Sensor fusion method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of vehicles, in particular to a sensor fusion method and device, electronic equipment and a storage medium, and the method comprises the steps: determining a first to-be-detected fusion region; obtaining all fusion sensor equipotential lines of the first to-be-detected fusion area, and determining the goodness of fit of all sensors in the first to-be-detected fusion area according to all fusion sensor equipotential lines of the first to-be-detected fusion area; and if the goodness of fit is greater than a first threshold, taking the first fusion region to be detected as a qualified fusion region. Therefore, the problems that a sensor fusion method is high in fusion requirement and poor in flexibility are solved, recognition results of sensors of any type, number and arrangement can be fused, a unified potential field theory is formed, sensing information of multiple sensors can be compatible, and the accuracy of the fusion result is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a sensor fusion method, device, electronic device and storage medium. Background Art

[0002] With the development of intelligent driving technology, the number of vehicle-side sensors has shown characteristics of multiple types, multiple quantities, and multiple distributions, and multi-sensor fusion has become particularly important.

[0003] There are two main types of sensor fusion methods in related technologies. One is the front fusion (data-level fusion) method, which requires the raw data of multiple sensors to be input into the recognition algorithm. The advantage is that the sensor information loss is small and the fusion level is deeper. The disadvantage is that it has high requirements on the recognition algorithm. In addition, due to the weak correlation between the raw data, the fusion of the recognition results is generally unexplainable, and problems cannot be quickly checked. The other is the post-fusion (target-level fusion) method, which generally uses the recognition algorithms of each sensor to identify the obstacle target once, and then fuses it according to the correlation characteristics between the targets, such as target ID, target type, target distance, target speed, etc. The advantage is that the fusion difficulty is relatively low and the fusion rules are easy to modify. The disadvantage is that it relies more on the correlation attributes of the target-level features. It is easy for the same obstacle to be identified as two types by different sensors, resulting in ineffective fusion. In addition, once the sensor layout plan, quantity and type are changed, the fusion algorithm needs to be adjusted accordingly, which is not flexible.

[0004] In summary, most sensor fusion methods in related technologies adopt pre-fusion methods or post-fusion methods, which have high fusion requirements and poor flexibility, and need to be solved urgently. Summary of the invention

[0005] The present application provides a sensor fusion method, device, electronic device and storage medium to solve the problems of high fusion requirements and poor flexibility of sensor fusion methods. The present application can fuse the recognition results of sensors of any type, quantity and arrangement to form a unified potential field theory, which can be compatible with the perception information of multiple sensors and improve the accuracy of the fusion results.

[0006] The first aspect of the present application provides a sensor fusion method, comprising the following steps:

[0007] Determine a first fusion area to be detected;

[0008] Acquire all equipotential lines of the fused sensors in the first to-be-detected fused area, and determine the degree of coincidence of all sensors in the first to-be-detected fused area according to the equipotential lines of all fused sensors in the first to-be-detected fused area;

[0009] If the degree of fit is greater than a first threshold, the first fusion area to be detected is taken as a qualified fusion area.

[0010] Optionally, in some embodiments, the determining the first to-be-detected fusion area includes:

[0011] Determine multiple sensors to be fused;

[0012] Establishing a safety potential field for each sensor to be fused to obtain a plurality of safety potential fields, and performing coordinate system transformation on the plurality of safety potential fields to obtain a plurality of transformed safety potential fields;

[0013] The multiple converted safety potential fields are sensed and fused to obtain a fusion result, so as to determine the first fusion area to be detected from the fusion result, wherein the fusion result includes multiple fusion areas.

[0014] Optionally, in some embodiments, when the plurality of converted safety potential fields are sensed and fused to obtain the fusion result, the method further includes:

[0015] Determine a second fusion area to be detected;

[0016] If the state of any sensor in the second to-be-detected fusion area is dangerous, the fusion result of the second to-be-detected fusion area is dangerous.

[0017] Optionally, in some embodiments, after determining a plurality of sensors to be fused, the method further includes:

[0018] Determining whether the equipotential lines of each sensor to be fused meet a preset jump condition;

[0019] If the equipotential lines of the sensor to be fused meet the preset jump condition, the sensor to be fused corresponding to the equipotential lines that meet the preset jump condition is marked.

[0020] Optionally, in some embodiments, after determining the degree of coincidence of all sensors in the first to-be-detected fusion area according to the equipotential lines of all fusion sensors in the first to-be-detected fusion area, the method further includes:

[0021] Determining whether the degree of fit is less than the first threshold;

[0022] If the degree of agreement is less than the first threshold, and the equipotential lines of all the fusion sensors meet the preset recognition condition, the equipotential lines of all the fusion sensors are averaged to obtain the true fusion result of the first fusion area to be detected.

[0023] A second aspect of the present application provides a sensor fusion device, including:

[0024] A first determining module, used to determine a first fusion area to be detected;

[0025] an acquisition module, configured to acquire equipotential lines of all fused sensors in the first to-be-detected fusion area, and determine the degree of coincidence of all sensors in the first to-be-detected fusion area according to the equipotential lines of all fused sensors in the first to-be-detected fusion area;

[0026] The second determining module is used to take the first to-be-detected fusion area as a qualified fusion area when the degree of fit is greater than a first threshold.

[0027] Optionally, in some embodiments, the first determining module includes:

[0028] A first determining unit, used to determine a plurality of sensors to be fused;

[0029] An establishing unit, used for respectively establishing the safety potential field of each sensor to be fused to obtain a plurality of safety potential fields, and performing coordinate system transformation on the plurality of safety potential fields to obtain a plurality of transformed safety potential fields;

[0030] The second determination unit is used to sense and fuse the multiple converted safety potential fields to obtain a fusion result, so as to determine the first to-be-detected fusion area from the fusion result, wherein the fusion result includes multiple fusion areas.

[0031] Optionally, in some embodiments, when the plurality of converted safety potential fields are sensed and fused to obtain the fusion result, the second determining unit further includes:

[0032] A first determining subunit, used to determine a second fusion area to be detected;

[0033] The second determining subunit is configured to determine that if the state of any sensor in the second to-be-detected fusion area is dangerous, the fusion result of the second to-be-detected fusion area is dangerous.

[0034] Optionally, in some embodiments, after determining a plurality of sensors to be fused, the first determining unit further includes:

[0035] A first judgment subunit is used to judge whether the equipotential line of each sensor to be fused meets a preset jump condition;

[0036] The marking subunit is used to mark the sensor to be fused corresponding to the equipotential line that meets the preset jump condition when the equipotential line of the sensor to be fused meets the preset jump condition.

[0037] Optionally, in some embodiments, after determining the degree of coincidence of all sensors in the first to-be-detected fusion area according to the equipotential lines of all fusion sensors in the first to-be-detected fusion area, the acquisition module further includes:

[0038] A second judging subunit, used to judge whether the degree of fit is less than the first threshold;

[0039] The processing subunit is used to perform mean processing on the equipotential lines of all the fusion sensors to obtain the true fusion result of the first fusion area to be detected when the degree of fit is less than the first threshold and the equipotential lines of all the fusion sensors meet the preset recognition conditions.

[0040] A third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the sensor fusion method as described in the above embodiment.

[0041] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the sensor fusion method as described in the above embodiment.

[0042] Therefore, by determining the first fusion area to be detected, and obtaining the equipotential lines of all fusion sensors in the first fusion area to be detected, and determining the degree of fit of all sensors in the first fusion area to be detected based on the equipotential lines of all fusion sensors in the first fusion area to be detected, if the degree of fit is greater than the first threshold, the first fusion area to be detected is used as a qualified fusion area. In this way, the problem of high fusion requirements and poor flexibility of the sensor fusion method is solved. The present application can fuse the recognition results of sensors of any type, quantity, and arrangement to form a unified potential field theory, which can be compatible with the perception information of multiple sensors and improve the accuracy of the fusion results.

[0043] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0045] Figure 1 A flowchart of a sensor fusion method provided according to an embodiment of the present application;

[0046] Figure 2 A schematic diagram of a sensor to be fused according to an embodiment of the present application;

[0047] Figure 3 A schematic diagram of the principle of a sensor fusion method provided according to an embodiment of the present application;

[0048] Figure 4 A schematic diagram of a sensor potential field before fusion provided according to an embodiment of the present application;

[0049] Figure 5 A schematic diagram of a sensor potential field after fusion according to an embodiment of the present application;

[0050] Figure 6 A schematic diagram of the principle of a sensor fusion method provided according to another embodiment of the present application;

[0051] Figure 7 A block diagram of a sensor fusion device provided according to an embodiment of the present application;

[0052] Figure 8 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0053] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0054] The following describes the sensor fusion method, device, electronic device and storage medium of the embodiment of the present application with reference to the accompanying drawings. In view of the problem of high fusion requirements and poor flexibility of the sensor fusion method mentioned in the above background technology, the present application provides a sensor fusion method, in which a first fusion area to be detected is determined, and all fusion sensor equipotential lines of the first fusion area to be detected are obtained, and the degree of fit of all sensors in the first fusion area to be detected is determined according to all fusion sensor equipotential lines of the first fusion area to be detected. If the degree of fit is greater than a first threshold, the first fusion area to be detected is used as a qualified fusion area. Thus, the problem of high fusion requirements and poor flexibility of the sensor fusion method is solved. The present application can fuse the recognition results of sensors of any type, quantity and arrangement to form a unified potential field theory, which can be compatible with the perception information of multiple sensors and improve the accuracy of the fusion results.

[0055] Specifically, Figure 1 A schematic diagram of a flow chart of a sensor fusion method provided in an embodiment of the present application.

[0056] like Figure 1 As shown, the sensor fusion method includes the following steps:

[0057] In step S101, a first fusion area to be detected is determined.

[0058] Optionally, in some embodiments, determining a first fusion area to be detected includes: determining multiple sensors to be fused; establishing a safety potential field for each sensor to be fused to obtain multiple safety potential fields, performing coordinate system transformation on the multiple safety potential fields to obtain multiple transformed safety potential fields; perceiving and fusing the multiple transformed safety potential fields to obtain a fusion result, so as to determine the first fusion area to be detected from the fusion result, wherein the fusion result includes multiple fusion areas.

[0059] Among them, the sensors to be fused may include one or more of a front-view camera, a front millimeter-wave radar, a lidar, a side front-view camera, a side rear-view camera, and a rear ultrasonic radar, and the safety potential field is a safety situation or a safety barrier.

[0060] Specifically, combined Figure 2 and 3 As shown in the figure, multiple sensors to be fused can form their own safety potential fields for the obstacle information around the vehicle according to their respective effective detection ranges and intervals. The establishment of the safety potential field enables the vehicle to accurately perceive the surrounding obstacle information, which is convenient for the later realization of obstacle avoidance, path planning and other functions. It should be noted that for the area within the blind spot of the sensor, it can be considered to be in a safe situation, and the potential field situation is safe.

[0061] The establishment of the safety potential field is based on the coordinate system of each sensor, which needs to be uniformly converted. After the safety potential field of each sensor to be fused is established, the safety potential field of all sensors in their respective coordinate systems is converted to the vehicle center of mass coordinate system to facilitate potential field fusion. The center of mass coordinate system refers to the origin at the center of mass of the vehicle, the X-axis points to the front of the vehicle, and the Y-axis points to the left side of the vehicle.

[0062] Furthermore, in some embodiments, when a plurality of converted safety potential fields are sensed and fused to obtain a fusion result, it also includes: determining a second fusion area to be detected; if the potential state of any sensor in the second fusion area to be detected is dangerous, the fusion result of the second fusion area to be detected is dangerous.

[0063] In the embodiment of the present application, after the coordinate system is converted, the potential field of the unified coordinate system is fused. The fusion principle is that the potential field situation is "dangerous rather than safe". Specifically, as long as there is a potential field in the area where the situation is dangerous, it is fused according to the dangerous situation. The display of the multi-sensor potential field before fusion and the sensor potential field after fusion is as follows: Figure 4 and Figure 5 shown.

[0064] After obtaining the fused sensor potential field, the embodiment of the present application determines a first fusion area to be detected from the fusion result, wherein the fusion result includes multiple fusion areas, and the fused sensor potential field can be output to the intelligent driving controller for obstacle avoidance, planning, and decision-making based on the obstacle information around the vehicle.

[0065] Optionally, in some embodiments, after determining multiple sensors to be fused, it also includes: judging whether the equipotential lines of each sensor to be fused meet the preset jump conditions; if the equipotential lines of the sensors to be fused meet the preset jump conditions, marking the sensors to be fused corresponding to the equipotential lines that meet the preset jump conditions.

[0066] The preset jump condition is that the equipotential lines jump.

[0067] It can be understood that if the equipotential line speeds are smooth and continuous, then all sensor recognition results are temporarily considered valid. If the equipotential lines jump, the sensor may have a detection failure. The embodiment of the present application can obtain the equipotential lines of each sensor to be fused, and determine whether the equipotential lines of each sensor to be fused jump; if the equipotential lines of the sensor to be fused jump, then the sensor to be fused corresponding to the equipotential lines that jump is marked.

[0068] In step S102, all fused sensor equipotential lines of the first to-be-detected fused area are obtained, and the degree of coincidence of all sensors in the first to-be-detected fused area is determined according to the equipotential lines of all fused sensors in the first to-be-detected fused area.

[0069] Specifically, after determining the first fusion area to be detected from the fusion results, all fusion sensors in the first fusion area to be detected are determined, and the equipotential lines of all fusion sensors are obtained, and the equipotential lines of all fusion sensors are compared to determine the consistency of all sensors in the first fusion area to be detected.

[0070] In step S103, if the degree of fit is greater than a first threshold, the first fusion region to be detected is taken as a qualified fusion region.

[0071] The first threshold may be preset by a user, obtained through a limited number of experiments, or obtained through a limited number of computer simulations, and is not specifically limited here.

[0072] It can be understood that if the degree of consistency of the equipotential lines of each sensor in the first fusion area to be detected is high, it means that the fusion effect is very good, and the regional perception fusion result here can be fully trusted. The first fusion area to be detected can be used as a qualified fusion area, otherwise further analysis is required for the mismatch.

[0073] Combination Figure 6As shown in the figure, if the degree of consistency of the equipotential lines of each sensor is low, the first fusion area to be detected is taken as the non-matching area, and it is determined whether the non-matching area is located in the blind area of ​​a certain sensor. If so, the potential field results of other non-blind area sensors in this area are trusted. Otherwise, it is necessary to focus on analyzing the non-matching equipotential lines of multiple sensors located in the effective detection area.

[0074] Then determine the relative stationary relationship between the equipotential line (obstacle position) and the vehicle. If it is relatively stationary, then from a safety perspective, trust the equipotential line with a closer distance. Otherwise, calculate the moving speed of the equipotential line of each sensor.

[0075] Optionally, in some embodiments, after determining the degree of fit of all sensors in the first fusion area to be detected based on the equipotential lines of all fusion sensors in the first fusion area to be detected, it also includes: judging whether the degree of fit is less than a first threshold; if the degree of fit is less than the first threshold, and the equipotential lines of all fusion sensors meet preset recognition conditions, then performing mean processing on the equipotential lines of all fusion sensors to obtain the true fusion result of the first fusion area to be detected.

[0076] Among them, the preset recognition condition is that the equipotential lines are smooth and continuous.

[0077] Specifically, if the equipotential line velocities of multiple sensors are smooth and continuous, the recognition results of all sensors are temporarily considered valid, all inconsistent equipotential lines are averaged and fused, sensors with equipotential line velocities that jump, and other sensor equipotential lines are trusted.

[0078] Therefore, the sensor fusion method proposed in this application establishes a unified potential field theory for various types of sensors, performs potential field fusion on multiple sensors to identify obstacle targets, and then performs further verification and feedback on the perception fusion results. On the one hand, it improves the trustworthiness of potential field fusion, and on the other hand, it can detect sensors with incorrect perception and recognition, so as to better update the recognition algorithm later.

[0079] According to the embodiment of the present application, a sensor fusion method is proposed, by determining the first fusion area to be detected, and obtaining the equipotential lines of all fusion sensors in the first fusion area to be detected, and determining the degree of fit of all sensors in the first fusion area to be detected based on the equipotential lines of all fusion sensors in the first fusion area to be detected, if the degree of fit is greater than the first threshold, the first fusion area to be detected is used as a qualified fusion area. Thus, the problem of high fusion requirements and poor flexibility of the sensor fusion method is solved. The present application can fuse the recognition results of sensors of any type, quantity, and arrangement to form a unified potential field theory, which can be compatible with the perception information of multiple sensors and improve the accuracy of the fusion results.

[0080] Next, the sensor fusion device proposed in accordance with the embodiment of the present application is described with reference to the accompanying drawings.

[0081] Figure 7 It is a block diagram of a sensor fusion device according to an embodiment of the present application.

[0082] like Figure 7 As shown, the sensor fusion device 10 includes: a first determination module 100 , an acquisition module 200 and a second determination module 300 .

[0083] The first determination module 100 is used to determine a first fusion area to be detected.

[0084] The acquisition module 200 is used to acquire the equipotential lines of all fused sensors in the first to-be-detected fusion area, and determine the degree of coincidence of all sensors in the first to-be-detected fusion area according to the equipotential lines of all fused sensors in the first to-be-detected fusion area.

[0085] The second determination module 300 is configured to determine the first fusion region to be detected as a qualified fusion region when the degree of fit is greater than a first threshold.

[0086] Optionally, in some embodiments, the first determination module 100 includes: a first determination unit, an establishment unit and a second determination unit.

[0087] Wherein, the first determining unit is used to determine a plurality of sensors to be fused.

[0088] The establishing unit is used to respectively establish the safety potential field of each sensor to be fused to obtain multiple safety potential fields, and perform coordinate system transformation on the multiple safety potential fields to obtain multiple transformed safety potential fields.

[0089] The second determination unit is used to sense and fuse the multiple converted safety potential fields to obtain a fusion result, so as to determine a first fusion area to be detected from the fusion result, wherein the fusion result includes multiple fusion areas.

[0090] Optionally, in some embodiments, when a plurality of converted safety potential fields are sensed and fused to obtain a fusion result, the second determination unit further includes: a first determination subunit and a second determination subunit.

[0091] Wherein, the first determination subunit is used to determine the second fusion area to be detected.

[0092] The second determining subunit determines that if the state of any sensor in the second to-be-detected fusion area is dangerous, the fusion result of the second to-be-detected fusion area is dangerous.

[0093] Optionally, in some embodiments, after determining a plurality of sensors to be fused, the first determining unit further includes: a first judging subunit and a marking subunit.

[0094] The first judgment subunit is used to judge whether the equipotential line of each sensor to be fused meets the preset jump condition.

[0095] The marking subunit is used to mark the sensor to be fused corresponding to the equipotential line that meets the preset jump condition when the equipotential line of the sensor to be fused meets the preset jump condition.

[0096] Optionally, in some embodiments, after determining the consistency of all sensors in the first fusion area to be detected according to the equipotential lines of all fusion sensors in the first fusion area to be detected, the acquisition module 200 further includes: a second judgment subunit and a processing subunit.

[0097] The second judgment subunit is used to judge whether the degree of fit is less than a first threshold.

[0098] The processing subunit is used to perform mean processing on the equipotential lines of all fusion sensors to obtain the true fusion result of the first fusion area to be detected when the degree of fit is less than the first threshold and the equipotential lines of all fusion sensors meet the preset recognition conditions.

[0099] It should be noted that the above explanation of the sensor fusion method embodiment is also applicable to the sensor fusion device of this embodiment, which will not be repeated here.

[0100] According to the sensor fusion device proposed in the embodiment of the present application, by determining the first fusion area to be detected, and obtaining the equipotential lines of all fusion sensors in the first fusion area to be detected, and determining the degree of fit of all sensors in the first fusion area to be detected based on the equipotential lines of all fusion sensors in the first fusion area to be detected, if the degree of fit is greater than the first threshold, the first fusion area to be detected is used as a qualified fusion area. In this way, the problem of high fusion requirements and poor flexibility of the sensor fusion method is solved. The present application can fuse the recognition results of sensors of any type, quantity, and arrangement to form a unified potential field theory, which can be compatible with the perception information of multiple sensors and improve the accuracy of the fusion results.

[0101] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0102] A memory 801 , a processor 802 , and a computer program stored in the memory 801 and executable on the processor 802 .

[0103] When the processor 802 executes the program, the sensor fusion method provided in the above embodiment is implemented.

[0104] Furthermore, the electronic device further comprises:

[0105] The communication interface 803 is used for communication between the memory 801 and the processor 802 .

[0106] The memory 801 is used to store computer programs that can be executed on the processor 802 .

[0107] The memory 801 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0108] If the memory 801, the processor 802 and the communication interface 803 are implemented independently, the communication interface 803, the memory 801 and the processor 802 can be connected to each other through a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0109] Optionally, in a specific implementation, if the memory 801, the processor 802 and the communication interface 803 are integrated on a chip, the memory 801, the processor 802 and the communication interface 803 can communicate with each other through an internal interface.

[0110] The processor 802 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0111] An embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above sensor fusion method is implemented.

[0112] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0113] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0114] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0115] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array, a field programmable gate array, etc.

[0116] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0117] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A sensor fusion method, characterized in that: The following steps are involved: Determine a first fusion area to be detected; Acquire all equipotential lines of the fused sensors in the first to-be-detected fused area, and determine the degree of coincidence of all sensors in the first to-be-detected fused area according to the equipotential lines of all fused sensors in the first to-be-detected fused area; If the degree of fit is greater than a first threshold, the first to-be-detected fusion area is taken as a qualified fusion area.

2. The method according to claim 1, characterized in that The determining the first to-be-detected fusion area includes: Determine multiple sensors to be fused; Establishing a safety potential field for each sensor to be fused to obtain a plurality of safety potential fields, and performing coordinate system transformation on the plurality of safety potential fields to obtain a plurality of transformed safety potential fields; The multiple converted safety potential fields are sensed and fused to obtain a fusion result, so as to determine the first fusion area to be detected from the fusion result, wherein the fusion result includes multiple fusion areas.

3. The method according to claim 2, characterized in that When the plurality of converted safety potential fields are sensed and fused to obtain the fusion result, the method further includes: Determine a second fusion area to be detected; If the state of any sensor in the second to-be-detected fusion area is dangerous, the fusion result of the second to-be-detected fusion area is dangerous.

4. The method according to claim 2, characterized in that: After determining a plurality of sensors to be fused, the method further includes: Determining whether the equipotential lines of each sensor to be fused meet a preset jump condition; If the equipotential lines of the sensor to be fused meet the preset jump condition, the sensor to be fused corresponding to the equipotential lines that meet the preset jump condition is marked.

5. The method according to claim 1, characterized in that After determining the consistency of all sensors in the first to-be-detected fusion area according to the equipotential lines of all fusion sensors in the first to-be-detected fusion area, the method further includes: Determining whether the degree of fit is less than the first threshold; If the degree of agreement is less than the first threshold, and the equipotential lines of all the fusion sensors meet the preset recognition condition, the equipotential lines of all the fusion sensors are averaged to obtain the true fusion result of the first fusion area to be detected.

6. A sensor fusion device, characterized in that: include: A first determining module, used to determine a first fusion area to be detected; an acquisition module, configured to acquire equipotential lines of all fused sensors in the first to-be-detected fusion area, and determine the degree of coincidence of all sensors in the first to-be-detected fusion area according to the equipotential lines of all fused sensors in the first to-be-detected fusion area; The second determining module is used to take the first to-be-detected fusion area as a qualified fusion area when the degree of fit is greater than a first threshold.

7. The device according to claim 6, characterized in that The first determining module includes: A first determining unit, used to determine a plurality of sensors to be fused; An establishing unit, used for respectively establishing the safety potential field of each sensor to be fused to obtain a plurality of safety potential fields, and performing coordinate system transformation on the plurality of safety potential fields to obtain a plurality of transformed safety potential fields; The second determination unit is used to sense and fuse the multiple converted safety potential fields to obtain a fusion result, so as to determine the first to-be-detected fusion area from the fusion result, wherein the fusion result includes multiple fusion areas.

8. The device according to claim 7, characterized in that When the plurality of converted safety potential fields are sensed and fused to obtain the fusion result, the second determining unit further includes: A first determining subunit, used to determine a second fusion area to be detected; The second determining subunit is configured to determine that if the state of any sensor in the second to-be-detected fusion area is dangerous, the fusion result of the second to-be-detected fusion area is dangerous.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the sensor fusion method according to any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the sensor fusion method as described in any one of claims 1 to 5.

Images