Smart city emergency lane data discrimination system

Abstract

This invention relates to a smart city emergency lane data identification system, comprising: a directional acquisition device, positioned above the emergency lane of a highway to acquire an image of the emergency lane; and a data identification device, used to intelligently identify the sub-blurring processing type of the emergency lane image based on various backup reference images, the original image, the emergency lane image, and various lane data of the highway's emergency lane using an intelligent identification model. The smart city emergency lane data identification system of this invention is stable in operation and widely applicable. Because it can use various lane data of the highway's emergency lane, various backup reference images, the original image, and the emergency lane image as multiple pieces of basic information for intelligent identification of the sub-blurring processing type of the emergency lane image, and employs a customized intelligent identification model for performing intelligent identification of the sub-blurring processing type, the effectiveness of the intelligent identification results is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of highway monitoring, and more particularly to a smart city emergency lane data identification system. Background Technology

[0002] The emergency lane on a highway refers to a section of the road adjacent to the right-hand driving lane, with a width of at least 3 meters and an effective length of at least 30 meters, including the hard shoulder, sufficient to accommodate parking for motor vehicles. In an emergency, vehicles may drive or park in the emergency lane. If a breakdown or other unsolvable problem occurs, the vehicle should be stopped in the emergency stopping area, hazard warning lights activated, and a warning triangle placed 150 meters behind the vehicle. At night, in rain, or fog, the side marker lights, taillights, and rear fog lights should also be activated. All other occupants must evacuate to a safe area and, if necessary, call the highway emergency number for assistance.

[0003] However, in the existing technology, even if an emergency lane image is obtained, it is impossible to determine whether the emergency lane image has undergone Gaussian blur processing, no scaling transformation blur processing, bilateral filtering blur processing, or median blur processing. This makes it impossible to clearly obtain the original data of the emergency lane image and accurately identify and judge the on-site condition of the emergency lane. Summary of the Invention

[0004] To address the technical problems in existing technologies, this invention provides a smart city emergency lane data identification system. By using various lane data, backup reference images, the original image, and the emergency lane image as foundational information for intelligent identification of the emergency lane image undergoing sub-blurring processing, the system ensures the effectiveness of the intelligent identification results and provides a reference for judging the authenticity of the emergency lane image content. Specifically, the lane data includes the emergency lane width, the number of surrounding lanes, and the length of the emergency lane within the field of view of the directional acquisition device. Each image participating in intelligent identification is represented numerically as a JPEG digital file. The intelligent identification model used for sub-blurring processing is customized by introducing a model conversion device to convert a deep convolutional inverse graph network (DCNN) into an intelligent identification model. The DCNN undergoes multiple learning operations to complete the conversion from DCNN to the intelligent identification model, and the number of learning operations performed on the DCNN is proportional to the number of pixels in the photoelectric sensing component of the directional acquisition device, further ensuring the effectiveness of the intelligent identification results.

[0005] According to the present invention, a smart city emergency lane data identification system is provided, the system comprising:

[0006] A model conversion device is used to convert a deep convolutional inverse graph network into an intelligent discrimination model. The conversion of the deep convolutional inverse graph network into an intelligent discrimination model includes performing various learning operations on the deep convolutional inverse graph network to complete the conversion from the deep convolutional inverse graph network to the intelligent discrimination model.

[0007] The instant alert device, connected to the data identification device, is used to display the sub-blurring type of the emergency lane image upon receiving the sub-blurring type of the emergency lane image.

[0008] A directional acquisition device is installed above the emergency lane of a highway to perform image acquisition and processing of the emergency lane during the highway's opening hours, so as to obtain and output the corresponding emergency lane image.

[0009] A lane detection device is used to acquire various lane data of the emergency lane of a highway. The various lane data of the emergency lane of the highway include the lane width of the emergency lane, the number of surrounding lanes, and the length of the emergency lane within the field of view of the directional acquisition device.

[0010] The data identification device is connected to the model conversion device, the directional acquisition device, the lane detection device, and the real-time reminder device, respectively. It is used to acquire each backup reference image obtained after the original image output by the directional acquisition device has been processed by each sub-fuzzing type under the fuzzing processing type. The intelligent identification model is used to intelligently identify the sub-fuzzing type processed by the emergency lane image based on each backup reference image, the original image, the emergency lane image, and various lane data of the emergency lane of the highway. Among them, each backup reference image, the original image, and the emergency lane image are all in the numerical representation of JPEG digital files, and the sub-fuzzing type processed by the intelligently identified emergency lane image is in the numerical representation of ASCII code.

[0011] The sub-blurring types are Gaussian blurring, no scaling transformation blurring, bilateral filtering blurring, and median blurring.

[0012] The directional acquisition device is also used to stop image acquisition and processing of the emergency lane of the highway during the highway closure period;

[0013] The model conversion device is used to convert a deep convolutional inverse graph network into an intelligent discrimination model. The conversion of the deep convolutional inverse graph network into an intelligent discrimination model includes performing various learning operations on the deep convolutional inverse graph network to complete the conversion from the deep convolutional inverse graph network to the intelligent discrimination model. The number of learning operations performed on the deep convolutional inverse graph network is proportional to the number of pixels of the photoelectric sensing component of the directional acquisition device.

[0014] Therefore, the present invention has the following outstanding technical effects:

[0015] First, the various lane data, backup reference images, original images, and emergency lane images of the highway's emergency lane are used as multiple basic information for intelligent identification of the image processing of the emergency lane images, which undergoes sub-blurring processing. This ensures the effectiveness of the intelligent identification results and provides a reference for judging the authenticity of the emergency lane images.

[0016] Secondly: Specifically, the lane data of the emergency lane of the highway includes the lane width of the emergency lane, the number of other lanes around it, and the length of the emergency lane within the field of view of the directional acquisition device. The numerical representation of each image participating in intelligent identification is the numerical representation of the JPEG digital file of that image.

[0017] Furthermore, the structural customization of the intelligent identification model used to perform sub-fuzzy processing-type intelligent identification is manifested in the introduction of a model conversion device to convert the deep convolutional inverse graph network into an intelligent identification model. Here, each learning operation is performed on the deep convolutional inverse graph network to complete the conversion from the deep convolutional inverse graph network to the intelligent identification model, and the number of learning operations performed on the deep convolutional inverse graph network is proportional to the number of pixels of the photoelectric sensing component of the directional acquisition device.

[0018] The smart city emergency lane data identification system of this invention is stable in operation and widely applicable. Because it can use various lane data, backup reference images, original images, and emergency lane images of highways as multiple fundamental information for intelligent identification of the image processing (sub-fuzzing processing type) of the emergency lane image, and employs a customized intelligent identification model for performing sub-fuzzing processing type intelligent identification, the effectiveness of the intelligent identification results is guaranteed. Attached Figure Description

[0019] The embodiments of the present invention will now be described with reference to the accompanying drawings, wherein:

[0020] Figure 1 This is a structural block diagram of a smart city emergency lane data identification system according to Embodiment 1 of the present invention.

[0021] Figure 2 This is a structural block diagram of a smart city emergency lane data identification system according to Embodiment 2 of the present invention.

[0022] Figure 3 This is a structural block diagram of a smart city emergency lane data identification system according to Embodiment 3 of the present invention. Detailed Implementation

[0023] The embodiments of the smart city emergency lane data identification system of the present invention will now be described in detail with reference to the accompanying drawings.

[0024] Figure 1 The above is a structural block diagram of a smart city emergency lane data identification system according to Embodiment 1 of the present invention. The system includes:

[0025] A model conversion device is used to convert a deep convolutional inverse graph network into an intelligent discrimination model. The conversion of the deep convolutional inverse graph network into an intelligent discrimination model includes performing various learning operations on the deep convolutional inverse graph network to complete the conversion from the deep convolutional inverse graph network to the intelligent discrimination model.

[0026] The instant alert device, connected to the data identification device, is used to display the sub-blurring type of the emergency lane image upon receiving the sub-blurring type of the emergency lane image.

[0027] For example, an instant alert device, connected to a data identification device, is used to display the sub-blurred processing type of the emergency lane image while receiving the sub-blurred processing type of the emergency lane image. The instant alert device can be selected as a touch display screen or an LED display array.

[0028] A directional acquisition device is installed above the emergency lane of a highway to perform image acquisition and processing of the emergency lane during the highway's opening hours, so as to obtain and output the corresponding emergency lane image.

[0029] A lane detection device is used to acquire various lane data of the emergency lane of a highway. The various lane data of the emergency lane of the highway include the lane width of the emergency lane, the number of surrounding lanes, and the length of the emergency lane within the field of view of the directional acquisition device.

[0030] The data identification device is connected to the model conversion device, the directional acquisition device, the lane detection device, and the real-time reminder device, respectively. It is used to acquire each backup reference image obtained after the original image output by the directional acquisition device has been processed by each sub-fuzzing type under the fuzzing processing type. The intelligent identification model is used to intelligently identify the sub-fuzzing type processed by the emergency lane image based on each backup reference image, the original image, the emergency lane image, and various lane data of the emergency lane of the highway. Among them, each backup reference image, the original image, and the emergency lane image are all in the numerical representation of JPEG digital files, and the sub-fuzzing type processed by the intelligently identified emergency lane image is in the numerical representation of ASCII code.

[0031] The sub-blurring types are Gaussian blurring, no scaling transformation blurring, bilateral filtering blurring, and median blurring.

[0032] The directional acquisition device is also used to stop image acquisition and processing of the emergency lane of the highway during the highway closure period;

[0033] The model conversion device is used to convert a deep convolutional inverse graph network into an intelligent discrimination model. The conversion of the deep convolutional inverse graph network into an intelligent discrimination model includes performing various learning operations on the deep convolutional inverse graph network to complete the conversion from the deep convolutional inverse graph network to the intelligent discrimination model. The number of learning operations performed on the deep convolutional inverse graph network is proportional to the number of pixels of the photoelectric sensing component of the directional acquisition device.

[0034] The method employs an intelligent identification model to intelligently identify the sub-blurring type of the emergency lane image based on each backup reference image, the original image, the emergency lane image, and various lane data of the emergency lane of the highway. Each backup reference image, the original image, and the emergency lane image are in the numerical representation of JPEG digital files. The sub-blurring type of the emergency lane image identified by the intelligent model is in the numerical representation of ASCII code. This includes synchronously inputting each backup reference image, the original image, the emergency lane image, and various lane data of the emergency lane of the highway into the intelligent identification model.

[0035] Figure 2 This is a structural block diagram of a smart city emergency lane data identification system according to Embodiment 2 of the present invention.

[0036] Compared to Figure 1 , Figure 2 The smart city emergency lane data identification system may also include:

[0037] The on-site storage device is connected to the data identification device, the model conversion device, the lane detection device, and the instant reminder device respectively, and is used to provide data temporary storage services for the data identification device, the model conversion device, the lane detection device, and the instant reminder device in a time-sharing manner;

[0038] The on-site storage device is connected to the data identification device, the model conversion device, the lane detection device, and the instant reminder device, respectively, and is used to provide data temporary storage services for the data identification device, the model conversion device, the lane detection device, and the instant reminder device in a time-sharing manner. This includes the data identification device, the model conversion device, the lane detection device, and the instant reminder device being connected to the on-site storage device using different data channels.

[0039] The field storage device is connected to the data identification device, the model conversion device, the lane detection device, and the instant reminder device, respectively, and is used to provide data temporary storage services for the data identification device, the model conversion device, the lane detection device, and the instant reminder device in a time-division manner, including that the data identification device, the model conversion device, the lane detection device, and the instant reminder device share the same reference clock signal.

[0040] Figure 3 This is a structural block diagram of a smart city emergency lane data identification system according to Embodiment 3 of the present invention.

[0041] Compared to Figure 1 , Figure 3 The smart city emergency lane data identification system may also include:

[0042] A content display device is connected to the data identification device, the model conversion device, the lane detection device, and the real-time reminder device, respectively, and is used to simultaneously display various status information of the data identification device, the model conversion device, the lane detection device, and the real-time reminder device;

[0043] The content display device is connected to the data identification device, the model conversion device, the lane detection device, and the real-time reminder device, respectively, and is used to simultaneously display various status information of the data identification device, the model conversion device, the lane detection device, and the real-time reminder device, including: the simultaneously displayed status information of the data identification device, the model conversion device, the lane detection device, and the real-time reminder device includes the sleep state or working state of the data identification device, the model conversion device, the lane detection device, and the real-time reminder device;

[0044] The content display device is connected to the data identification device, the model conversion device, the lane detection device, and the real-time reminder device, respectively, and is used to simultaneously display various status information of the data identification device, the model conversion device, the lane detection device, and the real-time reminder device. The content display device is also a liquid crystal display screen or an LED display array.

[0045] The content display device, which is connected to the data identification device, the model conversion device, the lane detection device, and the real-time reminder device, and is used to simultaneously display various status information of the data identification device, the model conversion device, the lane detection device, and the real-time reminder device, further includes: the LED display array is composed of multiple LED display units arranged in a rectangular matrix pattern;

[0046] The content display device, which is connected to the data identification device, the model conversion device, the lane detection device, and the instant reminder device, and is used to simultaneously display various status information of the data identification device, the model conversion device, the lane detection device, and the instant reminder device, also includes: the multiple LED display units arranged in a rectangular matrix pattern have the same structure.

[0047] In addition, in the smart city emergency lane data identification system, an intelligent identification model is used to intelligently identify the sub-blurring type of the emergency lane image based on each backup reference image, the original image, the emergency lane image, and various lane data of the emergency lane of the highway. Each backup reference image, the original image, and the emergency lane image are in the numerical representation of JPEG digital files. The sub-blurring type of the emergency lane image identified by the intelligent model is in the numerical representation of ASCII code. The system also includes: executing the intelligent identification model to obtain the sub-blurring type of the emergency lane image output by the intelligent identification model.

[0048] In the foregoing specification, the invention has been described with reference to specific embodiments. However, those skilled in the art will understand that various modifications and changes can be made without departing from the scope defined by the appended claims. Therefore, the specification and drawings should be considered illustrative rather than restrictive, and it is intended that all such modifications be included within the scope of the invention.

[0049] The benefits, other advantages, and solutions to problems have been described above in conjunction with specific embodiments. However, any benefit, advantage, solution to a problem, and any other element that may produce or make any benefit, advantage, or solution more apparent should not be construed as a critical, essential, or fundamental feature or element of any or all claims. The terms “comprising,” “including,” or any other variations thereof as used herein are intended to cover a non-exclusive inclusion, such as a process, method, article, or apparatus, which includes not only those elements but also a number of other elements not explicitly listed or inherent to such a process, method, article, or apparatus.

Claims

1. A smart city emergency lane data identification system, characterized in that, The system includes: A model conversion device is used to convert a deep convolutional inverse graph network into an intelligent discrimination model, wherein learning operations are performed on the deep convolutional inverse graph network to complete the conversion from the deep convolutional inverse graph network to the intelligent discrimination model; The instant alert device, connected to the data identification device, is used to display the sub-blurring type of the emergency lane image upon receiving the sub-blurring type of the emergency lane image. A directional acquisition device is installed above the emergency lane of a highway to perform image acquisition and processing of the emergency lane during the highway's opening hours, so as to obtain and output the corresponding emergency lane image. Lane detection devices are used to acquire various lane data of the emergency lane on highways. These lane data include the lane width of the emergency lane, the number of surrounding lanes, and the length of the emergency lane within the field of view of the directional acquisition device. The data identification device is connected to the model conversion device, the directional acquisition device, the lane detection device, and the real-time reminder device, respectively. It is used to collect the original image output by the directional acquisition device and obtain each backup reference image after processing by each sub-fuzzing type under the fuzzing processing type. The intelligent identification model is used to intelligently identify the sub-fuzzing type processed by the emergency lane image based on each backup reference image, the original image, the emergency lane image, and various lane data of the emergency lane of the highway. Among them, each backup reference image, the original image, and the emergency lane image are all in the numerical representation of JPEG digital files, and the sub-fuzzing type processed by the intelligently identified emergency lane image is in the numerical representation of ASCII code. The sub-blurring types are Gaussian blurring, no scaling transformation blurring, bilateral filtering blurring, and median blurring. Among them, the directional acquisition device is also used to stop the image acquisition and processing of the emergency lane of the highway during the time when the highway is closed; The number of learning operations performed on the deep convolutional inverse graph network is proportional to the number of pixels in the photoelectric sensing component of the directional acquisition device.

2. The smart city emergency lane data identification system as described in claim 1, characterized in that: Each set of backup reference images, original images, emergency lane images, and various lane data of the emergency lane of the highway are synchronously input into the intelligent identification model.

3. The smart city emergency lane data identification system as described in claim 2, characterized in that, The system also includes: The on-site storage device is connected to the data identification device, the model conversion device, the lane detection device, and the instant reminder device respectively, and is used to provide data temporary storage services for the data identification device, the model conversion device, the lane detection device, and the instant reminder device in a time-sharing manner; The data identification device, the model conversion device, the lane detection device, and the real-time alert device are connected to the field storage device via different data channels.

4. The smart city emergency lane data identification system as described in claim 3, characterized in that: The data identification device, the model conversion device, the lane detection device, and the real-time alert device all use the same reference clock signal.

5. The smart city emergency lane data identification system as described in claim 2, characterized in that, The system also includes: The content display device is connected to the data identification device, the model conversion device, the lane detection device, and the real-time reminder device, respectively, and is used to simultaneously display various status information of the data identification device, the model conversion device, the lane detection device, and the real-time reminder device.

6. The smart city emergency lane data identification system as described in claim 5, characterized in that: The status information of the data identification device, the model conversion device, the lane detection device, and the instant reminder device displayed at the same time includes the dormant or working status of the data identification device, the model conversion device, the lane detection device, and the instant reminder device.

7. The smart city emergency lane data identification system as described in claim 6, characterized in that: The content display device is a liquid crystal display screen or an LED display array.

8. The smart city emergency lane data identification system as described in claim 7, characterized in that: The LED display array consists of multiple LED display units arranged in a rectangular matrix pattern.

9. The smart city emergency lane data identification system as described in claim 8, characterized in that: The multiple LED display units arranged in a rectangular array pattern have the same structure.

Images