Solar energy wireless transmission type intelligent driving video recorder
By integrating solar power supply and neural network processing modules, a low-cost collision warning system for dashcams on older vehicle models has been achieved, solving the problems of limited power supply and insufficient intelligence in traditional dashcams, and providing all-weather monitoring and warning capabilities.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- DONGGUAN PROTRONIC ELECTRONICS CO LTD
- Filing Date
- 2025-04-24
- Publication Date
- 2026-07-10
AI Technical Summary
Traditional dashcams rely on the vehicle's power supply and cannot continue to work after the vehicle is turned off. They also lack the ability to actively analyze the driving environment, making it difficult to meet the real-time warning and intelligent monitoring needs of modern traffic safety. In particular, they are expensive and have poor compatibility in older models and low-end vehicles.
It adopts a solar-powered intelligent driving video recorder with wireless transmission and integrates a neural network processing module. It realizes the collision warning function through image acquisition, analysis and wireless transmission. Independent of the vehicle's original system, it uses a CMOS image sensor, NPU chip and Wi-Fi 6 module for real-time data processing and wireless communication.
It enables continuous monitoring even after the vehicle is turned off, providing a low-cost collision warning function without requiring modifications to the vehicle's electronic systems, thus lowering the barrier to entry for safety features and improving the device's environmental adaptability and reliability.
Smart Images
Figure CN224480722U_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of wireless dashcams, and in particular to a solar-powered wireless transmission type intelligent dashcam. Background Technology
[0002] With the continuous growth of car ownership, driving safety has become a focus of social concern. As one of the core devices for vehicle safety, dashcams have evolved from initially being used only for recording accident evidence to becoming intelligent terminals integrating multiple functions. However, traditional dashcams generally rely on the vehicle's power supply and are limited to video recording and local storage. They cannot continue working after the vehicle is turned off and lack the ability to actively analyze the driving environment, making it difficult to meet the modern traffic safety demands for real-time warnings and intelligent monitoring.
[0003] Functions like collision warning are currently mainly integrated into the original equipment systems (OEMs) of mid-to-high-end new energy vehicles, relying on the collaborative work of pre-installed sensors (such as millimeter-wave radar and lidar) and the onboard computing platform. However, older gasoline vehicles, lower-spec models, and older vehicles, which constitute the majority of the market, lack OEM smart hardware support. If users want to install such functions, they need to modify the onboard electronic system and integrate sensor modules, which is not only costly and has poor compatibility, but may also cause safety hazards due to wiring modifications. As a result, many ordinary vehicles cannot effectively improve their active safety performance. Utility Model Content
[0004] The purpose of this application is to provide a solar-powered wireless transmission intelligent vehicle video recorder, which is a low-cost solution independent of the vehicle's original system. By optimizing the hardware architecture and function integration, it enables older vehicle models to obtain collision warning functions without modification.
[0005] To achieve the above objectives, this application provides the following technical solution:
[0006] A solar-powered wireless transmission intelligent vehicle video recorder includes a main control module, a neural network processing module, an image acquisition module, a storage module, a wireless transmission module, and a solar power supply module. The image acquisition module is connected to the neural network processing module via the main control module, transmitting captured image data to the neural network processing module in real time for processing. The neural network processing module is connected to the wireless transmission module via the main control module, sending output data to an external terminal via the wireless transmission module. The solar power supply module is connected to the image acquisition module, neural network processing module, wireless transmission module, storage module, and main control module, providing power to these modules. The storage module is connected to the neural network processing module via the main control module, supporting the neural network processing module's reading of model data and storage of processing results. The neural network processing module includes an alarm signal output terminal and a comparison circuit with pre-stored human and vehicle feature data. The output terminal of the comparison circuit is connected to the alarm signal output terminal via a distance calculation unit, and the alarm signal output terminal is connected to the GPIO alarm pin of the wireless transmission module.
[0007] Furthermore, the main control module is a multi-functional multimedia video processing chip, model XM530.
[0008] Furthermore, the neural network processing module is an NPU, which is used to analyze the images acquired by the image sensor, compare them with preset human and car models, and calculate the distance between the target and the vehicle.
[0009] Furthermore, the image acquisition module is a CMOS image sensor, model number SC1336.
[0010] Furthermore, the image acquisition module and the main control module are connected via a MIPI interface.
[0011] Furthermore, the wireless transmission module is model ATBM6062 Wi-Fi6.
[0012] Furthermore, the solar power supply module includes two monocrystalline silicon solar panels and a lithium battery. The monocrystalline silicon solar panels are connected to the lithium battery, and the monocrystalline silicon solar panels convert light energy into electrical energy, which is stored in the lithium battery.
[0013] Furthermore, it also includes a 940nm infrared light-emitting diode and a photoresistor, which are respectively connected to the main control module.
[0014] The beneficial effects of this application are as follows:
[0015] (1) This application adopts a power supply mode that complements the solar power supply module and the vehicle power supply. Even after the vehicle is turned off, it can still be powered by solar energy. This breaks through the limitation of traditional dashcams relying on a single vehicle power supply, realizes 24-hour uninterrupted monitoring, avoids functional interruption due to battery depletion, and significantly improves the environmental adaptability and reliability of the equipment.
[0016] (2) This application integrates a neural network processing module and a pre-set feature comparison circuit. Based on real-time image analysis from the image acquisition module, it communicates in real-time with an external terminal (such as a mobile phone) via a wireless transmission module. When an alarm signal is triggered, it immediately sends a warning message to the user, directly realizing the collision warning function without relying on the vehicle's original sensors (such as millimeter-wave radar or lidar) or onboard computing platform. This design allows older models and low-spec gasoline vehicles to have active safety functions added at low cost without modifying the onboard electronic system, solving the technical problems of high installation cost and poor compatibility in the prior art, and significantly lowering the threshold for popularizing safety functions. Attached Figure Description
[0017] Figure 1 A block diagram of a solar-powered wireless transmission type intelligent vehicle video recorder provided in an embodiment of this application;
[0018] Figure 2 A system power supply circuit diagram provided for one embodiment of this application;
[0019] Figure 3 A circuit diagram of the main control module power supply provided in one embodiment of this application;
[0020] Figure 4 A circuit diagram of an image acquisition module provided in one embodiment of this application;
[0021] Figure 5 A circuit diagram of a wireless transmission module provided in an embodiment of this application;
[0022] Explanation of reference numerals in the attached figures:
[0023] 1. Main control module; 2. Neural network processing module; 3. Image acquisition module; 4. Storage module; 5. Wireless transmission module; 6. Solar power supply module; 7. Infrared light-emitting diode; 8. Photoresistor; Detailed Implementation
[0024] The features and exemplary embodiments of various aspects of this application will now be described in detail. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only configured to explain this application and are not configured to limit this application. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples of this application.
[0025] like Figure 1 As shown, a solar-powered wireless transmission type intelligent vehicle video recorder includes a main control module 1, a neural network processing module 2, an image acquisition module 3, a storage module 4, a wireless transmission module 5, and a solar power supply module 6. The image acquisition module 3 is connected to the neural network processing module 2 through the main control module 1, transmitting the captured image data to the neural network processing module 2 for processing in real time. The neural network processing module 2 is connected to the wireless transmission module 5 through the main control module 1, sending the output data to an external terminal through the wireless transmission module 5. The solar power supply module 6 is connected to the image acquisition module 3, the neural network processing module 2, the wireless transmission module 5, the storage module 4, and the main control module 1, providing power to these modules. The storage module 4 is connected to the neural network processing module 2 through the main control module 1, supporting the neural network processing module 2 in reading model data and storing processing results. The neural network processing module 2 includes an alarm signal output terminal and a comparison circuit with pre-stored human and vehicle feature data. The output terminal of the comparison circuit is connected to the alarm signal output terminal through a distance calculation unit. The alarm signal output terminal is connected to the GPIO alarm pin of the wireless transmission module 5.
[0026] In this embodiment, the main control module 1 is a multi-functional multimedia video processing chip, model XM530. This chip selection allows the dashcam of this application to maintain a compact size (≤100cm²). 3 Under the premise of achieving near-vehicle domain controller processing power at only 1 / 5 of the cost of dedicated vehicle solutions, it is particularly suitable for large-scale adoption in the aftermarket.
[0027] In this embodiment, the neural network processing module 2 is an NPU. The neural network processing module 2 is used to analyze the images collected by the image sensor, compare them with preset human and car models, and calculate the distance between the target and the vehicle.
[0028] In this embodiment, the image acquisition module 3 is a CMOS image sensor, model SC1336. This sensor maintains automotive-grade reliability while being inexpensive and requiring no external ISP chip, reducing the overall solution cost by 35%. Its excellent low-light performance reduces the number of infrared illuminators (from the conventional two sets to one set), further optimizing system power consumption and size.
[0029] In this embodiment, the image acquisition module 3 and the main control module 1 are connected via a MIPI interface.
[0030] In this embodiment, the wireless transmission module 5 is an ATBM6062 Wi-Fi6. Its PCIe direct connection architecture with the XM530 main control chip reduces data transfer latency; and through the UL MU-MIMO characteristics of Wi-Fi6, it enables synchronous communication between the dashcam and the mobile phone / roadside unit.
[0031] In this embodiment, the solar power supply module 6 includes two monocrystalline silicon solar panels and a lithium battery. The monocrystalline silicon solar panels are connected to the lithium battery. The monocrystalline silicon solar panels convert light energy into electrical energy and store it in the lithium battery.
[0032] This embodiment also includes a 940nm infrared LED 7 and a photoresistor 8, which are respectively connected to the main control module 1. This embodiment achieves 90% of the daytime detection performance of the SC1336 sensor at the cost of less than 1W of power consumption, while completely avoiding the risk of driver glare caused by visible light supplemental lighting.
[0033] In this embodiment, the image acquisition module 3 (such as a wide-angle camera) continuously captures high-definition video streams of the area in front of and around the vehicle, and transmits the raw image data to the neural network processing module 2 through the main control module 1; the main control module 1 acts as a scheduling center, allocating the transmission priority of image data to ensure that key frames (such as sudden motion scenes) are processed first, thereby reducing latency.
[0034] The neural network processing module 2 (such as a chip equipped with an NPU) loads a pre-trained driving safety model (such as the YOLO object detection model) and parses the received image data frame by frame:
[0035] Target recognition: Extracting features (such as contours, colors, and motion trajectories) of targets such as pedestrians, vehicles, and lane lines;
[0036] Feature matching: Through the built-in matching circuit, real-time features are matched with pre-stored databases of human and vehicle features (such as standard vehicle size and pedestrian posture) to filter out invalid interference targets (such as road signs and trees).
[0037] The distance calculation unit (integrated into the neural network module) dynamically calculates the actual distance between the vehicle and the target based on the pixel displacement of the target in the image, the camera focal length, and calibration parameters, and predicts the time of collision (TTC) by combining vehicle speed information.
[0038] When the calculated collision time is lower than a preset threshold (e.g., 2 seconds) or the target enters the danger distance range, the alarm signal output terminal generates a digital signal (e.g., a high-level pulse) and transmits it to the wireless transmission module 5 (e.g., a 4G module) through the GPIO pin.
[0039] Multi-level early warning mechanism: Level 1 warning (low risk): The target continues to approach but does not reach the threshold, triggering log recording and data caching; Level 2 warning (high risk): When the trigger threshold is reached, an encrypted alarm signal (including risk type, location, and timestamp) is immediately sent to the user's mobile APP via the wireless transmission module 5.
[0040] The wireless transmission module 5 pushes alarm signals and key data (such as risk frame screenshots and distance information) to external terminals (such as mobile phones and cloud platforms) in real time via cellular network (4G / 5G) or Wi-Fi.
[0041] Terminal response: After the user's mobile APP analyzes the signal, it triggers an audible and visual alarm (such as a voice prompt "Collision risk ahead!") and a vibration alert.
[0042] Storage module 4 (such as an eMMC chip) interacts with neural network processing module 2 through main control module 1 to achieve dual-channel data management: model data reading: provides fast access to pre-stored feature library for neural network; processing result archiving: stores video clips before and after alarm events (such as 10 seconds before and 5 seconds after triggering) and sensor data (such as GPS location) for accident tracing or model iteration training.
[0043] Solar power module 6 operating modes: While driving: Prioritizes using the vehicle's power supply and charges the energy storage battery; After the engine is turned off: Automatically switches to solar power to maintain image acquisition, neural network standby, and motion detection functions; Low light conditions: Seamlessly switches between the energy storage battery and the vehicle's power supply to avoid power interruption. Power consumption optimization: Main control module 1 dynamically adjusts the power of each module according to the usage scenario (e.g., reducing the image acquisition frame rate at night) to extend the duration of solar power supply.
[0044] This solution does not rely on the vehicle's original factory system, but achieves collision warning solely through visual perception, making it compatible with all vehicle models. A dedicated NPU chip ensures image processing latency of ≤50ms, meeting emergency braking requirements. Solar power and a low-power design enable uninterrupted monitoring year-round (operation can be maintained with only 4 hours of average daily sunlight). This design effectively addresses the pain points of older vehicle models, such as the lack of active safety functions, high installation costs, and limited power supply, promoting the widespread adoption of driving safety technology.
[0045] In the description of the embodiments of this application, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, an indirect connection through an intermediate medium, or the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in the embodiments of this application according to the specific circumstances.
[0046] The devices or elements referred to in the embodiments of this application or implied herein must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as limiting the embodiments of this application. In the description of the embodiments of this application, "a plurality of" means two or more, unless otherwise precisely specified.
[0047] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “may include” and “have,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0048] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of this application, and are not intended to limit them. Although the embodiments of this application have been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.
Claims
1. A solar-powered wireless transmission type intelligent vehicle video recorder, characterized in that: The system includes a main control module, a neural network processing module, an image acquisition module, a storage module, a wireless transmission module, and a solar power supply module. The image acquisition module is connected to the neural network processing module through the main control module, transmitting captured image data to the neural network processing module in real time for processing. The neural network processing module is connected to the wireless transmission module through the main control module, sending output data to an external terminal via the wireless transmission module. The solar power supply module is connected to the image acquisition module, neural network processing module, wireless transmission module, storage module, and main control module, providing power to these modules. The storage module is connected to the neural network processing module through the main control module, supporting the neural network processing module in reading model data and storing processing results. The neural network processing module includes an alarm signal output terminal and a comparison circuit with pre-stored human and vehicle feature data. The output terminal of the comparison circuit is connected to the alarm signal output terminal through a distance calculation unit, and the alarm signal output terminal is connected to the GPIO alarm pin of the wireless transmission module.
2. The solar-powered wireless transmission type intelligent vehicle video recorder according to claim 1, characterized in that: The main control module is a multi-functional multimedia video processing chip, model XM530.
3. The solar-powered wireless transmission type intelligent vehicle video recorder according to claim 1, characterized in that: The neural network processing module is an NPU, which is used to analyze the images acquired by the image sensor, compare them with preset human and car models, and calculate the distance between the target and the vehicle.
4. A solar-powered wireless transmission type intelligent vehicle video recorder according to claim 1, characterized in that: The image acquisition module is a CMOS image sensor, model number SC1336.
5. A solar-powered wireless transmission type intelligent vehicle video recorder according to claim 1, characterized in that: The image acquisition module and the main control module are connected via a MIPI interface.
6. A solar-powered wireless transmission type intelligent vehicle video recorder according to claim 1, characterized in that: The wireless transmission module is model ATBM6062 Wi-Fi6.
7. A solar-powered wireless transmission type intelligent vehicle video recorder according to claim 1, characterized in that: The solar power module includes two monocrystalline silicon solar panels and a lithium battery. The monocrystalline silicon solar panels are connected to the lithium battery. The monocrystalline silicon solar panels convert light energy into electrical energy, which is stored in the lithium battery.
8. A solar-powered wireless transmission type intelligent vehicle video recorder according to claim 1, characterized in that: It also includes a 940nm infrared LED and a photoresistor, which are respectively connected to the main control module.