Automatic intelligent safe driving assistance system

Abstract

The invention relates to the technical field of intelligent driving, in particular to an automatic intelligent safe driving assistance system. An automatic intelligent safe driving assistance system is characterized by comprising an automobile data recorder, a cloud background, a fixed camera and a data interaction module, the automobile data recorder is adaptive to various automobile types, has the functions of network connection, video acquisition and automobile positioning, and is used for acquiring image data and positioning data in real time and uploading the data to the cloud background; the cloud background is used for receiving multi-source data, constructing a shared neural network, calculating a blind area and dead angle coverage rate and analyzing road condition information at the same time; and the fixed camera is erected in a road area where a blind area is easy to form. The beneficial effects of the invention are that the system breaks through the limitation of single-vehicle sensing, constructs a global shared sensing network through integrating the multi-source data of social vehicles and fixed cameras, eliminates the blind areas and dead angles of traditional single-vehicle sensing, and especially can cope with the complex scenes of bridge pier shielding, ghost probe, red light running at intersections and the like.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent driving, in particular to an automatic intelligent safe driving auxiliary system. BACKGROUND

[0002] Current intelligent driving auxiliary systems mostly rely on single-vehicle-mounted visual solutions, laser radars, infrared probes and other devices to realize environmental perception. However, such single-vehicle-perception modes have significant limitations: on the one hand, affected by the detection range of the device, obstructions (such as bridge piers and buildings), visual blind spots and perception dead angles are easily formed, and it is difficult to deal with sudden scenarios such as "ghost probes" and red light running at intersections; on the other hand, vehicle models that are not equipped with intelligent driving functions (such as traditional taxis, online taxis, and private cars) cannot participate in the construction of the road perception network, resulting in incomplete coverage of road perception data and difficulty in forming a global no-dead-angle road condition monitoring system.

[0003] In the prior art, some solutions attempt to supplement perception through roadside fixed cameras, but there is a lack of real-time data interconnection between fixed cameras and vehicle-mounted devices, which cannot timely feedback dynamic information captured by fixed devices to vehicles, nor can it expand the data collection range by utilizing the perception capabilities of a large number of social vehicles, resulting in delayed risk prediction and low accident avoidance efficiency.

[0004] Therefore, there is a need for an intelligent driving auxiliary system that can integrate social vehicles and fixed device resources, build a shared perception network, and break through the limitations of single-vehicle perception blind spots. SUMMARY

[0005] The present application aims to overcome the limitations of single-vehicle perception and incomplete data coverage of existing intelligent driving auxiliary systems, and provides an automatic intelligent safe driving auxiliary system that builds a shared neural network between vehicles and fixed devices to realize real-time global road condition perception and risk prediction, and improve driving safety.

[0006] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0007] An automatic intelligent safe driving auxiliary system, characterized in that it comprises a car recorder, a cloud background, a fixed camera and a data interaction module; the car recorder is adapted to various types of vehicles and has network connection, video capture and vehicle positioning functions, and is used to collect image data and positioning data in real time and upload them to the cloud background; the cloud background is used to receive multi-source data, build a shared neural network and calculate blind area dead angle coverage, and analyze road condition information at the same time; the fixed camera is installed in road areas prone to blind areas and is used to collect dynamic data and upload them to the cloud background; the data interaction module realizes real-time data transmission between components.

[0008] Preferably, the dashcam can be installed on vehicles that do not have intelligent driving functions, including taxis, ride-hailing vehicles, private cars and driverless taxis, so that the above-mentioned vehicles can become data contributing nodes.

[0009] Preferably, the cloud backend includes a data processing unit and a shared neural network construction unit; the data processing unit identifies obstacles, moving objects, and traffic events; the shared neural network construction unit integrates multi-source data to form a full-domain perception network and displays the blind spot coverage rate as a percentage.

[0010] Preferably, the fixed camera is installed at intersections of roads and near bridge piers, and the dynamic data collected serves as a supplement to the vehicle-mounted data, eliminating blind spots in fixed areas.

[0011] Preferably, it also includes a risk prediction and action execution module, which is integrated into the vehicle equipped with intelligent driving assistance functions, receives road condition analysis results from the cloud backend, predicts road risks, and controls the vehicle to perform real-time actions or warning actions.

[0012] Preferably, the data interaction module adopts 5G or vehicle-to-everything (V2X) protocols to achieve low-latency data uploading and downloading, ensuring real-time transmission of road condition information in blind spots.

[0013] Preferably, the risk prediction and action execution module performs risk prediction in conjunction with the vehicle's driving status, and the actions include deceleration, steering, emergency braking, and voice / light warnings.

[0014] Preferably, the image data collected by the dashcam includes information on road obstacles, moving objects, and traffic participants, and the positioning data is the real-time geographical location information of the vehicle.

[0015] The beneficial effects of this invention are:

[0016] Breaking through the limitations of single-vehicle perception: By integrating multi-source data from social vehicles and fixed cameras, a global shared perception network is constructed, eliminating blind spots and dead zones of traditional single-vehicle perception, especially capable of dealing with complex scenarios such as bridge pier obstruction, "ghost peeks" (protruding pedestrians), and running red lights at intersections.

[0017] Comprehensive data coverage: It supports vehicles without intelligent driving functions to access the system by adding a dashcam, which greatly expands the number of data collection nodes, improves the coverage of blind spots, and realizes a road safety perception mode of "participation by all".

[0018] Low-latency risk response: Employing a real-time data interaction and cloud-based rapid analysis mechanism, when a vehicle encounters a blind spot, it can promptly obtain road condition data from surrounding devices and, combined with the risk prediction module, take proactive actions, significantly improving accident avoidance efficiency.

[0019] High compatibility: It is compatible with various vehicle models and existing fixed camera equipment, without the need for large-scale modifications to existing vehicles or road infrastructure, thus reducing the cost of system promotion and application.

[0020] Obviously, based on the above description of the present invention, and according to common technical knowledge and conventional methods in the field, various other modifications, substitutions, or alterations can be made without departing from the basic technical concept of the present invention.

[0021] The following detailed embodiments further illustrate the above-described content of the present invention. However, this should not be construed as limiting the scope of the present invention to the following examples. All technologies implemented based on the above-described content of the present invention fall within the scope of the present invention. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of the system flow structure of the present invention. Detailed Implementation

[0023] The present invention is illustrated below with specific embodiments, which are not intended to limit the scope of the invention.

[0024] like Figure 1 As shown, an automatic intelligent safety driving assistance system includes a dashcam, a cloud backend, a fixed camera, and a data interaction module. The functions and connections of each component are as follows:

[0025] Dashcam: Compatible with various vehicle types, including but not limited to taxis, ride-hailing vehicles, private cars, and driverless taxis, featuring network connectivity, video capture, and vehicle location capabilities. The dashcam is used to collect real-time video data during vehicle operation, including information on road obstacles, moving objects, traffic participants, and real-time vehicle location data, and uploads this data to the cloud backend via the network. Vehicles without intelligent driving functions can connect to the system by installing this dashcam, becoming data contributing nodes.

[0026] The cloud backend is used to receive and store all video data, location data, and data uploaded by dashcams and fixed cameras; the cloud backend has a built-in data processing unit and a shared neural network construction unit.

[0027] Data processing unit: performs real-time analysis on received multi-source data: vehicle images, fixed camera images, and vehicle positioning, and identifies obstacles, foreign objects, and moving objects, such as pedestrians, non-motorized vehicles, and traffic events, such as accidents ahead and running red lights.

[0028] Shared neural network building unit: Based on the coverage of all access devices, such as dashcams and fixed cameras, calculate the blind spot coverage rate of the road, display it as a percentage, and integrate multi-source data to form a road perception network that is shared across the entire domain, enabling collaborative access to data between different devices.

[0029] Fixed cameras: installed in areas prone to blind spots, such as intersections of roads and near bridge piers, to collect real-time information on the movement of surrounding objects and road environment, and upload the collected data to the cloud backend in real time to supplement vehicle data and eliminate blind spots in fixed areas.

[0030] Data interaction module: Integrated between the dashcam and the cloud backend, and between the fixed camera and the cloud backend, it adopts a low-latency transmission protocol, such as the 5G / vehicle-to-everything (V2X) protocol, to achieve real-time data upload and download. When a vehicle's original sensing devices, such as vision systems, lidar, and infrared sensors, cannot detect blind spots, the cloud backend uses the data interaction module to download dashcam or fixed camera image data from vehicles in adjacent lanes or oncoming lanes to the vehicle, providing it with blind spot road condition information.

[0031] Risk prediction and action execution module: Integrated into vehicles equipped with intelligent driving assistance functions, it receives blind spot road condition analysis results from the cloud backend, and combines them with the vehicle's driving status: speed, steering, and braking status to predict actual road risks, such as collision risk and traffic obstruction risk. Based on the prediction results, it controls the vehicle to take real-time actions, such as deceleration, steering, emergency braking, or to issue early warning actions, such as honking the horn and lighting prompts, to avoid accidents.

[0032] The following describes in detail the workflow of the automatic intelligent safe driving assistance system of the present invention, taking into account specific application scenarios:

[0033] System deployment: Install fixed cameras at locations prone to blind spots, such as intersections on urban roads and both sides of bridge piers, and complete network connections with the cloud backend; at the same time, encourage taxi companies, ride-hailing platforms and private car users to install compatible dashcams in their vehicles to achieve real-time data communication between the dashcams and the cloud backend.

[0034] Data Acquisition and Network Construction: All dashcams connected to the system upload in-vehicle images and vehicle positioning data in real time, while fixed cameras upload dynamic data of intersections in real time. After receiving the data, the cloud backend calculates the blind spot coverage rate of various areas of urban roads through a shared neural network construction unit. For example, the coverage rate of a certain intersection reaches 98%, and the coverage rate of a certain suburban road section reaches 92%, and the shared sensing network is dynamically updated.

[0035] Blind Spot Perception and Data Distribution: When a private vehicle equipped with an intelligent driving assistance system drives near a bridge pier, and its lidar is blocked by the pier and cannot detect pedestrians behind it, the cloud backend uses a data processing unit to identify pedestrian image data captured by a fixed camera behind the pier and a dashcam in a taxi in the opposite lane. After analysis, the cloud backend determines the risk of a pedestrian crossing the road. Subsequently, the cloud backend distributes the blind spot road condition information to the vehicle through a data interaction module.

[0036] Risk prediction and action execution: After receiving blind spot road condition information, the vehicle's risk prediction and action execution module, combined with the vehicle's current speed and distance from the bridge pier, predicts that if the vehicle does not slow down, there will be a collision risk in 3 seconds. The module then controls the vehicle to perform a deceleration action and triggers an in-vehicle warning prompt, such as a voice broadcast "There is a pedestrian in the blind spot ahead, please pay attention and avoid the pedestrian" until the pedestrian passes through the blind spot area, ensuring driving safety.

[0037] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0038] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural transformations made using the contents of the present invention's specification and drawings under the inventive concept of the present invention, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

[0039] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An automatic intelligent safety driving assistance system, characterized in that, The system includes a dashcam, a cloud backend, a fixed camera, and a data interaction module. The dashcam is compatible with various vehicle models and features network connectivity, video capture, and vehicle positioning capabilities. It is used to collect image and positioning data in real time and upload them to the cloud backend. The cloud backend receives multi-source data, constructs a shared neural network, calculates blind spot coverage, and analyzes road condition information. The fixed camera is installed in road areas prone to blind spots to collect dynamic data and upload it to the cloud backend. The data interaction module enables real-time data transmission between the components.

2. The automatic intelligent safe driving assistance system according to claim 1, characterized in that, The dashcam can be installed on vehicles that do not have intelligent driving functions, including taxis, ride-hailing vehicles, private cars, and driverless taxis, making these vehicles data contributing nodes.

3. The automatic intelligent safe driving assistance system according to claim 1, characterized in that, The cloud backend includes a data processing unit and a shared neural network construction unit; the data processing unit identifies obstacles, moving objects, and traffic events; the shared neural network construction unit integrates multi-source data to form a full-domain perception network and displays the blind spot coverage rate as a percentage.

4. The automatic intelligent safe driving assistance system according to claim 1, characterized in that, The fixed cameras are installed at intersections of roads and near bridge piers. The dynamic data collected supplements the vehicle-mounted data and eliminates blind spots in fixed areas.

5. The automatic intelligent safe driving assistance system according to claim 1, characterized in that, It also includes a risk prediction and action execution module, which is integrated into vehicles equipped with intelligent driving assistance functions. It receives road condition analysis results from the cloud backend, predicts road risks, and controls the vehicle to perform real-time actions or warning actions.

6. The automatic intelligent safe driving assistance system according to claim 1, characterized in that, The data interaction module uses 5G or vehicle-to-everything (V2X) protocols to achieve low-latency data uploading and downloading, ensuring real-time transmission of road condition information in blind spots.

7. The automatic intelligent safe driving assistance system according to claim 1, characterized in that, The risk prediction and action execution module combines the vehicle's driving status to predict risks, and the actions include deceleration, steering, emergency braking, and voice / light warnings.

8. The automatic intelligent safe driving assistance system according to claim 1, characterized in that, The video data collected by the aforementioned dashcam includes information on road obstacles, moving objects, and traffic participants, and the location data is the vehicle's real-time geographical location information.

Images