ADB vehicle lamp double-area cooperative control method and system based on Internet of Vehicles

Abstract

The invention discloses an ADB vehicle lamp double-area cooperative control method and system based on the Internet of Vehicles, and relates to the technical field of intelligent networked vehicle self-adaptive light cooperative control, and the method comprises the steps: building an Internet of Vehicles information fusion mechanism, fusing the obtained vehicle information with the data collected by A vehicle equipment, forming an environment perception data set, and carrying out the recognition of the environment perception data set; dividing a road on the basis of an environment perception data set formed after fusion, secondarily obtaining real-time state information of the vehicle A and vehicles except the vehicle A on the basis of an illumination control rule algorithm and an illumination control rule algorithm on the basis of the illumination control rule, judging the divided areas of the road, and completing ADB vehicle lamp double-area cooperative control. According to the method, the sensing range is effectively expanded, the adaptability in a complex traffic scene is enhanced, the system response speed and the calculation efficiency are improved, linkage adjustment of lighting strategies of the vehicle and other vehicles is achieved, the night driving safety and comfort are improved, and the method has good application prospects and popularization value.

Description

Technical Field

[0001] The present invention relates to the technical field of adaptive lighting collaborative control of intelligent connected vehicles, and in particular to a method and system for dual-zone collaborative control of ADB headlights based on the Internet of Vehicles. Background Art

[0002] At present, with the rapid development of intelligent connected vehicle technology, the safety and intelligence level of vehicles are constantly improving. As an important part of improving nighttime driving safety, the intelligent lighting system is evolving towards self-adaptation and intelligence. The national and industry levels are also actively promoting the construction of relevant standard systems for intelligent connected vehicles, and encouraging the development of vehicle-road collaboration and multi-vehicle collaborative control technology to build a safer and more efficient traffic environment.

[0003] However, the existing ADB system mainly relies on single-vehicle sensors for environmental perception. Due to the limitations of the detection distance and angle of cameras and radars, its perception range is usually concentrated in a limited area in front of the vehicle, making it difficult to effectively obtain real-time status information of multiple vehicles in front, vehicles far away on the curve, or vehicles crossing from the side. In complex traffic scenarios, such as high-speed intersections at night, multi-lane parallel driving, or tunnel exits, this perception limitation can easily lead to inaccurate division of the headlight control area, resulting in problems such as high beams mistakenly illuminating oncoming vehicles or failure to enhance the lighting area in time, posing a safety hazard. In addition, the lack of an information sharing mechanism between vehicles also makes the lighting control of each vehicle independent of each other, unable to form collaborative optimization, further exacerbating the existence of control blind spots. That is, the detection range of a single vehicle's sensor is limited, and it is unable to obtain the real-time status of the vehicle in front or adjacent, resulting in blind spots in headlight control. Summary of the Invention

[0004] In view of the problems existing in the existing ADB headlight dual-zone collaborative control method and system based on the Internet of Vehicles, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that the detection range of the sensor of a single vehicle is limited, and it is unable to obtain the real-time status of the vehicle in front or adjacent, as well as the division of the road, resulting in blind spots in the control of the headlights.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a dual-zone coordinated control method for ADB headlights based on an Internet of Vehicles (IoV). The method includes establishing an IoV information fusion mechanism to obtain information about vehicles outside the detection range of vehicle A, and fusing the obtained vehicle information with data collected by equipment on vehicle A to form an environmental perception dataset. Vehicle A refers to the vehicle itself.

[0008] Based on the fused environmental perception data set, the road is divided and a differentiated lighting control strategy is implemented based on the divided areas. The differentiated lighting control strategy refers to the lighting control rules corresponding to the set ADB (Adaptive Bus Lighting). The ADB refers to adaptive bus lighting.

[0009] Based on the lighting control rules and the divided areas of the road, they work together in the on-board control unit to calculate and obtain the lighting control rule algorithm for vehicle A. Based on the lighting control rule algorithm, the real-time status information of vehicle A and vehicles other than vehicle A is obtained again, the road division areas are determined, and the dual-zone coordinated control of ADB headlights is completed.

[0010] As a preferred solution of the ADB headlight dual-zone coordinated control method based on the Internet of Vehicles of the present invention, wherein: the establishment of the Internet of Vehicles information fusion mechanism includes deploying a communication coordination node of the Internet of Vehicles, the communication coordination node includes integrating a dual-channel communication mechanism in the communication module of vehicle A, and the integrated dual-channel communication mechanism includes receiving information about surrounding vehicles and obtaining the surrounding traffic situation along the road;

[0011] The data collected by the equipment of vehicle A includes setting a sensing sensor array at the end of vehicle A and completing multimodal data collection of vehicle A through the vehicle-mounted control unit;

[0012] The sensor array is used to extract features from the multimodal data of vehicle A, and a lightweight deep neural network is used to identify the extracted features.

[0013] The received surrounding vehicle information and the acquired traffic situation along the road are mapped uniformly with the multimodal data of vehicle A after identification into a shared space, wherein the shared space includes spatial and temporal dimensions;

[0014] By establishing a local coordinate system in the spatial dimension with vehicle A as the origin and a time reference in the temporal dimension, the surrounding vehicle information and the acquired traffic situation along the road are aligned with the multimodal data of vehicle A after identification in the spatial and temporal dimensions to complete data fusion.

[0015] As a preferred solution of the ADB dual-zone coordinated control method for vehicle-to-vehicle (IoV) lights described in the present invention, the lightweight deep neural network includes a lightweight recognition network with dynamic channels to dynamically adjust multimodal data based on data fusion;

[0016] The dynamic adjustment includes introducing an environmental perception feedback module into the lightweight recognition network to receive the operating status of vehicle A;

[0017] According to the dynamic adjustment factor of the multimodal data output by the introduced environmental perception feedback module, the dynamic adjustment factor refers to the channel selection controller introduced into the environmental perception feedback module, which dynamically activates or shuts down the feature channels of each layer to complete the dynamic adjustment of the multimodal data;

[0018] The feature extraction of the multimodal data of vehicle A includes assigning priority weights to the multimodal data in a dynamic adjustment stage, and the weights are adaptively adjusted according to the current driving scene of vehicle A;

[0019] During the feature extraction process, priority weights are used to control the activation or shutdown ratio of feature channels at each layer and calculate the differences in multimodal data;

[0020] Based on the differences in multimodal data, a path that matches the current priority weight is dynamically selected, the operating status of vehicle A is identified, and the feedback is fed back to the communication module of vehicle A, so that vehicle A can control the activation or deactivation of each layer of feature channels based on the priority weight;

[0021] When the priority weight control feature channels of each layer are activated, the adaptive adjustment of the driving scene of vehicle A is started; otherwise, when the priority weight control feature channels of each layer are closed, the adaptive adjustment of the driving scene of vehicle A is closed.

[0022] As a preferred solution of the ADB dual-zone coordinated control method for vehicle-to-vehicle (IoV) lights according to the present invention, the formula for calculating the difference in multimodal data is:

[0023] in, Indicates modality The proportion of channels activated or closed that should be allocated in this layer, Indicates the The real-time priority weight of the modalities, represents the total number of modes of multimodal data, Indicates the The priority weight of the modal, Indicates the index number of the modal;

[0024] The environmental perception dataset includes generating perception feature dimensions of vehicle A based on the differences in multimodal data, and constructing a spatiotemporal alignment coordinate framework with vehicle A as the origin. The spatiotemporal alignment coordinate framework refers to establishing a local coordinate system of spatial dimensions with vehicle A as the origin and a time reference of the time dimension;

[0025] Use the local coordinate system with car A as the origin , the time benchmark of the time dimension , calculate and obtain the local perception data set, the specific formula is:

[0026] in, Indicates the The spatial coordinates of the perceived target, represents the feature vector, Indicates the timestamp of local perception data, Represents a collection of local sensing data;

[0027] The remote information obtained with vehicle A as the origin is uniformly mapped to form a remote environment perception data set. The formula of the remote environment perception data set is:

[0028] in, represents a remote environment perception data set, Indicates the The spatial position coordinate vector of the perception target, Indicates the The feature vector of the perceived target, timestamp indicating remote sensing information;

[0029] Local perception data collection and remote environmental perception data collection Processing is performed to construct a set of nodes as perception targets and edges as spatial relationships, and the fused environment perception dataset is output;

[0030] The formula for constructing a set where nodes are perception targets and edges are spatial relationships is:

[0031] in, represents the perception target, and the edges are the set of spatial relations. Represents a collection of nodes, represents an edge set;

[0032] The formula of the environmental perception dataset is:

[0033] in, Indicates the The fusion environment feature vector of each target, Represents a node, Indicates the The timestamp of the edge, Represents the environment perception dataset.

[0034] As a preferred solution of the ADB headlight dual-zone collaborative control method based on the Internet of Vehicles of the present invention, wherein: the road division includes logical area division of the environmental perception data set, and the logical area division includes semantic clustering analysis of the fusion environment feature vector of each target in the environmental perception data set, and dividing it into several semantic categories, combining the node Mapped to the corresponding fan-ring grid;

[0035] The area types of the fan-ring grid include main lighting area, avoidance area, transition area and blind spot prediction area;

[0036] The setting of lighting control rules corresponding to ADB includes prioritizing a number of semantic categories and generating a control mechanism that matches the ADB headlight executable instruction set in combination with the area type;

[0037] The control mechanism includes the following steps:

[0038] For the main lighting area, a high-brightness full coverage strategy is adopted, and the high-beam main beam module of the ADB light is enabled;

[0039] For the avoidance zone, a local mask is dynamically generated based on the relative position and motion state of the perceived target in the zone, and the LED pixel units in the corresponding direction are turned off or modulated;

[0040] For the transition zone, a brightness gradient control strategy is adopted to gradually adjust the light intensity distribution through a time sliding window mechanism;

[0041] For blind spot prediction areas, a low-intensity pre-scanning strategy is activated in advance based on communication delay and target motion prediction.

[0042] As a preferred embodiment of the ADB headlight dual-zone coordinated control method based on the Internet of Vehicles of the present invention, the coordinated operation in the vehicle control unit includes deploying a regional control rule mapping table in the vehicle control unit to map the main lighting zone, avoidance zone, transition zone, and blind spot prediction zone to corresponding ADB headlight control instruction parameters, including a light intensity coefficient, an obscuration mask generation function, a beam deflection angle function, and a pre-scanning light activation condition;

[0043] Use the vehicle control unit to perceive the current environment dataset After analysis, combined with the divided road area types and the control rule mapping table, the ADB headlight control instruction set for the current frame is calculated as follows:

[0044] in, Represents the initial control instruction set, Represents a single control instruction.

[0045] As a preferred embodiment of the ADB dual-zone coordinated control method for vehicle-to-vehicle lighting based on the Internet of Vehicles (IoV) of the present invention, determining the road division area includes sending a coordinated control request to surrounding vehicles via vehicle A communication based on an ADB lighting control instruction set, receiving their current ADB lighting control status information, spatially mapping the received external vehicle control information with the vehicle's zone division result, and performing a logical consistency check to identify whether there is a zone division conflict or a conflict between vehicle A and vehicles other than vehicle A.

[0046] During the ADB dual-zone collaborative control of the vehicle network, the conflict between vehicle A and vehicles other than vehicle A and the conflict in area division are judged.

[0047] In a second aspect, an embodiment of the present invention provides an ADB dual-zone collaborative control system for headlights based on the Internet of Vehicles (IoV), comprising: an IoV information fusion mechanism module that establishes an IoV information fusion mechanism, obtains vehicle information outside the detection range of vehicle A, and fuses the obtained vehicle information with data collected by equipment in vehicle A to form an environmental perception dataset, where vehicle A refers to the vehicle itself;

[0048] A road segmentation module divides the road into sections based on the fused environmental perception dataset and implements differentiated lighting control strategies based on the divided sections. The differentiated lighting control strategies refer to lighting control rules corresponding to the ADB (Adaptive Driver Assistance) lighting system (ADB).

[0049] The dual-zone collaborative control module operates collaboratively in the vehicle control unit based on the lighting control rules and the road division areas, calculates and obtains the lighting control rule algorithm for vehicle A, obtains the real-time status information of vehicle A and vehicles other than vehicle A based on the lighting control rule algorithm, determines the road division areas, and completes the ADB headlight dual-zone collaborative control.

[0050] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, it implements any step of the above-mentioned ADB headlight dual-zone collaborative control method based on the Internet of Vehicles.

[0051] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, wherein: when the computer program is executed by a processor, any step of the above-mentioned ADB vehicle light dual-zone collaborative control method based on the Internet of Vehicles is implemented.

[0052] The beneficial effects of the present invention are as follows: the present invention realizes multi-source information coordination between the vehicle and surrounding vehicles and road environment by establishing an information fusion mechanism of the Internet of Vehicles, thereby significantly improving the environmental perception capability and control accuracy of the ADB headlight system. Compared with the traditional ADB system that relies on single-vehicle sensors, the present invention effectively expands the perception range and enhances adaptability in complex traffic scenarios. By dynamically dividing road areas and executing differentiated lighting control strategies, combined with multimodal data feature extraction and lightweight neural network processing, the system response speed and computing efficiency are improved. At the same time, based on the collaborative operation mechanism of the on-board control unit, the linkage adjustment of the lighting strategy of the vehicle and other vehicles is realized, which improves the safety and comfort of night driving, and has good application prospects and promotion value. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0054] Figure 1 A flowchart of a method and system for dual-zone collaborative control of ADB headlights based on the Internet of Vehicles, provided in accordance with one embodiment of the present invention.

[0055] Figure 2 A system flow chart of a method and system for controlling dual-zone ADB headlights based on the Internet of Vehicles, provided as an embodiment of the present invention. DETAILED DESCRIPTION

[0056] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0058] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0059] The present invention is described in detail with reference to schematic diagrams. For ease of illustration, cross-sectional views of device structures may be partially enlarged and not to scale when describing embodiments of the present invention. Furthermore, the schematic diagrams are merely illustrative and should not limit the scope of the present invention. Furthermore, in actual production, the three-dimensional dimensions of length, width, and depth should be included.

[0060] In the description of the present invention, it should be noted that the terms "upper, lower, inner, and outer" and other references to orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0061] In this disclosure, unless otherwise specified or limited, the terms "mounted," "connected," and "connected" should be interpreted broadly. For example, they may refer to fixed, removable, or integral connections. They may also refer to mechanical, electrical, or direct connections, indirect connections through an intermediary, or internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in this disclosure.

[0062] Example 1

[0063] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides an ADB dual-zone coordinated control method for vehicle lights based on the Internet of Vehicles, including:

[0064] S1: Establish an information fusion mechanism for the Internet of Vehicles to obtain vehicle information outside the detection range of vehicle A, and fuse the obtained vehicle information with the data collected by vehicle A's equipment to form an environmental perception data set. Vehicle A refers to this vehicle.

[0065] The establishment of an IoV information fusion mechanism includes deploying IoV communication coordination nodes. The communication coordination nodes include integrating a dual-channel communication mechanism into the communication module of vehicle A. The integrated dual-channel communication mechanism includes receiving information from surrounding vehicles and obtaining information about traffic conditions along the road.

[0066] The data collected by the equipment on vehicle A includes a sensor array set up at the end of vehicle A, and the multi-modal data collection of vehicle A is completed through the vehicle control unit;

[0067] The sensor array is used to extract features from the multimodal data of vehicle A, and a lightweight deep neural network is used to identify the extracted features.

[0068] The received surrounding vehicle information and the acquired traffic situation along the road are mapped uniformly with the multimodal data of vehicle A after identification into a shared space. The shared space includes spatial and temporal dimensions.

[0069] By establishing a local coordinate system in the spatial dimension with vehicle A as the origin and a time reference in the temporal dimension, the surrounding vehicle information and the acquired traffic situation along the road are aligned with the multimodal data of vehicle A after identification in the spatial and temporal dimensions to complete data fusion.

[0070] S1.1: Lightweight deep neural network includes a lightweight recognition network with dynamic channels to dynamically adjust multimodal data based on data fusion.

[0071] Dynamic adjustment includes introducing an environmental perception feedback module into the lightweight recognition network to receive the operating status of vehicle A.

[0072] According to the dynamic adjustment factor of the multimodal data output by the introduced environmental perception feedback module, the dynamic adjustment factor refers to the channel selection controller introduced into the environmental perception feedback module, which dynamically activates or closes the feature channels of each layer to complete dynamic adjustment of the multimodal data.

[0073] Feature extraction of the multimodal data of vehicle A includes assigning priority weights to the multimodal data in a dynamic adjustment stage, and the weights are adaptively adjusted according to the current driving scene of vehicle A.

[0074] During the feature extraction process, priority weights are used to control the activation or shutdown ratio of feature channels at each layer and calculate the differences in multimodal data.

[0075] Based on the differences in multimodal data, a path that matches the current priority weight is dynamically selected, the operating status of vehicle A is identified, and the feedback is sent to the communication module of vehicle A, so that vehicle A can control the activation or deactivation of feature channels at each layer based on the priority weight.

[0076] When the priority weight control feature channels of each layer are activated, the adaptive adjustment of the driving scene of vehicle A is started; otherwise, when the priority weight control feature channels of each layer are closed, the adaptive adjustment of the driving scene of vehicle A is closed.

[0077] Furthermore, a dynamic adjustment factor controls the activation or deactivation ratio of feature channels at each layer in the lightweight neural network through a channel selection controller. Specifically, assume that the multimodal data includes four modalities: image, radar, infrared, and lidar. Each modality is assigned a different priority weight in different driving scenarios. For example, in low-light conditions at night, the infrared modality weight is set to 0.5, the image modality weight is reduced to 0.2, and the radar and lidar weights are set to 0.2 and 0.1, respectively. Based on this weight distribution, the channel selection controller activates the corresponding feature channels of each modality proportionally, for example, infrared modality accounts for 50% of the total number of channels, image modality accounts for 20%, radar accounts for 20%, and lidar accounts for 10%. The controller adjusts this ratio in real time based on the current operating state of vehicle A (such as speed, steering angle, and light intensity) to ensure that high-priority modalities receive a higher share of computing resources, achieving dynamic optimization and efficient resource utilization of multimodal data processing. The dynamic adjustment factor for multimodal data is output by the introduced environmental perception feedback module. The dynamic adjustment factor refers to the channel selection controller introduced into the environmental perception feedback module, which dynamically activates or deactivates feature channels at each layer to achieve dynamic adjustment of the multimodal data.

[0078] When the characteristic channels of each layer are closed, the dual-zone collaborative control is closed. When the characteristic channels of each layer are activated, the dual-zone collaborative control is opened.

[0079] The priority weights and feature channel activation ratios of multimodal sensors in different driving scenarios are shown in Table 1 below:

[0080] Table 1 Priority weights and feature channel activation ratios of multimodal sensors in different driving scenarios Sensor modality Night low-light scene weight Image clarity scene weight Radar-dominated scenario weight Night low-light scene channel activation ratio Channel activation ratio in clear image scenes Radar-dominated scenario channel activation ratio Image (camera) 0.2 0.6 0.1 20% 60% 10% radar 0.2 0.1 0.5 20% 10% 50% infrared 0.5 0.2 0.1 50% 20% 10% LiDAR 0.1 0.1 0.3 10% 10% 30%

[0081] Table 1 shows the priority weights of each sensor modality and the corresponding feature channel activation ratio distribution under different driving scenarios, reflecting the resource allocation strategy for dynamic scheduling of multimodal data.

[0082] S1.2: The formula for calculating the difference of multimodal data is:

[0083] in, Indicates modality The proportion of channels activated or closed that should be allocated in this layer, Indicates the The real-time priority weight of the modalities, represents the total number of modes of multimodal data, Indicates the The priority weight of the modalities, Indicates the index number of the modal.

[0084] The environmental perception dataset includes generating the perception feature dimensions of car A based on the differences in multimodal data, and constructing a spatiotemporal alignment coordinate framework with car A as the origin. The spatiotemporal alignment coordinate framework refers to establishing a local coordinate system in the spatial dimension with car A as the origin, and a time reference in the time dimension.

[0085] Use the local coordinate system with car A as the origin , the time benchmark of the time dimension , calculate and obtain the local perception data set, the specific formula is:

[0086] in, Indicates the The spatial coordinates of the perceived target, represents the feature vector, Indicates the timestamp of local perception data, Represents a collection of local sensing data.

[0087] The remote information obtained with vehicle A as the origin is uniformly mapped to form a remote environment perception data set. The formula for the remote environment perception data set is:

[0088] in, represents a remote environment perception data set, Indicates the The spatial position coordinate vector of the perception target, Indicates the The feature vector of the perceived target, Indicates the timestamp of remote sensing information.

[0089] Local perception data collection and remote environmental perception data collection Processing is performed to construct a set with nodes as perception targets and edges as spatial relationships, and the fused environment perception dataset is output.

[0090] The formula for constructing a set where nodes are perception targets and edges are spatial relationships is:

[0091] in, represents the perception target, and the edges are the set of spatial relations. Represents a collection of nodes, Represents a set of edges.

[0092] The formula for the environmental perception dataset is:

[0093] in, Indicates the The fusion environment feature vector of each target, Represents a node, Indicates the The timestamp of the edge, Represents the environment perception dataset.

[0094] S2: Based on the fused environmental perception dataset, the road is divided and differentiated lighting control strategies are implemented based on the divided areas. The differentiated lighting control strategy refers to the lighting control rules corresponding to the set ADB (Adaptive Bus Driver), where ADB stands for Adaptive Lighting.

[0095] Among them, dividing the road includes dividing the environmental perception data set into logical areas, and logical area division includes performing semantic clustering analysis on the fusion environmental feature vector of each target in the environmental perception data set and dividing it into several semantic categories, combining the node Mapped to the corresponding sector ring grid.

[0096] The area types of the fan-ring grid include main lighting area, avoidance area, transition area and blind spot prediction area.

[0097] Setting the lighting control rules corresponding to ADB includes prioritizing several semantic categories and combining the area types to generate a control mechanism that matches the ADB headlight executable instruction set.

[0098] The control mechanism includes the following steps:

[0099] For the main lighting area, a high-brightness full coverage strategy is adopted, and the high-beam main beam module of the ADB light is enabled;

[0100] For the avoidance zone, a local mask is dynamically generated based on the relative position and motion state of the perceived target in the zone, and the LED pixel units in the corresponding direction are turned off or modulated;

[0101] For the transition zone, a brightness gradient control strategy is adopted to gradually adjust the light intensity distribution through a time sliding window mechanism;

[0102] For blind spot prediction areas, a low-intensity pre-scanning strategy is activated in advance based on communication delay and target motion prediction.

[0103] S3: Based on the lighting control rules and the divided road areas, the on-board control unit operates collaboratively to calculate and obtain the lighting control rule algorithm for vehicle A. Based on the lighting control rule algorithm, the real-time status information of vehicle A and vehicles other than vehicle A is obtained again, the road division areas are determined, and the dual-zone coordinated control of ADB headlights is completed.

[0104] Among them, collaborative operation in the on-board control unit includes deploying an area control rule mapping table in the on-board control unit, mapping the main lighting area, avoidance area, transition area and blind spot prediction area with the corresponding ADB headlight control instruction parameters, including light intensity coefficient, occlusion mask generation function, beam deflection angle function and pre-scanning light activation conditions.

[0105] Use the vehicle control unit to perceive the current environment dataset After analysis, combined with the divided road area types and the control rule mapping table, the ADB headlight control instruction set for the current frame is calculated as follows:

[0106] in, Represents the initial control instruction set, Represents a single control instruction.

[0107] S3.1: Determining the road division area includes sending collaborative control requests to surrounding vehicles through vehicle A communication based on the ADB headlight control instruction set, receiving their current ADB lighting control status information, spatially mapping and logically verifying the received external vehicle control information with the area division result of the vehicle itself, and identifying whether there is an area division conflict or a conflict between vehicle A and vehicles other than vehicle A.

[0108] During the ADB dual-zone collaborative control of the vehicle network, the conflict between vehicle A and vehicles other than vehicle A and the conflict in area division are judged.

[0109] In a preferred embodiment, the ADB dual-zone coordinated control system for vehicle lights based on the Internet of Vehicles includes:

[0110] S310: IoV information fusion mechanism module, which establishes an IoV information fusion mechanism to obtain vehicle information outside the detection range of vehicle A and fuses the obtained vehicle information with data collected by vehicle A's equipment to form an environmental perception data set. Vehicle A refers to the vehicle itself.

[0111] S320: A road segmentation module divides the road into areas based on the fused environmental perception dataset and executes a differentiated lighting control strategy based on the divided areas. The differentiated lighting control strategy refers to lighting control rules corresponding to the set ADB (Adaptive Driver Assistance) system (ADB).

[0112] S330: Dual-zone collaborative control module, which operates collaboratively in the vehicle control unit based on the lighting control rules and the road division areas, calculates and obtains the lighting control rule algorithm of vehicle A, obtains the real-time status information of vehicle A and vehicles other than vehicle A based on the lighting control rule algorithm, determines the road division areas, and completes the ADB headlight dual-zone collaborative control.

[0113] The above-mentioned unit modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of the above-mentioned modules.

[0114] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0115] In summary, the present invention establishes an information fusion mechanism for the Internet of Vehicles to achieve multi-source information coordination between the vehicle and surrounding vehicles and the road environment, significantly improving the environmental perception capability and control accuracy of the ADB headlight system. Compared with the traditional ADB system that relies on single-vehicle sensors, the present invention effectively expands the perception range and enhances adaptability in complex traffic scenarios. By dynamically dividing road areas and executing differentiated lighting control strategies, combined with multimodal data feature extraction and lightweight neural network processing, the system response speed and computing efficiency are improved. At the same time, based on the collaborative operation mechanism of the on-board control unit, the coordinated adjustment of the lighting strategies of the vehicle and other vehicles is achieved, thereby improving the safety and comfort of night driving, and has good application prospects and promotion value.

[0116] Example 2

[0117] Reference Figure 1 and Figure 2 , which is the second embodiment of the present invention, provides an ADB headlight dual-zone collaborative control method based on the Internet of Vehicles. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0118] In a nighttime highway driving scenario, Car A (the vehicle itself) travels at 80 km / h on a winding road with low visibility. Car A's lightweight deep neural network integrates environmental perception based on data collected by onboard sensors (camera, millimeter-wave radar, infrared imager, lidar) and status information obtained through vehicle-to-vehicle communication regarding the two vehicles ahead (Cars B and C). (Car B is 120 meters ahead of Car A and traveling at 70 km / h; Car C is an oncoming vehicle, 180 meters away from Car A and traveling at 90 km / h).

[0119] The system sets the modal priority weights based on the current low-light environment at night: infrared 0.5, radar 0.2, image 0.2, and lidar 0.1, activates the corresponding channel ratios (infrared 50%, radar 20%, image 20%, lidar 10%), and completes multimodal feature extraction and recognition. Subsequently, based on the fused environmental perception dataset, the system divides the road ahead into four areas: the main lighting area (car-free area), the avoidance area (towards car C), the transition area (behind car B), and the blind spot prediction area (in front of the curve).

[0120] In terms of control strategy, the system activates a high-brightness high-beam main beam in the main lighting zone, achieving an illumination of 120 lx. A dynamic mask is generated for the avoidance zone, disabling LED pixels in the corresponding direction to prevent glare for the driver of vehicle C. A time sliding window mechanism is used in the transition zone, gradually reducing the light intensity to 60 lx. A low-intensity pre-scan light (30 lx) is pre-activated in the blind spot prediction zone to detect potential risks. Simultaneously, vehicle A receives the ADB control strategies of vehicles B and C via V2V communication. After identifying the direction of vehicle C's avoidance zone, it further optimizes the light shielding area of ​​its own vehicle, completing dual-zone coordinated control. A comparison of the present invention with the prior art is shown in Table 2 below:

[0121] Table 2 Comparison between the present invention and the prior art Comparison Item Existing technology The present invention Advantages Perception Relying only on the vehicle's sensors Integrate Internet of Vehicles information to expand perception range More comprehensive perception and improved environmental understanding Data processing Fixed processing, low efficiency Dynamic channel adjustment to optimize resource allocation according to scenarios Improve processing efficiency and adapt to different driving conditions Regional division Fixed area, not accurate enough Dynamic segmentation based on semantic clustering, more intelligent More precise division to adapt to complex traffic environments Lighting control Single-bike control, easy to interfere Dual-zone coordinated control, supporting multi-mode adjustment Safer, avoid glare, and improve lighting effects Multi-vehicle collaboration No coordination mechanism Support V2V communication coordination to avoid lighting conflicts Realize multi-vehicle lighting linkage to improve overall traffic safety Responsiveness and adaptability Slow response and poor adaptability Lightweight model, fast response, adaptable to various scenarios Faster and more stable, meeting the real-time control needs of complex scenarios

[0122] Table 2 describes the comprehensive optimization in perception, processing, control, and coordination, which enhances the intelligence, safety, and adaptability of the ADB headlight system, surpassing traditional solutions.

[0123] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. The ADB dual-zone coordinated control method for vehicle lights based on the Internet of Vehicles is characterized by: include, Establish an Internet of Vehicles information fusion mechanism to obtain vehicle information outside the detection range of vehicle A, and fuse the obtained vehicle information with the data collected by vehicle A's equipment to form an environmental perception data set. Vehicle A refers to the vehicle itself. Based on the fused environmental perception data set, the road is divided and a differentiated lighting control strategy is implemented based on the divided areas. The differentiated lighting control strategy refers to the lighting control rules corresponding to the set ADB (Adaptive Bus Lighting). The ADB refers to adaptive bus lighting. Based on the lighting control rules and the divided areas of the road, they work together in the on-board control unit to calculate and obtain the lighting control rule algorithm for vehicle A. Based on the lighting control rule algorithm, the real-time status information of vehicle A and vehicles other than vehicle A is obtained again, the road division areas are determined, and the dual-zone coordinated control of ADB headlights is completed.

2. The ADB dual-zone coordinated control method for vehicle lights based on the Internet of Vehicles according to claim 1, characterized in that: The establishment of the IoV information fusion mechanism includes deploying an IoV communication coordination node, wherein the communication coordination node includes integrating a dual-channel communication mechanism into the communication module of vehicle A, and the integrated dual-channel communication mechanism includes receiving information about surrounding vehicles and obtaining information about traffic conditions along the road. The data collected by the equipment of vehicle A includes setting a sensing sensor array at the end of vehicle A and completing multimodal data collection of vehicle A through the vehicle-mounted control unit; The sensor array is used to extract features from the multimodal data of vehicle A, and a lightweight deep neural network is used to identify the extracted features. The received surrounding vehicle information and the acquired traffic situation along the road are mapped uniformly with the multimodal data of vehicle A after identification into a shared space, wherein the shared space includes spatial and temporal dimensions; By establishing a local coordinate system in the spatial dimension with vehicle A as the origin and a time reference in the temporal dimension, the surrounding vehicle information and the acquired traffic situation along the road are aligned with the multimodal data of vehicle A after identification in the spatial and temporal dimensions to complete data fusion.

3. The ADB dual-zone coordinated control method for vehicle lights based on the Internet of Vehicles according to claim 2, characterized in that: The lightweight deep neural network includes a lightweight recognition network with dynamic channels to dynamically adjust multimodal data based on data fusion; The dynamic adjustment includes introducing an environmental perception feedback module into the lightweight recognition network to receive the operating status of vehicle A; According to the dynamic adjustment factor of the multimodal data output by the introduced environmental perception feedback module, the dynamic adjustment factor refers to the channel selection controller introduced into the environmental perception feedback module, which dynamically activates or shuts down the feature channels of each layer to complete the dynamic adjustment of the multimodal data; The feature extraction of the multimodal data of vehicle A includes assigning priority weights to the multimodal data in a dynamic adjustment stage, and the weights are adaptively adjusted according to the current driving scene of vehicle A; During the feature extraction process, priority weights are used to control the activation or shutdown ratio of feature channels at each layer and calculate the differences in multimodal data; Based on the differences in multimodal data, a path that matches the current priority weight is dynamically selected, the operating status of vehicle A is identified, and the feedback is fed back to the communication module of vehicle A, so that vehicle A can control the activation or deactivation of each layer of feature channels based on the priority weight; When the priority weight control feature channels of each layer are activated, the adaptive adjustment of the driving scene of vehicle A is started; otherwise, when the priority weight control feature channels of each layer are closed, the adaptive adjustment of the driving scene of vehicle A is closed.

4. The ADB dual-zone coordinated control method for vehicle lights based on the Internet of Vehicles according to claim 3, characterized in that: The formula for calculating the difference of multimodal data is: in, Indicates modality The proportion of channels activated or closed that should be allocated in this layer, Indicates the The real-time priority weight of the modalities, represents the total number of modes of multimodal data, Indicates the The priority weight of the modalities, Indicates the index number of the modal; The environmental perception dataset includes generating perception feature dimensions of vehicle A based on the differences in multimodal data, and constructing a spatiotemporal alignment coordinate framework with vehicle A as the origin. The spatiotemporal alignment coordinate framework refers to establishing a local coordinate system of spatial dimensions with vehicle A as the origin and a time reference of the time dimension; Use the local coordinate system with car A as the origin , the time benchmark of the time dimension , calculate and obtain the local perception data set, the specific formula is: in, Indicates the The spatial coordinates of the perceived target, represents the feature vector, Indicates the timestamp of local perception data, Represents a collection of local sensing data; The remote information obtained with vehicle A as the origin is uniformly mapped to form a remote environment perception data set. The formula of the remote environment perception data set is: in, represents a remote environment perception data set, Indicates the The spatial position coordinate vector of the perceived target, Indicates the The feature vector of the perceived target, timestamp indicating remote sensing information; Local perception data collection and remote environmental perception data collection Processing is performed to construct a set of nodes as perception targets and edges as spatial relationships, and the fused environment perception dataset is output; The formula for constructing a set where nodes are perception targets and edges are spatial relationships is: in, represents the perception target, and the edges are the set of spatial relations. Represents a collection of nodes, represents a set of edges; The formula of the environmental perception dataset is: in, Indicates the The fusion environment feature vector of each target, Represents a node, Indicates the The timestamp of the edge, Represents the environment perception dataset.

5. The ADB dual-zone coordinated control method for vehicle lights based on the Internet of Vehicles according to claim 4, characterized in that: The road division includes logical area division of the environmental perception data set, and the logical area division includes semantic clustering analysis of the fusion environment feature vector of each target in the environmental perception data set and dividing it into several semantic categories. Mapped to the corresponding fan-ring grid; The area types of the fan-ring grid include main lighting area, avoidance area, transition area and blind spot prediction area; The setting of lighting control rules corresponding to ADB includes prioritizing a number of semantic categories and generating a control mechanism that matches the ADB headlight executable instruction set in combination with the area type; The control mechanism includes the following steps: For the main lighting area, a high-brightness full coverage strategy is adopted, and the high-beam main beam module of the ADB light is enabled; For the avoidance zone, a local mask is dynamically generated based on the relative position and motion state of the perceived target in the zone, and the LED pixel units in the corresponding direction are turned off or modulated; For the transition zone, a brightness gradient control strategy is adopted to gradually adjust the light intensity distribution through a time sliding window mechanism; For blind spot prediction areas, a low-intensity pre-scanning strategy is activated in advance based on communication delay and target motion prediction.

6. The ADB dual-zone coordinated control method for vehicle lights based on the Internet of Vehicles according to claim 5, characterized in that: The coordinated operation in the vehicle control unit includes deploying a regional control rule mapping table in the vehicle control unit to map the main lighting area, the avoidance area, the transition area, and the blind spot prediction area to corresponding ADB headlight control instruction parameters, including a light intensity coefficient, an obscuration mask generation function, a beam deflection angle function, and a pre-scanning light activation condition; Use the vehicle control unit to perceive the current environment dataset After analysis, combined with the divided road area types and the control rule mapping table, the ADB headlight control instruction set for the current frame is calculated as follows: in, Represents the initial control instruction set, Represents a single control instruction.

7. The ADB dual-zone coordinated control method for vehicle lights based on the Internet of Vehicles according to claim 6, characterized in that: The determination of road division areas includes sending a cooperative control request to surrounding vehicles through vehicle A communication based on the ADB headlight control instruction set, receiving their current ADB lighting control status information, and performing spatial mapping and logical consistency verification on the received external vehicle control information and the vehicle's area division results to identify whether there is an area division conflict or a conflict between vehicle A and vehicles other than vehicle A; During the ADB dual-zone collaborative control of the vehicle network, the conflict between vehicle A and vehicles other than vehicle A and the conflict in area division are judged.

8. An ADB dual-zone coordinated control system for vehicle-to-vehicle lighting based on the vehicle-to-vehicle network, based on the ADB dual-zone coordinated control method for vehicle-to-vehicle lighting based on any one of claims 1 to 7, characterized in that: include, The IoV information fusion mechanism module establishes an IoV information fusion mechanism to obtain vehicle information outside the detection range of vehicle A and fuses the obtained vehicle information with the data collected by vehicle A's equipment to form an environmental perception data set. Vehicle A refers to the vehicle itself. A road segmentation module divides the road into sections based on the fused environmental perception dataset and implements differentiated lighting control strategies based on the divided sections. The differentiated lighting control strategies refer to lighting control rules corresponding to the ADB (Adaptive Driver Assistance) lighting system (ADB). The dual-zone collaborative control module operates collaboratively in the vehicle control unit based on the lighting control rules and the road division areas, calculates and obtains the lighting control rule algorithm for vehicle A, obtains the real-time status information of vehicle A and vehicles other than vehicle A based on the lighting control rule algorithm, determines the road division areas, and completes the ADB headlight dual-zone collaborative control.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the ADB headlight dual-zone collaborative control method based on the Internet of Vehicles according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the ADB vehicle light dual-zone collaborative control method based on the Internet of Vehicles according to any one of claims 1 to 7 are implemented.

Images