Image quality enhancement method and system based on MESH ad hoc network

Abstract

The invention discloses an image quality enhancement method and system based on an MESH ad-hoc network, and relates to the technical field of ad-hoc network image processing. The image quality enhancement method based on the MESH ad-hoc network comprises the following steps: node data acquisition delay error evaluation; evaluating a signal collision delay error; and evaluating a link fracture delay error. According to the method, whether detection node optimization is carried out or not is judged through a data acquisition delay error result, signal delay error evaluation is carried out through signal collision data so as to judge whether routing signal transmitting power fraction optimization is carried out or not, and link delay error evaluation is carried out through link fracture data so as to judge whether link gain optimization is carried out or not; the effect of improving the accuracy of the real-time passenger flow image analysis of the smart city traffic intersection is achieved, and the problem that the accuracy of the real-time passenger flow image analysis of the smart city traffic intersection is not high due to the fact that node image data corresponds to MESH ad hoc network route switching delay in the multi-hop transmission process in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of self-organizing network image processing, and in particular to an image quality enhancement method and system based on a MESH self-organizing network. Background Art

[0002] In complex, large-scale locations with a high density of people and equipment, such as smart city traffic intersections, transportation hubs, and industrial parks, applications such as image monitoring and intelligent inspections play a vital role in security and operational management. MESH (Mesh Network) represents a wireless mesh network. In the field of communications, it specifically refers to a decentralized, self-organizing network structure with multi-hop interconnection between nodes. Existing technologies use cross-layer collaborative mechanisms to perceive network status and dynamically adjust image coding parameters (such as network layer congestion level and transport layer throughput), ensuring reliable network operation layer by layer. Combining edge computing nodes and time synchronization features, lightweight convolutional neural network models are deployed to enhance images in real time, ultimately achieving a balance between image quality and transmission efficiency while ensuring transmission reliability.

[0003] For example, the invention patent announcement with announcement number CN110415184B discloses a multimodal image enhancement method based on an orthogonal metaspace, comprising: extracting the style and content codes of high aesthetic quality images using an encoder-decoder and a mutual information optimization strategy; mapping the style code of a reference image to a style metaspace spanned by a set of orthogonal bases; utilizing an adaptive instance normalization module and a feature decoupling method optimized for mutual information to improve the decoupling of the style and content codes of the reference image, and constructing a generative adversarial network based on encoder-decoder for model training; in the testing phase, inputting any ordinary image into the trained model, extracting the content code by the content encoder, and randomly sampling multiple style codes in the style metaspace. After fusing the content code with the style code, the code is fed into the generator to obtain a multimodal enhanced image.

[0004] For example, the low-light image enhancement method based on a multi-scale stacked attention network, as announced in the invention patent with announcement number CN114972107B, includes: preprocessing the training image pairs of the original low-light image and the normal-light image to obtain the training image pairs consisting of the original low-light image and the normal-light image; designing a multi-scale adaptive fusion stacked attention network as a low-light image enhancement network, which includes a multi-scale adaptive feature fusion module, a stacked attention residual module and a Fourier reconstruction module; designing the target loss function of the low-light image enhancement network, training the network until it converges to a threshold or the number of iterations reaches a threshold; inputting the image to be tested into the designed low-light image enhancement network, and using the trained network to predict and generate a normal-light image.

[0005] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0006] Dynamic routing protocols need to perceive and update routing information in mobility scenarios in real time, that is, the routing information of node links in the MESH self-organizing network. This means that in high-mobility scenarios (such as smart city traffic intersections), the frequency of topology changes of node links in the MESH self-organizing network may be much higher than the routing convergence time (for example, frequent link disconnection caused by vehicle movement). As a result, the dynamic routing protocol has not yet converged, and the topology structure changes again, which makes the topology change speed far exceed the routing convergence time. During the transmission of data packets, the transmission channel path formed by the node links in the MESH self-organizing network may be disconnected or congested, and the data packets can only be backlogged in the node buffer. Secondly, the data packets backlogged in the buffer queue for forwarding, resulting in a significant increase in end-to-end delay and even the formation of network islands. Ultimately, the adaptability of the MESH self-organizing network for image data transmission in dynamic environments is reduced, and it cannot meet real-time requirements. There is a problem that the node image data is delayed in the corresponding MESH self-organizing network route switching during multi-hop transmission, resulting in low accuracy of real-time passenger flow image analysis at smart city traffic intersections. Summary of the Invention

[0007] The embodiments of the present application provide an image quality enhancement method and system based on a MESH self-organizing network, thereby solving the problem in the prior art that the accuracy of real-time passenger flow image analysis at smart city traffic intersections is low due to the delay in MESH self-organizing network routing switching during the multi-hop transmission of node image data. This improves the accuracy of real-time passenger flow image analysis at smart city traffic intersections due to the delay in MESH self-organizing network routing switching during the multi-hop transmission of node image data.

[0008] An embodiment of the present application provides an image quality enhancement method based on a MESH self-organizing network, comprising the following steps: step 1, performing a data acquisition delay error evaluation on a passenger flow image data acquisition process of a passenger flow image based on a monitoring node signal collision rate, and determining whether to perform monitoring node optimization; if so, performing a signal delay error evaluation, otherwise performing monitoring node optimization; step 2, real-time monitoring of the node signal collision status of monitoring nodes in a specified area of the MESH network within a signal delay error evaluation period, performing a signal delay error evaluation on the node signal collision status based on the node signal collision data, and determining whether to perform routing signal transmission power score optimization; step 3, real-time monitoring of the node link breakage status of monitoring nodes in a specified area of the MESH network within a link delay error evaluation period, performing a link delay error evaluation on the node link breakage status based on the node link breakage data, and determining whether to perform link gain optimization.

[0009] An embodiment of the present application provides an image quality enhancement system based on a MESH self-organizing network, including: a data acquisition delay error evaluation module, a signal delay error evaluation module and a link delay error evaluation module; wherein the data acquisition delay error evaluation module is used to perform data acquisition delay error evaluation on the passenger flow image data acquisition process based on the monitoring node signal collision rate, and at the same time determine whether to perform monitoring node optimization, if so, perform signal delay error evaluation, otherwise perform monitoring node optimization; the signal delay error evaluation module is used to monitor in real time the node signal collision status of the monitoring nodes in a specified area in the MESH network within a signal delay error evaluation period, perform signal delay error evaluation on the node signal collision status based on the node signal collision data, and at the same time determine whether to perform routing signal transmission power score optimization; the link delay error evaluation module is used to monitor in real time the node link breakage status of the monitoring nodes in a specified area in the MESH network within a link delay error evaluation period, perform link delay error evaluation on the node link breakage status based on the node link breakage data, and at the same time determine whether to perform link gain optimization.

[0010] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0011] 1. Data collection delay error is evaluated by monitoring node signal collision rate to determine whether to optimize detection nodes, reduce data errors, and ensure data collection quality. Signal delay error is then evaluated through signal collision data to determine whether routing signal transmission power fraction optimization is performed to reduce signal overlap and interference and reduce signal delay. Finally, link delay error is evaluated through link breakage data to determine whether link gain optimization is performed to reduce link breakage caused by signal attenuation or external interference and improve link reliability, thereby improving the accuracy of real-time passenger flow image analysis at smart city traffic intersections.

[0012] 2. At the end of the signal delay error evaluation period, the obtained route reconstruction time, communication channel access time, and data packet retransmission time are compared with the node signal collision data preset in the database, and processed in combination with the node signal collision data compensation value to obtain the signal delay error index. Compared with the existing technology that only focuses on a single factor affecting signal delay, this method compares and processes these three key parameters, comprehensively covering the main links that cause delays in the signal transmission process, and reflecting changes in network status in real time, thereby reducing the impact of transmission interruptions caused by monitoring node signal collisions on the routing switching delay of the MESH self-organizing network.

[0013] 3. At the end of the link delay error evaluation period, the obtained link break frequency, link status update duration, and triggering link repair time are compared with the node link break data preset in the database, and processed in combination with the node link break data compensation value to obtain the link delay error index. Compared with the static environment compensation mechanism of the existing technology, this method characterizes the link delay error from different dimensions, captures the link status changes in a timely manner through dynamic evaluation, and reflects it in the link delay error index, thereby improving the evaluation reliability, thereby reducing the impact of transmission interruption caused by link breakage in network topology changes on the routing switching delay of the MESH self-organizing network. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 Flowchart of the image quality enhancement method based on MESH self-organizing network provided in an embodiment of the present application;

[0015] Figure 2 A logical framework diagram of the image quality enhancement method based on MESH self-organizing network provided in an embodiment of the present application;

[0016] Figure 3 A flowchart of data acquisition delay error evaluation provided in an embodiment of the present application;

[0017] Figure 4 A flow chart of signal delay error evaluation provided in an embodiment of the present application;

[0018] Figure 5 A flowchart of link delay error evaluation provided in an embodiment of the present application;

[0019] Figure 6 This is a structural diagram of the image quality enhancement system based on MESH self-organizing network provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] The embodiments of the present application provide an image quality enhancement method and system based on a MESH self-organizing network, which solves the problem in the prior art that the accuracy of real-time passenger flow image analysis at smart city traffic intersections is low due to the delay in MESH self-organizing network routing switching corresponding to the node image data during multi-hop transmission. The method evaluates the data acquisition delay error in the passenger flow image data acquisition process by monitoring the node signal collision rate, and determines whether to optimize the monitoring node. If the data acquisition is determined to be qualified, the node signal collision status and node link breakage status of the monitoring nodes in the specified area of the MESH network during the communication transmission stage are monitored in real time: the signal delay error of the node signal collision status is evaluated based on the node signal collision data, and it is determined whether to optimize the routing signal transmission power score; the link delay error of the node link breakage status is evaluated based on the node link breakage data, and it is determined whether to optimize the link gain. This achieves the effect of improving the accuracy of real-time passenger flow image analysis at smart city traffic intersections, and solves the problem in the prior art that the accuracy of real-time passenger flow image analysis at smart city traffic intersections is low due to the delay in MESH self-organizing network routing switching corresponding to the node image data during multi-hop transmission.

[0021] The technical solution in the embodiment of the present application is to solve the problem that the accuracy of real-time passenger flow image analysis at smart city traffic intersections is low due to the delay in MESH self-organizing network routing switching during the multi-hop transmission of the above-mentioned node image data. The overall idea is as follows:

[0022] The data collection delay error is evaluated by monitoring the node signal collision rate to determine whether to optimize the detection node. Then, the signal delay error is evaluated by signal collision data to determine whether to optimize the routing signal transmission power score. Finally, the link delay error is evaluated by link disconnection data.

[0023] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0024] like Figure 1 FIG. 1 is a flowchart of a method for enhancing image quality based on a MESH self-organizing network according to an embodiment of the present application. The method for enhancing image quality based on a MESH self-organizing network according to an embodiment of the present application comprises the following steps:

[0025] Step 1: Based on the monitoring node signal collision rate, the passenger flow image data collection process of the passenger flow image is evaluated for data collection delay error, and at the same time, it is determined whether to perform monitoring node optimization. If so, a signal delay error evaluation is performed, otherwise the monitoring node optimization is performed. The monitoring node optimization means adjusting the monitoring node transmission power and the monitoring node moving distance score to reduce the degree of delay of the monitoring node signal collision rate on the real-time passenger flow image analysis. The data collection delay error evaluation is used to measure the influence of the monitoring node signal collision rate on the MESH self-organizing network routing switching delay during the monitoring node data collection process. The monitoring node signal collision rate indicates the probability of conflict when multiple monitoring nodes send signals at the same time in a wireless communication network. The monitoring node optimization means adjusting the monitoring node transmission power and the monitoring node moving distance score to reduce the degree of delay of the monitoring node signal collision rate on the real-time passenger flow image analysis.

[0026] Step 2: Monitor the node signal collision status of the monitoring nodes in the specified area of the MESH network in real time during the signal delay error evaluation period, perform signal delay error evaluation on the node signal collision status based on the node signal collision data, and determine whether to optimize the routing signal transmission power score. The signal delay error evaluation is used to measure the impact of the transmission interruption caused by the monitoring node signal collision on the routing switching delay of the MESH self-organizing network. The routing signal transmission power score optimization means adjusting the routing signal transmission power to reduce the delay in real-time passenger flow image analysis caused by the monitoring node signal collision.

[0027] Step three: monitor the node link breakage status of the monitoring nodes in the specified area of the MESH network in real time during the link delay error evaluation period, perform link delay error evaluation on the node link breakage status based on the node link breakage data, and determine whether to perform link gain optimization. Link delay error evaluation is used to measure the impact of transmission interruption caused by link breakage during network topology changes on the routing switching delay of the MESH self-organizing network. Link gain optimization means adjusting the antenna gain value and coding gain value to reduce the delay in real-time passenger flow image analysis caused by link breakage.

[0028] like Figure 2 As shown, this is a logical framework diagram of the image quality enhancement method based on MESH self-organizing network provided in an embodiment of the present application. The specific design logic is: first evaluate the data acquisition process, avoid blind optimization, save node optimization resources, enable system resources to be reasonably allocated, improve overall resource utilization efficiency, speed up data acquisition in the network, enable data to reach the target node quickly, improve the stability and efficiency of data acquisition, ensure smooth and accurate data services, and meet the application scenario requirements with real-time requirements.

[0029] like Figure 3As shown, this is a data acquisition delay error evaluation flow chart provided in an embodiment of the present application. The specific design logic is: at the beginning of the process, the data acquisition process is first evaluated, the monitoring node signal collision rate is obtained, and the data acquisition delay error is evaluated based on the obtained monitoring node signal collision rate. Based on the data acquisition delay error evaluation result, it is determined whether to optimize the monitoring node. If so, the monitoring node transmission power and the monitoring node moving distance are adjusted. Otherwise, the data transmission process is evaluated.

[0030] Furthermore, based on the data acquisition delay error evaluation result, it is determined whether to perform monitoring node optimization. The specific process is as follows: based on the obtained monitoring node signal collision rate and the preset monitoring node signal collision rate in the database, it is determined whether there is a monitoring node optimization requirement: if there is a monitoring node optimization requirement, that is, the obtained monitoring node signal collision rate is not less than the preset monitoring node signal collision rate, then the data acquisition delay error evaluation result is determined as data acquisition failure and monitoring node optimization is performed. The monitoring node signal collision rate represents the probability that multiple monitoring nodes in a specified area in the MESH network send signals simultaneously, resulting in signal collisions. In wireless communication protocols (such as IEEE 802.11), nodes can identify signal collisions through the physical layer collision detection mechanism (such as CSMA / CA); if there is no monitoring node optimization requirement, that is, the obtained monitoring node signal collision rate is less than the preset monitoring node signal collision rate, then the data acquisition delay error evaluation result is determined as data acquisition qualification and a node status monitoring instruction for the communication transmission phase is sent. The node status monitoring instruction is used to monitor the node signal collision status and node link breakage status of the monitoring nodes in the MESH network in real time during the communication transmission phase.

[0031] Among them, the specific steps of monitoring node optimization are: taking the sum and average results of the acquired monitoring node signal collision rate deviation and the monitoring node overlap deviation as the monitoring node transmission power adjustment value to dynamically adjust the monitoring node transmission power, the monitoring node signal collision rate deviation represents the difference between the monitoring node signal collision rate acquired at the end of the data collection period and the preset monitoring node signal collision rate, the monitoring node overlap deviation represents the difference between the monitoring node overlap acquired at the end of the data collection period and the preset monitoring node overlap, the monitoring node overlap represents the degree of spatial overlap of the coverage of multiple monitoring nodes in a specified area in the MESH network, and is usually obtained by simulating the node coverage using a network simulation tool (such as NS-3, OMNeT++); if the monitoring node signal collision rate acquired again after one monitoring node overlap optimization is less than the preset monitoring node signal collision rate, the monitoring node overlap optimization is completed and the node status monitoring instruction of the communication transmission phase is sent, otherwise the monitoring node moving distance score optimization is performed.

[0032] The specific steps of optimizing the monitoring node moving distance score are as follows: taking the sum and average of the monitoring node signal collision rate deviation and the monitoring node moving distance score deviation re-obtained after the monitoring node overlap optimization as the monitoring node moving distance adjustment value to dynamically adjust the moving distance of the monitoring node. The monitoring node moving distance score deviation represents the difference between the corresponding monitoring node moving distance score at the end of the data acquisition delay error evaluation period and the preset monitoring node moving distance score. The node moving distance score represents the ratio of the corresponding node moving distance at the end of the data acquisition delay error evaluation period to the preset node moving distance. The node moving distance is obtained by monitoring the distance sensor. If the monitoring node signal collision rate re-obtained after the monitoring node moving distance score optimization is less than the preset monitoring node signal collision rate, the monitoring node optimization is completed and the node status monitoring instruction of the communication transmission phase is sent, otherwise a monitoring node data acquisition collision alarm is issued.

[0033] It should be understood that if the monitoring node signal collision rate reacquired after a monitoring node overlap optimization is not less than the preset monitoring node signal collision rate, it indicates that the monitoring node optimization includes a monitoring node overlap optimization and a monitoring node moving distance score optimization. If the monitoring node signal collision rate reacquired after a monitoring node overlap optimization is less than the preset monitoring node signal collision rate, it indicates that the monitoring node optimization refers to a monitoring node overlap optimization.

[0034] In this embodiment, the acquired monitoring node transmission power adjustment value and monitoring node moving distance adjustment value are used as the input of the PID (Proportional-Integral-Derivative) control algorithm in the monitoring node controller. Through the coordinated action of the three links of proportion, integration and differentiation, the transmission power adjustment result and the moving distance adjustment result are output, thereby reducing the signal coverage range, reducing the signal contention phenomenon of the monitoring node, and effectively improving the balance of the spatial layout of the monitoring node; the preset monitoring node signal collision rate is represented by the result of summing and averaging the corresponding monitoring node signal collision rates at the end of the historical monitoring node data collection period in the database, and the preset node moving distance is represented by the result of summing and averaging the corresponding node moving distances at the end of the historical monitoring node data collection period in the database.

[0035] This example uses dynamic calculation of signal collision rate deviation to reflect the current network conflict status in real time, thereby improving real-time performance, reducing overlap in node coverage areas, avoiding conflicts caused by simultaneous transmission of multiple nodes, and improving transmission efficiency. This dynamic adjustment mechanism can quickly respond to changes in the current network status, thereby ensuring the quality and integrity of data acquisition. This "real-time monitoring-instant adjustment" mechanism avoids long-term transmission congestion caused by accumulated conflicts, ensuring that data is transmitted in a short time, meeting the real-time system's requirements for rapid response.

[0036] like Figure 4 As shown, it is a signal delay error evaluation flow chart provided in an embodiment of the present application. The specific design logic is: at the beginning of the process, the data transmission process is first evaluated, the node signal collision data is obtained, and the signal delay error is evaluated based on the obtained node signal collision data. Based on the signal delay error evaluation result, it is determined whether to optimize the signal transmission power. If so, the routing signal transmission power is adjusted. Otherwise, the time alignment is obtained and a judgment is made to ensure that the subsequent link delay error evaluation is performed in a time synchronization state.

[0037] Furthermore, a signal delay error evaluation is performed on the node signal collision status based on the node signal collision data. The specific process is as follows: at the end of the signal delay error evaluation period, the acquired node signal collision data is compared with the node signal collision data preset in the database for difference, and at the same time, each difference comparison result is compensated in combination with the node signal collision data compensation value, and coupled processing is performed to obtain a signal delay error index. The signal delay error index represents the quantitative data of the delay degree of the signal collision data for the real-time passenger flow image analysis. The node signal collision data includes the route reconstruction time, the communication channel access time, and the data packet retransmission time. Time consumption, the preset node signal collision data represents the preset route reconstruction time consumption, communication channel access time consumption and data packet retransmission time consumption. The route reconstruction time consumption and communication channel access time consumption are monitored by the built-in timer of the monitoring node. The data packet retransmission time consumption is calculated by capturing the data packets sent and received by the node through the network packet capture tool deployed in the network. The signal delay error index represents the coupling processing result of the route reconstruction time consumption index, the communication channel access time consumption index and the data packet retransmission time consumption index. The node signal collision data compensation value includes the route reconstruction time consumption compensation value, the communication channel access time consumption compensation value and the data packet retransmission time consumption compensation value.

[0038] The specific limiting expression of the route reconstruction time index NCI1 is: Where NCI1 represents the route reconstruction time index corresponding to the monitoring node at the end of the signal delay error evaluation period, ρ1 represents the route reconstruction time compensation value, X1 represents the route reconstruction time corresponding to the monitoring node at the end of the signal delay error evaluation period, and X10 represents the preset route reconstruction time. The preset route reconstruction time is the result obtained by accumulating and summing the historical route reconstruction time corresponding to the end of the historical signal delay error evaluation period, and then calculating the average of the accumulated sums.

[0039] The specific limiting expression of the communication channel access time consumption index NCI2 is: Wherein, NCI2 represents the communication channel access time index corresponding to the monitoring node at the end of the signal delay error evaluation period, ρ2 represents the communication channel access time compensation value, X2 represents the communication channel access time corresponding to the monitoring node at the end of the signal delay error evaluation period, and X20 represents the preset communication channel access time. The preset communication channel access time is the result obtained by accumulating and summing the historical communication channel access times corresponding to the end of the historical signal delay error evaluation period, and then calculating the average value of the accumulated sum.

[0040] The specific limiting expression of the packet retransmission time index NCI3 is: Where NCI3 represents the corresponding packet retransmission time index of the monitoring node at the end of the signal delay error evaluation period, ρ3 represents the packet retransmission time compensation value, X3 represents the corresponding packet retransmission time of the monitoring node at the end of the signal delay error evaluation period, and X30 represents the preset packet retransmission time. The preset packet retransmission time is the result obtained by accumulating the retransmission time of each historical packet at the end of the historical signal delay error evaluation period and calculating the average of the accumulated sums.

[0041] The specific limiting expression of the signal delay error index NCI is: NCI=NCI1+NCI2+NCI3, where NCI represents the signal delay error index corresponding to the monitoring node at the end of the signal delay error evaluation period.

[0042] In this example, preset compensation values that are highly correlated with the signal delay error index are pre-stored in the database. Clear mapping rules are established between these compensation values and the route reconstruction time, communication channel access time, and data packet retransmission time in accordance with business requirements and system characteristics. This mapping can be a one-to-one correspondence between a single parameter and a compensation value, or a combination of multiple parameters that work together to correspond to a single compensation value. For example, when evaluating the signal delay error, the system can collect the actual values of the route reconstruction time, communication channel access time, and data packet retransmission time in real time, and call the preset mapping rules to accurately match and extract the corresponding compensation values.

[0043] Crucially, to ensure a smooth and unimpeded evaluation process and comparable evaluation results across different scenarios, this example uniformly limits the ranges of the route reconstruction time compensation, communication channel access time compensation, and packet retransmission time compensation values. These values are all controlled within the range of 0 to 1, and their sum always remains 1.

[0044] In this embodiment, the signal delay error index increases with the increase of route reconstruction time, communication channel access time and data packet retransmission time. Among them, the increase in route reconstruction time will lead to unstable network topology, aggravate monitoring node collision and communication channel access delay, increase communication channel access time and retransmission time, which may lead to increased transmission delay of routing protocol messages, thereby extending the route reconstruction time. The route reconstruction time is increased. After the data packet is sent, if the confirmation is not received within the specified time, the sender will trigger retransmission. When the channel access time increases, the sending delay of the data packet will be directly increased, resulting in timeout retransmission and increased data packet retransmission time.

[0045] This example comprehensively considers the mutual influence between the signal delay error index and the route reconstruction time, communication channel access time, and packet retransmission time to accurately locate the root cause of the problem. By optimizing the route reconstruction strategy, network optimization efficiency is improved, communication channel access and packet transmission processes are optimized, monitoring node collisions and communication delays are reduced, route reconstruction time is shortened, and the packet transmission success rate is increased.

[0046] Furthermore, based on the signal delay error evaluation result, it is determined whether to optimize the routing signal transmission power score. The specific process is: based on the obtained signal delay error index and the signal delay error index preset in the database, it is determined whether there is a need for optimization of the routing signal transmission power score: if there is a need for optimization of the routing signal transmission power score, that is, the obtained signal delay error index is greater than the signal delay error index preset in the database, then the signal delay error evaluation result is determined as unqualified routing signal and the routing signal transmission power score optimization is performed; if there is no need for optimization of the routing signal transmission power score, that is, the obtained signal delay error index is not greater than the signal delay error index preset in the database, then the signal delay error evaluation result is determined as qualified routing signal and the link delay error evaluation is performed.

[0047] Among them, the routing signal transmission power score optimization specifically includes the following steps: taking the sum and average of the obtained signal delay error index deviation and the routing signal transmission power score deviation as the routing signal transmission power score adjustment amount to reduce signal collisions between monitoring nodes and thereby reduce the communication interruption rate; the signal delay error index deviation is used to measure the degree of difference between the obtained signal delay error index and the signal delay error index preset in the database, that is, the difference between the obtained signal delay error index and the signal delay error index preset in the database; the routing signal transmission power score deviation represents the difference between the preset routing signal transmission power score and the routing signal transmission power score at the end of the signal delay error evaluation period; the routing signal transmission power score represents the ratio of the routing transmission power corresponding to the end of the signal delay error evaluation period to the preset routing transmission power; the routing transmission power is obtained by monitoring the power sensor; if the signal delay error index re-obtained after a routing signal transmission power score optimization is not greater than the preset signal delay error index, the routing signal transmission power score optimization is completed and the link delay error evaluation is performed; otherwise, a monitoring node signal transmission alarm is issued.

[0048] In this example, the PID control algorithm in the routing controller takes the obtained routing signal transmission power fraction adjustment amount as input, and dynamically adjusts the routing signal transmission power through the coordinated action of the three links of proportion, integration, and differentiation, and then outputs the routing signal transmission power adjustment result, thereby reducing signal collisions between nodes and reducing the communication interruption rate; the preset signal delay error index is represented by the sum and average of the corresponding preprocessing control efficiency index at the end of the historical signal delay error evaluation period in the database, and the preset routing signal transmission power is represented by the sum and average of the corresponding routing signal transmission power at the end of the historical signal delay error evaluation period in the database.

[0049] This example compares the obtained signal delay error index with the preset value in the database to promptly determine whether the routing signal is qualified. If it is unqualified, the optimization process is initiated to prevent the signal delay problem from continuing to deteriorate. It ensures a quick response in the event of signal interruption caused by signal collision, enables the network to adapt to communication environment and load changes, reduces data retransmission and waiting time, thereby ensuring the continuity and stability of data transmission and improving the real-time performance of data transmission.

[0050] like Figure 5As shown, it is a link delay error evaluation flow chart provided in an embodiment of the present application. The specific design logic is: at the beginning of the process, the data transmission process is first evaluated to obtain the time alignment, and based on the time alignment, it is determined whether to optimize the monitoring node movement speed score. If so, the monitoring node movement speed is adjusted, otherwise the node link breakage data is obtained, and the link delay error is evaluated based on the obtained node link breakage data. Based on the link delay error evaluation result, it is determined whether to optimize the link gain. If so, the antenna gain value and the coding gain value are adjusted, otherwise the process is completed and ended.

[0051] Furthermore, a link delay error evaluation is performed on the node link breakage status based on the node link breakage data. The specific process is: based on the acquired time alignment of the monitoring node and the preset time alignment in the database, it is determined whether there is a need to optimize the monitoring node's mobile speed score: if there is a need to optimize the monitoring node's mobile speed score, that is, the acquired time alignment is greater than the preset time alignment in the database, it is determined that the time synchronization is unqualified and a link delay error evaluation instruction is sent; if there is no need to optimize the monitoring node's mobile speed score, that is, the acquired time alignment is not greater than the preset time alignment in the database, it is determined that the time synchronization is qualified and the node link breakage data is acquired.

[0052] Among them, the monitoring node mobile speed score is optimized, and the specific steps are: mapping the time alignment deviation in the database to obtain the monitoring node mobile speed score adjustment value to reduce the time synchronization error caused by the mismatch of the monitoring node speed, thereby improving the time synchronization degree of the monitoring node, the monitoring node mobile speed score represents the ratio of the corresponding monitoring node mobile speed at the end of the link delay error evaluation period to the preset monitoring node mobile speed, the preset time alignment is represented by the sum and average of the time alignments corresponding to the end of the historical link delay error evaluation period in the database, the preset monitoring node mobile speed is represented by the sum and average of the monitoring node mobile speeds corresponding to the end of the historical link delay error evaluation period in the database, the time alignment deviation represents the difference between the time alignment obtained at the end of the link delay error evaluation period and the preset time alignment, and the monitoring node mobile speed score deviation represents the absolute value of the difference between the monitoring node mobile speed score obtained at the end of the link delay error evaluation period and the preset monitoring node mobile speed score.

[0053] At the end of the link delay error evaluation period, the obtained node link break data is compared with the node link break data preset in the database for difference. At the same time, the difference comparison results are compensated and coupled with the node link break data compensation value to obtain a link delay error index. The link delay error index represents the quantitative data of the delay degree of the node link break data for the real-time passenger flow image analysis. The node link break data includes the link break frequency, the link status update duration and the time consumption of triggering link repair. The preset node link break data includes the preset link break frequency, the link status update duration and the time consumption of triggering link repair. The link break frequency is monitored by a network analyzer, and the link status update duration and the time consumption of triggering link repair are monitored by the built-in timer of the monitoring node. The link delay error index represents the coupling processing result of the link break frequency index, the link status update duration index and the time consumption index of triggering link repair. The node link break data compensation value includes the link break frequency compensation value, the link status update duration compensation value and the time consumption compensation value of triggering link repair.

[0054] Specifically, the specific limiting expression of the link disconnection frequency index LDI1 is: Where LDI1 represents the link break frequency index corresponding to the monitoring node at the end of the link delay error evaluation period, σ1 represents the link break frequency compensation value, Y1 represents the link break frequency corresponding to the monitoring node at the end of the link delay error evaluation period, and Y10 represents the preset link break frequency. The preset link break frequency is the result obtained by accumulating and averaging the historical link break frequencies corresponding to the end of the historical link delay error evaluation period.

[0055] The specific limiting expression of the link state update duration index LDI2 is: Where LDI2 represents the link state update duration index corresponding to the monitoring node at the end of the link delay error evaluation period, σ2 represents the link state update duration compensation value, Y2 represents the link state update duration corresponding to the monitoring node at the end of the link delay error evaluation period, and Y20 represents the preset link state update duration. The preset link state update duration is the result obtained by accumulating and summing the historical link state update durations corresponding to the end of the historical link delay error evaluation period and then calculating the average of the accumulated sums.

[0056] The specific limiting expression for triggering the link repair time index LDI3 is: Where LDI3 represents the trigger link repair time index corresponding to the monitoring node at the end of the link delay error evaluation period, σ3 represents the trigger link repair time compensation value, Y3 represents the trigger link repair time corresponding to the monitoring node at the end of the link delay error evaluation period, and Y30 represents the preset trigger link repair time. The preset trigger link repair time is the result obtained by accumulating and averaging the historical trigger link repair time corresponding to the end of the historical link delay error evaluation period.

[0057] The specific limiting expression of the link delay error index LDI is: LDI=LDI1+LDI2+LDI3, where LDI represents the link delay error index corresponding to the monitoring node at the end of the link delay error evaluation period.

[0058] The database pre-stores preset compensation values that are highly correlated with the link delay error index. Clear mapping rules are established between these compensation values and the link break frequency, link status update duration, and time taken to trigger link repair, based on business requirements and system characteristics. This mapping can be a one-to-one correspondence between a single parameter and a compensation value, or a combination of multiple parameters that work together to correspond to a single compensation value. For example, when evaluating link delay errors, the system can collect the actual values of the link break frequency, link status update duration, and time taken to trigger link repair in real time, and call the preset mapping rules to accurately match and extract the corresponding compensation values.

[0059] Crucially, to ensure a smooth and unimpeded evaluation process and comparable evaluation results across different scenarios, this example uniformly limits the ranges of the link-down frequency compensation, link-status-update duration compensation, and link-repair triggering time compensation values. These values are all controlled within the range of 0 to 1, and their sum always remains 1.

[0060] In this embodiment, the link delay error index increases with the increase of link break frequency, link status update duration and time consumption for triggering link repair. Specifically, when the link status update period increases, in order to ensure timely synchronization of the link status, the control message overhead increases, which may aggravate the congestion of the communication channel and increase the time consumption for triggering link repair. When the update period decreases, the monitoring node can quickly detect the link break, trigger the repair starting point early, and reduce the overall repair time. If the link breaks frequently and the link break frequency increases, the monitoring node needs to obtain the latest topology information faster to avoid using the broken path. The link status update period decreases, multiple link repair requests occur simultaneously, the routing protocol is delayed due to resource preemption, and the time consumption for triggering link repair increases.

[0061] This example clarifies the complex relationship between the link state update period and the link delay error index, communication channel congestion, and the time it takes to trigger link repair. Based on the actual network operation status, it accurately adjusts the link state update period, speeds up the monitoring node's acquisition of the latest topology information, avoids the use of broken paths, reduces message overhead and link repair resource usage, and improves network resource utilization.

[0062] Furthermore, based on the link delay error evaluation result, it is determined whether to perform link gain optimization. The specific process is as follows: based on the obtained link delay error index and the preset link delay error index in the database, it is determined whether there is a link gain optimization requirement: if there is a link gain optimization requirement, that is, the obtained link delay error index is greater than the preset link delay error index, then the signal delay error evaluation result is determined to be link communication unqualified and link gain optimization is performed; if there is no link gain optimization requirement, that is, the obtained link delay error index is not greater than the preset link delay error index, then the signal delay error evaluation result is determined to be link communication qualified and a node status monitoring instruction for the next communication transmission stage is sent.

[0063] Among them, the specific process of link gain optimization is: based on the obtained link break delay error index deviation, the antenna gain value is mapped in the database to reduce the link break probability caused by signal attenuation, that is, antenna gain optimization, thereby shortening the repair time after the break. The link break delay error index deviation represents the difference between the obtained link break delay error index and the preset link break delay error index; at the same time, based on the obtained antenna gain deviation, the coding gain value is mapped in the database to improve the signal error resistance capability, that is, coding gain value optimization, thereby reducing the link break probability caused by error accumulation; if the link delay error index re-obtained after one link gain optimization is not greater than the preset link delay error index, the link gain optimization is completed and the node status monitoring instruction for the next communication transmission stage is sent, otherwise a transmission link break alarm is issued. One link gain optimization includes one antenna gain optimization and one coding gain value optimization.

[0064] In this embodiment, the antenna gain value adjustment amount and the coding gain value adjustment amount are input by the least squares method in the linear regression algorithm, and the antenna gain value and the coding gain value are dynamically adjusted according to the linear relationship equation set in the linear regression algorithm to output the antenna gain value adjustment result and the coding gain value adjustment result, thereby accelerating the network node to perceive the link status change and reroute, thereby improving the network recovery stability; the preset link delay error index is represented by the result of summing and averaging the corresponding link delay error indices at the end of the historical link delay error evaluation period in the database.

[0065] This example optimizes the link in a targeted manner, enabling signals to quickly reach the receiving end. It also monitors link status in real time and promptly adjusts link parameters to ensure stable link operation during data transmission and enhance signal anti-interference capabilities. After link gain is increased, it accelerates the efficiency of network nodes sensing link status changes and rerouting, improving network recovery stability, reducing link disruptions and delays, and thereby increasing the accuracy of data acquisition in real-time passenger flow image analysis.

[0066] like Figure 6 As shown, it is a structural schematic diagram of the image quality enhancement system based on the MESH self-organizing network provided by an embodiment of the present application. The image quality enhancement system based on the MESH self-organizing network provided by an embodiment of the present application includes: a data acquisition delay error evaluation module, a signal delay error evaluation module and a link delay error evaluation module; wherein, the data acquisition delay error evaluation module is used to perform data acquisition delay error evaluation on the passenger flow image data acquisition process based on the monitoring node signal collision rate, and at the same time determine whether to perform monitoring node optimization. If so, perform signal delay error evaluation, otherwise perform monitoring node optimization; the signal delay error evaluation module is used to monitor the node signal collision status of the monitoring nodes in the specified area of the MESH network in real time within the signal delay error evaluation period, perform signal delay error evaluation on the node signal collision status based on the node signal collision data, and at the same time determine whether to perform routing signal transmission power score optimization; the link delay error evaluation module is used to monitor the node link breakage status of the monitoring nodes in the specified area of the MESH network in real time within the link delay error evaluation period, perform link delay error evaluation on the node link breakage status based on the node link breakage data, and at the same time determine whether to perform link gain optimization.

[0067] In this embodiment, the three modules are closely linked to monitor and optimize the entire process of multi-hop transmission of node image data, forming a complete feedback optimization closed loop, effectively reducing the delay caused by MESH self-organizing network routing switching, and improving the transmission efficiency and quality of real-time passenger flow image data at smart city traffic intersections, thereby ensuring the accuracy of passenger flow image analysis.

[0068] In summary, the embodiment of the present application evaluates the data acquisition delay error by monitoring the node signal collision rate to determine whether to optimize the detection node, reduce data errors, and ensure the quality of data acquisition. Then, the signal delay error is evaluated through the signal collision data to determine whether to optimize the routing signal transmission power score, which can reduce signal overlap and interference and reduce signal delay. Finally, the link delay error is evaluated through the link breakage data to determine whether to optimize the link gain, thereby reducing link breakage caused by signal attenuation or external interference and improving the reliability of the link, thereby achieving the effect of improving the accuracy of real-time passenger flow image analysis at smart city traffic intersections.

[0069] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0071] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0073] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0074] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. An image quality enhancement method based on a MESH self-organizing network is characterized in that: The following steps are involved: Step 1: Based on the monitoring node signal collision rate, the data collection delay error of the passenger flow image data collection process is evaluated, and at the same time, it is determined whether to perform monitoring node optimization. If so, the signal delay error evaluation is performed; otherwise, the monitoring node optimization is performed. The monitoring node optimization means adjusting the monitoring node transmission power and the monitoring node moving distance score to reduce the delay of the monitoring node signal collision rate on the real-time passenger flow image analysis; Step 2: Real-time monitoring of the node signal collision status of the monitoring nodes in the specified area of the MESH network within the signal delay error evaluation period, performing signal delay error evaluation on the node signal collision status based on the node signal collision data, and determining whether to optimize the routing signal transmission power score; Step 3: Monitor the node link breakage status of the monitoring nodes in the specified area of the MESH network in real time during the link delay error evaluation period, perform link delay error evaluation on the node link breakage status based on the node link breakage data, and determine whether to perform link gain optimization.

2. The image quality enhancement method based on MESH ad hoc network according to claim 1, characterized in that: The specific process of determining whether to optimize the monitoring node is as follows: Based on the obtained monitoring node signal collision rate and the preset monitoring node signal collision rate in the database, it is determined whether there is a need for monitoring node optimization. If so, the data acquisition delay error evaluation result is judged as data acquisition failure and the monitoring node optimization is performed. Otherwise, the data acquisition delay error evaluation result is judged as data acquisition qualification and the node status monitoring instruction of the communication transmission stage is sent; The monitoring node optimization specifically includes the following steps: The sum and average of the obtained monitoring node signal collision rate deviation and monitoring node overlap deviation is used as the monitoring node transmission power adjustment value to dynamically adjust the monitoring node transmission power; If the monitoring node signal collision rate reacquired after one monitoring node overlap optimization is less than the preset monitoring node signal collision rate, the monitoring node overlap optimization is completed and the node status monitoring instruction of the communication transmission phase is sent, otherwise the monitoring node moving distance score optimization is performed.

3. The image quality enhancement method based on MESH self-organizing network as claimed in claim 2, characterized in that: The monitoring node moving distance score optimization, the specific steps are: The sum and average of the monitoring node signal collision rate deviation and the monitoring node moving distance score deviation obtained after the optimization of the monitoring node overlap is used as the monitoring node moving distance adjustment value to improve the balance of the monitoring node spatial layout; If the monitoring node signal collision rate reacquired after the optimization of the monitoring node moving distance score is less than the preset monitoring node signal collision rate, the monitoring node optimization is completed and the node status monitoring instruction of the communication transmission phase is sent, otherwise a monitoring node data collection collision alarm is issued.

4. The image quality enhancement method based on MESH self-organizing network according to claim 1, characterized in that: The signal delay error evaluation of the node signal collision state based on the node signal collision data is performed in the following specific process: At the end of the signal delay error evaluation period, the acquired node signal collision data is compared with the node signal collision data preset in the database for difference. At the same time, each difference comparison result is compensated in combination with the node signal collision data compensation value, and coupled processing is performed to obtain a signal delay error index. The node signal collision data includes route reconstruction time, communication channel access time, and data packet retransmission time. The signal delay error index represents the quantitative data of the delay degree of signal collision data for real-time passenger flow image analysis.

5. The image quality enhancement method based on MESH ad hoc network according to claim 4, characterized in that: The specific process of determining whether to optimize the routing signal transmission power score is as follows: Determine whether there is a need to optimize the routing signal transmission power score based on the obtained signal delay error index and the signal delay error index preset in the database: If there is a need to optimize the routing signal transmission power score, the signal delay error evaluation result is determined to be unqualified for the routing signal and the routing signal transmission power score is optimized; If there is no requirement for optimizing the transmission power fraction of the routing signal, the signal delay error evaluation result is determined to be qualified for the routing signal and a link delay error evaluation is performed.

6. The image quality enhancement method based on MESH ad hoc network according to claim 5, characterized in that: The routing signal transmission power fraction optimization specifically comprises the following steps: The sum and average of the obtained signal delay error index deviation and the routing signal transmission power fraction deviation is used as the routing signal transmission power fraction adjustment amount to reduce signal collisions between monitoring nodes; If the signal delay error index re-obtained after the optimization of the routing signal transmission power score is not greater than the preset signal delay error index, the routing signal transmission power score optimization is completed and the link delay error evaluation is performed, otherwise a monitoring node signal transmission alarm is issued.

7. The image quality enhancement method based on MESH ad hoc network according to claim 1, characterized in that: The link delay error evaluation of the node link break state based on the node link break data is performed in the following specific process: Determine whether there is a need to optimize the moving speed score of the monitoring node based on the time alignment of the monitoring node obtained and the time alignment preset in the database: If there is a need to optimize the moving speed score of the monitoring node, it is determined that the time synchronization is unqualified and a link delay error evaluation instruction is sent; If there is no need to optimize the monitoring node's mobile speed score, the time synchronization is determined to be qualified and the node link disconnection data is obtained; The monitoring node movement speed score optimization, the specific steps are: The time alignment deviation and the monitoring node moving speed score deviation are mapped in the database to obtain the monitoring node moving speed adjustment value to reduce the time synchronization error caused by the mismatch of the monitoring node speed; At the end of the link delay error evaluation period, the acquired node link breakage data is compared with the node link breakage data preset in the database for difference. At the same time, each difference comparison result is compensated in combination with the node link breakage data compensation value, and coupled processing is performed to obtain a link delay error index. The link delay error index represents the quantitative data of the delay degree of the node link breakage data for the real-time passenger flow image analysis.

8. The image quality enhancement method based on MESH ad hoc network according to claim 7, characterized in that: The specific process of determining whether to perform link gain optimization is as follows: Determine whether link gain optimization is required based on the obtained link delay error index and the link delay error index preset in the database: If there is a need for link gain optimization, the signal delay error evaluation result is judged as link communication unqualified and link gain optimization is performed; If there is no link gain optimization requirement, the signal delay error evaluation result is determined to be link communication qualified and a node status monitoring instruction for the next communication transmission phase is sent.

9. The image quality enhancement method based on MESH ad hoc network according to claim 8, characterized in that: The link gain optimization process is as follows: Based on the obtained link break delay error index deviation, the antenna gain value is mapped in the database to reduce the link break probability caused by signal attenuation; At the same time, the obtained antenna gain deviation is mapped in the database to obtain the coding gain value to improve the signal error resistance capability; If the link delay error index re-obtained after one link gain optimization is not greater than the preset link delay error index, the link gain optimization is completed and the node status monitoring instruction for the next communication transmission stage is sent, otherwise a transmission link break alarm is issued. The one link gain optimization includes one antenna gain optimization and one coding gain value optimization.

10. A system using the image quality enhancement method based on MESH ad hoc network according to any one of claims 1 to 9, characterized in that: include: Data acquisition delay error assessment module, signal delay error assessment module and link delay error assessment module; The data acquisition delay error evaluation module is used to evaluate the data acquisition delay error of the passenger flow image data acquisition process based on the monitoring node signal collision rate, and to determine whether to perform monitoring node optimization. If so, the signal delay error evaluation is performed, otherwise the monitoring node optimization is performed. The signal delay error evaluation module is used to monitor the node signal collision status of the monitoring nodes in the specified area of the MESH network in real time within the signal delay error evaluation period, perform signal delay error evaluation on the node signal collision status based on the node signal collision data, and determine whether to optimize the routing signal transmission power score; The link delay error evaluation module is used to monitor the node link break status of the monitoring nodes in the specified area of the MESH network in real time within the link delay error evaluation period, perform link delay error evaluation on the node link break status based on the node link break data, and determine whether to perform link gain optimization.

Images