Fixed traffic environment visual content management system

Abstract

The invention relates to a fixed traffic environment visual content management system, and the system comprises a directional obtaining device which is fixed above a railway station platform and is used for obtaining and outputting a current captured picture; and the sequence analysis device is arranged at the visual monitoring end and is used for intelligently identifying a binary numerical value representing the sequence of each image processing executed by the currently captured picture in the directional acquisition equipment by adopting an extreme learning machine neural network model based on each shooting parameter of the directional acquisition equipment and each visual data of the currently captured picture. According to the invention, on the basis of the shooting parameters of the directional acquisition device and the visual data of the current captured picture, the extreme learning machine neural network model is adopted to intelligently identify the binary numerical value representing the processing sequence of each image executed by the current captured picture in the directional acquisition device; therefore, the sequence of various image processing executed by the currently captured picture is defined, and the monitoring end is helped to execute the restoration processing of the original picture.

Description

Technical Field

[0001] The present invention relates to the field of traffic management, and in particular to a visual content management system for a fixed traffic environment. Background Art

[0002] The purpose of traffic management is to understand and follow the inherent objective laws of road traffic flow, use modern technical means and scientific principles, methods and measures to continuously improve the efficiency and quality of traffic management, so as to achieve fewer delays, shorter operating time, greater capacity, better order and lower operating costs, thereby obtaining the best social, economic, transportation and environmental benefits, and serving economic development, improving people's living standards and travel quality.

[0003] In traffic management, trains are a major means of transportation. Generally, a monitoring device can be fixed above a train station platform to perform visual monitoring operations facing the train station platform when the train station platform is in a stopped state, and is used to obtain and output corresponding captured images. The problem is that even if the image receiving end knows that the received image has undergone various image processing, it is still difficult to restore the original image corresponding to the captured image and capable of reflecting the real scene of the train station platform because it is unable to determine the processing order of the various image processing. Summary of the invention

[0004] In order to solve the technical problems in the prior art, the present invention provides a visual content management system for a fixed traffic environment, which uses an extreme learning machine neural network model to intelligently identify a binary value representing the order of various image processing operations performed on the current captured image in the directional acquisition device based on various shooting parameters of the directional acquisition device and various visual data of the current captured image, wherein the binary value includes various order values ​​corresponding to the various image processing operations connected head to tail, and the order value corresponding to each image processing operation is represented by the execution sequence number of the image processing operation plus the ASCII code of the image processing operation, thereby clarifying the order of various image processing operations performed on the current captured image, wherein, The shooting parameters of the directional acquisition device are the shutter speed, exposure and resolution of the directional acquisition device, and the visual data of the current captured image are the maximum noise amplitude, the number of noise types, the background area ratio and the average of the brightness values ​​corresponding to each pixel point of the current captured image, thereby providing key basic information for the order analysis of various image processing, and the structure of the extreme learning machine neural network model used to perform the order analysis of various image processing is a targeted designed structure, specifically, a training mapping device is introduced to perform multiple training actions on the extreme learning machine neural network to obtain the extreme learning machine neural network after completing multiple training actions and output it as the extreme learning machine neural network model.

[0005] According to the present invention, a fixed traffic environment visual content management system is provided, the system comprising: A directional acquisition device, fixed above the platform of the train station to perform a visual monitoring operation facing the platform of the train station when the platform of the train station is in a train stop state, for acquiring and outputting a corresponding currently captured picture; A wireless notification device, connected to the order parsing device, for notifying a remote blockchain processing node via a wireless data channel of a received binary value representing the order of various image processing operations performed on the currently captured image in the directional acquisition device; A training mapping device is used to perform multiple training actions on the extreme learning machine neural network to obtain the extreme learning machine neural network after completing the multiple training actions and output it as an extreme learning machine neural network model; An order analysis device is provided at the visual monitoring end and is respectively connected to the directional acquisition device, the wireless notification device and the training mapping device, and is used to intelligently identify a binary value representing the order of various image processings executed in the directional acquisition device for the currently captured image using an extreme learning machine neural network model based on various shooting parameters of the directional acquisition device and various visual data of the currently captured image, wherein the binary value includes various order values ​​corresponding to various image processings connected head to tail, and the order value corresponding to each image processing is represented by the execution sequence number of the image processing plus the ASCII code of the image processing; Wherein, based on various shooting parameters of the directional acquisition device and various visual data of the currently captured picture, the binary value representing the order of various image processing executed in the directional acquisition device by using the extreme learning machine neural network model for intelligent identification includes: various shooting parameters of the directional acquisition device are the shutter speed, exposure and resolution of the directional acquisition device; Among them, the binary value representing the order of various image processing executed in the directional acquisition device for the currently captured image is intelligently identified by using an extreme learning machine neural network model based on various shooting parameters of the directional acquisition device and various visualization data of the currently captured image, and also includes: various visualization data of the currently captured image are the maximum noise amplitude of the currently captured image, the number of noise types, the background area ratio, and the average of each brightness value corresponding to each pixel point; Among them, the binary value includes order values ​​corresponding to each image processing connected head to tail, and the order value corresponding to each image processing is represented by the execution sequence number of the image processing plus the ASCII code of the image processing, including: each image processing is one of point image restoration processing, rotation correction processing, image sharpening processing, image enhancement processing and image filtering processing.

[0006] It can be seen that the present invention has at least the following main inventive concepts: The first inventive concept: based on the shooting parameters of the directional acquisition device and the visual data of the current captured picture, an extreme learning machine neural network model is used to intelligently identify a binary value representing the order of various image processings executed on the current captured picture in the directional acquisition device, wherein the binary value includes the order values ​​corresponding to the various image processings connected head to tail, and the order value corresponding to each image processing is represented by the execution sequence number of the image processing plus the ASCII code of the image processing, thereby clarifying the order of various image processings executed on the current captured picture; The second invention concept: the various shooting parameters of the directional acquisition device are the shutter speed, exposure and resolution of the directional acquisition device, and the various visualization data of the currently captured image are the maximum noise amplitude, the number of noise types, the background area ratio and the average of the brightness values ​​corresponding to each pixel point of the currently captured image, thereby providing key basic information for the order analysis of various image processing; The third inventive concept: The structure of the extreme learning machine neural network model for performing order analysis of various image processing is a targeted designed structure, specifically introducing a training mapping device for performing multiple training actions on the extreme learning machine neural network to obtain the extreme learning machine neural network after completing multiple training actions and output it as an extreme learning machine neural network model. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein: Figure 1 It is a structural block diagram of a visual content management system for a fixed traffic environment according to a primary embodiment of the present invention.

[0008] Figure 2 It is a structural block diagram of a visual content management system for a fixed traffic environment according to a secondary embodiment of the present invention.

[0009] Figure 3 FIG. 4 is a structural block diagram of a visual content management system for a fixed traffic environment according to another embodiment of the present invention. DETAILED DESCRIPTION

[0010] The following will describe in detail an embodiment of a visual content management system for a fixed traffic environment according to the present invention with reference to the accompanying drawings.

[0011] Figure 1 The structure block diagram of the fixed traffic environment visual content management system according to the primary embodiment of the present invention is shown, and the system includes: A directional acquisition device, fixed above the platform of the train station to perform a visual monitoring operation facing the platform of the train station when the platform of the train station is in a train stop state, for acquiring and outputting a corresponding currently captured picture; A wireless notification device, connected to the order parsing device, for notifying a remote blockchain processing node via a wireless data channel of a received binary value representing the order of various image processing operations performed on the currently captured image in the directional acquisition device; Specifically, the wireless notification device is connected to the order parsing device, and is used to notify the remote blockchain processing node through the wireless data channel of the received binary value representing the order of each image processing performed on the current captured picture in the directional acquisition device, including: the wireless data channel is a time division duplex communication link or a frequency division duplex communication link; A training mapping device is used to perform multiple training actions on the extreme learning machine neural network to obtain the extreme learning machine neural network after completing the multiple training actions and output it as an extreme learning machine neural network model; An order analysis device is provided at the visual monitoring end and is respectively connected to the directional acquisition device, the wireless notification device and the training mapping device, and is used to intelligently identify a binary value representing the order of various image processings executed in the directional acquisition device for the currently captured image using an extreme learning machine neural network model based on various shooting parameters of the directional acquisition device and various visual data of the currently captured image, wherein the binary value includes various order values ​​corresponding to various image processings connected head to tail, and the order value corresponding to each image processing is represented by the execution sequence number of the image processing plus the ASCII code of the image processing; Wherein, based on various shooting parameters of the directional acquisition device and various visual data of the currently captured picture, the binary value representing the order of various image processing executed in the directional acquisition device by using the extreme learning machine neural network model for intelligent identification includes: various shooting parameters of the directional acquisition device are the shutter speed, exposure and resolution of the directional acquisition device; Among them, the binary value representing the order of various image processing executed in the directional acquisition device for the currently captured image is intelligently identified by using an extreme learning machine neural network model based on various shooting parameters of the directional acquisition device and various visualization data of the currently captured image, and also includes: various visualization data of the currently captured image are the maximum noise amplitude of the currently captured image, the number of noise types, the background area ratio, and the average of each brightness value corresponding to each pixel point; The binary value includes order values ​​corresponding to the image processing items connected head to tail, and the order value corresponding to each image processing item is represented by the execution sequence number of the image processing item plus the ASCII code of the image processing item, including: each image processing item is one of point image restoration processing, rotation correction processing, image sharpening processing, image enhancement processing and image filtering processing; And wherein, based on the various shooting parameters of the directional acquisition device and the various visual data of the currently captured picture, an extreme learning machine neural network model is used to intelligently identify a binary value representing the order of various image processing executed in the currently captured picture in the directional acquisition device, wherein the binary value includes various order values ​​corresponding to the various image processing connected head to tail, and the order value corresponding to each image processing is represented by the execution sequence number of the image processing plus the ASCII code of the image processing, including: the various shooting parameters of the directional acquisition device and the various visual data of the currently captured picture are input into the extreme learning machine neural network model in parallel.

[0012] Figure 2 It is a structural block diagram of a visual content management system for a fixed traffic environment according to a secondary embodiment of the present invention.

[0013] Compared to Figure 1 , Figure 2 The visual content management system for fixed traffic environments in the network can also include: An ASIC processing device, connected to the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device, respectively, for providing configuration operations of working parameters for the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device in a time-sharing manner; The ASIC processing device is respectively connected to the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device, and is used to provide the configuration operation of the working parameters for the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device in a time-sharing manner, including: the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device share the same working parameter configuration interface; Wherein, the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device use different configuration address data; Wherein, a parallel connection of a communication data link is established between each of the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device through a parallel data bus; Among them, the parallel connection of the communication data link established between each of the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device through a parallel data bus includes: the parallel data bus is one of an 8-bit parallel data bus, a 16-bit parallel data bus and a 32-bit parallel data bus.

[0014] Figure 3 FIG. 4 is a structural block diagram of a visual content management system for a fixed traffic environment according to another embodiment of the present invention.

[0015] Compared to Figure 1 , Figure 3 The visual content management system for fixed traffic environments in the network can also include: A power support device, connected to the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device, respectively, for providing power distribution support of different working voltages for the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device in a time-sharing manner; The power support device is respectively connected to the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device, and is used to provide power distribution support of different working voltages for the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device in a time-sharing manner, including: two or more devices with the same working voltage requirements in the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device use the same power supply line; Wherein, the power support device is respectively connected to the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device, and is used to provide power distribution support of different working voltages for the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device in a time-sharing manner, and further includes: the power support device is an uninterruptible power supply device; Wherein, the power support device is respectively connected to the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device, and is used to provide power distribution support with different working voltages for the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device in time-sharing, and further includes: providing different working voltages including 3.3V working voltage for the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device in time-sharing; And wherein, the power support device is respectively connected to the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device, and is used to provide power distribution support with different working voltages for the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device in a time-sharing manner, and also includes: providing different working voltages including 5V working voltage for the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device in a time-sharing manner.

[0016] In addition, in the fixed traffic environment visual content management system, inputting various shooting parameters of the directional acquisition device and various visual data of the currently captured picture into the extreme learning machine neural network model in parallel includes: performing binary value conversion processing on various shooting parameters of the directional acquisition device and various visual data of the currently captured picture respectively and then inputting them into the extreme learning machine neural network model in parallel, and using a parallel control interface to perform a data processing process of performing binary value conversion processing on various shooting parameters of the directional acquisition device and various visual data of the currently captured picture respectively and then inputting them into the extreme learning machine neural network model in parallel; And wherein, each shooting parameter of the directional acquisition device and each visual data of the currently captured picture are respectively subjected to binary value conversion processing and then input in parallel to the extreme learning machine neural network model, and a parallel control interface is used to execute the data processing process of each shooting parameter of the directional acquisition device and each visual data of the currently captured picture are respectively subjected to binary value conversion processing and then input in parallel to the extreme learning machine neural network model, including: selecting and using a CPLD chip to implement the parallel control interface.

[0017] The fixed traffic environment visual content management system of the present invention solves the technical problem in the prior art that it is difficult to identify the true content of the received traffic scene pictures. By using an extreme learning machine neural network model based on the various shooting parameters of the directional acquisition device and the various visualization data of the currently captured picture, the binary value representing the order of various image processing executed in the directional acquisition device is intelligently identified, thereby clarifying the order of various image processing executed on the currently captured picture, helping the monitoring end to perform the restoration processing of the original picture, and thus solving the above technical problem.

[0018] While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of this disclosure, will appreciate that other embodiments can be devised which do not depart from the scope of the invention as disclosed herein. Accordingly, the scope of the invention should be limited only by the claims appended hereto.

Claims

1. A visual content management system for a fixed traffic environment, characterized in that: The system comprises: A directional acquisition device, fixed above the platform of the train station to perform a visual monitoring operation facing the platform of the train station when the platform of the train station is in a train stop state, for acquiring and outputting a corresponding currently captured picture; A wireless notification device, connected to the order parsing device, for notifying a remote blockchain processing node via a wireless data channel of a received binary value representing the order of various image processing operations performed on the currently captured image in the directional acquisition device; A training mapping device is used to perform multiple training actions on the extreme learning machine neural network to obtain the extreme learning machine neural network after completing the multiple training actions and output it as an extreme learning machine neural network model; An order analysis device is provided at the visual monitoring end and is respectively connected to the directional acquisition device, the wireless notification device and the training mapping device, and is used to intelligently identify a binary value representing the order of various image processings executed in the directional acquisition device for the currently captured image using an extreme learning machine neural network model based on various shooting parameters of the directional acquisition device and various visual data of the currently captured image, wherein the binary value includes various order values ​​corresponding to various image processings connected head to tail, and the order value corresponding to each image processing is represented by the execution sequence number of the image processing plus the ASCII code of the image processing; Wherein, based on various shooting parameters of the directional acquisition device and various visual data of the currently captured picture, the binary value representing the order of various image processing executed in the directional acquisition device by using the extreme learning machine neural network model for intelligent identification includes: various shooting parameters of the directional acquisition device are the shutter speed, exposure and resolution of the directional acquisition device; Among them, the binary value representing the order of various image processing executed in the directional acquisition device for the currently captured image is intelligently identified by using an extreme learning machine neural network model based on various shooting parameters of the directional acquisition device and various visualization data of the currently captured image, and also includes: various visualization data of the currently captured image are the maximum noise amplitude of the currently captured image, the number of noise types, the background area ratio, and the average of each brightness value corresponding to each pixel point; Among them, the binary value includes order values ​​corresponding to each image processing connected head to tail, and the order value corresponding to each image processing is represented by the execution sequence number of the image processing plus the ASCII code of the image processing, including: each image processing is one of point image restoration processing, rotation correction processing, image sharpening processing, image enhancement processing and image filtering processing.

2. The fixed traffic environment visual content management system according to claim 1, characterized in that: Based on the various shooting parameters of the directional acquisition device and the various visual data of the currently captured picture, an extreme learning machine neural network model is used to intelligently identify a binary value representing the order of various image processing operations performed on the currently captured picture in the directional acquisition device, wherein the binary value includes various order values ​​corresponding to the various image processing operations connected head to tail, and the order value corresponding to each image processing operation is represented by the execution sequence number of the image processing operation plus the ASCII code of the image processing operation, including: inputting the various shooting parameters of the directional acquisition device and the various visual data of the currently captured picture into the extreme learning machine neural network model in parallel.

3. The fixed traffic environment visual content management system according to claim 2, characterized in that: The system further comprises: An ASIC processing device, connected to the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device, respectively, for providing configuration operations of working parameters for the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device in a time-sharing manner; Among them, the ASIC processing device is respectively connected to the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device, and is used to provide the configuration operation of working parameters for the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device in a time-sharing manner, including: the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device share the same working parameter configuration interface.

4. The fixed traffic environment visual content management system according to claim 3, characterized in that: The order parsing device, the directional acquisition device, the wireless notification device and the training mapping device use different configuration address data.

5. The fixed traffic environment visual content management system according to claim 3, characterized in that: Establishing parallel connections of communication data links between the order parsing device, the directional acquisition device, the wireless notification device, and the training mapping device through parallel data buses; Among them, the parallel connection of the communication data link established between each of the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device through a parallel data bus includes: the parallel data bus is one of an 8-bit parallel data bus, a 16-bit parallel data bus and a 32-bit parallel data bus.

6. The fixed traffic environment visual content management system according to claim 2, characterized in that: The system further comprises: A power support device, connected to the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device, respectively, for providing power distribution support of different working voltages for the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device in a time-sharing manner; Among them, the power support device is respectively connected to the order analysis device, the directional acquisition device, the wireless notification device and the training mapping device, and is used to provide power distribution support with different working voltages for the order analysis device, the directional acquisition device, the wireless notification device and the training mapping device in a time-sharing manner, including: among the order analysis device, the directional acquisition device, the wireless notification device and the training mapping device, two or more devices with the same working voltage requirements use the same power supply line.

7. The fixed traffic environment visual content management system according to claim 6, characterized in that: The power support device is respectively connected to the order analysis device, the directional acquisition device, the wireless notification device and the training mapping device, and is used to provide power distribution support with different working voltages for the order analysis device, the directional acquisition device, the wireless notification device and the training mapping device in a time-sharing manner, and also includes: the power support device is an uninterruptible power supply device.

8. The fixed traffic environment visual content management system according to claim 7, characterized in that: The power support device is respectively connected to the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device, and is used to provide power distribution support with different working voltages for the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device in a time-sharing manner, and also includes: providing different working voltages including 3.3V working voltage for the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device in a time-sharing manner.

9. The fixed traffic environment visual content management system according to claim 8, characterized in that: The power support device is respectively connected to the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device, and is used to provide power distribution support with different working voltages for the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device in a time-sharing manner, and also includes: providing different working voltages including 5V working voltage for the order parsing device, the directional acquisition device, the wireless notification device and the training mapping device in a time-sharing manner.

Images