Multi-degree-of-freedom street lamp steering method, system and equipment based on thermal imaging positioning

Abstract

The invention discloses a multi-degree-of-freedom street lamp steering method, system and equipment based on thermal imaging positioning, and relates to the technical field of intelligent illumination, and the method comprises the steps: collecting thermal imaging data of a target road surface through a thermal imager, the target road surface being all road surface areas which can be irradiated and covered by a target street lamp; calling a heat source identification plan to process and analyze the thermal imaging data to obtain a real-time heat source target; judging whether the real-time heat source target conforms to a first predetermined constraint or not; if yes, acquiring a predetermined steering strategy corresponding to the real-time heat source target; the predetermined steering strategy performs multi-degree-of-freedom steering control on the target street lamp based on the real-time spatial attitude of the target street lamp. The technical problem that the street lamp cannot flexibly adapt to the road condition due to the fact that the illumination direction and the coverage range cannot be dynamically adjusted according to the environment change in the prior art is solved, and the technical effects of improving the illumination efficiency of the street lamp and improving the adaptability and the intelligent control level of the street lamp in different traffic environments are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent lighting, in particular to a multi-degree-of-freedom street lamp turning method, system and device based on thermal imaging positioning. BACKGROUND

[0002] In traditional applications, street lamps mainly rely on fixed light direction and range for work, and cannot dynamically adjust according to road conditions or environmental changes. With the continuous change of road traffic conditions, such as vehicle, pedestrian activities or different climate conditions, the fixed light mode is difficult to achieve the optimal lighting effect. This static lighting method not only leads to energy waste, but also cannot provide a flexible lighting solution to different road conditions and traffic density, affecting the efficiency and intelligent level of the lighting system. SUMMARY

[0003] The present application provides a multi-degree-of-freedom street lamp turning method, system and device based on thermal imaging positioning, which is used to solve the technical problem that the existing street lamps cannot dynamically adjust the light direction and coverage range according to environmental changes, resulting in the inability to flexibly adapt to road conditions.

[0004] In view of the above problems, the present application provides a multi-degree-of-freedom street lamp turning method, system and device based on thermal imaging positioning.

[0005] The first aspect of the present application provides a multi-degree-of-freedom street lamp turning method based on thermal imaging positioning, which comprises:

[0006] The thermal imager collects the thermal imaging data of the target road surface, wherein the target road surface refers to all road surface areas that can be irradiated and covered by the target street lamp; the thermal imaging data is processed and analyzed by calling the heat source identification plan to obtain a real-time heat source target; it is judged whether the real-time heat source target meets the first predetermined constraint; if it meets, the predetermined turning strategy corresponding to the real-time heat source target is obtained; the predetermined turning strategy is based on the real-time spatial pose of the target street lamp, and the multi-degree-of-freedom turning control of the target street lamp is performed.

[0007] The second aspect of the present application provides a multi-degree-of-freedom street lamp turning system based on thermal imaging positioning, which comprises:

[0008] The thermal imaging acquisition module is configured to acquire thermal imaging data of a target road surface by using a thermal imager, wherein the target road surface refers to all road surface regions that can be irradiated by the target street lamp; the processing and analysis module is configured to process and analyze the thermal imaging data by using a heat source identification plan to obtain a real-time heat source target; the judgment module is configured to judge whether the real-time heat source target meets a first predetermined constraint; the strategy acquisition module is configured to acquire a predetermined turning strategy corresponding to the real-time heat source target if the real-time heat source target meets the first predetermined constraint; and the turning control module is configured to perform multi-degree-of-freedom turning control on the target street lamp based on a real-time spatial pose of the target street lamp according to the predetermined turning strategy.

[0009] In a third aspect, the present application provides an electronic device, comprising: a memory configured to store executable instructions; and a processor configured to execute the executable instructions stored in the memory to implement the multi-degree-of-freedom street lamp turning method based on thermal imaging positioning provided by the present application.

[0010] The one or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0011] In the present application, the thermal imaging data of a target road surface is acquired by using a thermal imager, wherein the target road surface refers to all road surface regions that can be irradiated by the target street lamp; the thermal imaging data is processed and analyzed by using a heat source identification plan to obtain a real-time heat source target; it is judged whether the real-time heat source target meets a first predetermined constraint; a predetermined turning strategy corresponding to the real-time heat source target is acquired if the real-time heat source target meets the first predetermined constraint; and multi-degree-of-freedom turning control is performed on the target street lamp based on a real-time spatial pose of the target street lamp according to the predetermined turning strategy. The present application solves the technical problem that the street lamp in the prior art cannot dynamically adjust the illumination direction and coverage range according to the environmental changes, thereby failing to flexibly adapt to the road surface conditions. By combining the thermal imaging data to identify the heat source target in real time and adjusting the turning of the street lamp based on the position and spatial pose of the target heat source, the technical effects of improving the lighting efficiency of the street lamp and improving the adaptability and intelligent control level of the street lamp in different traffic environments are achieved. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0013] Figure 1 A flowchart of the multi-degree-of-freedom street lamp turning method based on thermal imaging positioning provided by the embodiments of the present application is shown in the figure.

[0014] Figure 2A structure schematic diagram of a multi-degree-of-freedom street lamp turning system based on thermal imaging positioning provided by an embodiment of the present application is shown in the figure.

[0015] Figure 3 A structure schematic diagram of an exemplary electronic device of the present application is shown in the figure.

[0016] Legend: bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface 305, thermal imaging acquisition module 11, processing and analysis module 12, judgment module 13, strategy acquisition module 14, turning control module 15. DETAILED DESCRIPTION

[0017] The present application provides a multi-degree-of-freedom street lamp turning method, system and device based on thermal imaging positioning, which solves the technical problem that the street lamp cannot dynamically adjust the light direction and coverage range according to the environmental changes in the prior art, resulting in the inability to flexibly adapt to the road conditions. By combining thermal imaging data to identify the heat source target in real time, and adjusting the turning of the street lamp based on the position and spatial attitude of the target heat source, the technical effects of improving the lighting efficiency of the street lamp and improving the adaptability and intelligent control level of the street lamp in different traffic environments are achieved.

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0019] It should be noted that any variation of the terms "comprise" and "have" is intended to cover non-exclusive inclusion, for example, a process, method, system, product or server comprising a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] Embodiment one, as shown in the figure, the present application provides a multi-degree-of-freedom street lamp turning method based on thermal imaging positioning, which comprises: Figure 1

[0021] Step S100: acquiring the thermal imaging data of the target road surface by a thermal imager, wherein the target road surface refers to all road surface areas that can be irradiated and covered by the target street lamp.

[0022] ​In the embodiments of the present application, the thermal imaging data of the target road surface is collected by a thermal imager at the target street lamp. The target road surface refers to all the road surface regions that can be illuminated and covered by the target street lamp. Specifically, the thermal imager uses an infrared radiation sensing method to generate thermal imaging data by detecting and capturing the infrared thermal radiation emitted by objects in the target road surface region. The thermal imager includes infrared sensors that can sense the heat released by different objects (such as vehicles, pedestrians, etc.).

[0023] Step S200: calling the heat source identification plan to process and analyze the thermal imaging data to obtain a real-time heat source target.

[0024] In the embodiments of the present application, when the heat source identification plan is called to process and analyze the thermal imaging data, first, a temperature threshold is set according to the real-time environmental temperature, and the candidate heat source region is extracted from the thermal imaging data with the temperature threshold as a constraint. Then it is judged whether the extracted candidate heat source region meets the second predetermined constraint. If it meets, the candidate region is analyzed according to the type determination scheme in the heat source identification plan, and finally the real-time heat source target is determined. The second predetermined constraint is that there is only one heat source region, i.e. only one heat source target.

[0025] If the candidate region does not meet the second predetermined constraint, the region is segmented to obtain multiple segmentation results, and a first region block is extracted therefrom. Next, the first region block is analyzed according to the scheme in the heat source identification plan to obtain a first heat source target. Finally, the real-time heat source target is determined according to the first heat source target.

[0026] Further, in the method provided by the embodiments of the present application, calling the heat source identification plan to process and analyze the thermal imaging data to obtain a real-time heat source target further includes:

[0027] setting a temperature threshold according to the real-time environmental temperature; extracting the thermal imaging data with the temperature threshold as a constraint to obtain a candidate heat source region; judging whether the candidate heat source region meets a second predetermined constraint; if it meets, analyzing the candidate heat source region according to the type determination scheme in the heat source identification plan to determine the real-time heat source target.

[0028] In the embodiments of the present application, when the temperature threshold is set according to the real-time environmental temperature, a temperature threshold is dynamically set according to the current environmental temperature. For example, in a cold weather environment, the environmental temperature may be between 0℃ and 10℃, and the temperature threshold is set to 30℃; in a warm environment, the environmental temperature may be between 10℃ and 25℃, and the temperature threshold is set to 40℃; and in a hot summer, the environmental temperature is higher than 30℃, and the temperature threshold is increased to more than 50℃.

[0029] Next, with the temperature threshold as a constraint, candidate heat source regions are extracted from the thermal imaging data. The thermal imaging data records temperature information of various regions on the target road surface. By screening these data, regions with temperature higher than the set threshold are extracted, obtaining candidate heat source regions. These regions are considered as potential heat source regions, representing vehicles, pedestrians or other objects on the road surface.

[0030] Next, it is determined whether the extracted candidate heat source region meets the second predetermined constraint, i.e. whether the region contains only one heat source target. The second predetermined constraint requires that there is only one significant heat source target in the candidate heat source region, such as a vehicle or a pedestrian.

[0031] If the candidate heat source region meets the second predetermined constraint, the candidate heat source region is analyzed according to the type determination scheme in the heat source identification plan. Specifically, first, the shape of the candidate heat source region is identified according to the predetermined type identification scheme, and the shape features of the region are extracted to obtain a shape identification result. Then, the region is filtered by size according to the type scheme, and regions that do not meet the size requirement are excluded to obtain a size filtering result. Finally, the shape identification result and the size filtering result are analyzed together, and the real-time heat source target is determined through the comprehensive judgment of the two results.

[0032] Further, the method provided by the application embodiment further comprises:

[0033] According to the type determination scheme, the shape of the candidate heat source region is identified to obtain an identification result; according to the type determination scheme, the candidate heat source region is filtered by size to obtain a filtering result; and the real-time heat source target is determined in cooperation with the identification result and the filtering result.

[0034] In the application embodiment, first, the shape of the candidate heat source region is identified according to the type determination scheme. In this process, edge detection (such as Canny edge detection) method is used to extract the edge information of the candidate heat source region, and the object is identified by analyzing the contour shape of the region. For example, when the heat source region presents a rectangular or rectangular contour, it is considered that the region may be a vehicle. When the heat source region presents a circular or more irregular shape, it is considered that the region may be a pedestrian or other object. Through this process, an identification result is obtained.

[0035] Next, the candidate heat source region is size filtered according to a type determination scheme. The type determination scheme is a preset scheme. Size filtering is a process of screening the candidate heat source region based on a preset heat source target size range. For example, the size of a standard small vehicle is set to 4m x 2m in the type determination scheme, and the size range of a pedestrian is 0.5m x 0.5m x 1.8m. According to the actual size of the candidate heat source region, it is determined whether it meets the size standard. If the size of the candidate region exceeds the set range (for example, a rectangular region greater than 4m x 2m), it is considered that the region does not meet the heat source target, and it is excluded. If the size of the candidate region meets the predetermined range, the region is retained, and a size filtering result is obtained. The filtering result determines which regions meet the size requirements of the effective heat source target, and excludes regions that do not meet the size conditions.

[0036] Then, the real-time heat source target is determined in combination with the recognition result and the filtering result. In this step, the shape recognition result and the size filtering result are combined to comprehensively determine whether the candidate heat source region is an actual heat source target. Specifically, fusion analysis is performed according to the output results of shape recognition and size filtering. For example, if the shape recognition indicates that the candidate region meets the rectangular shape of a vehicle, and the size filtering result also indicates that the size of the region is suitable for a small vehicle (for example, 4m x 2m), it is determined that the candidate region is a vehicle as a real-time heat source target; if the shape of the region meets the characteristics of a pedestrian, and the size filtering result is also within the range of a pedestrian (for example, 0.5m x 0.5m x 1.8m), it is confirmed that the region is a pedestrian heat source target. Through this step, the real-time heat source target is finally obtained, which can be a vehicle or a pedestrian.

[0037] Further, in the method provided by the application embodiment, after it is determined that the candidate heat source region does not meet the second predetermined constraint, the method further includes:

[0038] If it does not meet, the candidate heat source region is segmented to obtain a segmentation result, and a first region block in the segmentation result is extracted; the first region block is analyzed according to the type determination scheme to obtain a first heat source target; and the real-time heat source target is established based on the first heat source target.

[0039] In the application embodiment, if the candidate heat source region does not meet the second predetermined constraint, it is considered that the region contains multiple heat source targets, and the candidate heat source region is segmented to obtain a segmentation result. Specifically, the edges of the candidate heat source region are extracted using Canny edge detection to ensure the accuracy of the region contour. Then, the K-means clustering algorithm is used to segment the extracted region, and the candidate heat source region is segmented into multiple sub-regions, each of which represents an independent potential heat source target. Through this process, the segmentation result is obtained.

[0040] Next, a first region block is randomly extracted from the segmentation results. The first region block is a sub-region randomly selected from the plurality of segmentation regions and is a region containing a heat source target.

[0041] Subsequently, the first region block is analyzed according to a type determination scheme to obtain a first heat source target. In this step, shape recognition and size filtering are performed on the first region block according to a preset target type recognition scheme. Through shape recognition, it is determined whether the region conforms to the shape characteristics of a vehicle, a pedestrian, or the like. Through size filtering, it is confirmed whether the size of the region conforms to a predetermined heat source target range (such as 4 m x 2 m for a small vehicle or 0.5 m x 0.5 m x 1.8 m for a pedestrian). Once the analysis is confirmed, the region block is identified as a valid heat source target, i.e., the first heat source target.

[0042] Finally, based on the obtained first heat source target, a real-time heat source target is established by traversing all segmentation results. In this process, the same analysis process is performed on each sub-region in the segmentation results to identify and confirm each heat source target one by one. By traversing all segmentation results, all heat source targets are summarized to establish a real-time heat source target. The real-time heat source target contains multiple heat sources.

[0043] Step S300: determining whether the real-time heat source target conforms to a first predetermined constraint.

[0044] In the embodiments of the present application, the real-time heat source target and the first predetermined constraint are compared. The first predetermined constraint specifically refers to only one heat source target, i.e., the real-time heat source target is only a pedestrian or only a vehicle. When the real-time heat source target is only a pedestrian or only a vehicle, it is considered that the real-time heat source target conforms to the first predetermined constraint.

[0045] Step S400: if yes, obtaining a predetermined turning strategy corresponding to the real-time heat source target.

[0046] In the embodiments of the present application, when the real-time heat source target conforms to the first predetermined constraint, a predetermined turning strategy is obtained. The predetermined turning strategy includes a turning strategy corresponding to the real-time heat source target being a pedestrian or a vehicle.

[0047] Step S500: the predetermined turning strategy is used to perform multi-degree-of-freedom turning control on the target street lamp based on a real-time spatial pose of the target street lamp.

[0048] In the embodiments of the present application, the predetermined turning strategy is used to perform multi-degree-of-freedom turning control on the target street lamp based on a real-time spatial pose of the target street lamp. When the real-time heat source target is a vehicle, a predetermined spatial pose in the predetermined turning strategy is extracted and analyzed in coordination with the real-time spatial pose to generate a first turning control decision. Subsequently, the turning of the target street lamp is adjusted according to the first turning control decision.

[0049] When the real-time heat source target is a pedestrian, first, the real-time position coordinates of the pedestrian are obtained, and a three-dimensional coordinate system is established with the target street lamp as the origin, and the position coordinates of the pedestrian are marked in the coordinate system. Then, the three-dimensional coordinate system is analyzed to determine the target spatial posture of the target street lamp, and a second steering control decision is generated through collaborative analysis with the real-time spatial posture. Finally, the target street lamp is controlled according to the second steering control decision.

[0050] Further, the method provided by the application embodiment further comprises:

[0051] When the real-time heat source target is a vehicle, the predetermined spatial posture in the predetermined steering strategy is extracted; the real-time spatial posture and the predetermined spatial posture are collaboratively analyzed to obtain a first steering control decision; and the target street lamp is controlled according to the first steering control decision; wherein the predetermined spatial posture comprises a predetermined pitch angle and a predetermined horizontal rotation angle, wherein the predetermined pitch angle refers to the upper limit value of the pitch angle threshold of the target street lamp, and the predetermined horizontal rotation angle refers to the median value of the horizontal rotation angle threshold of the target street lamp.

[0052] In the application embodiment, when the real-time heat source target is a vehicle, the predetermined spatial posture in the predetermined steering strategy is extracted. The predetermined spatial posture comprises a predetermined pitch angle and a predetermined horizontal rotation angle. Specifically, the predetermined pitch angle refers to the upper limit value of the adjustable pitch angle of the target street lamp, i.e., the maximum up-down angle that the street lamp can adjust. To cope with the situation where the vehicle travels at a high speed, the predetermined pitch angle is set to the maximum value (for example, set to +90°), so as to ensure that the street lamp can provide the maximum range of illumination and cover a larger area. At the same time, the predetermined horizontal rotation angle refers to the rotation range of the street lamp in the horizontal plane, which is usually set to a median value, for example, ±30°. This means that the street lamp can rotate in the left and right directions to ensure that its illumination area covers the central position of the target road surface. When the vehicle travels, the horizontal rotation angle of the street lamp will be dynamically adjusted according to the travel trajectory of the vehicle to ensure that the vehicle is always within the illumination range.

[0053] Next, the real-time spatial pose is analyzed in coordination with the predetermined spatial pose. The real-time spatial pose refers to the current actual angle and direction of the target streetlight, which is fed back in real time by sensors such as gyroscopes and accelerometers. Through these sensors, the current pitch angle and horizontal rotation angle of the streetlight are obtained. The coordination analysis is achieved by comparing the real-time spatial pose with the predetermined spatial pose to determine whether the streetlight needs to adjust its angle. If there is a gap between the real-time pitch angle and the predetermined pitch angle, the angle that needs to be adjusted is calculated and a control command is issued. If there is a difference between the real-time horizontal rotation angle and the predetermined horizontal rotation angle, the horizontal rotation angle of the streetlight is adjusted. Through this analysis, the first steering control decision is obtained, that is, the specific angle that the streetlight needs to adjust.

[0054] After obtaining the first steering control decision, multi-degree-of-freedom steering control is performed on the target streetlight according to the decision. Multi-degree-of-freedom steering control refers to the independent adjustment of the streetlight in multiple directions, usually including pitch angle (up and down adjustment), yaw angle (left and right rotation), and roll angle (rotation around an axis). By controlling the servo motor system, the pitch angle and horizontal rotation angle of the streetlight are adjusted to face the driving direction of the vehicle, thereby providing accurate lighting. Finally, the dynamic adjustment of the streetlight is completed according to the first steering control decision, and it is ensured that the illumination area always follows the direction of the vehicle's travel.

[0055] Further, the method provided by the application embodiment further comprises:

[0056] When the real-time heat source target is a pedestrian, the real-time position coordinates of the pedestrian are obtained; a three-dimensional coordinate system is established with the target streetlight as the origin, and the real-time position coordinates are marked to the three-dimensional coordinate system; the target spatial pose of the target streetlight is determined by analyzing the three-dimensional coordinate system; the real-time spatial pose and the target spatial pose are analyzed in coordination to obtain a second steering control decision; and multi-degree-of-freedom steering control of the target streetlight is performed according to the second steering control decision.

[0057] In the application embodiment, when the real-time heat source target is a pedestrian, the real-time position coordinates of the pedestrian are first obtained. This process is achieved through infrared sensors or video monitoring systems. In this step, video analysis is performed through a camera, and image processing techniques such as background subtraction and foreground detection are used to extract the position of the pedestrian. By calculating the depth map or using stereo vision, the coordinates of the pedestrian in three-dimensional space are obtained, for example, assuming that the real-time coordinates of the pedestrian are (5, 3, 0), which means that the pedestrian is located 5 meters in front of the streetlight, deviating from the center of the streetlight by 3 meters, and parallel to the ground.

[0058] Next, a three-dimensional coordinate system is established with the target streetlight as the origin, and the real-time position coordinates of the pedestrian are marked in this coordinate system. The coordinates of the target streetlight are the origin (0, 0, 0) of the three-dimensional coordinate system, and then the pedestrian coordinates (5, 3, 0) are mapped into this coordinate system. In the three-dimensional coordinate system, the X-axis represents the horizontal position, the Y-axis represents the depth (front-back direction), and the Z-axis is the vertical height. At this time, the pedestrian coordinates (5, 3, 0) mean that the pedestrian is located 5 meters away from the streetlight in the X-axis direction, 3 meters away from the streetlight in the Y-axis direction, and no vertical deviation in the Z-axis.

[0059] Next, the target space posture of the target streetlight is determined by analyzing the three-dimensional coordinate system. The target space posture refers to the best illumination angle that the streetlight should adjust to, to ensure that its illumination direction accurately points to the pedestrian. Through trigonometric calculation, the distance between the pedestrian and the streetlight is calculated by the Pythagorean theorem. Then the pitch angle (up-down angle) and horizontal rotation angle (left-right rotation angle) of the streetlight are calculated. Assuming that the coordinates of the pedestrian are (5, 3, 0), the pitch angle (θ) of the target space posture of the target streetlight can be calculated by the arctangent function (arctan), 0.96°. This indicates that the target streetlight needs to adjust the pitch angle to about 30.96° to ensure that it illuminates the pedestrian's position. The calculation of the horizontal rotation angle is determined according to the relative position of the pedestrian and the streetlight in the horizontal plane. Assuming that the streetlight is facing north and the pedestrian is located in the east direction of the streetlight, the horizontal rotation angle is 0°. If the pedestrian deviates from the east side, the horizontal angle is calculated using the arctangent to ensure that the illumination area is adjusted to the pedestrian's position.

[0060] Next, the real-time space posture and the target space posture are analyzed in coordination. The real-time space posture represents the current actual angle of the target streetlight, which is obtained through sensors such as gyroscopes and accelerometers. If the real-time pitch angle of the target streetlight is 10° and the predetermined pitch angle of the target space posture is 30.96°, the streetlight is adjusted by an increment of 20.96°. Similarly, if the real-time horizontal rotation angle is 10° and the horizontal rotation angle of the target space posture is 0°, adjust it by 10° to align it with the pedestrian's position. Through this coordinated analysis, the required adjustment angle is calculated, and the second steering control decision is obtained, which is to increase the pitch angle of the streetlight by 20.96° and the horizontal rotation angle by 10°.

[0061] Finally, multi-degree-of-freedom steering control of the target streetlight is performed according to the second steering control decision. Multi-degree-of-freedom steering control means that the streetlight not only adjusts a single angle, but also independently controls the pitch angle and horizontal rotation angle through a servo motor or a stepper motor. Through precise control of the motor, the pitch angle of the streetlight is adjusted to 30.96°, and the streetlight is adjusted according to the calculated horizontal rotation angle to ensure that its illumination area always covers the position of the pedestrian. For example, a servo motor is used to adjust the pitch angle of the streetlight, while the horizontal rotation angle is controlled to ensure that the streetlight can be flexibly adjusted when the pedestrian moves, ensuring that the lighting accurately follows the pedestrian.

[0062] Further, the method provided by the application embodiment further comprises, after the multi-degree-of-freedom steering control of the target streetlight according to the second steering control decision:

[0063] collecting motion features of the pedestrian, wherein the motion features include a walking direction and a walking speed; extracting a horizontal rotation angle in the second steering control decision; and dynamically controlling the horizontal rotation angle according to the walking direction and the walking speed.

[0064] In the application embodiment, the motion features of the pedestrian are first collected, including the walking direction and the walking speed. At this time, the motion information of the pedestrian is obtained through video monitoring or infrared sensors. For example, the video monitoring system detects the position of the pedestrian through the optical flow method or the background subtraction method, and calculates the walking direction of the pedestrian, i.e., the angle of the pedestrian movement, by using consecutive image frames. The walking speed is obtained by calculating the relationship between the displacement of the pedestrian and the time between each frame. For example, if the pedestrian moves from coordinate (5, 3) to coordinate (6, 3) in 1 second, the walking speed of the pedestrian is 1 meter / second.

[0065] Next, the horizontal rotation angle in the second steering control decision is extracted. The horizontal rotation angle refers to the horizontal rotation angle of the target streetlight, which determines the adjustment of the illumination direction of the streetlight. Based on the previous analysis, the horizontal rotation angle that the current target streetlight should adjust is extracted from the steering control decision. This angle reflects how the streetlight should adjust its illumination direction in the horizontal plane in order to aim at the pedestrian or its expected position.

[0066] Then the horizontal rotation angle is dynamically controlled according to the walking direction and the walking speed. The dynamic control target here is to achieve follow-up lighting, that is, to adjust the illumination direction of the street lamp in real time according to the motion characteristics of the pedestrian. First, the path that the pedestrian will go to is predicted according to the walking direction, and the possible direction of the pedestrian at the next moment is calculated. For example, if the pedestrian starts to walk to the right, it is predicted that he will continue to walk to the right, and the horizontal rotation angle of the street lamp is adjusted in advance. Then, the walking speed is combined to decide the speed of adjusting the street lamp. If the pedestrian walks fast, the adjustment frequency of the street lamp rotation is increased to ensure fast tracking; if the pedestrian walks slowly, the adjustment frequency of the street lamp will be reduced to avoid unnecessary over-adjustment. In this way, the illumination angle of the street lamp is dynamically adjusted with the change of the position of the pedestrian, and always remains in the best illumination range.

[0067] Further, the method provided by the application embodiment further comprises the following steps after judging whether the real-time heat source target meets the first predetermined constraint:

[0068] If not, the multi-degree-of-freedom steering control of the target street lamp is performed according to the first steering control decision.

[0069] In the application embodiment, when the real-time heat source target does not meet the first predetermined constraint, that is, when there are multiple heat source targets such as vehicles and pedestrians, the lighting demand of the vehicle is given priority, and the multi-degree-of-freedom steering control of the target street lamp is performed according to the first steering control decision. Specifically, first, the predetermined spatial posture in the predetermined steering strategy is extracted, including the predetermined pitch angle and the predetermined horizontal rotation angle, and the real-time spatial posture is analyzed in coordination with the predetermined spatial posture to obtain the adjustment angle decision. In this process, the pitch angle and the horizontal rotation angle are adjusted to ensure that the street lamp can quickly adjust its illumination direction to ensure that the vehicle is always within the illumination range of the street lamp, and the multi-degree-of-freedom steering control of the target street lamp is completed.

[0070] In the application embodiment, as described above, the application embodiment has at least the following technical effects:

[0071] The application obtains the thermal imaging data of the target road surface through a thermal imager, wherein the target road surface refers to all road surface areas that can be irradiated and covered by the target street lamp; a heat source identification plan is called to process and analyze the thermal imaging data to obtain a real-time heat source target; it is judged whether the real-time heat source target meets a first predetermined constraint; if yes, a predetermined turning strategy corresponding to the real-time heat source target is obtained; the predetermined turning strategy is based on the real-time spatial posture of the target street lamp to perform multi-degree-of-freedom turning control on the target street lamp. The application solves the technical problem that the street lamp in the prior art cannot dynamically adjust the illumination direction and coverage range according to the environmental changes, resulting in the inability to flexibly adapt to the road surface conditions. The application realizes the technical effects of improving the street lamp lighting efficiency, improving the adaptability and intelligent control level of the street lamp in different traffic environments by combining the thermal imaging data to identify the heat source target in real time and adjusting the turning of the street lamp based on the position and spatial posture of the target heat source.

[0072] In the embodiment two, based on the same inventive concept as the multi-degree-of-freedom street lamp turning method based on thermal imaging positioning in the foregoing embodiments, as shown in the embodiment two, the application provides a multi-degree-of-freedom street lamp turning system based on thermal imaging positioning. The system and method embodiments in the application embodiment are based on the same inventive concept. The system comprises: Figure 2

[0073] The thermal imaging acquisition module 11 is configured to acquire thermal imaging data of a target road surface through a thermal imager, wherein the target road surface refers to all road surface areas that can be irradiated and covered by the target street lamp; the processing and analyzing module 12 is configured to call a heat source identification plan to process and analyze the thermal imaging data to obtain a real-time heat source target; the judging module 13 is configured to judge whether the real-time heat source target meets a first predetermined constraint; the strategy obtaining module 14 is configured to obtain a predetermined turning strategy corresponding to the real-time heat source target if the real-time heat source target meets the first predetermined constraint; and the turning control module 15 is configured to perform multi-degree-of-freedom turning control on the target street lamp based on the real-time spatial posture of the target street lamp according to the predetermined turning strategy.

[0074] Further, the system is further configured to implement the following functions:

[0075] A temperature threshold is set according to a real-time environmental temperature; the thermal imaging data is extracted with the temperature threshold as a constraint to obtain a candidate heat source area; it is judged whether the candidate heat source area meets a second predetermined constraint; if yes, the candidate heat source area is analyzed according to a type determination scheme in the heat source identification plan to determine the real-time heat source target.

[0076] Further, the system is further configured to implement the following functions:

[0077] ​According to the type determination scheme, the candidate heat source area is subjected to shape recognition to obtain a recognition result; according to the type determination scheme, the candidate heat source area is subjected to size filtering to obtain a filtering result; and the real-time heat source target is determined in cooperation with the recognition result and the filtering result.

[0078] Further, the system is further used to implement the following functions:

[0079] If the condition is not met, the candidate heat source area is segmented to obtain a segmentation result, and a first region block in the segmentation result is extracted; the first region block is analyzed according to the type determination scheme to obtain a first heat source target; and the real-time heat source target is established based on the first heat source target.

[0080] Further, the system is further used to implement the following functions:

[0081] When the real-time heat source target is a vehicle, a predetermined spatial posture in the predetermined steering strategy is extracted; the real-time spatial posture and the predetermined spatial posture are analyzed in cooperation to obtain a first steering control decision; and the multi-degree-of-freedom steering control of the target street lamp is performed according to the first steering control decision; wherein the predetermined spatial posture includes a predetermined pitch angle and a predetermined horizontal rotation angle, wherein the predetermined pitch angle is an upper limit value of a pitch angle threshold of the target street lamp, and the predetermined horizontal rotation angle is a median value of a horizontal rotation angle threshold of the target street lamp.

[0082] Further, the system is further used to implement the following functions:

[0083] When the real-time heat source target is a pedestrian, a real-time position coordinate of the pedestrian is obtained; a three-dimensional coordinate system is established with the target street lamp as the origin, and the real-time position coordinate is marked to the three-dimensional coordinate system; the target spatial posture of the target street lamp is analyzed based on the three-dimensional coordinate system; the real-time spatial posture and the target spatial posture are analyzed in cooperation to obtain a second steering control decision; and the multi-degree-of-freedom steering control of the target street lamp is performed according to the second steering control decision.

[0084] Further, the system is further used to implement the following functions:

[0085] The motion characteristics of the pedestrian are collected, wherein the motion characteristics include a walking direction and a walking speed; a horizontal rotation angle in the second steering control decision is extracted; and the horizontal rotation angle is dynamically controlled based on the walking direction and the walking speed.

[0086] Further, the system is further used to implement the following functions:

[0087] If the condition is not met, the multi-degree-of-freedom steering control of the target street lamp is performed according to the first steering control decision.

[0088] In the third embodiment, based on the inventive concept of the multi-degree-of-freedom street lamp steering method based on thermal imaging positioning in the foregoing embodiments, the application further provides an electronic device, comprising: at least one processor; a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of any one of the method in the first embodiment.

[0089] It should be noted that the above-mentioned sequence of the embodiments of the application is only for description, not representing the advantages and disadvantages of the embodiments. And the above-mentioned description is for the specific embodiments of the present application. The processes depicted in the drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0090] The above only describes the preferred embodiments of the application and does not limit the application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application shall be included in the protection scope of the application.

[0091] The specification and drawings are merely exemplary of the application, and any and all modifications, variations, combinations or equivalents that are within the scope of the application should be considered. Obviously, those skilled in the art can make various modifications and variations to the application without departing from the scope of the application. Thus, if these modifications and variations of the application belong to the scope of the application and its equivalents, the application is intended to include these modifications and variations.

Claims

1. A multi-degree of freedom street light steering method based on thermographic positioning, characterized in that, The method comprises the steps of: acquiring thermal imaging data of a target road surface by a thermal imager, wherein the target road surface refers to all road surface areas that can be irradiated by a target street lamp; processing and analyzing the thermal imaging data by calling a heat source identification plan to obtain a real-time heat source target; determining whether the real-time heat source target meets a first predetermined constraint; if yes, obtaining a predetermined turning strategy corresponding to the real-time heat source target; the predetermined turning strategy is based on a real-time spatial pose of the target street lamp to perform multi-degree-of-freedom turning control on the target street lamp.

2. The multi-degree of freedom street light steering method based on thermal imaging positioning according to claim 1, characterized in that, processing and analyzing the thermal imaging data by calling a heat source identification plan to obtain a real-time heat source target, comprising: setting a temperature threshold according to a real-time environmental temperature; extracting the thermal imaging data with the temperature threshold as a constraint to obtain a candidate heat source area; determining whether the candidate heat source area meets a second predetermined constraint; if yes, analyzing the candidate heat source area according to a type determination scheme in the heat source identification plan to determine the real-time heat source target.

3. The multi-degree of freedom street light steering method based on thermal imaging positioning according to claim 2, characterized in that, analyzing the candidate heat source area according to a type determination scheme in the heat source identification plan to determine the real-time heat source target, comprising: performing shape recognition on the candidate heat source area according to the type determination scheme to obtain an identification result; performing size filtering on the candidate heat source area according to the type determination scheme to obtain a filtering result; determining the real-time heat source target in cooperation with the identification result and the filtering result.

4. The multi-degree of freedom street light steering method based on thermal imaging positioning according to claim 2, characterized in that, after determining whether the candidate heat source area meets a second predetermined constraint, further comprising: if no, segmenting the candidate heat source area to obtain a segmentation result, and extracting a first area block in the segmentation result; analyzing the first area block according to the type determination scheme to obtain a first heat source target; based on the first heat source target, the real-time heat source target is established.

5. The multi-degree of freedom street light steering method based on thermal imaging positioning according to claim 1, characterized in that, the predetermined turning strategy is based on a real-time spatial pose of the target street lamp to perform multi-degree-of-freedom turning control on the target street lamp, comprising: when the real-time heat source target is a vehicle, extracting a predetermined spatial pose in the predetermined turning strategy; performing cooperative analysis on the real-time spatial pose and the predetermined spatial pose to obtain a first turning control decision; performing multi-degree-of-freedom turning control of the target street lamp according to the first turning control decision wherein the predetermined spatial pose includes a predetermined pitch angle and a predetermined horizontal rotation angle, wherein the predetermined pitch angle is an upper limit value of a pitch angle threshold of the target street lamp, and the predetermined horizontal rotation angle is a median value of a horizontal rotation angle threshold of the target street lamp.

6. The multi-degree of freedom street light steering method based on thermal imaging positioning according to claim 1, characterized in that, the predetermined turning strategy is based on a real-time spatial pose of the target street lamp to perform multi-degree-of-freedom turning control on the target street lamp, further comprising: when the real-time heat source target is a pedestrian, obtaining a real-time position coordinate of the pedestrian; establishing a three-dimensional coordinate system with the target street lamp as the origin, and marking the real-time position coordinate to the three-dimensional coordinate system; analyzing the three-dimensional coordinate system to determine a target spatial pose of the target street lamp; performing cooperative analysis on the real-time spatial pose and the target spatial pose to obtain a second turning control decision; performing multi-degree-of-freedom steering control of the target street lamp according to the second steering control decision.

7. The multi-degree of freedom street light steering method based on thermal imaging positioning according to claim 6, characterized in that, after performing multi-degree-of-freedom steering control of the target street lamp according to the second steering control decision, further comprising: collecting motion features of the pedestrian, wherein the motion features include a walking direction and a walking speed; extracting a horizontal rotation angle in the second steering control decision; dynamically controlling the horizontal rotation angle according to the walking direction and the walking speed.

8. The multi-degree of freedom street light steering method based on thermal imaging positioning according to claim 5, characterized in that, after judging whether the real-time heat source target meets the first predetermined constraint, further comprising: if not, performing multi-degree-of-freedom steering control of the target street lamp according to the first steering control decision.

9. A multi-degree of freedom street light turning system based on thermographic positioning, characterized in that, The system is used to perform the multi-degree-of-freedom street lamp steering method based on heat imaging positioning according to any one of claims 1-8, and the system comprises: a heat imaging collection module, configured to collect heat imaging data of a target road surface by a thermal imager, wherein the target road surface refers to all road surface areas that can be irradiated by a target street lamp; a processing and analysis module, configured to process and analyze the heat imaging data by using a heat source identification plan to obtain a real-time heat source target; a judgment module, configured to judge whether the real-time heat source target meets a first predetermined constraint; a strategy acquisition module, configured to acquire a predetermined steering strategy corresponding to the real-time heat source target if the real-time heat source target meets the first predetermined constraint; a steering control module, configured to perform multi-degree-of-freedom steering control of the target street lamp based on a real-time spatial posture of the target street lamp according to the predetermined steering strategy.

10. An electronic device, comprising: The electronic device comprises: a memory, configured to store executable instructions; a processor, configured to execute the executable instructions stored in the memory to implement the multi-degree-of-freedom street lamp steering method based on heat imaging positioning according to any one of claims 1-8.

Images