Processing method and related device based on charging integrated cloud warehouse intelligent kiosk
By employing a multimodal fusion decision-making mechanism, and utilizing vehicle identity features obtained from vehicle license plates, external image features, and signal recognition channels, the accuracy and reliability issues of vehicle identity authentication in complex environments are resolved, achieving higher authentication accuracy and system adaptability.
Patent Information
- Application Number
- CN202511619333.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-06
- Publication Date
- 2026-02-17
AI Technical Summary
Existing vehicle identification methods have low accuracy and reliability in complex environments, which can easily lead to authentication failure or misidentification.
A multimodal fusion decision mechanism is adopted to obtain the license plate and shape image features and their confidence levels of vehicles through roadside units, and to obtain vehicle identity features and their signal quality confidence levels by combining them with the signal recognition channel. The multi-feature fusion decision mechanism is then used for identity authentication.
It significantly improves the accuracy of vehicle identity authentication and the system's adaptability in complex environments, ensuring the robustness and reliability of authentication results.
Smart Images
Figure CN121545360A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of data processing, and in particular to a processing method and related apparatus based on a smart kiosk with integrated toll collection cloud warehouse. Background Technology
[0002] With the rapid development of intelligent transportation systems, cloud-based smart kiosk systems are widely used in areas such as road toll collection and vehicle management. Existing vehicle identification methods typically rely on a single recognition technology, such as license plate recognition or radio frequency signal recognition. However, in complex environments, such as insufficient light or signal interference, the accuracy and reliability of a single recognition method are low, easily leading to authentication failure or misidentification. Summary of the Invention
[0003] This application provides a processing method and related apparatus based on a smart kiosk with integrated toll collection cloud warehouse to improve the above-mentioned problems.
[0004] To achieve the above objectives, this application adopts the following technical solution: In a first aspect, this application proposes a processing method based on a cloud-based smart kiosk with integrated toll collection. The method is applied to a cloud-based smart kiosk system, which includes a roadside unit and a control terminal. The method is applicable to the control terminal and includes: Based on the image data acquired by the roadside unit, the first image feature and the second image feature corresponding to the approaching target vehicle are determined. The first image feature is the image feature corresponding to the license plate of the target vehicle, and the second image feature is the image feature corresponding to the shape of the target vehicle. Based on the image data, determine the first confidence level corresponding to the first image feature and the second confidence level corresponding to the second image feature; The first vehicle identity feature corresponding to the target vehicle is obtained based on the signal recognition channel of the roadside unit, and the third confidence level is obtained based on the current signal quality of the signal recognition channel. Based on the first image features, the second image features, and the first vehicle identity features, three corresponding target vehicle features are obtained from the server. If at least two different target vehicles have the same features and the sum of their corresponding confidence scores is greater than the first threshold, then the vehicle identity authentication is considered successful. If the sum of all confidence levels is lower than the second threshold, where the second threshold is less than the first threshold, then the vehicle identity authentication is deemed to have failed.
[0005] In conjunction with the first aspect, in some implementations, the cloud warehouse smart kiosk system further includes a detection unit. If at least two different target vehicles are found to have identical features, and the sum of their corresponding confidence levels is greater than a first threshold, then before determining successful vehicle identity authentication, the following steps are taken: When the roadside unit acquires the second image features, the control detection unit sends excitation electrical measurement waves to the target vehicle and receives feedback information, and determines the second vehicle identity features based on the feedback information; Obtain the target vehicle feature corresponding to the first vehicle identity feature from the server, as well as multiple historical second vehicle identity features corresponding to the target vehicle feature; Based on multiple historical second vehicle identity features and second vehicle identity features, determine the fourth confidence level corresponding to the second vehicle identity features; Based on the second vehicle identity features, obtain the features of a target vehicle.
[0006] In conjunction with the first aspect, in some embodiments, based on image data acquired by the roadside unit, a first image feature and a second image feature corresponding to the approaching target vehicle are determined, wherein the first image feature is the image feature corresponding to the license plate of the target vehicle, and the second image feature is the image feature corresponding to the shape of the target vehicle, including: At a preset location, a target image corresponding to the target vehicle is acquired based on a roadside unit, and the target image is used as a second image feature. Based on image data, determine a first confidence level corresponding to a first image feature and a second confidence level corresponding to a second image feature, including: Multiple historical target images are obtained from the server, and a second confidence level is determined based on the multiple historical target images and the target image.
[0007] In conjunction with the first aspect, in some implementations, when the roadside unit acquires the second image features, the control detection unit sends excitation electrical measurement waves to the target vehicle and receives feedback information, and determines the second vehicle identification features based on the feedback information, including: When the roadside unit acquires the target image, it simultaneously controls the detection unit to send excitation electrical measurement waves to the target vehicle and obtain feedback information, and determines the second vehicle's identity features based on the feedback information.
[0008] In conjunction with the first aspect, in some implementations, when the roadside unit acquires the target image, it simultaneously controls the detection unit to send excitation electrical measurement waves to the target vehicle and acquire feedback information, and determines the second vehicle identification characteristics based on the feedback information, including: Based on the roadside unit receiving electromagnetic wave signals reflected by the target vehicle; Based on electromagnetic wave signals, the corresponding spectral and temporal characteristics are obtained; The second vehicle's identity features are determined based on a combination of spectral and temporal features.
[0009] In conjunction with the first aspect, in some implementations, determining a first confidence level corresponding to a first image feature and a second confidence level corresponding to a second image feature based on image data includes: Image data is acquired based on roadside units, and the average sharpness of multiple frames of images in the image data is obtained. The first confidence level is determined based on sharpness, where sharpness is proportional to the first confidence level.
[0010] In conjunction with the first aspect, in some implementations, if at least two different target vehicles are found to have identical features, and the sum of their corresponding confidence scores is greater than a first threshold, then after determining that the vehicle identity authentication is successful, the process includes: The first image feature, the second image feature, and the first vehicle identity feature corresponding to the target vehicle whose vehicle identity authentication was successful are uploaded to the server.
[0011] A second aspect of this invention proposes a processing system based on an integrated cloud-based smart kiosk for toll collection, comprising a roadside unit and a control terminal, the system being configured as follows: Based on the image data acquired by the roadside unit, the first image feature and the second image feature corresponding to the approaching target vehicle are determined. The first image feature is the image feature corresponding to the license plate of the target vehicle, and the second image feature is the image feature corresponding to the shape of the target vehicle. Based on the image data, determine the first confidence level corresponding to the first image feature and the second confidence level corresponding to the second image feature; The first vehicle identity feature corresponding to the target vehicle is obtained based on the signal recognition channel of the roadside unit, and the third confidence level is obtained based on the current signal quality of the signal recognition channel. Based on the first image features, the second image features, and the first vehicle identity features, three corresponding target vehicle features are obtained from the server. If at least two different target vehicles have the same features and the sum of their corresponding confidence scores is greater than the first threshold, then the vehicle identity authentication is considered successful. If the sum of all confidence levels is lower than the second threshold, where the second threshold is less than the first threshold, then the vehicle identity authentication is deemed to have failed.
[0012] In conjunction with the second aspect, in some implementations, the system is configured as follows: The cloud warehouse smart kiosk system also includes a detection unit. If at least two different target vehicles are found to have the same characteristics, and the sum of their corresponding confidence scores is greater than a first threshold, then the vehicle identity authentication is considered successful. This includes the following steps: When the roadside unit acquires the second image features, the control detection unit sends excitation electrical measurement waves to the target vehicle and receives feedback information, and determines the second vehicle identity features based on the feedback information; Obtain the target vehicle feature corresponding to the first vehicle identity feature from the server, as well as multiple historical second vehicle identity features corresponding to the target vehicle feature; Based on multiple historical second vehicle identity features and second vehicle identity features, determine the fourth confidence level corresponding to the second vehicle identity features; Based on the second vehicle identity features, obtain the features of a target vehicle.
[0013] In conjunction with the second aspect, in some implementations, the system is configured as follows: Based on image data acquired from roadside units, a first image feature and a second image feature corresponding to the approaching target vehicle are determined. The first image feature is the image feature corresponding to the target vehicle's license plate, and the second image feature is the image feature corresponding to the target vehicle's overall shape, including: At a preset location, a target image corresponding to the target vehicle is acquired based on a roadside unit, and the target image is used as a second image feature. Based on image data, determine a first confidence level corresponding to a first image feature and a second confidence level corresponding to a second image feature, including: Multiple historical target images are obtained from the server, and a second confidence level is determined based on the multiple historical target images and the target image.
[0014] In conjunction with the second aspect, in some implementations, the system is configured as follows: When the roadside unit acquires the second image features, the control detection unit sends excitation electrical measurement waves to the target vehicle and receives feedback information, and determines the second vehicle identification features based on the feedback information, including: When the roadside unit acquires the target image, it simultaneously controls the detection unit to send excitation electrical measurement waves to the target vehicle and obtain feedback information, and determines the second vehicle's identity features based on the feedback information.
[0015] In conjunction with the second aspect, in some implementations, the system is configured as follows: When the roadside unit acquires the target image, it simultaneously controls the detection unit to send excitation electrical measurement waves to the target vehicle and acquire feedback information. Based on the feedback information, it determines the second vehicle's identity features, including: Based on the roadside unit receiving electromagnetic wave signals reflected by the target vehicle; Based on electromagnetic wave signals, the corresponding spectral and temporal characteristics are obtained; The second vehicle's identity features are determined based on a combination of spectral and temporal features.
[0016] In conjunction with the second aspect, in some implementations, the system is configured as follows: Based on image data, determine a first confidence level corresponding to a first image feature and a second confidence level corresponding to a second image feature, including: Image data is acquired based on roadside units, and the average sharpness of multiple frames of images in the image data is obtained. The first confidence level is determined based on sharpness, where sharpness is proportional to the first confidence level.
[0017] In conjunction with the second aspect, in some implementations, the system is configured as follows: If at least two different target vehicles are found to have identical features, and the sum of their corresponding confidence scores is greater than the first threshold, then the vehicle identity authentication is considered successful, including: The first image feature, the second image feature, and the first vehicle identity feature corresponding to the target vehicle whose vehicle identity authentication was successful are uploaded to the server.
[0018] A third aspect of this invention provides an electronic device, which includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method proposed in the first aspect of the present invention.
[0019] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in the first aspect of the present invention.
[0020] In summary, the above method and apparatus have the following technical effects: This application proposes a processing method and system based on a smart kiosk with integrated toll collection and cloud storage. First, based on image data collected by roadside units, the first image feature of the target vehicle's license plate and the second image feature of its shape are extracted, and their corresponding first and second confidence levels are determined. Simultaneously, a first vehicle identity feature and its third confidence level based on the current signal quality are obtained through a signal recognition channel. Then, these three features are sent to a server for matching to obtain the corresponding three target vehicle features. Finally, a multimodal fusion decision mechanism is adopted: when at least two different target vehicle features match successfully and the sum of their corresponding confidence levels is greater than a first threshold, identity authentication is considered successful; if the sum of all confidence levels is lower than a second threshold, authentication is considered unsuccessful. This method and system, through multi-feature fusion and confidence level evaluation, significantly improves the accuracy of vehicle identity authentication and the system's adaptability in complex environments. Attached Figure Description
[0021] Figure 1 This is a flowchart illustrating a processing method for a smart kiosk based on an integrated cloud warehouse for toll collection, as proposed in an embodiment of this application. Detailed Implementation
[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0023] This application proposes a processing method based on a cloud-based smart kiosk with integrated toll collection. The method is applied to a cloud-based smart kiosk system, which includes a roadside unit and a control terminal. The method is applicable to the control terminal. Please refer to [link to relevant documentation]. Figure 1 This includes the following steps: S101: Based on the image data acquired by the roadside unit, determine the first image feature and the second image feature corresponding to the approaching target vehicle, wherein the first image feature is the image feature corresponding to the license plate of the target vehicle, and the second image feature is the image feature corresponding to the shape of the target vehicle.
[0024] Understandably, when a target vehicle is approaching the cloud warehouse smart kiosk, the system can identify and trigger a detection action. Specifically, in this embodiment, images or video streams of the target vehicle can be continuously or periodically captured by the camera of the roadside unit. Image recognition algorithms, such as deep learning-based target detection models YOLO and SSD, are then used to determine the features to be detected. Specific algorithms have been disclosed in relevant technical documents and are not limited here.
[0025] Understandably, the image features corresponding to a license plate can be either the visual representation of the license plate in an image or the corresponding numbers; this application does not limit the specific features. For example, a high-dimensional, abstract feature vector can be extracted from the license plate region image using a convolutional neural network (CNN). This vector can be viewed as a digital fingerprint of the license plate image. This feature vector is unique and is used to compare with known license plate features stored in a server database to identify the vehicle.
[0026] S102: Based on the image data, determine the first confidence level corresponding to the first image feature and the second confidence level corresponding to the second image feature.
[0027] Understandably, in this application, confidence level is a quantified value that can be set between 0 and 1, or expressed as a percentage, representing the system's degree of certainty regarding its identification or extraction results. By setting the confidence level, the entire system is upgraded from a feature matching system to a weighted decision-making system, thereby making more robust and accurate judgments in complex and ever-changing real-world environments.
[0028] Specifically, in this embodiment, for the first confidence level corresponding to the license plate data, image data can be obtained based on the roadside unit, and the average sharpness of multiple frames of data images in the image data can be obtained. Then, the first confidence level is determined based on the sharpness, wherein the sharpness is proportional to the first confidence level.
[0029] Understandably, image sharpness is highly correlated with the accuracy of license plate recognition. A sharp image is easier to identify correctly, thus having high confidence; a blurry image, due to weather, lens contamination, etc., may be difficult to identify and prone to errors, thus having low confidence. The roadside unit's camera does not take just one photo, but captures multiple images in a short period of time, that is, an image sequence or video stream.
[0030] Sharpness is quantified using specific image processing algorithms. For example, the intensity of edges and contours in an image can be calculated. Sharp images have sharp edges and large gradient values. Alternatively, high-frequency components can be extracted using the Laplacian operator, and their variance can be calculated. The larger the variance, the sharper the image. Specific image processing algorithms are not limited in this application. The sharpness scores of all frames are summed and then divided by the total number of frames to obtain the average sharpness, which is a stable and reliable image quality assessment value representing the overall image quality level during the acquisition process.
[0031] Furthermore, a correspondence between sharpness intervals and confidence levels can be predefined. For example, it could be as follows: Sharpness 0-100 → Confidence 0.3 Resolution 101-200 → Confidence 0.6 Resolution 201-300 → Confidence 0.9 The above method transforms sharpness into a confidence index that the decision-making system can directly use. Furthermore, using multiple images avoids the randomness of a single image. For example, a single frame might be blurred due to momentary jitter or occlusion, but multiple frames provide a more stable and comprehensive evaluation basis.
[0032] For the second confidence level related to vehicle appearance, a target image corresponding to the target vehicle can be acquired based on roadside units at a preset location, and the target image can be used as the second image feature. Then, multiple historical target images are acquired from the server, and the second confidence level is determined based on the multiple historical target images and the target image.
[0033] Understandably, if the current image of the vehicle's shape is very similar to the vehicle's historical records stored on the server, it indicates that the captured image features can well represent the vehicle, and the confidence level is high. Conversely, if the difference is large, it means that the current image may have failed to capture the vehicle's true stable features due to reasons such as angle, occlusion, lighting, or pollution, and the confidence level is low.
[0034] It should be noted that the target image needs to be captured at a preset location, and its secondary image features need to be extracted. Understandably, as before, this step ensures that all images used for comparison are acquired under the same conditions, eliminating the huge variations caused by different angles and distances, making historical images comparable to current images.
[0035] For example, in this embodiment, it is ensured that both the current image and historical images have been converted into high-dimensional feature vectors. The distance between the current feature vector and each historical feature vector is calculated, for example, cosine distance or Euclidean distance. The smaller the distance, the more similar the images are. These distances are aggregated into a comprehensive index, such as the average distance or the minimum distance. Finally, this average distance or minimum distance is mapped to a confidence score. The smaller the comprehensive distance, the higher the consistency between the current vehicle appearance and the historical records, i.e., the higher the second confidence score. Conversely, the larger the comprehensive distance, the more significant the difference between the current appearance and the historical records, i.e., the lower the second confidence score.
[0036] Of course, image matching can also be performed in other ways, which are not limited in this application.
[0037] S103: When the roadside unit acquires the target image, it simultaneously controls the detection unit to send excitation electrical measurement waves to the target vehicle and acquire feedback information, and determines the second vehicle identity features based on the feedback information.
[0038] Understandably, the advantage of electromagnetic wave detection lies in its independence from optical conditions, allowing it to operate normally in adverse weather or low light conditions. The excitation electromagnetic waves transmitted may be radar signals of specific frequencies. When these waves encounter a vehicle, they exhibit unique reflection characteristics due to the vehicle's metallic structure, material composition, and other physical properties. In other words, electromagnetic wave detection can still function normally even in poor lighting conditions, with obscured license plates, or when visual recognition is difficult. Furthermore, triggering electromagnetic wave detection simultaneously with acquiring an image of the vehicle's exterior enables the synchronous acquisition of both visual and non-visual data. This ensures that both data sources originate from the same vehicle at the same time, avoiding data mismatch issues caused by time differences.
[0039] Specifically, the excitation electromagnetic wave can be a beam of radio waves with a specific frequency and waveform actively emitted by the detection unit towards the target vehicle. When this electromagnetic wave encounters the vehicle, it interacts with the vehicle's metal body, plastic parts, glass, and other materials. Some of the wave is reflected back by the vehicle's surface, some is scattered in different directions at various parts of the vehicle's complex shape, or some of the wave's energy is absorbed by the vehicle's materials. The detection unit's antenna receives these reflected / scattered echoes modulated by the vehicle. Ultimately, this information is fused into one or a set of feature vectors, which constitute the second vehicle identification feature. This feature is strongly correlated with the vehicle's physical properties.
[0040] Specifically, in this embodiment, electromagnetic wave signals reflected by the target vehicle can be received by a roadside unit, and then the corresponding spectral and temporal characteristics can be obtained based on the electromagnetic wave signals. The overall shape and size of the vehicle, as well as the reflection intensity at different radial locations, are different. The echo broadening and undulation on the time axis are different for a long, narrow truck and a round sedan. Spectral characteristics describe the distribution of signal energy with frequency. It transforms the signal from the time dimension to the frequency dimension using methods such as Fourier transform.
[0041] The second vehicle's identity features are determined based on a combination of spectral and temporal features.
[0042] For example, different features can be assigned weights, such as a weight of 0.4 for time-domain features and 0.6 for spectral features, or the time-domain feature vector and the spectral feature vector can be concatenated, or they can be directly combined by mapping to a high-dimensional space through a kernel function. The specific method is not limited in this application.
[0043] S104: Based on multiple historical second vehicle identity features and second vehicle identity features, determine the fourth confidence level corresponding to the second vehicle identity features.
[0044] For example, after normalizing the currently acquired electromagnetic features, the system retrieves the vehicle's most recent N (e.g., 5) historical electromagnetic feature records from the server. A modified Euclidean distance algorithm is used to calculate the similarity between the current feature and each historical feature, and finally, the similarity is converted into a confidence score in the 0-1 range.
[0045] S105: Obtain the first vehicle identity feature corresponding to the target vehicle based on the signal recognition channel of the roadside unit, and obtain the third confidence level based on the current signal quality of the signal recognition channel.
[0046] Understandably, the first vehicle identification feature can be the feature fed back by the ETC installed on the vehicle itself, and the specific implementation method is not limited in this application. Signal quality can be achieved through signal-to-noise ratio or other feasible implementation methods, which are not limited in this application. It should be noted that signal quality is directly proportional to the corresponding third confidence level.
[0047] S106: Based on the first image feature, the second image feature, the first vehicle identity feature, and the second vehicle identity feature, respectively, obtain four corresponding target vehicle features from the server.
[0048] Understandably, the target vehicle's characteristics are the registered, standardized vehicle identifiers returned by the server after searching its database based on the aforementioned characteristics. Typically, this is directly the vehicle's unique ID, such as a license plate number string or an internal system ID.
[0049] S107: If at least two different target vehicle features are the same and the sum of the corresponding confidence levels is greater than the first threshold, it is determined that the vehicle identity authentication is successful.
[0050] S108: If the sum of all confidence levels is lower than the second threshold, where the second threshold is less than the first threshold, it is determined that the vehicle identity authentication fails.
[0051] It can be understood that the first threshold is the success threshold. For example, it can be set within the range of 0.85 - 0.95. At the same time, two conditions need to be met: at least two heterogeneous features match (such as electromagnetic features + visual features), and the weighted sum of the corresponding confidence levels exceeds the threshold. As long as there are multiple independent and highly reliable evidences pointing to the same conclusion, it is adopted; conversely, if all evidences have low quality, we reject making a judgment. Exemplarily, if the license plate and the vehicle shape both point to Beijing A12345, this constitutes strong cross - verification. If it is just two pictures taken by the same camera, their independence is much weaker.
[0052] It is a value less than the first threshold, which sets a lower limit for the overall unacceptable quality. This threshold is usually low. It can be understood that this condition is to handle the situation where the quality of all sensor data is extremely poor.
[0053] Optionally, upload the first image feature, the second image feature, and the first vehicle identity feature of the target vehicle for which the vehicle identity authentication is determined to be successful to the server. It can be understood that in this way, it ensures that the entire cloud warehouse intelligent kiosk system is not a static and one - time authentication tool, but a dynamic system that can continuously evolve and become smarter.
[0054] This application proposes a processing method based on a toll - integrated cloud warehouse intelligent kiosk. First, based on the image data collected by the roadside unit, extract the first image feature of the license plate and the second image feature of the vehicle shape of the target vehicle, and determine their respective first confidence level and second confidence level; at the same time, obtain the first vehicle identity feature and its third confidence level based on the current signal quality through the signal recognition channel. Then, send the above three features to the server for matching to obtain the corresponding three target vehicle features. Finally, adopt a multi - modal fusion decision mechanism: when at least two different target vehicle features match successfully and the sum of their corresponding confidence levels is greater than the first threshold, it is determined that the identity authentication is successful; if the sum of all confidence levels is lower than the second threshold, it is determined that the authentication fails. This method significantly improves the accuracy of vehicle identity authentication and the adaptability of the system in complex environments through multiple feature fusion and confidence level evaluation.
[0055] Based on the same inventive concept, the embodiment of this application also proposes a processing system based on a toll - integrated cloud warehouse intelligent kiosk, including a roadside unit and a control terminal. This system is configured as: Based on the image data acquired by the roadside unit, the first image feature and the second image feature corresponding to the approaching target vehicle are determined. The first image feature is the image feature corresponding to the license plate of the target vehicle, and the second image feature is the image feature corresponding to the shape of the target vehicle. Based on the image data, determine the first confidence level corresponding to the first image feature and the second confidence level corresponding to the second image feature; The first vehicle identity feature corresponding to the target vehicle is obtained based on the signal recognition channel of the roadside unit, and the third confidence level is obtained based on the current signal quality of the signal recognition channel. Based on the first image features, the second image features, and the first vehicle identity features, three corresponding target vehicle features are obtained from the server. If at least two different target vehicles have the same features and the sum of their corresponding confidence scores is greater than the first threshold, then the vehicle identity authentication is considered successful. If the sum of all confidence levels is lower than the second threshold, where the second threshold is less than the first threshold, then the vehicle identity authentication is deemed to have failed.
[0056] In some implementations, the system is configured as follows: The cloud warehouse smart kiosk system also includes a detection unit. If at least two different target vehicles are found to have the same characteristics, and the sum of their corresponding confidence scores is greater than a first threshold, then the vehicle identity authentication is considered successful. This includes the following steps: When the roadside unit acquires the second image features, the control detection unit sends excitation electrical measurement waves to the target vehicle and receives feedback information, and determines the second vehicle identity features based on the feedback information; Obtain the target vehicle feature corresponding to the first vehicle identity feature from the server, as well as multiple historical second vehicle identity features corresponding to the target vehicle feature; Based on multiple historical second vehicle identity features and second vehicle identity features, determine the fourth confidence level corresponding to the second vehicle identity features; Based on the second vehicle identity features, obtain the features of a target vehicle.
[0057] In some implementations, the system is configured as follows: Based on image data acquired from roadside units, a first image feature and a second image feature corresponding to the approaching target vehicle are determined. The first image feature is the image feature corresponding to the target vehicle's license plate, and the second image feature is the image feature corresponding to the target vehicle's overall shape, including: At a preset location, a target image corresponding to the target vehicle is acquired based on a roadside unit, and the target image is used as a second image feature. Based on image data, determine a first confidence level corresponding to a first image feature and a second confidence level corresponding to a second image feature, including: Multiple historical target images are obtained from the server, and a second confidence level is determined based on the multiple historical target images and the target image.
[0058] In some implementations, the system is configured as follows: When the roadside unit acquires the second image features, the control detection unit sends excitation electrical measurement waves to the target vehicle and receives feedback information, and determines the second vehicle identification features based on the feedback information, including: When the roadside unit acquires the target image, it simultaneously controls the detection unit to send excitation electrical measurement waves to the target vehicle and obtain feedback information, and determines the second vehicle's identity features based on the feedback information.
[0059] In some implementations, the system is configured as follows: When the roadside unit acquires the target image, it simultaneously controls the detection unit to send excitation electrical measurement waves to the target vehicle and acquire feedback information. Based on the feedback information, it determines the second vehicle's identity features, including: Based on the roadside unit receiving electromagnetic wave signals reflected by the target vehicle; Based on electromagnetic wave signals, the corresponding spectral and temporal characteristics are obtained; The second vehicle's identity features are determined based on a combination of spectral and temporal features.
[0060] In some implementations, the system is configured as follows: Based on image data, determine a first confidence level corresponding to a first image feature and a second confidence level corresponding to a second image feature, including: Image data is acquired based on roadside units, and the average sharpness of multiple frames of images in the image data is obtained. The first confidence level is determined based on sharpness, where sharpness is proportional to the first confidence level.
[0061] In some implementations, the system is configured as follows: If at least two different target vehicles are found to have identical features, and the sum of their corresponding confidence scores is greater than the first threshold, then the vehicle identity authentication is considered successful, including: The first image feature, the second image feature, and the first vehicle identity feature corresponding to the target vehicle whose vehicle identity authentication was successful are uploaded to the server.
[0062] This application proposes a processing system based on a smart kiosk integrated with a toll collection cloud warehouse. First, based on image data collected by roadside units, the system extracts the first image feature of the target vehicle's license plate and the second image feature of its shape, determining their corresponding first and second confidence levels. Simultaneously, it acquires the first vehicle identity feature and its third confidence level based on the current signal quality through a signal recognition channel. Then, these three features are sent to a server for matching to obtain the corresponding three target vehicle features. Finally, a multimodal fusion decision mechanism is employed: if at least two different target vehicle features match successfully and the sum of their corresponding confidence levels is greater than a first threshold, the identity authentication is considered successful; if the sum of all confidence levels is lower than a second threshold, the authentication is considered unsuccessful. This system, through multi-feature fusion and confidence level evaluation, significantly improves the accuracy of vehicle identity authentication and the system's adaptability in complex environments.
[0063] Based on the same inventive concept, embodiments of this application also propose an electronic device, which includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the processing method based on the smart kiosk of the integrated cloud warehouse according to the embodiments of this application.
[0064] Furthermore, to achieve the above objectives, embodiments of this application also propose a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the processing method of the smart kiosk based on the integrated cloud warehouse for toll collection, as described in the embodiments of this application.
[0065] The following is a detailed introduction to the various components of the electronic device: In this context, the processor is the control center of the electronic device. It can be a single processor or a collective term for multiple processing elements. For example, a processor can be one or more central processing units (CPUs), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).
[0066] Alternatively, the processor can perform various functions of the electronic device by running or executing software programs stored in memory and by calling data stored in memory.
[0067] The memory is used to store the software program that executes the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can be referred to the above method embodiment, which will not be repeated here.
[0068] Optionally, the memory can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory can be integrated with the processor or exist independently and coupled to the processor through an interface circuit of an electronic device; the embodiments of the present invention do not specifically limit this.
[0069] A transceiver is used to communicate with network devices or with terminal devices.
[0070] Optionally, the transceiver may include a receiver and a transmitter. The receiver is used to implement the receiving function, and the transmitter is used to implement the sending function.
[0071] Optionally, the transceiver can be integrated with the processor or exist independently and coupled to the processor through the router's interface circuit. This embodiment of the invention does not specifically limit this.
[0072] Furthermore, the technical effects of the electronic device can be referred to the technical effects of the data transmission method in the above method embodiments, and will not be repeated here.
[0073] It should be understood that the processor in the embodiments of the present invention can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.
[0074] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDRSDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DRRAM).
[0075] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. A computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.
[0076] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.
[0077] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.
[0078] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0079] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.
Claims
1. A processing method based on a toll integrated cloud warehouse intelligent kiosk, characterized in that, The method is applied to a cloud warehouse intelligent kiosk system, the cloud warehouse intelligent kiosk system comprises a roadside unit and a control terminal, the method is suitable for the control terminal, comprising: Based on the image data obtained by the roadside unit, the first image feature corresponding to the target vehicle approaching and the second image feature are determined, wherein the first image feature is the image feature corresponding to the license plate of the target vehicle, and the second image feature is the image feature corresponding to the shape of the target vehicle; Based on the image data, the first confidence degree corresponding to the first image feature and the second confidence degree corresponding to the second image feature are determined; Based on the signal recognition channel of the roadside unit, the first vehicle identity feature corresponding to the target vehicle is obtained, and the third confidence degree is obtained based on the current signal quality of the signal recognition channel; Based on the first image feature, the second image feature, and the first vehicle identity feature respectively, three corresponding target vehicle features are obtained from the server; If at least two different target vehicle features are the same and the sum of the corresponding confidence degrees is greater than a first threshold, it is determined that the vehicle identity authentication is successful; If the sum of all the confidence degrees is lower than a second threshold, wherein the second threshold is lower than the first threshold, it is determined that the vehicle identity authentication fails. 2.The processing method of the charging integrated cloud warehouse intelligent kiosk according to claim 1, characterized in that, The cloud warehouse intelligent kiosk system further comprises a detection unit, and before it is determined that the vehicle identity authentication is successful if at least two different target vehicle features are the same and the sum of the corresponding confidence degrees is greater than a first threshold, comprising: When the roadside unit obtains the second image feature, the detection unit is controlled to send an excitation electric wave to the target vehicle and accept feedback information, and a second vehicle identity feature is determined based on the feedback information; The target vehicle feature corresponding to the first vehicle identity feature and a plurality of historical second vehicle identity features corresponding to the target vehicle feature are obtained from the server; Based on a plurality of the historical second vehicle identity features and the second vehicle identity feature, a fourth confidence degree corresponding to the second vehicle identity feature is determined; Based on the second vehicle identity feature, one target vehicle feature is obtained. 3.The processing method of claim 2, wherein, Based on the image data obtained by the roadside unit, the first image feature corresponding to the target vehicle approaching and the second image feature are determined, wherein the first image feature is the image feature corresponding to the license plate of the target vehicle, and the second image feature is the image feature corresponding to the shape of the target vehicle, comprising: At a preset position, a target image corresponding to the target vehicle is obtained based on the roadside unit, and the target image is taken as the second image feature; Based on the image data, the first confidence degree corresponding to the first image feature and the second confidence degree corresponding to the second image feature are determined, comprising: A plurality of historical target images are obtained from the server, and based on a plurality of the historical target images and the target image, the second confidence degree is determined.
4. The processing method of claim 3, wherein, When the roadside unit obtains the second image feature, the detection unit is controlled to send excitation electric waves to the target vehicle and receive feedback information, and the second vehicle identity feature is determined based on the feedback information, including: When the roadside unit obtains the target image, the detection unit is controlled to send excitation electric waves to the target vehicle and obtain the feedback information, and the second vehicle identity feature is determined based on the feedback information.
5. The processing method of claim 4, wherein, When the roadside unit obtains the target image, the detection unit is controlled to send excitation electric waves to the target vehicle and obtain the feedback information, and the second vehicle identity feature is determined based on the feedback information, including: Based on the roadside unit receiving electromagnetic wave signals reflected by the target vehicle; Based on the electromagnetic wave signals, the corresponding frequency spectrum feature and time domain feature are obtained; Based on the combination of the frequency spectrum feature and the time domain feature, the second vehicle identity feature is determined.
6. The processing method of claim 1, wherein, Based on the image data, the first confidence corresponding to the first image feature and the second confidence corresponding to the second image feature are determined, including: Based on the image data obtained by the roadside unit, the average clarity of multiple frames of data images in the image data is obtained; Based on the clarity, the first confidence is determined, wherein the clarity is proportional to the first confidence.
7. The processing method of claim 1, wherein, If at least two different target vehicle features are the same and the sum of the corresponding confidences is greater than a first threshold, it is determined that the vehicle identity authentication is successful, including: The first image feature, the second image feature, and the first vehicle identity feature corresponding to the target vehicle whose vehicle identity authentication is determined to be successful are uploaded to the server.
8. A processing system based on a toll integrated cloud warehouse intelligent kiosk, characterized in that, The system includes a roadside unit and a control terminal, which is configured to: Based on the image data obtained by the roadside unit, the first image feature and the second image feature corresponding to the target vehicle approaching are determined, wherein the first image feature is the image feature corresponding to the license plate of the target vehicle, and the second image feature is the image feature corresponding to the shape of the target vehicle; Based on the image data, the first confidence corresponding to the first image feature and the second confidence corresponding to the second image feature are determined; Based on the signal recognition channel of the roadside unit, the first vehicle identity feature corresponding to the target vehicle is obtained, and the third confidence is obtained based on the current signal quality of the signal recognition channel; Based on the first image feature, the second image feature, and the first vehicle identity feature, three corresponding target vehicle features are obtained from the server respectively; If at least two different target vehicle features are the same and the sum of the corresponding confidences is greater than a first threshold, it is determined that the vehicle identity authentication is successful. If the sum of all confidences is less than a second threshold, wherein the second threshold is less than the first threshold, it is determined that the vehicle identity authentication fails.
9. An electronic device, comprising: It includes: At least one processor; And a memory in communication connection with the at least one processor; The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method as claimed in any one of claims 1-7.
10. A computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the method as claimed in any one of claims 1-7.