Image acquisition method, device and equipment for parking lot and medium

Abstract

A method, apparatus, device, and medium for image acquisition in parking lots are disclosed. The method includes: acquiring vehicle status information and / or current environmental information of the vehicle within the parking lot; determining the type of a target area within the parking lot in which the vehicle is located based on the vehicle status information and / or the current environmental information; determining an image acquisition strategy based on the type of the target area; and acquiring images in the target area according to the image acquisition strategy. This solution, without relying on prior image knowledge, can employ differentiated image acquisition strategies based on the type of area the vehicle is in within the parking lot. This avoids the large number of invalid images and redundant calculations caused by indiscriminate acquisition across the entire scene. Therefore, necessary acquisition is performed only within the effective area, significantly reducing invalid image data and resource waste.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent driving technology, specifically to an image acquisition method, device, equipment, and medium for parking lots. Background Technology

[0002] With the development of intelligent vehicle technology, users are increasingly demanding automation and convenience in vehicle driving and parking scenarios, making contactless parking payment an important functional direction for intelligent in-vehicle systems. Currently, parking lot payment mainly relies on methods such as manual QR code scanning, queuing at the exit, and automatic deduction based on license plate binding.

[0003] Therefore, how to avoid invalid image acquisition without relying on prior image information has become an urgent problem to be solved. Summary of the Invention

[0004] To address the aforementioned technical problems, this disclosure provides an image acquisition method, apparatus, device, and medium for parking lots. This method can employ differentiated image acquisition strategies based on the type of vehicle located in different areas of the parking lot, without relying on prior image knowledge, thereby significantly reducing invalid image data and resource waste.

[0005] The first aspect of this disclosure provides an image acquisition method for a parking lot, comprising: Obtain vehicle status information and / or the vehicle's current environmental information within the parking lot; Based on the vehicle status information and / or the current environment information, determine the type of the vehicle located in the target area within the parking lot; Based on the type of the target region, determine the image acquisition strategy; Images are acquired in the target area according to the image acquisition strategy described above.

[0006] A second aspect of this disclosure provides an image acquisition device for a parking lot, comprising: The first acquisition module is used to acquire vehicle status information and / or the current environmental information of the vehicle in the parking lot; The first determining module is used to determine the type of the vehicle located in the target area within the parking lot based on the vehicle status information and / or the current environment information; The second determining module is used to determine the image acquisition strategy based on the type of the target region; The first execution module is used to acquire images in the target area according to the image acquisition strategy.

[0007] A third aspect of this disclosure provides a computer-readable storage medium storing a computer program for performing the image acquisition method for parking lots described in the first aspect above.

[0008] A fourth aspect of this disclosure provides an electronic device comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the image acquisition method for parking lots described in the first aspect above.

[0009] A fifth aspect of this disclosure provides a computer program product that, when executed by an instruction processor, performs the image acquisition method for parking lots as proposed in the first aspect of this disclosure.

[0010] The technical solution provided in this disclosure can determine the type of target area where the vehicle is located in the parking lot based on vehicle status information and / or the vehicle's current environmental information within the parking lot. It first determines the corresponding image acquisition strategy based on the type of the target area, and then performs image acquisition in the corresponding target area according to the image acquisition strategy. Since this solution can adopt differentiated image acquisition strategies for different areas within the parking lot without relying on prior image knowledge, it avoids the large number of invalid images and redundant calculations caused by indiscriminate acquisition across the entire scene. Therefore, it only performs necessary acquisition within the effective area, significantly reducing invalid image data and resource waste. Thus, this solution can intelligently adapt the acquisition behavior according to the parking lot area structure, ensuring the effectiveness of acquisition in key areas while discarding invalid acquisition, significantly improving resource utilization and payment QR code acquisition efficiency. Attached Figure Description

[0011] Figure 1 This is a system architecture diagram of an image acquisition system 100 for a parking lot provided in an exemplary embodiment of this disclosure.

[0012] Figure 2 This is a schematic flowchart of an image acquisition method for a parking lot provided in an exemplary embodiment of this disclosure.

[0013] Figure 3 This is a flowchart illustrating an image acquisition method for a parking lot provided in another exemplary embodiment of this disclosure.

[0014] Figure 4 This is a schematic flowchart of an image acquisition method for a parking lot provided in another exemplary embodiment of this disclosure.

[0015] Figure 5 This is a flowchart illustrating an image acquisition method for a parking lot provided in yet another exemplary embodiment of this disclosure.

[0016] Figure 6 This is a flowchart illustrating an image acquisition method for a parking lot provided in another exemplary embodiment of this disclosure.

[0017] Figure 7 This is a schematic diagram of the structure of an image acquisition device for a parking lot provided in an exemplary embodiment of the present disclosure.

[0018] Figure 8 This is a structural diagram of an electronic device provided in an exemplary embodiment of this disclosure. Detailed Implementation

[0019] To explain this disclosure, exemplary embodiments of the disclosure will now be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the disclosure, and not all of them. It should be understood that the disclosure is not limited to exemplary embodiments.

[0020] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0021] Application Overview In related technologies, the conventional solution for achieving contactless parking payment is to use an in-vehicle camera to automatically acquire a payment QR code. However, this solution heavily relies on prior image information, requiring image acquisition and processing before determining the existence of a payment QR code. This results in the acquisition of a large number of invalid images, leading to significant resource waste.

[0022] Based on the aforementioned technical problems, the technical solution provided in this disclosure can determine the type of the target area where the vehicle is located in the parking lot based on vehicle status information and / or the vehicle's current environmental information within the parking lot. It first determines the corresponding image acquisition strategy based on the type of the target area, and then performs image acquisition in the corresponding target area according to the image acquisition strategy. Since this solution can adopt differentiated image acquisition strategies for different areas within the parking lot without relying on prior image knowledge, it avoids the large number of invalid images and redundant calculations caused by indiscriminate acquisition across the entire scene. Therefore, it only performs necessary acquisition within the effective area, significantly reducing invalid image data and resource waste. Thus, this solution can intelligently adapt the acquisition behavior according to the parking lot area structure, ensuring the effectiveness of acquisition in key areas while discarding invalid acquisition, significantly improving resource utilization and payment QR code acquisition efficiency.

[0023] Exemplary System Figure 1This is a system architecture diagram of an image acquisition system 100 for a parking lot provided in an exemplary embodiment of this disclosure. The system architecture mainly includes a data acquisition module 110, a region type recognition module 120, an image acquisition strategy generation module 130, an image acquisition execution module 140, and a data processing module 150.

[0024] The data acquisition module 110 is used to acquire vehicle status information and the vehicle's current environmental information in the parking lot in real time. The vehicle status information may include the vehicle's driving speed, vehicle steering information, vehicle braking status, etc.; the current environmental information includes light intensity, wireless signal strength, and navigation positioning signal (GPS) strength, etc.; and the acquired vehicle status information and current environmental information are transmitted to the area type recognition module 120.

[0025] The area type identification module 120 receives data from the data acquisition module 110 and determines the type of the target area within the parking lot where the vehicle is currently located. The target area type can include preset node areas and non-preset node areas. Preset node areas refer to areas within the parking lot where parking payment codes will appear, such as the parking lot entrance area and parking lot exit area. The area type identification module 120 determines the type of the target area by fusing and analyzing vehicle status information and current environmental information, and then sends this type information to the image acquisition strategy generation module 130.

[0026] The image acquisition strategy generation module 130 is used to generate a corresponding image acquisition strategy based on the type of the received target area. Different target area types correspond to different image acquisition requirements. Furthermore, the image acquisition strategy generation module 130 can send the generated image acquisition strategy to the image acquisition execution module 140.

[0027] The image acquisition execution module 140, as the core component that actually performs the image acquisition task, acquires images in the target area according to the received image acquisition strategy; and transmits the acquired image data to the data processing module 150.

[0028] The data processing module 150 is used to recognize the received image to obtain the payment code acquisition status of the target area. If the payment code acquisition status is "no parking payment code acquired", the data processing module 150 sends an image compensation strategy to the image acquisition execution module 140; if the payment code acquisition status is "parking payment code acquired", image acquisition can be stopped, or the parking payment code can be parsed to extract the vehicle parking information contained therein, such as entry time, license plate number, parking area number and other key data for subsequent payment.

[0029] The aforementioned image acquisition system employs different image acquisition strategies for different areas of the parking lot where vehicles are located, thus enabling intelligent control and precise processing of parking lot image acquisition. This avoids the large number of invalid images and redundant calculations resulting from indiscriminate acquisition across the entire scene without relying on prior image knowledge. Therefore, necessary acquisition is performed only within the effective area, significantly reducing invalid image data and resource waste.

[0030] Exemplary methods Figure 2 This is a schematic flowchart illustrating an exemplary embodiment of an image acquisition method for a parking lot provided by this disclosure. This embodiment can be applied to electronic devices, such as... Figure 2 As shown, it includes the following steps: Step 201: Obtain vehicle status information and / or the vehicle's current environmental information within the parking lot.

[0031] In some examples, the vehicle status information mentioned above may include at least one of the following: vehicle speed information, acceleration information, vehicle steering information, vehicle braking status (e.g., reversing, parking, or moving forward), gear information, and vehicle attitude information (e.g., pitch angle, yaw angle, etc.). The current environmental information mentioned above may include light intensity, wireless signal strength, and GPS signal strength.

[0032] For example, the vehicle status information mentioned above can be collected through various sensors installed on the vehicle. For instance, a speed sensor can collect vehicle speed information, an acceleration sensor can acquire acceleration information, a steering angle sensor can acquire vehicle steering information, and attitude sensors such as gyroscopes and tilt sensors can collect vehicle attitude information such as pitch and yaw angles. The vehicle's braking status can also be detected through sensors such as brake pedal position sensors or brake fluid pressure sensors; and the vehicle's gear information can be read from the On-Board Diagnostics (OBD) interface. Of course, vehicle speed, engine speed, gear position, and braking signals can also be directly read through the OBD interface. By combining these methods, comprehensive and accurate information about the vehicle's status within the parking lot can be obtained.

[0033] For example, the light intensity in a parking lot can be monitored in real time using a light sensor integrated into the vehicle. This sensor can convert light signals into electrical signals and output quantifiable light intensity values ​​to determine whether the environment is in a strong light, normal light, or weak light state. Wireless communication modules (such as Wi-Fi or Bluetooth modules) can be used to receive signals from surrounding wireless access points or Bluetooth devices and calculate the strength of the wireless signal using a signal strength detection algorithm, for example, using the Received Signal Strength Indication (RSSI) value. For navigation and positioning signal strength, the vehicle's GPS receiver can receive positioning signals from satellites. The strength of the GPS signal can be evaluated based on parameters such as the number of satellites received and the signal-to-noise ratio (SNR). A sufficient number of satellites and a high SNR indicate a strong GPS signal, while a limited number of satellites indicates a weak GPS signal.

[0034] Step 202: Based on vehicle status information and / or current environmental information, determine the type of the target area where the vehicle is located within the parking lot.

[0035] In some embodiments, vehicle operating states differ depending on the target area within the parking lot. For example, in the vehicle entrance / exit area, vehicles typically travel at low speeds and queue for entry, with frequent start-stop operations. In the main passageway area, vehicles generally travel at a relatively stable medium speed, with smoother routes and fewer prolonged stops. When a vehicle enters a parking space, its speed further decreases, and it performs precise maneuvers such as turning and reversing to complete the parking action; some vehicles may even remain stationary within the parking space. In the elevator entrance / exit area, vehicles are often temporarily parked or used for passenger pick-up / drop-off. Vehicles may briefly stop or pull over, or move slowly at extremely low speeds. Drivers or passengers typically perform actions such as opening / closing doors and carrying items in this area. Therefore, when a vehicle exhibits different operating states, it is located in different areas of the parking lot, and its surrounding environmental characteristics, vehicle motion parameters (such as speed, acceleration, and steering angle), and driver actions all differ significantly.

[0036] In some embodiments, the detected environmental information will vary significantly depending on the target area of ​​the vehicle within the parking lot. For example, the light intensity is often high in the vehicle entrance / exit area of ​​the parking lot; while the light intensity is relatively uniform in the passageway area; the light in the parking space area may be affected by factors such as surrounding vehicles blocking the light and the position of ceiling lights, resulting in weaker light. Furthermore, the wireless signal strength and navigation positioning signal strength are usually high in the vehicle entrance / exit area of ​​the parking lot, while the wireless signal and navigation positioning signal strength may be attenuated or unstable in the passageway area and parking space area due to factors such as building structure and wall obstruction. Some more remote parking spaces may even experience weak or no signal.

[0037] For different target areas within a parking lot, since vehicles will exhibit different operating states and the detected current environmental information will also vary significantly, the type of target area where a vehicle is located within the parking lot can be determined by combining vehicle status information and / or current environmental information.

[0038] Step 203: Determine the image acquisition strategy based on the type of the target area.

[0039] In some embodiments, corresponding image acquisition strategies can be pre-configured for different types of target regions. Based on the identified target region type, an image acquisition strategy adapted to the target region is matched and determined. The aforementioned image acquisition strategy refers to the rules and methods for adjusting and controlling the operating parameters of the image acquisition device. For example, the image acquisition strategy may include the image acquisition frequency of the image acquisition device in the target region; or, for example, the image acquisition strategy may also include the image acquisition duration of the image acquisition device in the target region. Of course, in addition to image acquisition frequency and image acquisition duration, the image acquisition strategy may also include other adjustment rules, which are not limited in this embodiment.

[0040] Step 204: Acquire images in the target area according to the image acquisition strategy.

[0041] For example, after determining the image acquisition strategy matching the target area, the image acquisition device can be controlled to perform specific image acquisition operations in the target area according to the image acquisition strategy. For instance, if the target area is the vehicle entrance / exit area of ​​a parking lot, and the corresponding image acquisition strategy is to acquire two frames per second, then the vehicle's front-facing camera is set to a working mode of acquiring two frames per second, and the front-facing camera is controlled to continuously acquire images in the target area at a frequency of two frames per second. As another example, if the target area is a regular passageway area within the parking lot, and the corresponding image acquisition strategy is to acquire one frame per five seconds, then the vehicle's front-facing camera is set to a working mode of acquiring one frame per five seconds, and the front-facing camera is controlled to acquire images in the regular passageway area at a frequency of one frame per five seconds. By flexibly adjusting the image acquisition strategy according to different target area types, the image acquisition frequency can be increased in areas where the probability of parking payment codes appearing is high to ensure effective capture of payment code information, while the acquisition frequency can be reduced in areas where pedestrian activity is relatively frequent but the probability of payment codes appearing is low. This effectively reduces unnecessary image data acquisition while meeting image acquisition requirements.

[0042] The technical solution provided in this disclosure can determine the type of target area where the vehicle is located in the parking lot based on vehicle status information and / or the vehicle's current environmental information within the parking lot. It first determines the corresponding image acquisition strategy based on the type of the target area, and then performs image acquisition in the corresponding target area according to the image acquisition strategy. Because this solution can adopt differentiated image acquisition strategies for different types of areas within the parking lot without relying on prior image knowledge, it avoids the large number of invalid images and redundant calculations caused by indiscriminate acquisition across the entire scene. Therefore, it only performs necessary acquisition within the effective area, significantly reducing invalid image data and resource waste. Thus, this solution can intelligently adapt the acquisition behavior according to the parking lot area structure, ensuring the effectiveness of acquisition in key areas while discarding invalid acquisition, significantly improving resource utilization and payment QR code acquisition efficiency.

[0043] like Figure 3 As shown above, in the above Figure 2 Based on the illustrated embodiment, step 202 above may include the following steps 2021 or 2022: Step 2021: In response to the target area being a preset node area, the image acquisition strategy is determined by acquiring images in the target area at the first acquisition frequency.

[0044] In some embodiments, the aforementioned preset node areas typically refer to key areas within the parking lot where parking payment codes will appear, such as the parking lot vehicle entrance area, parking lot vehicle exit area, parking lot elevator entrance area, parking lot elevator exit area, parking lot stairs, parking lot pedestrian walkway entrance area, parking lot pedestrian walkway exit area, and the area where self-service payment machines are located within the parking lot. These areas are the main locations where vehicles perform payment operations during parking. Therefore, when a vehicle enters these areas, there is a high probability that the payment QR code image needs to be collected to complete the contactless parking payment process. By setting these areas as preset node areas, when the target area where the vehicle is located within the parking lot is determined as the preset node area, that is, when the vehicle enters the preset node area, a relatively high first acquisition frequency is used to acquire images to ensure that key information such as the parking payment code within the preset node area can be captured in a timely and accurate manner, avoiding information omissions due to insufficient acquisition frequency, thereby providing reliable data support for subsequent payment code recognition and processing.

[0045] In some examples, a mapping relationship between different node regions and their corresponding acquisition frequencies is pre-built. This mapping relationship can exist in the form of data tables, configuration files, or database records, which explicitly record the unique identifier of each preset node region (such as region number, region name, or region coordinate range) and the image acquisition frequency parameters bound to it. For example, for preset node regions such as the entrance gate area and exit gate area of ​​a parking lot, the corresponding acquisition frequency can be set to the first acquisition frequency in the mapping relationship, such as acquiring 10 frames per second; while for non-preset node regions such as ordinary driving lanes and open parking areas in the parking lot, a relatively lower second acquisition frequency is set in the mapping relationship, such as acquiring 1 frame per 3 seconds. In this way, when it is determined that the target area where the vehicle is currently located is a preset node region, the mapping relationship can be directly queried to quickly obtain the acquisition frequency corresponding to the target area as the first acquisition frequency. Then, the image acquisition device (such as a camera) can be controlled to acquire images according to the first acquisition frequency, realizing the automated and precise switching of the acquisition strategy.

[0046] In other embodiments, different image acquisition strategies can be adopted for preset areas of different types of nodes. For example, when the target area is the vehicle entrance / exit area of ​​a parking lot, long-term high-frequency sampling can be used, while when the target area is the elevator entrance / exit area of ​​a parking lot, short-term high-frequency sampling can be used. In this way, differentiated image acquisition strategies can be achieved by setting different image acquisition durations.

[0047] Step 2022: In response to the target area being a non-preset node area, the image acquisition strategy is determined by acquiring images in the target area at the second acquisition frequency.

[0048] The second sampling frequency is different from the first sampling frequency.

[0049] In some examples, the aforementioned non-preset node areas typically refer to areas within a parking lot where the probability of a parking payment code appearing is extremely low. These include regular parking spaces, passageways connecting different functional zones, and public service areas (such as temporary rest areas and areas near restrooms). In these areas, vehicles are primarily moving at low to medium speeds or parked, making it less likely or easier to acquire critical interactive information like parking payment codes through image capture. Therefore, when a vehicle enters a non-preset node area, using a relatively low second acquisition frequency for image acquisition can effectively reduce the workload of the image acquisition equipment, minimize unnecessary image data storage, and reduce energy consumption caused by high-frequency acquisition, while meeting basic monitoring requirements. Therefore, the second acquisition frequency is usually lower than the first acquisition frequency, and can even be zero, meaning image acquisition can be turned off in non-preset node areas.

[0050] In some examples, with a pre-established mapping relationship between different node regions and their corresponding acquisition frequencies, once the target region where the vehicle is currently located is determined to be a preset node region, this mapping relationship can be directly queried to quickly obtain the acquisition frequency corresponding to that target region as the second acquisition frequency. Then, the image acquisition device (e.g., a camera) can be controlled to acquire images according to the second acquisition frequency. In this way, the acquisition frequency is configured differently based on the node type.

[0051] Based on the above embodiments, the acquisition frequency of the image acquisition device is dynamically adjusted according to the type of the target area where the vehicle is currently located (preset node area or non-preset node area), realizing intelligent and differentiated image acquisition strategy. Therefore, this differentiated configuration not only ensures the image acquisition needs in important areas, but also reduces invalid or redundant image data generated in non-important areas, thereby reducing the occupation of system storage resources and realizing the rational use of resources.

[0052] like Figure 4 As shown above, in the above Figure 2 Based on the illustrated embodiment, step 201 above may include the following steps: Step 2011: Based on the preset area determination model, process the vehicle status information and / or current environment information, and output the probability that the vehicle is currently in at least one preset node area.

[0053] In some examples, the aforementioned region determination model is based on sample data including vehicles in different preset node regions within a parking lot under different vehicle states (e.g., driving, stationary, turning) and environmental conditions. A selected pre-trained model is trained, and by continuously adjusting the model parameters, the model can accurately learn the mapping relationship between vehicle state information, environmental information, and the probability of a vehicle being in each preset node region. After the model training is complete, the region determination model is obtained. For example, the aforementioned region determination model can be a neural network model or other types of machine learning models.

[0054] In some examples, the real-time vehicle status information and current environment information can be converted and standardized to ensure consistency with the input data format used during the training of the region determination model. The preprocessed vehicle status information and current environment information are then input into the trained region determination model. Based on this model, layer-by-layer calculations and feature extraction are performed on the input multi-dimensional feature data. Through non-linear transformations of the activation function, low-dimensional features are mapped to a high-dimensional space, thereby capturing complex patterns in the vehicle status and environment information that have a crucial impact on region determination. Finally, the model outputs a probability distribution vector, where each element corresponds to the probability value of the vehicle currently being in a certain preset node region, and the sum of all probability values ​​is 1, thus clearly quantifying the likelihood of the vehicle being in each preset node region.

[0055] For example, consider at least one preset node region including: a parking lot vehicle entrance / exit region, a parking lot elevator entrance / exit region, and a pedestrian walkway entrance / exit region. Based on a preset region determination model, the real-time acquired vehicle status information and current environmental information are processed. This model is used to match and calculate the features of each preset node region, resulting in the following output: the probability of a vehicle being located in the parking lot vehicle entrance / exit region is 0.85; the probability of it being located in the parking lot elevator entrance / exit region is 0.12; and the probability of it being located in the pedestrian walkway entrance / exit region is 0.03.

[0056] Step 2012: Determine the type of the target region based on the probability of at least one preset node region and a preset threshold.

[0057] In some embodiments, after determining the probability that the vehicle is currently in each preset node region, the probability of each preset node region can be compared with a preset threshold. Based on the comparison result, it can be determined whether the vehicle is located in a target region of a specific type. The type of target region includes preset node regions and non-preset node regions. For details, please refer to the detailed description in the following embodiments.

[0058] In some embodiments, step 2012 above may specifically include the following step (a) or step (b): Step (a): In response to the probability that the first preset node region exists in at least one preset node region is greater than or equal to a preset threshold, the type of the target region is determined based on the type of the first preset node region.

[0059] In some embodiments, the aforementioned first preset node region refers to a preset node region where the probability of a vehicle being located in that preset node region among all preset node regions reaches or exceeds a preset threshold. The probabilities of all preset node regions are compared with the preset threshold, and the preset node regions whose probability values ​​are greater than or equal to the preset threshold are determined as the first preset node region. In other words, the aforementioned target region must be a preset node region.

[0060] In some examples, the number of first preset node regions can be one or more. When the first preset node region includes one preset node region, that preset node region is directly determined as the target region. When the first preset node region includes multiple preset node regions, the preset node region with the highest probability among these multiple preset node regions can be selected as the target region.

[0061] For example, suppose all preset node areas within a parking lot can include the parking lot entrance area, the parking lot exit area, and the pedestrian walkway entrance / exit area, and the preset threshold is 0.6. When the probability of a vehicle being located in the parking lot entrance area is 0.7, the probability of it being located in the parking lot exit area is 0.2, and the probability of it being located in the pedestrian walkway entrance / exit area is 0.1, the probability of the parking lot entrance area (0.7) is greater than the preset threshold of 0.6, while the probabilities of the parking lot exit area (0.2) and the pedestrian walkway entrance / exit area (0.1) are both less than 0.6. Therefore, the first preset node area is only the parking lot entrance area, and thus the parking lot entrance area can be directly identified as the target area.

[0062] For example, suppose all preset node areas within a parking lot can include the parking lot entrance area, the parking lot exit area, and the pedestrian walkway entrance / exit area, and the preset threshold is 0.45. When the probability of a vehicle being in the parking lot entrance area is 0.5, the probability of it being in the parking lot exit area is 0.45, and the probability of it being in the pedestrian walkway entrance / exit area is 0.05, then the probability of the parking lot entrance area (0.5) is greater than the preset threshold (0.45), the probability of the parking lot exit area (0.45) is equal to the preset threshold (0.45), and the probability of the pedestrian walkway entrance / exit area (0.05) is less than the preset threshold (0.45). Therefore, the first preset node area includes both the parking lot entrance area and the parking lot exit area. Since both the parking lot entrance area and the parking lot exit area have a probability greater than the preset threshold, the parking lot entrance area with the highest probability can be selected as the target area.

[0063] Step (b): In response to the probability that at least one preset node region is less than a preset threshold, the type of the target region is determined to be a non-preset node region.

[0064] In some embodiments, the probabilities of all preset node regions are compared with preset thresholds. If the comparison result is that the probabilities of each preset node region are less than the preset threshold, then the target region is not any of the preset node regions, that is, the type of the target region is determined to be a non-preset node region.

[0065] For example, suppose all preset node areas within a parking lot can include the parking lot entrance area, the parking lot exit area, and the pedestrian walkway entrance / exit area, and the preset threshold is 0.8. When the calculated probability of the parking lot entrance area is 0.4, the probability of the parking lot exit area is 0.5, and the probability of the pedestrian walkway entrance / exit area is 0.1, since the probabilities of these three preset node areas are all less than the preset threshold of 0.8, the target area is determined to be a non-preset node area.

[0066] Based on the above embodiments, the region determination model accurately outputs the probability that a vehicle is currently in at least one preset node region. By comparing the probabilities of each preset node region with preset thresholds, the type of target region the vehicle is currently in can be accurately identified—whether it belongs to a preset node region or a non-preset node region. Furthermore, when the target region is determined to be a preset node region, it can be clearly identified as that specific preset node region, ensuring that subsequent image acquisition work can focus on the truly critical areas. This provides a precise decision-making basis for subsequently adjusting the image acquisition strategy for those critical areas. In this way, unnecessary image acquisition in non-critical, non-preset node regions is avoided, reducing the generation of invalid or redundant image data at the source. This effectively reduces the pressure on system storage resources and improves the overall operating efficiency and resource utilization of the parking lot image acquisition system.

[0067] like Figure 5 As shown, when the target area is a preset node area, in the above... Figure 2 Based on the illustrated embodiment, step 204 above may include the following steps: Step 2041: A first image is acquired when the vehicle enters the preset node area, a second image is acquired when the vehicle decelerates or stops in the preset node area, and a third image is acquired when the vehicle leaves the preset node area.

[0068] In some embodiments, when the target area is a preset node area, since the vehicle spends a short time in the preset node area, to ensure that the vehicle can capture the complete parking payment code, the vehicle can perform targeted image acquisition at different stages of entering, stopping, and leaving the area. For example, when the vehicle just enters the preset node area, the image acquisition device on the vehicle can be controlled to immediately start the first image acquisition; when the vehicle stops briefly in the preset node area or moves at a slower speed, the image acquisition device on the vehicle can be controlled to perform a second image acquisition, at which time the vehicle is relatively stable and can more clearly capture the area where the parking payment code is located; and at the moment when the vehicle is about to leave the preset node area, a third image acquisition is performed to supplement any unclear or missing images from the first two acquisitions that may have been caused by vehicle shaking or changes in lighting. In this way, by acquiring images at these three different stages, the acquisition of a complete and clear parking payment code image can be guaranteed to the greatest extent, avoiding the problem of missed or incorrect images due to the vehicle quickly passing through the preset node area, thereby effectively improving the success rate and accuracy of parking payment code recognition.

[0069] In some embodiments, the acquisition frequency of the first image acquisition and the third image acquisition is greater than the acquisition frequency of the second image acquisition; or, the acquisition frequency of the first image acquisition and the second image acquisition is greater than the acquisition frequency of the third image acquisition.

[0070] For example, considering the rapid changes in a vehicle's position and state when it first enters and is about to leave the preset node area, which may involve significant uncertainty, a scheme can be adopted where the acquisition frequency of the first and third images is higher than that of the second image acquisition. For instance, when a vehicle first enters the preset node area, its speed may not have fully decreased, or the driver may be performing steering maneuvers, causing instability in the vehicle's posture; conversely, when the vehicle is about to leave the preset node area, it may begin to accelerate, also in a dynamic state. Increasing the acquisition frequency during these two stages, such as from 1 frame per second in the second image acquisition to 3-5 frames per second, allows for the acquisition of more image samples in a shorter time, thereby increasing the probability of capturing clear and valid parking payment code images. Even if some images are blurry or invalid due to vehicle movement, other images are still available. Conversely, during the second image acquisition stage, the vehicle is usually in a relatively stable state, such as briefly stopping or slowly moving within the preset node area. At this time, a lower acquisition frequency, such as 1 frame per second, can meet the requirement of acquiring clear images while avoiding unnecessary resource consumption. This reduces the storage pressure on image data and the computational load of subsequent processing.

[0071] For example, based on different scenario requirements and resource optimization considerations, a scheme can be adopted where the acquisition frequency of the first and second images is higher than that of the third image acquisition. For instance, in some parking lots, the exit of the preset node area may be relatively narrow, or the driving path of the vehicle leaving the preset node area may be relatively fixed, and the vehicle posture may be relatively stable. In this case, the frequency requirement for the third image acquisition can be appropriately reduced. During the first image acquisition stage, since the vehicle travels at a relatively high speed, a higher acquisition frequency is needed to ensure that more image samples are acquired in a short time, increasing the probability of capturing clear and valid parking payment code images. During the second image acquisition stage, since the vehicle may remain stationary or move slowly for a relatively long time, this stage is crucial for acquiring the parking payment code. By increasing the acquisition frequency, such as 2-3 frames per second, multiple and multi-angle shots can be taken of the area where the parking payment code is located, further improving the image clarity and completeness, ensuring accurate identification of the payment code information. The third image acquisition stage mainly serves as a supplement and verification. Under the premise of relatively stable vehicle posture, a lower frequency, such as 0.5-1 frames per second, can be used to meet the needs of filling in gaps while also reasonably controlling the overall system resource consumption. By flexibly adjusting the acquisition frequency at different stages, the system resources can be optimized while ensuring image acquisition quality, thereby improving the practicality and economy of the image acquisition method.

[0072] In other examples, the same sampling frequency can be used for image acquisition at different stages of vehicle entry, parking, and departure, depending on actual needs. For instance, if the ambient lighting conditions in the parking lot are stable, vehicle speeds are generally slow, or the system resource utilization requirements are not high, a uniform sampling frequency of 1-2 frames per second can be used. This satisfies the basic image information requirements at each stage, simplifies the system control logic, and reduces the system complexity and potential risks that may arise from frequent frequency adjustments. Thus, this uniform frequency setting can serve as an effective supplement to the flexible frequency adjustment strategy in specific scenarios, adapting to the actual operating environment and technical conditions of different parking lots.

[0073] Based on the above embodiments, by acquiring images at different stages of a vehicle entering, stopping, and leaving the preset node area, a comprehensive acquisition of the node space can be achieved. This effectively captures complete image information of key vehicle behavior nodes within the parking lot, increasing the probability of capturing clear and valid parking payment code images. Furthermore, by flexibly adjusting the image acquisition frequency at different stages, not only is the image clarity and completeness further improved, ensuring accurate identification of payment code information, but the resource utilization efficiency of the parking lot image acquisition system is also significantly enhanced.

[0074] like Figure 6 As shown above, in the above Figure 2 Based on the illustrated embodiments, the image acquisition method for parking lots provided in this disclosure may further include the following steps: Step 205: Recognize the collected image to obtain the payment code acquisition status of the target area.

[0075] In some embodiments, one possible approach is to process each image acquired from the target area immediately upon acquisition to obtain the payment code acquisition status. This real-time recognition method can quickly determine whether the current image contains a valid payment code. Once the parking payment code is identified, subsequent payment information parsing and processing can be triggered promptly, avoiding processing delays caused by image accumulation. Another possible approach is to perform centralized recognition processing on all images acquired from the target area after the acquisition of images from the target area is completed. This batch recognition method can improve the accuracy and completeness of parking payment code recognition by integrating information from multiple frames of images, and is particularly suitable for scenarios where the parking payment code's position in the image is not fixed, its clarity fluctuates, or it is partially obscured. For example, when a vehicle briefly stops in the target area and the vehicle body may partially obscure the parking payment code, batch recognition of multiple continuously acquired images can comprehensively extract parking payment code features from images of different angles and clarity, thereby reducing the probability of recognition failure due to single-frame image quality issues. In practical applications, real-time recognition or batch recognition methods can be flexibly selected based on the specific environment of the parking lot and the priority requirements for real-time performance and recognition success rate, in order to achieve the best image recognition effect for parking payment codes.

[0076] In some examples, the acquired images can be preprocessed, such as by noise reduction or enhancing image contrast. Then, an edge detection algorithm is used to locate and extract the region of interest (ROI) from the preprocessed image, which may contain the parking payment code. The image features of the ROI are then extracted and analyzed to determine if a valid payment code pattern exists. If a clear and complete parking payment code is identified from the ROI, the payment code acquisition status is determined to be successful. If no parking payment code is detected from the ROI, or if the detected parking payment code is severely blurred, incomplete, or deformed, making it undecodingable, the payment code acquisition status is determined to be unacquired. For example, the parking payment code can be a QR code, barcode, or other graphic encoding form capable of carrying parking payment information; this disclosure does not specifically limit this.

[0077] Step 206: Based on the status obtained from the payment code, execute the target strategy.

[0078] In some embodiments, after obtaining the payment code acquisition status of the target area, different target strategies can be executed based on the payment code acquisition status. If the payment code acquisition status is "Successfully acquired parking payment code", image acquisition can be terminated; if the payment code acquisition status is "No parking payment code acquired", a preset auxiliary image acquisition mechanism can be triggered.

[0079] In some embodiments, step 206 may specifically include: in response to the payment code acquisition status being that no parking payment code has been acquired, executing an image compensation strategy; wherein the image compensation strategy includes at least one of the following: increasing the image acquisition duration, increasing the image acquisition frequency, and acquiring images when the vehicle stops parking.

[0080] For example, increasing the image acquisition time mentioned above refers to extending the image acquisition time for the target area based on the original planned image acquisition cycle. For instance, if the original plan was to continuously acquire images for 5 seconds after the vehicle enters the preset node area, and no payment code is obtained from the acquired images, the image acquisition time can be extended to 8 or 10 seconds, giving more time to capture the payment code image that may appear in the target area. Increasing the image acquisition frequency further increases the number of image acquisition frames per unit time during the image compensation stage, for example, from the original 1-2 frames per second to 4-6 frames per second. Through denser image sampling, the possibility of capturing a clear image of the payment code at an instant increases, especially for scenarios where the vehicle is still slightly shaking in the target area. Acquiring images at the end of the vehicle's parking is a mandatory image acquisition method. When the vehicle completes the parking operation in the preset node area and is about to leave, the vehicle's posture is usually relatively stable. At this time, performing an image acquisition can effectively supplement the situation where a valid parking payment code image may not have been acquired in the previous acquisition process, further improving the success rate of payment code acquisition. By using one or more of the above image compensation strategies in combination, even if the initial acquisition fails, the acquisition parameters and timing of the image acquisition device can be adjusted to obtain a valid parking payment code image as much as possible, thereby ensuring the continuous and stable operation of the parking lot image acquisition system and the smooth progress of the payment process.

[0081] In some examples, one or more of the above image compensation strategies can be executed based on preset conditions currently met by the vehicle. For example, preset conditions may include: no parking payment code was recognized in the image acquired from a preset node area (i.e., the target area is a preset node area), or a valid parking payment code image was not acquired before parking ended. Of course, if no parking payment code is recognized in the image acquired from a non-preset node area (i.e., the target area is not a preset node area), the image compensation strategy may not be triggered.

[0082] Based on the above embodiments, by recognizing the collected images to obtain the payment code acquisition status of the target area, and when the payment code acquisition status is identified as not having acquired the parking payment code, the corresponding image compensation strategy is executed. This can effectively address the problem of initial acquisition failure caused by vehicle speed, obstruction, changes in light, etc., thereby maximizing the success rate of acquiring the parking payment code image and ensuring the smooth execution of subsequent payment processes.

[0083] Exemplary device Figure 7 This is a schematic diagram of an image acquisition device for a parking lot, provided as an exemplary embodiment of the present disclosure. The device can be installed in electronic devices such as terminal devices and servers, or on objects such as vehicles, to execute the image acquisition method for a parking lot according to any of the embodiments described above.

[0084] like Figure 7 As shown, the above-mentioned device 300 may include: a first acquisition module 301, used to acquire vehicle status information and / or the current environmental information of the vehicle in the parking lot; a first determination module 302, used to determine the type of the target area in the parking lot where the vehicle is located based on the vehicle status information and / or the current environmental information; a second determination module 303, used to determine an image acquisition strategy based on the type of the target area; and a first execution module 304, used to acquire images in the target area according to the image acquisition strategy.

[0085] In one possible implementation, the second determining module 303 is specifically used to: determine the image acquisition strategy by acquiring images in the target area at a first acquisition frequency in response to the target area being a preset node area; or, determine the image acquisition strategy by acquiring images in the target area at a second acquisition frequency in response to the target area being a non-preset node area; wherein the second acquisition frequency is different from the first acquisition frequency.

[0086] In one possible implementation, the first determining module 302 is specifically used to: process the vehicle status information and / or the current environment information based on a preset region determination model, and output the probability that the vehicle is currently in at least one preset node region; and determine the type of the target region based on the probability of the at least one preset node region and a preset threshold.

[0087] In one possible implementation, the first determining module 302 is specifically used to: determine the type of the target region based on the type of the first preset node region in response to the probability that the probability of the existence of the first preset node region in the at least one preset node region being greater than or equal to the preset threshold; or, determine the type of the target region as a non-preset node region in response to the probability that the probability of the at least one preset node region being less than the preset threshold.

[0088] In one possible implementation, the target area is a preset node area; the first execution module 304 is specifically used to: perform a first image acquisition when the vehicle enters the preset node area, perform a second image acquisition when the vehicle decelerates or stops in the preset node area, and perform a third image acquisition when the vehicle leaves the preset node area.

[0089] In one possible implementation, the acquisition frequency of the first image acquisition and the third image acquisition is greater than the acquisition frequency of the second image acquisition; or, the acquisition frequency of the first image acquisition and the second image acquisition is greater than the acquisition frequency of the third image acquisition.

[0090] In one possible implementation, the above-mentioned device may further include: an image recognition module for recognizing the acquired image to obtain the payment code acquisition status of the target area; and a second execution module for executing the target strategy based on the payment code acquisition status.

[0091] In one possible implementation, the second execution module is specifically used to: execute an image compensation strategy in response to the payment code acquisition status being that no parking payment code has been acquired; wherein the image compensation strategy includes at least one of the following: increasing the image acquisition duration, increasing the image acquisition frequency, and acquiring images when the vehicle stops parking.

[0092] The beneficial technical effects corresponding to the exemplary embodiments of this device can be found in the corresponding beneficial technical effects of the exemplary method section above, and will not be repeated here.

[0093] Exemplary electronic devices Figure 8 A structural diagram of an electronic device provided in an embodiment of this disclosure includes at least one processor 111 and a memory 112.

[0094] The processor 111 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 11 to perform desired functions.

[0095] The memory 112 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 111 may execute one or more computer program instructions to implement the image acquisition method for parking lots and / or other desired functions of the various embodiments of this disclosure described above.

[0096] In one example, the electronic device 11 may also include an input device 113 and an output device 114, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0097] The input device 113 may include various sensors, including but not limited to: a distance sensor for detecting the distance between a target object and the vehicle; an image sensor for acquiring information about the vehicle's surrounding environment. In some examples, the input device may also include a pressure sensor for detecting seat pressure to determine the presence and location of passengers; a temperature sensor for monitoring the temperature inside the cabin; a humidity sensor for monitoring the humidity inside the cabin to assist in regulating the in-vehicle environment; an air quality sensor for monitoring in-vehicle air quality, such as carbon dioxide and volatile organic compounds (VOCs); a light sensor for detecting the intensity of light inside and outside the vehicle; an acceleration sensor for detecting changes in the vehicle's acceleration; a distance sensor for detecting the distance between the vehicle and other objects; a touchscreen sensor for interaction with the vehicle's infotainment system; biometric sensors, such as fingerprint recognition and facial recognition; a heart rate monitor for monitoring the driver's heart rate; a sound sensor for voice recognition and interaction to enable voice control; a seat sensor for monitoring seat usage, such as whether the seat is occupied and the passenger's body size; and wireless communication sensors, such as Bluetooth and Wi-Fi, for connecting to smart devices to achieve data transmission and remote control. In addition to the examples given above, the input device may include more or fewer sensors, which will not be elaborated here.

[0098] The output device 114 can output various information or signals to other hardware or devices, which may include displays, car audio systems, seats, windows, steering wheels, communication networks, and their connected remote output devices. The displays may include multiple different displays such as a driver's side display, a passenger side display, and a rear-seat display. The car audio system may include multiple speakers located in different positions within the vehicle cabin, and each display or speaker can operate independently.

[0099] Of course, for the sake of simplicity, Figure 8 Only some of the components of the electronic device 11 relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device 11 may include any other suitable components depending on the specific application.

[0100] Exemplary computer program products and computer-readable storage media In addition to the methods and devices described above, embodiments of this disclosure may also provide a computer program product, including computer program instructions that, when executed by a processor, cause the processor to perform the steps in the image acquisition method for a parking lot described in the various embodiments of this disclosure in the "Exemplary Methods" section above.

[0101] Computer program products can be written in any combination of one or more programming languages ​​to perform the operations of embodiments of this disclosure. These programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0102] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the image acquisition method for a parking lot described in the various embodiments of this disclosure in the "Exemplary Methods" section above.

[0103] Computer-readable storage media may take the form of any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, but is not limited to, systems, apparatuses, or devices that are electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0104] The basic principles of this disclosure have been described above with reference to specific embodiments. However, the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0105] Various modifications and variations can be made to this disclosure without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this disclosure and their equivalents, this disclosure is also intended to include such modifications and variations.

Claims

1. An image acquisition method for parking lots, comprising: Obtain vehicle status information and / or the vehicle's current environmental information within the parking lot; Based on the vehicle status information and / or the current environment information, determine the type of the vehicle located in the target area within the parking lot; Based on the type of the target region, determine the image acquisition strategy; Images are acquired in the target area according to the image acquisition strategy described above.

2. The method according to claim 1, wherein, The step of determining the image acquisition strategy based on the type of the target region includes: In response to the target area being a preset node area, the image acquisition strategy is determined by acquiring images in the target area at a first acquisition frequency; or... In response to the target area being a non-preset node area, the image acquisition strategy is determined by acquiring images in the target area at the second acquisition frequency. The second sampling frequency is different from the first sampling frequency.

3. The method according to claim 1, wherein, The step of determining the type of the vehicle located in the target area within the parking lot based on the vehicle status information and / or the current environmental information includes: Based on a preset region determination model, the vehicle status information and / or the current environment information are processed to output the probability that the vehicle is currently in at least one preset node region. The type of the target region is determined based on the probability of the at least one preset node region and a preset threshold.

4. The method according to claim 3, wherein, Determining the type of the target region based on the probability of the at least one preset node region and a preset threshold includes: In response to the probability that a first preset node region exists in the at least one preset node region being greater than or equal to the preset threshold, the type of the target region is determined based on the type of the first preset node region; or... If the probability of the at least one preset node region is less than the preset threshold, the target region is determined to be a non-preset node region.

5. The method according to claim 1, wherein, The target area is a preset node area; Acquiring images in the target area according to the image acquisition strategy includes: A first image is captured when the vehicle enters the preset node area, a second image is captured when the vehicle decelerates or stops in the preset node area, and a third image is captured when the vehicle leaves the preset node area.

6. The method according to claim 5, wherein the acquisition frequency of the first image acquisition and the third image acquisition is greater than the acquisition frequency of the second image acquisition; or, The acquisition frequency of the first image acquisition and the second image acquisition is greater than the acquisition frequency of the third image acquisition.

7. The method according to claim 1, further comprising: The collected images are identified to obtain the payment code acquisition status of the target area; Based on the payment code acquisition status, the target strategy is executed.

8. The method according to claim 7, wherein, The step of executing the target strategy based on the payment code acquisition status includes: In response to the payment code acquisition status being "no parking payment code acquired", an image compensation strategy is executed; wherein, the image compensation strategy includes at least one of the following: increasing the image acquisition duration, increasing the image acquisition frequency, and acquiring images when the vehicle stops parking.

9. An image acquisition device for a parking lot, comprising: The first acquisition module is used to acquire vehicle status information and / or the current environmental information of the vehicle in the parking lot; The first determining module is used to determine the type of the vehicle located in the target area within the parking lot based on the vehicle status information and / or the current environment information; The second determining module is used to determine the image acquisition strategy based on the type of the target region; The first execution module is used to acquire images in the target area according to the image acquisition strategy.

10. A computer-readable storage medium storing a computer program for performing the image acquisition method for a parking lot as described in any one of claims 1-8.

11. An electronic device, the electronic device comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the image acquisition method for parking lots as described in any one of claims 1-8.

Images