the characteristic information of the target device itself;

[0056] Specifically, the target device pre-stores its own feature information, travel route, and operation actions. The feature information consists of state images of the target device in different directions and with different operation actions, which are pre-collected by an image acquisition device. Then, the SIFT (Scale-Invariant Feature Transform) algorithm is used to calculate the feature information of the target device, and the feature information is stored in the storage module.

[0057] The SIFT algorithm is used to detect local features of a target device. It obtains local features by calculating key feature points in an image and their scale and orientation descriptors, which are then used for subsequent feature point matching. Key points extracted by SIFT are scale-invariant, rotation-invariant, and unaffected by factors such as lighting, affine transformations, and noise.

[0058] The main steps of the SIFT algorithm are as follows:

[0059] S11. Construct the scale space of the target device to obtain the scale features of the target device image at different scales;

[0060] The scale space of the target device is constructed to simulate the scale characteristics of the target device's images at different scales. This scale space is represented using a Gaussian pyramid.

[0061] The scale space is defined as follows:

[0062] The scale space L(x, y, σ) of the target device's image is defined as the convolution of a Gaussian function G(x, y, σ) with varying scales and the original image I(x, y):

[0063] L(x,y,σ)=G(x,y,σ)*I(x,y)

[0064]

[0065] Where σ is the standard deviation of the normal distribution; the larger the σ value, the smoother the image. x and y are the coordinates in the image, and m and n are the width and height of the image. To detect feature points that exist at different scales, a good operator for feature point detection is the Laplacian of Gaussian (LoG), i.e., Δ... 2 G

[0066]

[0067] While the Laplacian of Gaussian operator (LoG) is effective at detecting feature points in images, its computational cost is prohibitively high. A common approximation is the Difference-of-Gaussian (DoG) method, which approximates the LoG. Let k be the scaling factor between two adjacent Gaussian scale spaces; then the DoG is defined as:

[0068] D(x,y,σ)=[G(x,y,kσ)-G(x,y,σ)]*I(x,y)=L(x,y,kσ)-L(x,y,σ)

[0069] S12. Detect feature points in the scale space;

[0070] In order to find feature points in the scale space, each sampling point is compared with all its neighboring points to determine whether it is larger or smaller than its neighboring points in the image domain and scale domain.

[0071] like Figure 2 As shown, the detection point in the middle is compared with its 8 neighboring points at the same scale and 9x2 points corresponding to the adjacent scales above and below, for a total of 26 points, to ensure that extreme points are detected in both the scale space and the two-dimensional image space.

[0072] S13. Remove unwanted feature points;

[0073] Removing unwanted feature points involves eliminating pixels with highly asymmetrical local curvature, such as low-contrast keypoints and unstable edge response points. The DoG operator generates strong edge responses, necessitating the removal of unstable edge response points. The specific method is as follows:

[0074] Obtain the Hessian matrix at the feature point, and the principal curvature is obtained by using a 2x2 Hessian matrix H(x,y).

[0075]

[0076] S14. Assign a 128-dimensional parameter to the determined feature point;

[0077] In the previous step, the feature points of each image were determined, and a direction was calculated for each feature point. Further calculations were performed based on this direction. The gradient direction distribution characteristics of the neighboring pixels of the key point were used to specify the direction parameters for each key point, so that the DoG operator has rotation invariance.

[0078] For example, the argument and magnitude of the region image centered on the feature point and with a radius of 3×1.5σ, and the magnitude m(x,y) and direction θ(x,y0) of the gradient at each point L(x,y), can be obtained using the following formula:

[0079]

[0080]

[0081] Based on SIFT matching, descriptors for two images, A and B (k1*128 dimensions and k2*128 dimensions respectively), were generated. By matching the descriptors at each scale in the two images, a match of 128 dimensions can be used to represent the matching of two feature points.

[0082] S2. The target device searches for and tracks the device via the soft bus;

[0083] Specifically, both the target device and the camera device are industrial control devices equipped with the OpenHarmony system. The target device acquires signal strength measurements from multiple wireless communication WiFi access points (APs) of various target devices and filters out devices that match the camera device's fingerprint. The device fingerprint refers to pre-collecting various information about the device, assigning it a unique identifier, and using multiple association and similarity search algorithms to ensure the stability of this identifier. This prevents the access of incompatible devices in complex network environments. Only by accurately identifying devices in the network can the camera function effectively. The collected information includes features such as the device's hardware ID, interface information, operating system, various system plugins, browser language settings and time zone, mobile phone IMEI, network card MAC address, font settings, and LBS address. The collected information mainly comprises three parts: hardware, network, and system.

[0084] S3. Sort all received signal measurements from tracking devices and find the tracking device with the strongest signal;

[0085] Specifically, the signal measurement values ​​of all received tracking devices are sorted, and the tracking device with the largest signal measurement value is selected as the current tracking device.

[0086] S4. Name the current tracking device as the first tracking device, and send its own feature information to the first tracking device;

[0087] Specifically, the device with the largest signal measurement value is designated as the first tracking device, and the target device sends its SIFT feature information to the first tracking device via a soft bus. This allows the first tracking device to communicate directly with the target device and obtain relevant information directly, without the need for intermediaries such as servers or remote terminals, thus improving the flexibility, security, and reliability of device integration and collaboration.

[0088] S5. The first tracking device tracks the target device in real time and collects and matches the target feature information of the target device.

[0089] Specifically, the first tracking device uses the SIFT algorithm for matching.

[0090] The first tracking device matches the target feature information collected in real time with its own feature information transmitted from the target device in order to confirm the target device and thus continuously track the target device.

[0091] Further preferably, during the tracking process, the current status of the target device is confirmed to determine whether the target device is in an abnormal state.

[0092] If the target device is detected to be in an abnormal state, the first tracking device sends a stop command to the target device;

[0093] If no abnormalities are found, the target device continues to move forward, and the first tracking device continues to track the target device in real time. During the tracking process, it stores the acquired images of the target device in real time and generates real-time target feature information of the target device, which is then stored in the storage module of the first tracking device. This allows for monitoring and control of the target device's status to prevent damage to personnel or resources in abnormal situations.

[0094] Furthermore, such as Figure 6 As shown, in another embodiment of the present invention, the target tracking method based on a soft bus includes:

[0095] S1. Acquire and store the characteristic information of the target device itself;

[0096] S2. The target device searches for and tracks the device via the soft bus;

[0097] S3. Sort all received signal measurements from tracking devices and find the tracking device with the strongest signal;

[0098] S4. Name the current tracking device as the first tracking device, and send the target feature information to the first tracking device;

[0099] S5. The first tracking device tracks the target device in real time and collects and matches the target feature information of the target device;

[0100] S6. The target device detects that the signal enhancement of another tracking device exceeds that of the first tracking device, and names the other tracking device as the second tracking device, and the second tracking device becomes the current tracking device.

[0101] Specifically, for example, Figure 3 As shown, when the camera is used as a tracking device, during the movement of the target device, the signal strength of the WiFi access point AP of the camera module 2 obtained by the target device is greater than that of the camera module 1, that is, the target device sends its own feature information to the camera module 2, and the camera module 2 begins to track the target device.

[0102] like Figure 7 As shown, in another embodiment of the present invention, the target tracking method based on a soft bus includes:

[0103] S1. Acquire and store the characteristic information of the target device itself;

[0104] S2. The target device searches for and tracks the device via the soft bus;

[0105] S3. Sort all received signal measurements from tracking devices and find the tracking device with the strongest signal;

[0106] S4. Name the current tracking device as the first tracking device, and send the target feature information to the first tracking device;

[0107] S5. The first tracking device tracks the target device in real time and collects and matches target feature information;

[0108] S6. The target device detects that the signal enhancement of another tracking device exceeds that of the first tracking device, and names the other tracking device as the second tracking device, and the second tracking device becomes the current tracking device;

[0109] S7. The first tracking device detects whether the target device has entered the monitoring area of ​​the second tracking device;

[0110] Specifically, such as Figure 4 As shown, if the tracking device is a camera module, the overlapping area of ​​each camera is first calculated using the SIFT algorithm.

[0111] The first camera module 1 determines whether the target device has entered the monitoring area of ​​the second camera module 2. During the movement of the target device, when the target device obscures or overlaps with the target area, the target has entered the monitoring area of ​​the second camera. The first camera module 1 and the second camera module 2 communicate with each other using soft bus technology, sending the real-time feature information of the target device collected by the first camera module 1 along with the target device's own feature information to the second camera module 2.

[0112] S8. The second tracking device tracks the target device in real time, and the first tracking device enters sleep mode.

[0113] Specifically, when the tracking device is a camera module, the second camera module 2 receives the target device's own feature information 1 and the real-time target feature information 2 collected by the first camera module, and uses the fused feature information obtained by fusing the two feature information as the reference feature information of the second camera module 2.

[0114] By fusing feature information 1 and feature information 2, the fusion weight can be set to feature information 2 being greater than feature information 1. This allows us to utilize both the real-time target feature information collected by the tracking device and the feature information of the target device itself. Moreover, the real-time target feature information is combined with the environmental information at that time, which improves the detection accuracy and robustness to the environment compared to using only the feature information of the target device itself.

[0115] Furthermore, when the second camera module 2 has detected the target device, it notifies the first camera module 1 to enter sleep mode via a soft bus. This saves power consumption of the first camera module 1 and other cameras, reduces the computer performance requirements of other camera modules, and prevents monitoring vulnerabilities where the target device is not within the capture range of the second camera module 2 even though the second camera module 2 is connected to it.

[0116] like Figure 1 As shown in the embodiment of this application, a target tracking system based on a distributed soft bus is disclosed. This embodiment includes multiple tracking devices (such as camera modules) and target devices. The target tracking based on the distributed soft bus selects the tracking device by the signal strength to track and monitor the target device in real time.

[0117] In a specific implementation scenario, the tracking device can be a camera equipped with the OpenHarmony system. Such camera devices have the ability to acquire images, perform real-time calculations, and connect to networks. The various tracking devices are connected through a distributed soft bus to form a self-organizing network.

[0118] In a specific implementation scenario, the target device can be an industrial control device equipped with the OpenHarmony system, such as a coal mining machine in a coal mine operation or a robot in a warehouse patrol operation, or other equipment that needs to be monitored in real time. It has real-time computing, network connection, and storage capabilities. The target device and the tracking device are connected through a distributed soft bus to form a self-organizing network.

[0119] The target device acquires and stores its own feature information and searches for and tracks devices via a soft bus. Specifically, the target device pre-stores its own feature information, travel route, and operation actions. The feature information consists of state images of the target device in different directions and with different operation actions, which are pre-collected by an image acquisition device. Then, the SIFT (Scale-Invariant Feature Transform) algorithm is used to calculate the feature information of the target device, and the feature information is stored in the storage module.

[0120] The SIFT algorithm is used to detect local features of a target device. It obtains local features by calculating key feature points in an image and their scale and orientation descriptors, which are then used for subsequent feature point matching. Key points extracted by SIFT are scale-invariant, rotation-invariant, and unaffected by factors such as lighting, affine transformations, and noise.

[0121] The signal measurements from all received tracking devices are sorted, and the tracking device with the strongest signal is selected as the current tracking device. Specifically, both the target device and the camera device are industrial control devices equipped with the OpenHarmony system. The target device acquires signal strength measurements from multiple wireless communication WiFi access points (APs) of each target device and selects the tracking device with the strongest signal as the current tracking device.

[0122] The target device names the current tracking device as the first tracking device and sends its own feature information to the first tracking device;

[0123] The first tracking device tracks the target device in real time and collects and matches the target feature information of the target device.

[0124] The first tracking device matches the target feature information collected in real time with its own feature information transmitted from the target device in order to confirm the target device and thus continuously track the target device.

[0125] Further preferably, during the tracking process, the current status of the target device is confirmed to determine whether the target device is in an abnormal state.

[0126] If the target device is detected to be in an abnormal state, the first tracking device sends a stop command to the target device;

[0127] If there are no abnormalities, the target device continues to move forward, and the first tracking device continues to track the target device in real time. During the tracking process, the acquired target device images are stored in real time, and the real-time target feature information of the target device is generated and stored in the storage module of the first tracking device.

[0128] As an embodiment of this application, preferably, when the target device detects that the signal of another tracking device is enhanced and exceeds that of the first tracking device, the other tracking device is named the second tracking device, and the second tracking device is used as the current tracking device.

[0129] Specifically, for example, Figure 3 As shown, when the camera is used as a tracking device, during the movement of the target device, the signal strength of the WiFi access point AP of the camera module 2 obtained by the target device is greater than that of the camera module 1, that is, the target device sends its own feature information to the camera module 2, and the camera module 2 begins to track the target device.

[0130] As an embodiment of this application, preferably, the system further includes:

[0131] The first tracking device and the second tracking device communicate with each other via a soft bus, sending the target feature information of the target device collected in real time by the first tracking device and the self-feature information sent by the target device to the second tracking device.

[0132] The second tracking device fuses the target device's own feature information received with the target feature information collected in real time by the first tracking device, and the resulting fused feature information is used as the reference feature information for the second tracking device.

[0133] The first camera module 1 determines whether the target device has entered the monitoring area of ​​the second camera module 2. During the movement of the target device, when the target device obscures or overlaps with the target area, the target has entered the monitoring area of ​​the second camera. The first camera module 1 and the second camera module 2 communicate with each other using soft bus technology, sending the real-time feature information of the target device collected by the first camera module 1 along with the target device's own feature information to the second camera module 2.

[0134] S8. The second tracking device tracks the target device in real time, and the first tracking device enters sleep mode.

[0135] Specifically, when the tracking device is a camera module, the second camera module 2 receives the target device's own feature information 1 and the real-time target feature information 2 collected by the first camera module, and uses the fused feature information obtained by fusing the two feature information as the reference feature information of the second camera module 2.

[0136] By fusing feature information 1 and feature information 2, the fusion weight can be set to feature information 2 being greater than feature information 1. This allows us to utilize both the real-time target feature information collected by the tracking device and the feature information of the target device itself. Moreover, the real-time target feature information is combined with the environmental information at that time, which improves the detection accuracy and robustness to the environment compared to using only the feature information of the target device itself.

[0137] like Figure 8 As shown, in a third aspect, to solve the technical problems of this application, embodiments of this application also provide a tracking device, the tracking device comprising:

[0138] A communication module is used to form an ad hoc network with several other tracking devices via a soft bus, wherein the target device to be tracked forms an ad hoc network with the several tracking devices;

[0139] The receiving module is used to receive the target device's own characteristic information sent by the target device to be tracked. The target device searches for the tracking device through the soft bus, sorts the signal measurement values ​​of all received tracking devices, and finds the tracking device with the strongest signal as the current tracking device. The target device names the current tracking device as the first tracking device.

[0140] The tracking module is used to collect and match target feature information of the target device.

[0141] As an embodiment of this application, preferably, when the target device detects that the signal of another tracking device has increased and surpassed that of the first tracking device, the other tracking device is named the second tracking device, and the second tracking device is used as the current tracking device, wherein the tracking device further includes:

[0142] The sending module is used to send the target feature information of the target device acquired in real time and the self-feature information sent by the target device to the second tracking device. The second tracking device fuses the received self-feature information of the target device and the target feature information, and the resulting fused feature information is used as the reference feature information of the second tracking device. The implementation of the tracking device is the same as the implementation of the target tracking method and system described above, and will not be repeated here.

[0143] The above-described target tracking method, system, and device based on a distributed soft bus enable the target device and tracking devices, as well as the tracking devices themselves, to form a self-organizing network. This allows for information exchange without the need for remote terminals or backend servers. The target device's feature information can be actively sent to the tracking devices, such as camera devices or modules, which then automatically track the target based on the provided information, eliminating the need for manual selection. Furthermore, compared to traditional image-based target tracking methods, where the camera continuously executes target recognition algorithms even when the target object is not within the camera's field of view, consuming significant computing power and increasing power consumption, this application utilizes a distributed soft bus technology. The target device and camera are networked together, and the target tracking algorithm is only activated after the network connection is established. The algorithm is not activated when no camera is connected, reducing computer usage and power consumption. Additionally, when the target device image is small and has significant deformation, the camera in this application can enhance target tracking and matching accuracy by using target feature information provided by the target device and information collected by the previous camera.

[0144] To address the aforementioned technical problems, in a fourth aspect, embodiments of this application also provide a computer storage medium storing computer instructions that, when executed by at least one processor, implement the steps of the target tracking method as described above.

[0145] It is understood that the computer storage medium in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The computer storage media of the apparatuses and methods described herein are intended to include, but are not limited to, these and any other suitable types of memory.

[0146] The processor may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0147] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or combinations thereof.

[0148] For software implementation, the techniques described herein can be achieved through modules (e.g., procedures, functions, etc.) that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented within the processor or externally.

[0149] Alternatively, as another embodiment, the processor is also configured to perform the steps of the method described in the foregoing embodiments when running the computer program.

[0150] From the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0151] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0152] It should be noted that the above embodiments can be freely combined as needed. The above are only some embodiments of this application. For those skilled in the art, several improvements and modifications can be made without departing from the principles of this application, and these improvements and modifications should also be considered within the protection scope of this application.

Claims

1. A target tracking method based on a distributed soft bus, characterized in that, The method includes: S1. Acquire and store the characteristic information of the target device itself; S2. The target device searches for and tracks the device via a soft bus; S3. Sort all received signal measurements from tracking devices and find the tracking device with the strongest signal as the current tracking device; S4. Name the current tracking device as the first tracking device, and send its own feature information to the first tracking device; S5. The first tracking device tracks the target device in real time and collects and matches the target feature information of the target device; S6. The target device detects that the signal of another tracking device has increased and surpassed that of the first tracking device, and names the other tracking device as the second tracking device, and the second tracking device is used as the current tracking device; S7. The first tracking device detects whether the target device has entered the monitoring area of ​​the second tracking device; S8. The first tracking device detects that the target device has entered the monitoring area of ​​the second tracking device, and the first tracking device enters sleep mode.

2. The target tracking method based on a distributed soft bus according to claim 1, characterized in that, The method further includes: The first tracking device and the second tracking device communicate with each other via a soft bus, sending the target feature information of the target device collected in real time by the first tracking device and the self-feature information sent by the target device to the second tracking device. The second tracking device fuses the target device's own feature information received with the target feature information collected in real time by the first tracking device, and the resulting fused feature information is used as the reference feature information for the second tracking device.

3. A target tracking system based on a distributed soft bus, characterized in that, The system specifically includes: The system comprises a target device and several tracking devices, wherein the target device and the tracking devices form a self-organizing network via a soft bus, and the tracking devices themselves form a self-organizing network. The target device acquires and stores its own characteristic information, and searches for and tracks other devices via a soft bus; Sort all received signal measurements from tracking devices and select the tracking device with the strongest signal as the current tracking device. The target device names the current tracking device as the first tracking device and sends its own feature information to the first tracking device; The first tracking device tracks the target device in real time and collects and matches the target feature information of the target device; The target device detects that the signal of another tracking device has increased and surpassed that of the first tracking device, and names the other tracking device as the second tracking device, which becomes the current tracking device; The first tracking device detects whether the target device has entered the monitoring area of ​​the second tracking device. When the first tracking device detects that the target device has entered the monitoring area of ​​the second tracking device, the first tracking device enters sleep mode.

4. The target tracking system based on a distributed soft bus according to claim 3, characterized in that, The system also includes: The first tracking device and the second tracking device communicate with each other via a soft bus, sending the target feature information of the target device collected in real time by the first tracking device and the self-feature information sent by the target device to the second tracking device. The second tracking device fuses the target device's own feature information received with the target feature information collected in real time by the first tracking device, and the resulting fused feature information is used as the reference feature information for the second tracking device.

5. A tracking device, characterized in that, The tracking device includes: A communication module is used to form an ad hoc network with several other tracking devices via a soft bus, wherein the target device to be tracked forms an ad hoc network with the several tracking devices; The receiving module is used to receive the target device's own characteristic information sent by the target device to be tracked. The target device searches for the tracking device through the soft bus, sorts the signal measurement values ​​of all received tracking devices, and finds the tracking device with the strongest signal as the current tracking device. The target device names the current tracking device as the first tracking device. The tracking module is used to collect and match target feature information of the target device; When the target device detects that the signal of another tracking device has increased and surpassed that of the first tracking device, the other tracking device is designated as the second tracking device, and the second tracking device becomes the current tracking device. The first tracking device detects whether the target device has entered the monitoring area of ​​the second tracking device. When the first tracking device detects that the target device has entered the monitoring area of ​​the second tracking device, the first tracking device enters a sleep mode. The tracking device further includes: The sending module is used to send the target feature information of the target device collected in real time and the self-feature information sent by the target device to the second tracking device. The second tracking device fuses the self-feature information and target feature information of the target device received, and the resulting fused feature information is used as the reference feature information of the second tracking device.

Images